From 14413408c6e1df19fd08e7c8ac3ddd65a31d9f3f Mon Sep 17 00:00:00 2001 From: dishabhagat Date: Fri, 8 Aug 2025 11:51:53 -0400 Subject: [PATCH] Instana self monitoring integration package --- .../instana-self-monitoring/README.md | 147 + ...monitoring__profile_related_pipelines.json | 2223 ++++++++ ...itoring__scale_high_perf_metrics_down.json | 4647 +++++++++++++++++ ...oring__scale_high_perf_processor_down.json | 4079 +++++++++++++++ ...onitoring__scale_high_perf_spans_down.json | 3458 ++++++++++++ ...ring__scale_high_perf_ui_profile_down.json | 1736 ++++++ ...onitoring__scale_metrics_profile_down.json | 4320 +++++++++++++++ ...self_monitoring__scale_processor_down.json | 2888 ++++++++++ ..._monitoring__scale_spans_profile_down.json | 3239 ++++++++++++ ...elf_monitoring__scale_ui_profile_down.json | 1736 ++++++ ...self_monitoring__usage_k8s_components.json | 3944 ++++++++++++++ .../acceptor_high_job_queue_utilizatio.json | 18 + .../acceptor_high_span_error_rate.json | 18 + ...sor_failed_to_heal_online_infra_graph.json | 18 + ...essor_failed_to_heal_online_snapshots.json | 18 + .../appdata_processor_high_span_dropping.json | 18 + .../appdata_processor_service_explosion.json | 18 + .../butler/butler_jobs_queue_utilization.json | 18 + .../butler_very_busy_http_thread_pool.json | 18 + .../metrics_cassandra_unreachable_node.json | 18 + .../profiles_cassandra_unreachable_node.json | 18 + .../spans_cassandra_unreachable_node.json | 18 + .../state_cassandra_unreachable_node.json | 18 + .../state_cassandra_write_latency.json | 18 + ...house_ap_too_many_parts_per_partition.json | 23 + ...ickhouse_ap_too_many_rejected_inserts.json | 18 + ...ouse_ap_too_many_simultaneous_queries.json | 18 + ...ckhouse_distribution_queue_filling_up.json | 18 + ..._is_not_running_on_the_expected_hosts.json | 17 + ...khouse_mount_points_full_nvme1n1_used.json | 18 + ...khouse_mount_points_full_nvme2n1_used.json | 18 + ...khouse_mount_points_full_nvme3n1_used.json | 18 + ...clickhouse_mount_points_full_sdb_used.json | 18 + ...clickhouse_mount_points_full_sdc_used.json | 18 + ..._failing_due_to_memory_limit_exceeded.json | 18 + .../clickhouse/clickhouse_read_only_mode.json | 18 + .../clickhouse_rejects_inserts.json | 18 + ...clickhouse_replica_max_insert_queue30.json | 18 + ...lickhouse_replica_max_insert_queue450.json | 18 + ...ickhouse_replication_queue_filling_up.json | 18 + ..._is_not_running_on_the_expected_hosts.json | 17 + ...ch-NG_Unassigned_Shards-elasticsearch.json | 18 + .../ElasticSearch-NG_Unassigned_Shards.json | 18 + ...lasticsearch_client_search_error_rate.json | 18 + ...ticsearch_data_disk_full_nvme1n1_used.json | 18 + ...ticsearch_data_disk_full_nvme2n1_used.json | 18 + ...elasticsearch_data_disk_full_sdb_used.json | 18 + ...elasticsearch_data_disk_full_sdc_used.json | 18 + ..._is_not_running_on_the_expected_hosts.json | 17 + ...lasticsearch_red_status-elasticsearch.json | 18 + .../elasticsearch_red_status.json | 18 + .../elasticsearch_root_disk_full.json | 18 + ...ratio_requests_instana_k8s_pod_filler.json | 18 + .../filler_cassandra_rollup_dropping.json | 18 + .../filler_cassandra_writes_failing.json | 18 + .../filler_group_members_error_rate.json | 18 + .../fillers/filler_group_members_lag.json | 18 + .../fillers/filler_info_event_dropping.json | 18 + .../fillers/filler_kafka_rollup_dropping.json | 18 + .../events/fillers/filler_lag.json | 18 + .../fillers/filler_metric_dropping.json | 18 + .../fillers/filler_outdated_snapshots.json | 18 + .../fillers/filler_raw_events_dropping.json | 18 + .../fillers/filler_raw_message_dropping.json | 18 + .../filler_raw_metrics_error_rate.json | 18 + .../filler_snapshot_change_dropping.json | 18 + .../fillers/filler_snapshot_processing.json | 18 + .../filler_stopped_expiring_snapshots.json | 18 + .../fillers/filler_stopped_fetching.json | 18 + ...ndskeeper_datacenter_activation_error.json | 18 + .../events/kafka/kafka_high_io_wait.json | 18 + .../events/kafka/kafka_open_files.json | 18 + .../kafka_under_replicated_partitions.json | 18 + .../lhp_lagging_incoming_logs.json | 18 + ..._dropping_one_percent_of_test_results.json | 19 + .../shp_is_dropping_test_results.json | 19 + .../shp_is_not_receiving_test_results.json | 19 + .../events/synthetics/shp_kafka_failing.json | 18 + ...nthetics_acceptor_addon_license_error.json | 18 + ...acceptor_external_storage_write_error.json | 18 + ...hetics_reader_clickhouse_queued_calls.json | 18 + ...tics_reader_clickhouse_select_failure.json | 18 + ...cs_reader_external_storage_read_error.json | 18 + ...tics_writer_clickhouse_insert_failure.json | 18 + .../tag_processor_cleanup_stalled.json | 18 + .../tag_processor_dropping_snapshots.json | 18 + ...ssor_dropping_tag_propagation_actions.json | 18 + .../tag_processor_dropping_tag_sets.json | 18 + ...tag_processor_dropping_tagged_metrics.json | 18 + .../tag_processor_snapshot_lag.json | 18 + .../instana-self-monitoring/package.json | 18 + 91 files changed, 33862 insertions(+) create mode 100644 packages/@instana-integration/instana-self-monitoring/README.md create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__profile_related_pipelines.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_metrics_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_processor_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_spans_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_ui_profile_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_metrics_profile_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_processor_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_spans_profile_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_ui_profile_down.json create mode 100644 packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__usage_k8s_components.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_job_queue_utilizatio.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_span_error_rate.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_infra_graph.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_snapshots.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_high_span_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_service_explosion.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/butler/butler_jobs_queue_utilization.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/butler/butler_very_busy_http_thread_pool.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/cassandra/metrics_cassandra_unreachable_node.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/cassandra/profiles_cassandra_unreachable_node.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/cassandra/spans_cassandra_unreachable_node.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_unreachable_node.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_write_latency.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_parts_per_partition.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_rejected_inserts.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_simultaneous_queries.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_distribution_queue_filling_up.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_is_not_running_on_the_expected_hosts.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme1n1_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme2n1_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme3n1_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdb_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdc_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_queries_failing_due_to_memory_limit_exceeded.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_read_only_mode.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_rejects_inserts.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue30.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue450.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replication_queue_filling_up.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/clickhouse/zookeeper_clickhouse_is_not_running_on_the_expected_hosts.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards-elasticsearch.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_client_search_error_rate.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme1n1_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme2n1_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdb_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdc_used.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_is_not_running_on_the_expected_hosts.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status-elasticsearch.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_root_disk_full.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/cpu_usage_ratio_requests_instana_k8s_pod_filler.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_rollup_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_writes_failing.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_error_rate.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_lag.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_info_event_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_kafka_rollup_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_lag.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_metric_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_outdated_snapshots.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_events_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_message_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_metrics_error_rate.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_change_dropping.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_processing.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_expiring_snapshots.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_fetching.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/groundskeeper/synthetics_groundskeeper_datacenter_activation_error.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_high_io_wait.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_open_files.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_under_replicated_partitions.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/log-health-processor/lhp_lagging_incoming_logs.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_one_percent_of_test_results.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_test_results.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_not_receiving_test_results.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_kafka_failing.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_addon_license_error.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_external_storage_write_error.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_queued_calls.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_select_failure.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_external_storage_read_error.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_writer_clickhouse_insert_failure.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_cleanup_stalled.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_snapshots.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_propagation_actions.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_sets.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tagged_metrics.json create mode 100644 packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_snapshot_lag.json create mode 100644 packages/@instana-integration/instana-self-monitoring/package.json diff --git a/packages/@instana-integration/instana-self-monitoring/README.md b/packages/@instana-integration/instana-self-monitoring/README.md new file mode 100644 index 0000000..9d2ae41 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/README.md @@ -0,0 +1,147 @@ +# @instana-integration/instana-self-monitoring + +This integration package provides dashboards and event monitoring to support self-observability for Instana’s internal systems. + +## Dashboards + +Below are the dashboards that are currently supported by this integration package. + +| Dashboard Title | Description | +|--------------------------------------------------------|----------------------------------------------------------------------------------------| +| OAC - Self Monitoring: profile related pipelines | Monitors health and activity of pipelines related to profiling functionality. | +| OAC - Self Monitoring: scale high perf metrics down | Tracks how high-performance metric services behave during scale-down. | +| OAC - Self Monitoring: scale high perf processor down | Observes performance and resource usage when scaling down high-perf processors. | +| OAC - Self Monitoring: scale high perf spans down | Monitors system behavior when scaling down span-handling components in high-perf mode. | +| OAC - Self Monitoring: scale high perf ui profile down | Tracks UI profiling components under high-performance scale-down scenarios. | +| OAC - Self Monitoring: scale metrics profile down | Provides insights into metric profiling as related components are scaled down. | +| OAC - Self Monitoring: scale processor down | Visualizes resource and performance metrics during standard processor scale-down. | +| OAC - Self Monitoring: scale spans profile down | Monitors how span profiles react to downscaling actions. | +| OAC - Self Monitoring: scale ui profile down | Evaluates the impact of scaling down UI profiling modules. | +| OAC - Self Monitoring: Usage k8s components | Displays usage and performance of Kubernetes components across the cluster. | + + +## Metrics + +### Semantic Conventions + +Below are the runtime metrics that are currently supported by this integration package. + +[None] + +### Resource Attributes + +Below are the resource attributes that are currently supported by this integration package. + +[None] + +## Events + +Below are the events that are currently supported by this integration package. + +Note: In each event definition, conditionValue represents a threshold used to trigger the event and is provided as a default or reference value. Please adjust this value based on your specific environment. + +| Event Name | Description | +|---------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| [SRESLO] Acceptor HTTP job queue is filling up [TF] | The HTTP threads of this instance do not seem to be able to handle the number of incoming requests causing job queue to fill up. This may eventually result in rejected HTTP requests and Acceptor responding with HTTP status code ENHANCE_YOUR_CALM. Potential causes for this are the respective Acceptor instance receiving too much traffic or problems with the Kafka cluster. | +| [SRESLO] Acceptor spans_error_rate rate is too high [TF] | This indicates problems with either too high load on the individual Acceptor node or problems with the Kafka cluster in this region and leads to gaps in metrics and calls for customers. | +| appdata-processor - Failed to heal online infra graph [TF] | https://www.notion.so/instana/appdata-processor-Failure-to-heal-online-infra-graph-8daaf2073f0143f790607e78abb4a663 | +| appdata-processor - Failed to heal online snapshots [TF] | https://www.notion.so/instana/appdata-processor-failed-to-heal-online-snapshots-c36dd6b9f2ec4a26ac4717d92c1911ba | +| [SRETUSLO] appdata-processor is dropping > 25% spans [TF] | This can lead to missing traces and results in wrong call counts. Possible reasons are an increase in ingress for the customer or that the component is running on an overloaded worker. If the traffic is reasonable (e.g. not spikes through load tests) consider scaling the spans profile for this TU up or scale out appdata-processor. See also https://www.notion.so/instana/appdata-processor-Spans-are-being-dropped-173977adc97d4e1b9b08bbbc7e56b8ec | +| appdata-processor - service explosion [TF] | https://www.notion.so/instana/appdata-processor-Service-explosion-6794827fd9484a1cb557c06c7f7ce969 | +| [SRESLO] Butler HTTP thread pool is very busy [TF] | The HTTP threads of this instance do not seem to be able to handle the number of incoming requests causing job queue to fill up. This may eventually result in OOPS page in web-UI. Potential cause for this is butler produce exceeded db access(queries) to PostgreSQL(butler) in rainbow. You might need to check the PostgreSQL in rainbow. | +| [SRESLO] Butler http thread is very busy [TF] | The HTTP threads of this instance do not seem to be able to handle the number of incoming requests causing job queue to fill up. This may eventually result in OOPS page in web-UI. Potential cause for this is butler produce exceeded db access(queries) to PostgreSQL(butler) in rainbow. You might need to check the PostgreSQL in rainbow. | +| [SREInfraSLO] metrics-cassandra node unreachable for > 5m [TF] | A node in the metrics-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards. | +| [SREInfraSLO] profiles-cassandra node unreachable for > 5m [TF] | A node in the profiles-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards. | +| [SREInfraSLO] spans-cassandra node unreachable for > 5m [TF] | A node in the spans-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards. | +| [SREInfraSLO] state-cassandra node unreachable for > 5m [TF] | A node in the state-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards. | +| [SREInfraSLO] state-cassandra write latency greater than 1 minute [TF] | A node in the state-cassandra cluster is having very high write latency. This indicates a major issue which will affect dependent components like tag-processor. Try restarting the node. | +| ClickHouse - AP - Too many parts in one of the partitions of the XXX table [TF] | https://www.notion.so/instana/ClickHouse-Too-many-parts-in-one-of-the-partitions-of-the-XXX-table-01b7add852d74a499ed0216115ed8804. ##Note: The 'conditionValue' (currently set to 830) is a sample reference for the variable 'active_parts_threshold'. Please adjust this value based on your specific environment. | +| ClickHouse - AP - Too Many inserts are rejected [TF] | The data is getting lost. Caused by 'Too many parts' exception due to high number of active data parts for partition. https://www.notion.so/instana/ClickHouse-Too-many-parts-in-one-of-the-partitions-of-the-XXX-table-01b7add852d74a499ed0216115ed8804. ##Note: The 'conditionValue' (currently set to 13500) is a sample reference for the variable 'clickhouse_rejected_inserts_threshold'. Please adjust this value based on your specific environment. | +| ClickHouse - AP - Too many simultaneous queries [TF] | https://www.notion.so/instana/ClickHouse-Too-many-simultaneous-queries-8adf725a6c4c49088eee518b1af6880e | +| [SREInfraSLO] ClickHouse - Distribution queue is filling up [TF] | https://www.notion.so/instana/Clickhouse-Distribution-queue-is-filling-up-9453591a12df4a5bb9e27 | +| [SREInfraSLO] ClickHouse is not running on the host. [TF] | The ClickHouse process is not running on the underlying host. This can be caused by issues related to the replication process. Please check ClickHouse logs for any recurring exceptions / errors and if none are present you [start the ClickHouse recovery process](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/#recovery-after-failures). | +| [SREInfraSLO] Clickhouse disk fs./dev/nvme1n1.used more than 85% full. [TF] | This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/nvme1n1.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards. | +| [SREInfraSLO] Clickhouse disk fs./dev/nvme2n1.used more than 85% full. [TF] | This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/nvme2n1.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards. | +| [SREInfraSLO] Clickhouse disk fs./dev/nvme3n1.used more than 85% full. [TF] | This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/nvme3n1.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards. | +| [SREInfraSLO] Clickhouse disk fs./dev/sdb.used more than 85% full. [TF] | This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/sdb.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards. | +| [SREInfraSLO] Clickhouse disk fs./dev/sdc.used more than 85% full. [TF] | This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/sdc.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards. | +| ClickHouse - Queries failing due to memory limit exceeded [TF] | https://www.notion.so/instana/ClickHouse-Queries-failing-due-to-memory-limit-exceeded-8f2a3e6daea2438eb97289c0892459f2 | +| [SREInfraSLO] ClickHouse replica is in read-only mode for > 1m [TF] | This can occur if there is an unknown error during (re)initialization of sessions with Zookeeper, or during session reinitialization in ZK itself. Run the following command on the alerting ClickHouse node to verify that the replica is still in read-only mode. Initiate Clickhouse client first via root user using the following command: `clickhouse-client` Once client has started, use: `SELECT * FROM system.replicas WHERE is_readonly = 1 LIMIT 10;` If nothing points to more severe problems, try to **restart the ClickHouse node that contains the read-only replica.** | +| ClickHouse - Inserts are rejected [TF] | The data is getting lost. Caused by 'Too many parts' exception due to high number of active data parts for partition. https://www.notion.so/instana/ClickHouse-Too-many-parts-in-one-of-the-partitions-of-the-XXX-table-01b7add852d74a499ed0216115ed8804 | +| ClickHouse - Replica Max Insert Queue Filling Up [TF] | There is an increase of files that are stockpiling at the Clickhouse level. The associated graph in SRE:Clickhouse-AP should highlight whether this is a collection of CH nodes, or if a single CH node is handling most of the files that are piling up. Additionally, Appdata-Writer errors may be present and may need investigation. | +| ClickHouse - Replica Max Insert Queue Filling Up [TF] | There is an increase in insertions for a Clickhouse server, or multiple servers. There may also be an increase in Distributed Files to Insert. Additional items to check are Appdata-Writer Clickhouse Error Rates. For a development perspective of this error: https://www.notion.so/instana/ClickHouse-Replication-queue-is-filling-up-405a445e25be4316add4cca943bf9d20 | +| ClickHouse - Replication queue is filling up [TF] | https://www.notion.so/instana/ClickHouse-Replication-queue-filling-up-405a445e25be4316add4cca943bf9d20 | +| [SREInfraSLO] Zookeeper is not running for Clickhouse. [TF] | The Zookeeper process is not running on the underlying host. This will prevent Clickhouse from functioning untill it is restored. | +| [SREInfraSLO] Elasticsearch-NG has high number of unassigned shards [TF] | Number of unassigned shards are increasing and is above 5. This can indicate underlying resource issue. There may not be enough elastic data nodes to assign the new shards. | +| [SREInfraSLO] Elasticsearch-NG has high number of unassigned shards [TF] | Number of unassigned shards are increasing and is above 5. This can indicate underlying resource issue. There may not be enough elastic data nodes to assign the new shards. | +| [EXPTUSLO] High ES Client Search Error Rate [TF] | Searches from this component to ElasticSearch are failing at a high rate. ## Consequences - If this is a user facing component, users may be seeing errors on the UI - If this is a processing component, processing may not be proceeding as fast as necessary, or data may be out of sync, leading to incorrect information being shown on the UI ## Remediation - Check that ElasticSearch (NG) is healthy in this region. - Check that this component is able to connect to Elasticsearch - If the error rate is very high, and ES is otherwise healthy, a component restart may resolve the issue | +| [SREInfraSLO] elasticsearch data disk utilized > 85% [TF] | The elasticsearch disk usage for data is greater than 85%. This indicates the disk is getting closer to max capacity. This may require cleanup of disk space. If not addressed in time, it may cause the node to stop working and possibly leave the cluster. | +| [SREInfraSLO] elasticsearch data disk utilized > 85% [TF] | The elasticsearch disk usage for data is greater than 85%. This indicates the disk is getting closer to max capacity. This may require cleanup of disk space. If not addressed in time, it may cause the node to stop working and possibly leave the cluster. | +| [SREInfraSLO] elasticsearch data disk utilized > 85% [TF] | The elasticsearch disk usage for data is greater than 85%. This indicate the disk is getting closer to max capacity. This may require to cleanup the disk space. If this is not fixed on time, it may cause the node stop working and possible leave the cluster. | +| [SREInfraSLO] elasticsearch data disk utilized > 85% [TF] | The elasticsearch disk usage for data is greater than 85%. This indicates the disk is getting closer to max capacity. This may require cleanup of disk space. If not addressed in time, it may cause the node to stop working and possibly leave the cluster. | +| [SREInfraSLO] Elasticsearch is not running on the host. [TF] | The Elasticsearch process is not running on the underlying host. Please check Elasticsearch logs for any recurring exceptions / errors and if none are present restart the process | +| [SREInfraSLO] elasticsearch is in red status [TF] | Elasticsearch is in red status. This indicates that at least one primary shard and all of its replicas are not allocated to a node, meaning that some data is unavailable. Please check this issue as it will impact read/write operations. | +| [SREInfraSLO] elasticsearch is in red status [TF] | Elasticsearch is in red status. This indicates that at least one primary shard and all of its replicas are not allocated to a node, meaning that some data is unavailable. Please check this issue as it will impact read/write operations. | +| [SREInfraSLO] elasticsearch root disk utilized > 85% [TF] | The elasticsearch disk usage for root is greater than 85%. This indicate the disk is getting closer to max capacity around 20G. This may require to cleanup the disk space. If this is not fixed on time, it may cause the node stop working and possible leave the cluster. | +| [DEVTUSLO] Instana filler pod CPU usage to CPU requests > 200% [TF] | This Instana filler pod's CPU usage is over twice the CPU requests for more than 1h. This either indicates that the pod has too little requests and should be resized or that there is a problem with an upstream component (e.g. spike in usage on a specific pod). | +| [SRETUSLO] filler is dropping > 10% Cassandra rollups [TF] | Rollups are being dropped before being written to Metrics Cassandra. This can be caused by too high load on the worker node or high processing pressure on the filler. ## Consequences This means there will be gaps in historical data for metrics. ## Remediation - Increase the TU toggle `config.rollup.cassandra.downstream.threads` (Default is 1. Shouldn't be more than 4). To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ) | +| [SRETUSLO] filler writes to Cassandra are failing [TF] | There is a high error rate when trying to write rollups to Cassandra. This can be caused by bugs (e.g. unsupported rollups used) or *a lot more likely* a broken connection between `filler` and Metrics Cassandra or general Metrics Cassandra problems. ## Consequences Alerting and live metrics viewing in the UI will be affected. ## Remediation - Check whether Cassandra is accessible from `filler`. - Otherwise report to team Infrastructure. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ) | +| [EXPTUSLO] filler is failing to publish group member data [TF] | Sending group members to the group processing instance is failing at a high rate. This probably indicates a serious issue with the kafka producer. ## Consequences Group entities will not be updated ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=5ilU_JJoTuWHKd9uz1PKXQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=WnDP6tKCTTOKCBIeR9Dx1w) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=1eqIS6ThSrud09h-fZzLRA) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=n1ruCLQvQhm--a1IbkXxyw) | +| [EXPTUSLO] group member metrics data are delayed [TF] | Group member aggregation is being processed with a long delay - this means group member metrics are very delayed This is a sign that GroupMemberDataSource in Filler cannot keep up with the number data messages are written to the group_members topic. ## Consequences Group member metrics and entities might be dropped and may display an incorrect data ## Remediation - scale saas_instanaops_*_group_members topic to multiple partitions to allow multiple Filler instances to consume the group members topic To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=5ilU_JJoTuWHKd9uz1PKXQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=WnDP6tKCTTOKCBIeR9Dx1w) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=1eqIS6ThSrud09h-fZzLRA) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=n1ruCLQvQhm--a1IbkXxyw) | +| [SRETUSLO] filler is dropping info events [TF] | Events are being dropped before being published to the events kafka topic. ## Consequences This will cause alerts not to be triggered. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. - Check the logs to see if any unexpected errors have occurred. - If the metric `com.instana.filler.raw-messages.processed` has dropped to zero, no messages are flowing and `filler`. - Take a heap dump and inform team Infrastructure - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg) | +| [SRETUSLO] filler is dropping > 10% Kafka rollups [TF] | Rollups are being dropped before being written to Kafka. This can be caused by too high load on the worker node or high processing pressure on the filler. ## Consequences Alerting and live metrics viewing in the UI will be affected. ## Remediation - Increasing the TU toggle `config.rollup.kafka.downstream.threads` (Default is 1. Shouldn't be more than 4). To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ) | +| [SRETUSLO] filler raw message lag > 5 seconds [TF] | Filler raw message processing is lagging. The lag has been greater than five seconds for the last fifteen minutes. ## Consequences We are ingesting both tags and metrics more slowly than we should. Data will not become available in Instana in a timely fashion or might be dropped. ## Remediation Steps to take _until remediation_ - Upsize the metrics profile for the TU. - Move this filler to the highperf nodepool. - Move off other high-load components running on the same worker. - Scale out the filler. | +| [EXPTUSLO] filler outdated snapshots [TF] | There is a difference in the snapshot cache and the snapshot state from ElasticSearch. ## Consequences If this condition persists, it could lead to outdated entities. ## Remediation - Check ElasticSearch cluster load. - If this is specific to this tenant, possibly there are too many online snapshots. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=WgHDS_DRRSWjVYOzKoojeg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=gjymdolcRCmhsSBDYa9tEw) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=d4cBzHW5Se-zzmtgQ9SLsw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=OYEqU6yTTFmsdkhnuPNidQ) | +| [SRETUSLO] filler is dropping raw events [TF] | Raw events are being dropped before being published to the raw_events kafka topic. ## Consequences This will cause alerts not to be triggered. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. - Check the logs to see if any unexpected errors have occurred. - If the metric `com.instana.filler.raw-messages.processed` has dropped to zero, no messages are flowing and `filler`. - Take a heap dump and inform team Infrastructure - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg) | +| [SRETUSLO] filler is dropping > 15% raw messages [TF] | Raw messages, i.e. messages coming from agents, are being dropped. This is a sign that `filler` is running with too little resources or on a over-utilized host. ## Consequences This will cause gaps in metrics dashboards, broken alerting and permanent online/offline events. ## Remediation Steps to take _until remediation_ - Upsize the metrics profile for the TU. - Move this filler to the highperf nodepool. - Move off other high-load components running on the same worker. - Scale out the filler. If all the above have been done, then the filler is likely hitting limits in the snapshot processing pipeline. The infra team is working on improving limits and performance for the snapshot processing pipeline, but please inform team infra for further investigations. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg) | +| [EXPTUSLO] filler is failing to publish raw metric data [TF] | Sending raw metrics to kafka (for beeinstana ingestion) is failing at a high rate. This probably indicates a serious issue with the kafka producer. ## Consequences Metrics will be lost. ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ) | +| [SRETUSLO] filler is dropping snapshot changes [TF] | Snapshot changes are being dropped before being written to ElasticSearch. This is a sign that `filler` is running with too little resources or on a over-utilized host. ## Consequences All reporting entities in this TU will go offline and there will effectively be no infrastructure monitoring. ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg) | +| [EXPTUSLO] filler is not processing any snapshot data [TF] | Filler is not processing any entity heartbeats, which means it is not processing any snapshots. ## Consequences All reporting entities in this TU will go offline and there will effectively be no infrastructure monitoring. ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ) | +| [EXPTUSLO] filler stopped synchronizing ES search index [TF] | Check for unexpired snapshots has not successfully run. ## Consequences If this condition persists, it could lead to DFQ searches not returning correct results ## Remediation - Check ElasticSearch cluster load. - Check `filler` logs. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=WgHDS_DRRSWjVYOzKoojeg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=gjymdolcRCmhsSBDYa9tEw) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=d4cBzHW5Se-zzmtgQ9SLsw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=OYEqU6yTTFmsdkhnuPNidQ) | +| [SRETUSLO] filler stopped fetching raw messages [TF] | Metrics may not have been flowing for several minutes. ## Consequences If this condition persists, it will result in loss of metrics. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. - Check the logs to see if any unexpected errors have occurred. - If the metric `com.instana.filler.raw-messages.processed` has dropped to zero, no messages are flowing in `filler`. - Take a heap dump and inform team Infrastructure - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg) | +| [SRESLO] Synthetics Datacenter Activation Errors [TF] | This indicates problems in the Synthetics Datacenter Activation / Managed Location Deployment process. | +| [SREInfraSLO] Kafka node is showing high I/O wait times [TF] | A Kafka node is showing high wait times for a longer period of time. This can indicate underlying hardware issues (in case of local SSDS), a general load issue with the Kafka cluster in that region or a load increase for a certain customers whos partitions are located on that node. In case of hardware failures, replace the node in questions. Otherwise look into balancing topics acros the cluster to spread the load. | +| [SREInfraSLO] Kafka node is approaching max open files [TF] | A Kafka node has too many open files. This can result in a crash or restart of one or more kafka nodes in the cluster. Collect logs, check the kafka service on the host is running, and restart if necessary. | +| [SREInfraSLO] Kafka node has under replicated topic partitions [TF] | There are under replicated topic partitions on a Kafka node for a longer period of time. This can indicate one or more Kafka nodes are down or the Kafka cluster is overloaded and followers can't catch up from leaders. In case of hardware failures, replace the node in questions. If it's cluster overloaded, consider to expand Kafka cluster. If the node is overloaded(significant topics on the node) instead of the whole cluster, try to balance the topics across the cluster. | +| [DevSLO] Incoming logs are lagging [TF] | LHP is significantly lagging to consume from `enriched_logs` topic. This can result in `false positives` (e.g. wrong unusual low number of logs detected) or `false negatives` (no detection) in Smart-Alerts. Even when the dropping metrics indicate a low dropping rate of logs, depending on the lag and Smart Alert rule, this can mean that there is hidden dropping, either by hitting the Kafka retention limits, or by the fact that the logs are consumed too late to be considered. **Action Item:** Check the internal dashboard for dropping and lag of logs, and whether the bottleneck is the processing capacity of LHP, or originating upstream. | +| [DevSLO] synthetics-health-processor is dropping test results [TF] | `synthetics-health-processor is dropping more than 1% of incoming test results.`Action Item:`Check the internal dashboard for dropping, and whether this is just due to a general increase in incoming test results:` - if `yes`: Ask SRE to scale-out - if `no`: Investigate whether a performance problem or bug was introduced | +| [DevSLO] synthetics-health-processor is dropping test results [TF] | `synthetics-health-processor is dropping more than 10% of incoming test results.` `Action Item:`Check the internal dashboard for dropping, and whether this is just due to a general increase in incoming test results: - if `yes`: Ask SRE to scale-out - if `no`: Investigate whether a performance problem or bug was introduced | +| [DevSLO] synthetics-health-processor is not receiving test results [TF] | `synthetics-health-processor is not receiving test results.` `Action Item:` Most likely there is a problem in synthetics-health-processor or in the components upstream: - As a quick fix, ask SRE to restart - Investigate whether a problem or bug was introduced in synthetics-health-processor or upstream components | +| [SLO] Writes of health events to Kafka are failing [TF] | Failed writes of health events to Kafka means loss of events in the events product area and loss of alerts send out to the alert channels. Check the logs and the network between this node and the Kafka nodes. | +| [SRESLO] Synthetics Acceptor Addon License Errors [TF] | This indicates problems with the Synthetics Acceptor receiving data from a Managed location for a TU that does not have a synthetic addon license purchased. | +| [SRESLO] Synthetics Acceptor External Storage Write Errors [TF] | This indicates problems with the Synthetics Acceptor inserting data to the External Storage. | +| [SRESLO] Synthetics Reader ClickHouse Queued Calls [TF] | This indicates problems with the Synthetics Reader queuing calls to retrieve data from ClickHouse. ## Consequences This will cause Synthetics Tests and Locations pages to timeout without showing any data. ## Remediation - If the metric `metrics.gauges.clickHouse.clustered.queuedCalls` is high, the execution time of all calls will increase causing timeouts: - Take a thread dump of the `synthetics-reader` pods and inform team Synthetics - Restart `synthetics-reader` | +| [SRESLO] Synthetics Reader ClickHouse Select Failures [TF] | This indicates problems with the Synthetics Reader retrieving data from ClickHouse. | +| [DevSLO] - Synthetics Reader External Storage Read Errors [TF] | This indicates problems with the Synthetics Reader retrieving data from the External Storage. | +| [SRESLO] Synthetics Writer ClickHouse Insert Failures [TF] | This indicates problems with the Synthetics Writer inserting data in ClickHouse. | +| [SRESLO] tag-processor is not cleaning up tag sets [TF] | Tag processor is is not running the cleanup of tag sets. ## Consequences Changes which have been dropped will not be fixed and updates to tag sets will not be reflected. This could cause some entities to not show up in searches and smart alerts based on these tags become unreliable and have false alerts. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Cassandra and Kafka. - Consider a rolling restart of pods - Inform engineering | +| [SRESLO] tag-processor is dropping snapshot updates [TF] | Tag processor is dropping records when reading the `snapshots` topic to reduce latency. This means tag-processor is having trouble keeping up with the number of snapshot updates for some TUs. ## Consequences As long as this occurs, there may be delays in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka. - Consider increasing the number of tag-processor instances to keep up with increased load. You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.SnapshotUpdateDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg) | +| [DEVSLO] tag-processor is dropping tag propagation actions [TF] | Tag processor is having trouble keeping up with tag changes and tag propagation for some TUs. ## Consequences As long as this occurs, there may be delays in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka or State Cassandra. - Consider increasing the number of tag-processor instances to keep up with increased load. You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.TagPropagationActionDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg) | +| [SRESLO] tag-processor is dropping tag set updates [TF] | Tag processor is having trouble writing tag sets into Elasticsearch for some TUs. ## Consequences As long as this occurs, there may be delays in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka or Elasticsearch. - Consider increasing the number of tag-processor instances to keep up with increased load. You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.TagSetUpdateDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg) | +| [SRESLO] tag-processor is dropping tagged metrics [TF] | Tag processor is having trouble keeping up with the number of tagged metrics that are being published from some TUs. ## Consequences As long as this occurs, there may be delays in multi-dimensional metrics in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka. - Consider increasing the number of tag-processor instances to keep up with increased load. - Consider decreasing the filler tagged metric publish count You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.TaggedMetricDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg) | +| [SRESLO] tag-processor is lagging [TF] | Updates written to ES are not live - we have some lag in some part of the tag-processor pipeline. This can come from: - latency writing into ES - latency in State Cassandra - latency writing to Kafka - High GC or High CPU from too many upstream updates ## Consequences There will be delays and possibly data-loss for changes that are occurring in customer environments in Custom Dashboards or Infrastructure Analyze. ## Remediation Steps to take _until remediation_ - Consider adjusting the dropping configuration e.g. decrease `config.tag.processor.start.dropping.age.ms` to enforce more dropping and reduce lag. - Verify that there are no issues with Kafka or Elasticsearch. - Consider increasing the number of tag-processor instances to keep up with increased load. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg) | + +## Installation and Usage + +With [Instana CLI for integration package management](https://github.com/instana/observability-as-code?tab=readme-ov-file#instana-cli-for-integration-package-management), you can manage the lifecycle of this package, such as downloading the package and importing it into Instana. You can find the available binaries for the CLI on different platforms on the [release page of this project](https://github.com/instana/observability-as-code/releases). Select the binary from the latest release that matches your platform to download, then rename it to stanctl-integration. You should now be able to run it on your local machine. + +Downloading the package: + +```shell +$ stanctl-integration download --package @instana-integration/instana-self-monitoring +``` + +Importing the package into Instana: + +```shell +$ stanctl-integration import --package @instana-integration/instana-self-monitoring + --server $INSTANA_SERVER + --token $API_TOKEN + --set servicename=$SERVICE_NAME + --set serviceinstanceid=$SERVICE_INSTANCE_ID +``` + +- INSTANA_SERVER: This is the base URL of an Instana tenant unit, e.g. https://test-example.instana.io, which is used by the CLI to communicate with Instana server for package lifecycle management. +- API_TOKEN: Requests against the Instana API require valid API tokens. The API token can be generated via the Instana user interface. For more information, please refer to [Instana documentation](https://www.ibm.com/docs/en/instana-observability/current?topic=apis-instana-rest-api#usage-of-api-token). +- SERVICE_NAME: Logical name of the service. +- SERVICE_INSTANCE_ID: The string ID of the service instance. The ID helps to distinguish instances of the same service that exist at the same time (e.g. instances of a horizontally scaled service). \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__profile_related_pipelines.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__profile_related_pipelines.json new file mode 100644 index 0000000..70ae89d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__profile_related_pipelines.json @@ -0,0 +1,2223 @@ +{ + "id": "GNeisQvUTdyw3ZuaSXwC8w", + "title": "Self Monitoring: profile related pipelines", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "1o2diO-Hl3t5_OfP", + "title": "log-processor: error rate", + "width": 4, + "height": 17, + "x": 0, + "y": 124, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.processing.trace_logs.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.processing.trace_logs.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Duplicate of Dropwizard meter KPI.processing.trace_logs.errors", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.trace_logs.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.trace_logs.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "iv13WQbEW0fhK4NK", + "title": "Kafka Node under replicated partitions", + "width": 12, + "height": 13, + "x": 0, + "y": 141, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "kafka", + "metricPath": [ + "Others", + "Kafka Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "broker.underReplicatedPartitions", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Under-replicated Partitions", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "BgvigXlJKNjJydDi", + "title": "otlp-acceptor error rate", + "width": 3, + "height": 13, + "x": 6, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "grpc.server.concurrencyLimit.acquire.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.grpc.server.concurrencyLimit.acquire.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "otlp-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge grpc.server.concurrencyLimit.acquire.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "grpc.server.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.grpc.server.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "otlp-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge grpc.server.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.outgoing.spans.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.outgoing.spans.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "otlp-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.outgoing.spans.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.processing.span_messages.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.processing.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "otlp-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.processing.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.log.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "otlp-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge log.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "5eUvgRapk1m6DGpc", + "title": "tag-processor Dropping", + "width": 4, + "height": 15, + "x": 0, + "y": 38, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Tag Sets", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.com.instana.tags.processing.TagSetUpdateDropper.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.tags.processing.TagSetUpdateDropper.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Snapshots", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.com.instana.tags.processing.SnapshotUpdateDropper.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.tags.processing.SnapshotUpdateDropper.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Tagged Metrics", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.com.instana.tags.processing.TaggedMetricDropper.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.tags.processing.TaggedMetricDropper.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Tagged Propagation Actions", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.com.instana.tags.processing.TagPropagationActionDropper.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.namespace.name", + "type": "TAG_FILTER", + "value": "instana-blue", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.tags.processing.TagPropagationActionDropper.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "dWtI_wmXRGbEqaay", + "title": "Acceptor Error Rate top 5", + "width": 3, + "height": 13, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.outgoing.spans.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.outgoing.spans.error_rate", + "crossSeriesAggregation": "MAX" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "HyHk3YdIm-YDiTRm", + "title": "Processor (metrics profile)", + "width": 12, + "height": 6, + "x": 0, + "y": 66, + "type": "markdown", + "config": "This is useful widgets for processor errors" + }, + { + "id": "w1eYaMkw8O5V4wD8", + "title": "TU Processor droppping incidents top 5 (max)", + "width": 12, + "height": 13, + "x": 0, + "y": 72, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "Processor incoming error rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "0W1xPF6xxH8TIqZl", + "title": "Logging pipeline (spans profile)", + "width": 12, + "height": 6, + "x": 0, + "y": 118, + "type": "markdown", + "config": "This is useful widgets for logging errors" + }, + { + "id": "rKfoHY3bM-VMKy9k", + "title": "Metrics (infrastructure) pipeline (metrics profile)", + "width": 12, + "height": 6, + "x": 0, + "y": 19, + "type": "markdown", + "config": "This is useful widgets for metrics pipeline errors" + }, + { + "id": "73niR7Zd6zu7nQ1O", + "title": "Beeinstana agg Kafka Error Count", + "width": 4, + "height": 15, + "x": 4, + "y": 38, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "SUM", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "beeInstanaNode", + "metricPath": [ + "Others", + "BeeInstana Server" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "Aggregator.KafkaCommon.KafkaError.sum", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Aggregator metric KafkaCommon.KafkaError.sum", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "zIYqNSh417zksgzf", + "title": "log-writer: outgoing error_rate", + "width": 4, + "height": 17, + "x": 8, + "y": 124, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log_tag_sets_error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.outgoing.log_tag_sets.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.outgoing.log_tag_sets.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "cDlg_9NheTwgnWpl", + "title": "tag-reader Error rate", + "width": 4, + "height": 15, + "x": 8, + "y": 38, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "InstanaElasticsearchClient.GetIndexRequest.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.com.instana.elastic.InstanaElasticsearchClient.GetIndexRequest.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag-reader", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.elastic.InstanaElasticsearchClient.GetIndexRequest.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "InstanaElasticsearchClient.SearchRequest.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.com.instana.elastic.InstanaElasticsearchClient.SearchRequest.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag-reader", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.elastic.InstanaElasticsearchClient.SearchRequest.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "grpc.server.concurrencyLimit.acquire.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.grpc.server.concurrencyLimit.acquire.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag-reader", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge grpc.server.concurrencyLimit.acquire.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "grpc.server.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.grpc.server.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag-reader", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge grpc.server.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.log.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag-reader", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge log.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "BezsD4UCvyXOfNx0", + "title": "appdata-reader : clickHouse.clustered.error_rate", + "width": 4, + "height": 14, + "x": 8, + "y": 104, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "appdata-reader : clickHouse.clustered.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.clickHouse.clustered.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-reader", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge clickHouse.clustered.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "p3PNduR81rSVZw6H", + "title": "TU Raw message dropping Top 5", + "width": 12, + "height": 13, + "x": 0, + "y": 25, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "kVqeR3lsjEgS6iXI", + "title": "log-writer: incoming error rate", + "width": 4, + "height": 17, + "x": 4, + "y": 124, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "tag-sets-error-rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.tag_sets.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.tag_sets.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log-messages-error-rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.log_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.log_messages.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log_tag_sets_error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.log_tag_sets.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.log_tag_sets.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "TiHAQKxzcACnjmjo", + "title": "TU Span dropping Incidents Top 5", + "width": 12, + "height": 13, + "x": 0, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "8uZsVwVdz4Qg71--", + "title": "appdata-writer: Clickhouse Error Rate", + "width": 4, + "height": 14, + "x": 0, + "y": 104, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "insert.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.com.instana.clickhouse.client.ClickHouseHttpClient.insert.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-writer", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge com.instana.clickhouse.client.ClickHouseHttpClient.insert.error_rate", + "crossSeriesAggregation": "SUM" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "clickhouse clustered error rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.clickHouse.clustered.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-writer", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge clickHouse.clustered.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ByMhOEuC688WXw9W", + "title": "Elasticsearch unassigned shards", + "width": 9, + "height": 13, + "x": 0, + "y": 53, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "cRed", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "elasticsearchCluster", + "metricPath": [ + "ElasticSearch", + "Elasticsearch Cluster" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "unassigned_shards", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Unassigned Shards", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "9iXhP9v78e9T9bzS", + "title": "Application pipeline (spans profile)", + "width": 12, + "height": 6, + "x": 0, + "y": 85, + "type": "markdown", + "config": "This is useful widgets for application pipeline errors" + }, + { + "id": "vhTPZbcbcipX-xKJ", + "title": "Acceptor", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "This is useful widgets for acceptor errors" + }, + { + "id": "MAiMEB3o-8kOxAoH", + "title": "serverless-acceptor error rate", + "width": 3, + "height": 13, + "x": 3, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.outgoing.spans.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "unit": "number", + "metric": "metrics.gauges.KPI.outgoing.spans.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.outgoing.spans.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.processing.bundle_messages.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "unit": "number", + "metric": "metrics.gauges.KPI.processing.bundle_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.processing.bundle_messages.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.processing.span_messages.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "unit": "number", + "metric": "metrics.gauges.KPI.processing.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.processing.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "unit": "number", + "metric": "metrics.gauges.log.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge log.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [], + "formatterSelected": false + }, + "type": "TIME_SERIES" + } + }, + { + "id": "sIQBnSNWZdbFDAxC", + "title": "appdata-live-agg: Error Rate", + "width": 4, + "height": 14, + "x": 4, + "y": 104, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "grpc.server.concurrencyLimit.acquire.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.grpc.server.concurrencyLimit.acquire.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-live-aggregator", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge grpc.server.concurrencyLimit.acquire.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "grpc.server.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.grpc.server.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-live-aggregator", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge grpc.server.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.deserializing.calls.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.deserializing.calls.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-live-aggregator", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.deserializing.calls.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "KPI.incoming.calls.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.calls.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-live-aggregator", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.calls.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.log.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.pod.label", + "type": "TAG_FILTER", + "value": "appdata-live-aggregator", + "key": "app", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge log.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "m6IuJINL6SF_qUJn", + "title": "EUM acceptor error rate", + "width": 3, + "height": 13, + "x": 9, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "userTimestampTrustAttempts.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.instana.beaconProcessing.userTimestampTrustAttempts.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge instana.beaconProcessing.userTimestampTrustAttempts.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "mobile.userTimestampTrustAttempts.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.instana.mobileBeaconProcessing.userTimestampTrustAttempts.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge instana.mobileBeaconProcessing.userTimestampTrustAttempts.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "kafka.beacons.writes.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.kafka.beacons.writes.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge kafka.beacons.writes.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "kafka.spans.writes.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.kafka.spans.writes.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge kafka.spans.writes.error_rate", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "log.error_rate", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "formatter": "number.detailed", + "unit": "number", + "metric": "metrics.gauges.log.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge log.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_metrics_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_metrics_down.json new file mode 100644 index 0000000..574209d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_metrics_down.json @@ -0,0 +1,4647 @@ +{ + "id": "cSuGFLJaSBaNfTa3C_uB9g", + "title": "Self Monitoring: scale high perf metrics down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "GIKreYfAmX7fdcxD", + "title": "metrics_xxxl CPU total (top 50)", + "width": 3, + "height": 18, + "x": 6, + "y": 60, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "idlyHX5tTK7OMXaF", + "title": "metrics_xxl (24GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 99, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "c1hUuk8Q3_FHw9pK", + "title": "metrics_xxxl TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "hDaZ4zQ8eEWgcmbE", + "title": "metrics_xl pod count", + "width": 3, + "height": 16, + "x": 9, + "y": 137, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "HxgiIovbOXZ8rclH", + "title": "Custom Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "qF4wpeXuni6m_HFB", + "title": "TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "iZkCLjJFcmmganRS", + "title": "metrics_l TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 159, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "zone" + } + ], + "name": "zone", + "availability": [], + "type": "STRING" + }, + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "pxUM8pCpwEjiUJZS", + "title": "metrics_xl TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 122, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "08oAX4hXquZ5mMOa", + "title": "metrics_xl bottom 10 metric count per pod (max 900k metrics [coral])", + "width": 3, + "height": 15, + "x": 0, + "y": 122, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "kor8PuXeI_FZGtVH", + "title": "metrics_xl JVM mem used %", + "width": 3, + "height": 16, + "x": 3, + "y": 137, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "tJ0-i92l75mDg7Vi", + "title": "metrics_xxxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 39, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "UkxicvTqfeiaiKMg", + "title": "metrics_xl Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 122, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "NnkqJutcuZO67_HH", + "title": "metrics_xl Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 122, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "0o2jf9qNf-MC1y09", + "title": "metrics_l Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 153, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "LbSrbSrqfQFBNWM5", + "title": "metrics_xxl JVM mem used %", + "width": 3, + "height": 17, + "x": 3, + "y": 99, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "9qe-hvr5FkmOAdgc", + "title": "metrics_xxxl JVM mem used %", + "width": 3, + "height": 18, + "x": 3, + "y": 60, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "PBU0JXN09ye0dJ-S", + "title": "metrics_m CPU total (top 50)", + "width": 3, + "height": 19, + "x": 6, + "y": 212, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "GlfKxIQnYm1l3pxR", + "title": "metrics_xl (15.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 137, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "KUosBDSm4dtMmmoB", + "title": "metrics_s TOP 5 metric count per pod", + "width": 12, + "height": 13, + "x": 0, + "y": 236, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "7c8Oi4nOYeWLDQLZ", + "title": "custom profile mem", + "width": 3, + "height": 18, + "x": 0, + "y": 21, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "d4j5kh2xpO0w19wu", + "title": "metrics_xxl Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 84, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xxl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "NK_pyEUgOpYJvibN", + "title": "metrics_xxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 78, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "zVNNv40o6je6oA-B", + "title": "metrics_xxl TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 84, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "1ZFvdjD7vkvO5Fz2", + "title": "metrics_m Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 196, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_m Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "-zZxPJ1rEXpvQ9bA", + "title": "metrics_xxl pod count", + "width": 3, + "height": 17, + "x": 9, + "y": 99, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "GrAWlZc4Bg0WZDBe", + "title": "metrics_m bottom 10 metric count per pod", + "width": 3, + "height": 15, + "x": 0, + "y": 196, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "VEuYmOsqlztgU7i6", + "title": "custom JVM mem used %", + "width": 3, + "height": 18, + "x": 3, + "y": 21, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "custom JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "WkCf80peuGo_GHUj", + "title": "metrics_m Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 196, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "MgF7AXS90NK-x7Nx", + "title": "metrics_xxxl Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "5QmcudkXEcd0E1t-", + "title": "metrics_xxl Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 84, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "MaZgN7aTveboetO7", + "title": "custom pod count", + "width": 3, + "height": 18, + "x": 9, + "y": 21, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "SCUvrvH2SlEeMtIw", + "title": "metrics_l (7GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 174, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "tyTnZwGMqi7t9tdn", + "title": "metrics_m (4.6GB) profile mem", + "width": 3, + "height": 19, + "x": 0, + "y": 212, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Others", + "Regex" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "byte", + "regex": true, + "metric": "memory\\.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "memory\\.used_percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "oKT68HxEIyOXBBoK", + "title": "Custom bottom 10 metric count per pod", + "width": 3, + "height": 15, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Q4vKYxfynvNPCdy_", + "title": "custom CPU total (top 50)", + "width": 3, + "height": 18, + "x": 6, + "y": 21, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "_5gWfuIG0FdwOJRi", + "title": "metrics_xl CPU total (top 50)", + "width": 3, + "height": 16, + "x": 6, + "y": 137, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "9rcsh_J2fw2wjGrZ", + "title": "metrics_l Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 159, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "URtdOOQgC8MPPOOP", + "title": "metrics_l bottom 10 metric count per pod (max 570k metrics [coral])", + "width": 3, + "height": 15, + "x": 0, + "y": 159, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "LLQEk1OP73mLkgQ6", + "title": "metrics_m pod count", + "width": 3, + "height": 19, + "x": 9, + "y": 212, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "uWt2yg_l-lNfKTaw", + "title": "metrics_xxxl (40GB) profile mem", + "width": 3, + "height": 18, + "x": 0, + "y": 60, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "HwQo4rXOhKKnROJg", + "title": "metrics_m TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 196, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighPerf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "BkF1VMx7JnIVxKRP", + "title": "metrics_xxl bottom 10 metric count per pod(max 900k metrics [coral])", + "width": 3, + "height": 15, + "x": 0, + "y": 84, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "iZ14sB-o8jtVWFtT", + "title": "metrics_l CPU total (top 50)", + "width": 3, + "height": 16, + "x": 6, + "y": 174, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "q-oe2je-d5kYGNyQ", + "title": "metrics_xl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 116, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "3obZqhaWsvdqLhEB", + "title": "metrics_m JVM mem used %", + "width": 3, + "height": 19, + "x": 3, + "y": 212, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "4e25pwdB_Sc66GjF", + "title": "metrics_xxxl pod count", + "width": 3, + "height": 18, + "x": 9, + "y": 60, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "6xmKLxvZA5Xdf5Q-", + "title": "custom Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "YP5KXsmmAEoV1Cv2", + "title": "metrics_xxl CPU total (top 50)", + "width": 3, + "height": 17, + "x": 6, + "y": 99, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "h_3MmtZuLhM-OZZl", + "title": "metrics_xxxl bottom 10 metric count per pod(max 1.25M metrics [coral])", + "width": 3, + "height": 15, + "x": 0, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "UueCAHOLUtmANkMy", + "title": "metrics_l pod count", + "width": 3, + "height": 16, + "x": 9, + "y": 174, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "jBLR2MXHw9p1z1TR", + "title": "metrics_s Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 229, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "1_WeADUuvUwc-xfO", + "title": "metrics_l Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 159, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_l Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "kgXscnrfzYIKzw-b", + "title": "Custom Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xxl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "3lJ--lfAbi-thcDp", + "title": "metrics_m Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 190, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "smd_T-dO9UNoo27M", + "title": "metrics_xxxl Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xxxl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "_qaW4_HXMgUsRlJu", + "title": "metrics_l JVM mem used %", + "width": 3, + "height": 16, + "x": 3, + "y": 174, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_processor_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_processor_down.json new file mode 100644 index 0000000..0c81e36 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_processor_down.json @@ -0,0 +1,4079 @@ +{ + "id": "dUrVS9ukTkKgZlI0_oautA", + "title": "Self Monitoring: scale high perf processor down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "dkTEgKpdslpgYZoe", + "title": "custom incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "-OuC-JNOPUQPOeqA", + "title": "processor xxl (10.5GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 9500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "K3L1Ql1_WMnp6nkT", + "title": "custom incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "dz8wSjti8lBVF5J7", + "title": "#Β metrics_xxl processor pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 91, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "ryxe4WpPKyPcNQD9", + "title": "metrics_xl incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 113, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "VmWhRv5ydicZrQ5a", + "title": "metrics_xxxl incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "NKej2qMzul6Aqmq0", + "title": "metrics_xl incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 113, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "rL7v3vMnimaq9Bng", + "title": "custom processor CPU total (bottom 5)", + "width": 3, + "height": 17, + "x": 3, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "jdHJQXOwgK89fbSl", + "title": "processor xl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 126, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "processor xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "dR1J3KyV9hkSQQ2d", + "title": "processor xxl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "N_z_SiuiQdmYw7wv", + "title": "metrics_xxxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 36, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "D1udS8RQlWiMys1B", + "title": "metrics_l Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 142, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "04OG2QaBidDPBQaS", + "title": "#Β metrics_l filler pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 161, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "W7RvCTW-gmvPZFEs", + "title": "custom processor profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 10500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "WFULiMjVHCRdGe6U", + "title": "#Β metrics_xxxl processor pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 55, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "EyN00AHbXDQqpf6q", + "title": "custom processor JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "custom processor JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "sli", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "health", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "log", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "eum", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "OIE77jJPrQks16iP", + "title": "metrics_xxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 72, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "sjwrsq80KVrNnIaS", + "title": "metrics_xxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "PibvwHq4oUMhSSod", + "title": "metrics_xxxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "aMD0he9Q_5NQlw8W", + "title": "processor xxl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "1377vUfX-elcnh_Z", + "title": "processor l (6.5GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 161, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 4600000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "k-XWS78567d7N5QW", + "title": "metrics_xxxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "v1jzcUzZ95B_LR1E", + "title": "processor xxxl JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "processor xxxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "XIiqB7qnrv1FMIY0", + "title": "custom incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "L-Zufg1kVkNxGDQZ", + "title": "#Β metrics_xl processor pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 126, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "zYQUCFBGCuMrAama", + "title": "processor l CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 161, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "M1wbtk_1XqUxn5Zw", + "title": "metrics_m incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 183, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "hnYdLJG1o0ScHZLf", + "title": "metrics_l incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 148, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "acLiLtwgJOOjIHFe", + "title": "processor xxxl (14GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 10500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "vaBoQ5VO0l0Rmqf4", + "title": "metrics_m incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 187, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "a_hoUaTQthcPZfkv", + "title": "metrics_m incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 183, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "gKor0BYSWNqjFoSf", + "title": "metrics_l incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 148, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "krTsV0kYh59ktkHX", + "title": "metrics_xl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 107, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "m6lnMfp_aPvCvGTu", + "title": "processor xxxl CPU total (bottom 5)", + "width": 3, + "height": 17, + "x": 3, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "j4Cz8eDeAxYoI622", + "title": "metrics_xl incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 113, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "OImEgrdHWAJ0K-a3", + "title": "Custom Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "w-vWX7wQck88FPVX", + "title": "processor xl (9.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 126, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 6500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "sMwEIhl1Vousfbw-", + "title": "processor xl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 126, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "lfedis2L2AUy4-pn", + "title": "metrics_xxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "R2Ecj01-7PB8LsWf", + "title": "metrics_l incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 148, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Z4FyyE47GrPhCL3F", + "title": "metrics_xxl incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "KtoV3VxLgXIXu6Kq", + "title": "processor l JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 161, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "processor l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Wjj9sAR3O6TH-XUX", + "title": "metrics_m Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 177, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "BItB1cnJd98qoAQj", + "title": "custom processor pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 19, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_spans_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_spans_down.json new file mode 100644 index 0000000..2424059 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_spans_down.json @@ -0,0 +1,3458 @@ +{ + "id": "9qhEUViHRTu--dKZM6DYUQ", + "title": "Self Monitoring: scale high perf spans down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "mQa3nkRSMMlvMtAB", + "title": "spans_xxl Span dropping > 25% spans ", + "width": 4, + "height": 13, + "x": 8, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "izux2qFUS_TpAXg5", + "title": "custom Span dropping > 25% spans ", + "width": 4, + "height": 13, + "x": 8, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "_spans", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "JA7dHa7BFCgBg0mZ", + "title": "#Β ADP pod count spans_m", + "width": 3, + "height": 17, + "x": 9, + "y": 166, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "1XtQRLuiEX0x0oRH", + "title": "custom processed per pod", + "width": 4, + "height": 13, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "llUdyevC7Rha7fm1", + "title": "spans_l Span Producers per customer", + "width": 4, + "height": 15, + "x": 4, + "y": 114, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "U2RTtjZpe4PxJlLf", + "title": "spans l JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 129, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "span_l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "0EmAa-7EVcol5Qs9", + "title": "spans_l Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 108, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "jWce3D2pYqCJRCuk", + "title": "spans_s Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 183, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "T5_yLJfrVcKrMgoZ", + "title": "spans_m JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 166, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "UiulJl7Nhug__yZq", + "title": "spans_xxl CPU total (top 50)", + "width": 3, + "height": 17, + "x": 0, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "oNKWcHZz_gGyFk9n", + "title": "#Β ADP pod count spans_xl", + "width": 3, + "height": 17, + "x": 9, + "y": 91, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "A0aWo_y-QNFMfLvu", + "title": "Custom Span Producers per customer", + "width": 4, + "height": 13, + "x": 4, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Kkt3EuGCldelPKOE", + "title": "spans_xxl (19.5 GB) profile mem", + "width": 3, + "height": 17, + "x": 3, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "9FahLRk6nHXJoyr1", + "title": "spans_xxl processed per pod", + "width": 4, + "height": 13, + "x": 0, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "usQjBYQD61dFBRoP", + "title": "spans_xl Span dropping > 25% spans ", + "width": 4, + "height": 13, + "x": 8, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "uEIRXmIgrq51kvj-", + "title": "spans_m CPU total (bottom 5)", + "width": 3, + "height": 17, + "x": 0, + "y": 166, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "JkiioaiPpkt9PwFK", + "title": "spans_xl processed per pod", + "width": 4, + "height": 13, + "x": 0, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ruxRgi3devmnzeV3", + "title": "spans_xxl Span Producers per customer", + "width": 4, + "height": 13, + "x": 4, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "qDhkjQPRlZlRwHLW", + "title": "#Β ADP pod count spans_l", + "width": 3, + "height": 17, + "x": 9, + "y": 129, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "eSGh-RCYKRBpGmeb", + "title": "spans_xl (13 GB) profile mem", + "width": 3, + "height": 17, + "x": 3, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "zeux9j7sthDY5A0f", + "title": "spans_l (7.8GB) profile mem", + "width": 3, + "height": 17, + "x": 3, + "y": 129, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "EUE-x_FWrG2clH_f", + "title": "custom ADP pod count", + "width": 3, + "height": 17, + "x": 9, + "y": 19, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "NjN2EFci3jNxIPZz", + "title": "spans_s Span dropping > 25% spans ", + "width": 4, + "height": 14, + "x": 8, + "y": 189, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "lC74edE1XMdv2_75", + "title": "spans_xxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 36, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "T7iLBR9DL1iZi8yz", + "title": "spans_xxl JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "jdenOHzSv97C4Cyc", + "title": "custom CPU total (top 50)", + "width": 3, + "height": 17, + "x": 0, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "COCEQpkxtYI7nvfL", + "title": "custom spans JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "custom spans JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "G15aRhbFG_iZUqXI", + "title": "spans_m Span dropping > 25% spans ", + "width": 4, + "height": 14, + "x": 8, + "y": 152, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "mKZISOQZPJ1gHWBH", + "title": "spans_l processed per TU", + "width": 4, + "height": 15, + "x": 0, + "y": 114, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "GJI2gTXbx8Ear32o", + "title": "spans_xl Span Producers per customer", + "width": 4, + "height": 13, + "x": 4, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "R7p5VuiEPAGQ7COV", + "title": "spans_l CPU total (top 50)", + "width": 3, + "height": 17, + "x": 0, + "y": 129, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "410rTZaNPehLi-Pa", + "title": "spans_m (4.6GB) profile mem", + "width": 3, + "height": 17, + "x": 3, + "y": 166, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 2400000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "hyb-bA_r1LO9hXj1", + "title": "spans_xl JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "uUHPrVGsrtnsJefH", + "title": "spans_s Span Producers per customer", + "width": 4, + "height": 14, + "x": 4, + "y": 189, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "XhS0XIxqG0Scz29k", + "title": "custom mem usage", + "width": 3, + "height": 17, + "x": 3, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "IRnK5QCg9vwXJkQ7", + "title": "spans_s processed per TU", + "width": 4, + "height": 14, + "x": 0, + "y": 189, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "NCLdOpzXvyop57zu", + "title": "spans_m Span Producers per customer", + "width": 4, + "height": 14, + "x": 4, + "y": 152, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "--GyvFjhCN5KT8Eb", + "title": "spans_l Span dropping > 25% spans ", + "width": 4, + "height": 15, + "x": 8, + "y": 114, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnitHighperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "dYMcLOly6rD0Q_Oo", + "title": "spans_xl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 72, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "oOBIy6m--oqcV8vS", + "title": "#Β ADP pod count spans_xxl", + "width": 3, + "height": 17, + "x": 9, + "y": 55, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "6NbyPgMJgXEhky_r", + "title": "spans_xl CPU total (top 50)", + "width": 3, + "height": 17, + "x": 0, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "e4x5ACReczeG8JyD", + "title": "spans_m Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 146, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "u05C6Sw7F7vcmpdQ", + "title": "spans_m processed per TU", + "width": 4, + "height": 14, + "x": 0, + "y": 152, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "iIVf5Zb3_Oy7-Ong", + "title": "Custom Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "_______________________________________________" + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_ui_profile_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_ui_profile_down.json new file mode 100644 index 0000000..caf1ea8 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_high_perf_ui_profile_down.json @@ -0,0 +1,1736 @@ +{ + "id": "QL3cPEQ8TcaOABJlpDpHHg", + "title": "Self Monitoring: scale high perf ui profile down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "CX4i8v_VJ6UeyeiA", + "title": "ui-backend m (3.9GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 65, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 2400000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Ju4Bib4BGmjCUmcg", + "title": "ui-backend m CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 62, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "MbpT3WxcPcvrYw4d", + "title": "#xxlΒ ui-backend pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 17, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "CuHv-Y6ZqXnN7y42", + "title": "#Β ui-backend xl filler pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 33, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "EckneRcc6E_NHCZi", + "title": "ui-backend xxl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 17, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "yBEqGATv4cxy88Qn", + "title": "ui-backend_xxxl filler pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 0, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "2UdK_YdJ6CvjlCK9", + "title": "ui-backend_l filler pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 49, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "BPdh_cDsSAp9PQ8q", + "title": "ui-backend xxxl (32GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 22000000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ZsflKuafFpbTfwYX", + "title": "ui-backend l JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 49, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "fn8s8XrI08eOSGlg", + "title": "ui-backend xxl (22GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 17, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 15500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "TCL7-Pek8WqC_zt3", + "title": "ui-backend xl (11.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 33, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 7000000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "qeUKjFD9968v4oAJ", + "title": "ui-backend m JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 65, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "bzLLs4ZBhb1YjO2h", + "title": "ui-backend xxl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 17, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "BThS0RARafw8h-KB", + "title": "ui-backend l CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 50, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "j5kWvT_YYx3v4z3G", + "title": "#Β metrics_m filler pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 65, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "qBDbowRN1uIOcxsC", + "title": "ui-backend xxxl JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "EWpJPio9UmrqjJ4G", + "title": "ui-backend xl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 33, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "FtpWQIOb0O4WMYk_", + "title": "ui-backend xl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 33, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "6xo0KbDEngOlA3AQ", + "title": "ui-backend xxxl CPU total (bottom 5)", + "width": 3, + "height": 17, + "x": 3, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "xsBCVM-9chzCkGhg", + "title": "ui-backend l (7GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 49, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 4600000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_metrics_profile_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_metrics_profile_down.json new file mode 100644 index 0000000..6b6f24a --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_metrics_profile_down.json @@ -0,0 +1,4320 @@ +{ + "id": "yD0CfvVhTAWKTSB2aA7DZw", + "title": "Self Monitoring: scale metrics profile down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "4YNuxLC6EHOOYAoc", + "title": "metrics_s Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 194, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "NbHLS0k4xoCpPFwE", + "title": "metrics_l Metrics Processing", + "width": 3, + "height": 16, + "x": 3, + "y": 120, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_l Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "et83WBwv9xfwnPwB", + "title": "metrics_xl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 77, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "br4iVIAxtICq0Ch0", + "title": "metrics_xxxl TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "WU-D_ywnbwur8AXZ", + "title": "metrics_xxxl (40GB) profile mem", + "width": 3, + "height": 18, + "x": 0, + "y": 21, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 24000000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "tl0MUX0m9eXPe6wt", + "title": "metrics_s Raw message lag > 5s", + "width": 3, + "height": 17, + "x": 9, + "y": 200, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "9ZBl0mUGiekBNfOu", + "title": "metrics_xl TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 83, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "T0_3n0jssSXDRv81", + "title": "metrics_m CPU total (top 50)", + "width": 3, + "height": 19, + "x": 6, + "y": 175, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "QndpKeMvPDPGEfhU", + "title": "metrics_xxl (24GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 60, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "zpgMm3hZaL_qtjhX", + "title": "metrics_xxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 39, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "Q3UklJ7QIImVgOsm", + "title": "metrics_xxxl Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "KNGGUEs4GgCFGEZD", + "title": "metrics_xxxl pod count", + "width": 3, + "height": 18, + "x": 9, + "y": 21, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "73-XL7QlKcefpy7j", + "title": "metrics_m pod count", + "width": 3, + "height": 19, + "x": 9, + "y": 175, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "NqwApM-12rttNPSO", + "title": "metrics_m TU Raw message > 15%", + "width": 3, + "height": 17, + "x": 6, + "y": 158, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "iTOHSYLHZb6L7UE7", + "title": "metrics_l JVM mem used %", + "width": 3, + "height": 16, + "x": 3, + "y": 136, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "01D6J3f8dOI5cRZY", + "title": "metrics_s TU Raw message dropping > 15%", + "width": 3, + "height": 17, + "x": 6, + "y": 200, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "mSP8E9sRJv31R8B4", + "title": "metrics_m Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 152, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "3tIg4pE1KGlKtysT", + "title": "metrics_xxl TU Raw message dropping > 15%", + "width": 3, + "height": 15, + "x": 6, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Zhx3OnAWO5KdTaV-", + "title": "metrics_xxxl bottom 10 metric count per pod(max 715k metrics [orange])", + "width": 3, + "height": 15, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "copper-aliproduction-filler", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "luna0sbul6-cyan-filler", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "7WgmC1JH_Gsj22k1", + "title": "metrics_xl CPU total (top 50)", + "width": 3, + "height": 16, + "x": 6, + "y": 98, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "d-SFYIMiecVU4P6B", + "title": "metrics_xxl JVM mem used %", + "width": 3, + "height": 17, + "x": 3, + "y": 60, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "r8-yjX26mKXgPCr0", + "title": "metrics_s Metrics Processing", + "width": 3, + "height": 17, + "x": 3, + "y": 200, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_s Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "4lxC8LHVhUZ61NL0", + "title": "metrics_m Metrics Processing", + "width": 3, + "height": 17, + "x": 3, + "y": 158, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_m Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ECET1fGDm32czc6C", + "title": "metrics_xxxl CPU total (bottom 5)", + "width": 3, + "height": 18, + "x": 6, + "y": 21, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "xOB4EKblc1eZ-PmN", + "title": "metrics_xxxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "dVIeQuGjiLj3mNZ8", + "title": "metrics_xl bottom 10 metric count per pod (max 300k metrics [orange])", + "width": 3, + "height": 15, + "x": 0, + "y": 83, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "VhzbaP8teTcX-mAS", + "title": "metrics_s TOP 5 metric count per pod", + "width": 3, + "height": 17, + "x": 0, + "y": 200, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "dlAUHNfDZYwgJ1zw", + "title": "metrics_xxxl JVM mem used %", + "width": 3, + "height": 18, + "x": 3, + "y": 21, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "2drPVVsX6zU-Bral", + "title": "metrics_xl pod count", + "width": 3, + "height": 16, + "x": 9, + "y": 98, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "XJYuc6Dc_ATUnS42", + "title": "metrics_m bottom 10 metric count per pod (max 180k metrics [orange])", + "width": 3, + "height": 17, + "x": 0, + "y": 158, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "2-OS73lvWZZmAVDz", + "title": "metrics_xxl Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "tuYiZFdqOED9Osto", + "title": "metrics_l bottom 10 metric count per pod (max 415k metrics [orange])", + "width": 3, + "height": 16, + "x": 0, + "y": 120, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "kPwbrHMzdKVhu-Yi", + "title": "metrics_xl (15.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 98, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "0Yx4XrTqHemlFqfv", + "title": "metrics_xxxl Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xxxl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "mZO19EirMolZxAyD", + "title": "metrics_m (4.6GB) profile mem", + "width": 3, + "height": 19, + "x": 0, + "y": 175, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "pmhtUHshsKdjNCEH", + "title": "metrics_xxl bottom 10 metric count per pod (max 400k metrics [coral])", + "width": 3, + "height": 15, + "x": 0, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "fxJ7r8w9PfuBcpxI", + "title": "metrics_xl Raw message lag > 5s", + "width": 3, + "height": 15, + "x": 9, + "y": 83, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ox-lyT1av91aQU8o", + "title": "metrics_m Raw message lag > 5s", + "width": 3, + "height": 17, + "x": 9, + "y": 158, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "M8klJ6C9c-urRtRo", + "title": "metrics_l CPU total (top 50)", + "width": 3, + "height": 16, + "x": 6, + "y": 136, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "pvZm0Be3yxouCiEw", + "title": "metrics_xl JVM mem used %", + "width": 3, + "height": 16, + "x": 3, + "y": 98, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Ya56J5DoOq0IU0W-", + "title": "metrics_s (4.6GB) profile mem", + "width": 3, + "height": 19, + "x": 0, + "y": 228, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "GvsPTZB7IZZQff8d", + "title": "metrics_xl Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 83, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xxxl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Tq7P8pafRtZvSY_l", + "title": "metrics_s pod count", + "width": 3, + "height": 19, + "x": 9, + "y": 217, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "JJDeHD9RdGDlvZPH", + "title": "metrics_l Raw message lag > 5s", + "width": 3, + "height": 16, + "x": 9, + "y": 120, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 5000, + "max": 100000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "P99", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard timer com.instana.filler.topology.RawMessagesStreamInitializer.time-difference 99th percentile", + "crossSeriesAggregation": "P99" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "4_XuasSq-SZlJqFr", + "title": "metrics_l pod count", + "width": 3, + "height": 16, + "x": 9, + "y": 136, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "kj8AZuEJ9o_BLEc2", + "title": "metrics_xxl CPU total (top 50)", + "width": 3, + "height": 17, + "x": 6, + "y": 60, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "i2gAHi2ekSeY7k9P", + "title": "metrics_m JVM mem used %", + "width": 3, + "height": 19, + "x": 3, + "y": 175, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "9-YJ9Ng6qYUDzbFv", + "title": "metrics_xxl Metrics Processing", + "width": 3, + "height": 15, + "x": 3, + "y": 45, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "metrics_xxxl Metrics Processing", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.app", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter com.instana.filler.service.processingstatistics.ProcessingStatistics.metrics", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "cY6R6w7jLDL2gWnQ", + "title": "metrics_l TU Raw message dropping > 15%", + "width": 3, + "height": 16, + "x": 6, + "y": 120, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "min": 0.15, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.raw_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "LbtDNKSXxZ-YBDdx", + "title": "metrics_l Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 114, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "rLkcLuzkOwUrH4MF", + "title": "metrics_xxl pod count", + "width": 3, + "height": 17, + "x": 9, + "y": 60, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "JR5YFymg3yRjeEUB", + "title": "metrics_l (7GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 136, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "filler", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_processor_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_processor_down.json new file mode 100644 index 0000000..745208d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_processor_down.json @@ -0,0 +1,2888 @@ +{ + "id": "WVAjACXUS0ucLyTgp_3loA", + "title": "Self Monitoring: scale processor down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "tj-4Epffga1UJsmA", + "title": "metrics_xxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 36, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "BRD_nVvavPyHedJH", + "title": "processor l (6.5GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 113, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 4600000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "yqZJDTFseUVcTMx2", + "title": "processor xl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 77, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "sJTeElyOHo1OVet5", + "title": "metrics_l Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 94, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "8H1aPMMM4Mtt5F9U", + "title": "metrics_l incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 100, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "PewXBbiHhNk4DDZY", + "title": "#Β metrics_xl processor pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 77, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "ut-Ojkz1SVzV7RJn", + "title": "processor xxl (10.5GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 9500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "gkGQD66_xO2KX6cg", + "title": "processor m CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 129, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "SBIe14rJYwcPYzKa", + "title": "metrics_xxxl incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "PU5B4huOMVgTy4lF", + "title": "processor xxxl CPU total (bottom 5)", + "width": 3, + "height": 17, + "x": 3, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "X9RU6kEMfQdrBVMM", + "title": "metrics_xxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "CcUIieuoyygQx_Gb", + "title": "processor xl (9.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 77, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 6500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "SRELzMPcj_zGRJMR", + "title": "#Β metrics_xxl processor pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 55, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "aV-GtP5NwOKVphHx", + "title": "processor l CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 113, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "NWZ8ARzzakcKFeVq", + "title": "metrics_l incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 97, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "v50Sv9nJVkboczXW", + "title": "processor xxxl (14GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 10500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "xPWlazFEmXrpUMzz", + "title": "processor m (4.6GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 129, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 2400000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "XRT0aFpfbWFSspye", + "title": "metrics_xxxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "7NfD2fsIUQlPvn2a", + "title": "metrics_xl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 71, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "jQjZIUeg_53dh-JS", + "title": "metrics_xxxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "T80CXRj0bzu5zt3_", + "title": "metrics_xxl incoming rollup error rate", + "width": 4, + "height": 13, + "x": 8, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "pod" + }, + { + "label": "name" + } + ], + "name": "kubernetes.pod.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.rollups.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.rollups.error_rate", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "1GNUugUQU4gRJQps", + "title": "metrics_xxxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 4, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "deployment" + }, + { + "label": "name" + } + ], + "name": "kubernetes.deployment.name", + "type": "STRING" + }, + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "guctff98-O3VC1-E", + "title": "#Β metrics_xxxl processor pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 19, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "ZoeJkcQpx-U3RabO", + "title": "metrics_l incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 100, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "min": 0.2, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "rZItuaR68ipJurcI", + "title": "processor xl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 77, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "processor xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "kFJ2_cDvdU-BWffe", + "title": "processor xxl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "wXjPq9wfBXRz6KrA", + "title": "metrics_xxl incoming rollup calls", + "width": 4, + "height": 13, + "x": 0, + "y": 42, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "metrics.meters.KPI.incoming.rollups.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "tag", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.incoming.rollups.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": false + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ZcYNucke_pF4ZSFs", + "title": "processor xxxl JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "processor xxxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "apNLa_ugJ6p89fCH", + "title": "#Β metrics_m processor pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 128, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "mI4tOFP6UjyHMEjB", + "title": "processor xxl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 55, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "qiwuTuGrAPhuSxBm", + "title": "#Β metrics_l filler pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 112, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "XD65rFydOkjpDAde", + "title": "processor l JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 113, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "processor l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "sNR3FZJVTosi8tsB", + "title": "processor m JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 129, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "metrics_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata", + "entity": "NOT_APPLICABLE", + "operator": "NOT_CONTAIN" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_spans_profile_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_spans_profile_down.json new file mode 100644 index 0000000..008f79c --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_spans_profile_down.json @@ -0,0 +1,3239 @@ +{ + "id": "SHCxc8j6QQezLqlIUlzjAQ", + "title": "Self Monitoring: scale spans profile down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "vgTZIDHJvwN-wdbm", + "title": "spans_s Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 143, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "bFa52nXXfnUzAHcr", + "title": "spans m (4.6GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 126, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Kyz68RjFvWf1-pbI", + "title": "spans_xl Span Producers per customer", + "width": 4, + "height": 13, + "x": 4, + "y": 41, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "pIZgjgH2kHz4If-6", + "title": "spans_xxl processed per TU [approx 12 - 20k]", + "width": 4, + "height": 13, + "x": 0, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "1-riDP9OnosaQJrv", + "title": "spans_m Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 106, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "0Tg7q2FcKUGA7B1C", + "title": "spans_s Span dropping > 25% spans ", + "width": 4, + "height": 14, + "x": 8, + "y": 149, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "XiHF_TA1LKHMH0Xu", + "title": "spans_l Span Producers per customer", + "width": 4, + "height": 13, + "x": 4, + "y": 76, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 10, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "dN1xOlrhw_bxmTRc", + "title": "spans xl JVM mem used %", + "width": 3, + "height": 16, + "x": 3, + "y": 54, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "gM-nNZxOG-gB1bPK", + "title": "spans xxl (19.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "vYC2N87BE468kwMC", + "title": "#Β spans_m ADP pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 126, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "z3QO1iJviTcLxs86", + "title": "spans l JVM mem used %", + "width": 3, + "height": 17, + "x": 3, + "y": 89, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ItWzYyfOZNhRg43-", + "title": "spans xxl JVM mem used %", + "width": 3, + "height": 16, + "x": 3, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "h67LQP-LyPWbeTj4", + "title": "spans xl (13 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 54, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "BRjJIFae88Xpp92h", + "title": "#Β spans_xl ADP pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 54, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "LPg7mNmCPfEGvicL", + "title": "spans_xl Span dropping > 25% spans ", + "width": 4, + "height": 13, + "x": 8, + "y": 41, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "m8b_niahSl0_colw", + "title": "spans_xxl Span dropping > 25% spans ", + "width": 4, + "height": 13, + "x": 8, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "jTnVH37xukaXftJc", + "title": "spans_m Span Producers per customer", + "width": 4, + "height": 14, + "x": 4, + "y": 112, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ysr-ut0RTlWkCGNx", + "title": "spans s (1.7GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 163, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "mSeoiVokGTzdLWgv", + "title": "spans_s processed per TU", + "width": 4, + "height": 14, + "x": 0, + "y": 149, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "BCpw4UKMsf8dHzAj", + "title": "spans_xxl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 0, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "77EqxIdvyn6LO12V", + "title": "top spans_s Span Producers per customer", + "width": 4, + "height": 14, + "x": 4, + "y": 149, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "thDwjJc-dtEucNAt", + "title": "#Β spans_l ADP pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 89, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "hLZ8YC5Z_Jnttrov", + "title": "spans l CPU total (top 50)", + "width": 3, + "height": 17, + "x": 6, + "y": 89, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "1Goy9wX_B48PanvX", + "title": "#Β spans_s ADP pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 163, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "mdTJHlsYEt5eDeeJ", + "title": "spans_m Span dropping > 25% spans ", + "width": 4, + "height": 14, + "x": 8, + "y": 112, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "eUAmIyxTtZJ20Kp5", + "title": "spans_s CPU total (top 50)", + "width": 3, + "height": 17, + "x": 6, + "y": 163, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 0, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_s", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "DCHxL6KNOpHhdqCr", + "title": "spans_xxl Span Producers per customer", + "width": 4, + "height": 13, + "x": 4, + "y": 6, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Processed Spans", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.deployment.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "SUM" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "KWf6SPE5YN3ZhkNV", + "title": "spans xl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 6, + "y": 54, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "wjtfNt16t0TZDJ9Y", + "title": "#Β spans_xxl ADP pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 19, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "j3I1jxwzb8wvMsgC", + "title": "spans_l Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 70, + "type": "markdown", + "config": "_______________________________________________" + }, + { + "id": "tpK9M3JJ1PQjF_31", + "title": "spans_l processed per TU [ approx 4 - 7k ]", + "width": 4, + "height": 13, + "x": 0, + "y": 76, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "ez8wAln0eqgng-5q", + "title": "spans_s JVM mem used %", + "width": 3, + "height": 17, + "x": 3, + "y": 163, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "sXByXhxdTRJ8Cs7G", + "title": "spans xxl CPU total (top 50)", + "width": 3, + "height": 16, + "x": 6, + "y": 19, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "3b_bwJ0GAqQcDfCb", + "title": "spans_l Span dropping > 25% spans ", + "width": 4, + "height": 13, + "x": 8, + "y": 76, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "min": 0.25, + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": true, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard gauge KPI.incoming.span_messages.error_rate", + "crossSeriesAggregation": "MEAN" + } + ] + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "zXr87gvgIixpHrnk", + "title": "spans l (7.8GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 89, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "bytes.detailed", + "unit": "percentage", + "metric": "memory.used_percentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "8GEbEB_t-40xV0Wh", + "title": "spans m CPU total (top 50)", + "width": 3, + "height": 17, + "x": 6, + "y": 126, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "max": 0, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Other" + }, + { + "label": "tag.instana.io/tenantUnit" + } + ], + "name": "tag.instana.io/tenantUnit", + "availability": [], + "type": "STRING" + }, + "groupbyTag": "tag.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "percentage", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "vEfg286y_FTNOEfs", + "title": "spans_m processed per TU [approx 2 - 4k ] ", + "width": 4, + "height": 14, + "x": 0, + "y": 112, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "zlZ3P-dpS41CVJ-N", + "title": "spans_xl processed per TU [approx 7 - 12k ]", + "width": 4, + "height": 13, + "x": 0, + "y": 41, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "dropwizardApplicationContainer", + "metricPath": [ + "Others", + "Dropwizard App" + ], + "grouping": [ + { + "maxResults": 20, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "metrics.meters.KPI.processing.spans.calls", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Dropwizard meter KPI.processing.spans.calls", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Iwvj_YX-JJZbz404", + "title": "spans m JVM mem used %", + "width": 3, + "height": 17, + "x": 3, + "y": 126, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "spans m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "spans_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "appdata-processor", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "JcuxA-Q9IEgBV494", + "title": "spans_xl Profile", + "width": 12, + "height": 6, + "x": 0, + "y": 35, + "type": "markdown", + "config": "_______________________________________________" + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_ui_profile_down.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_ui_profile_down.json new file mode 100644 index 0000000..d741d9f --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__scale_ui_profile_down.json @@ -0,0 +1,1736 @@ +{ + "id": "cHm5-S3kTj2XuFeQUZg76A", + "title": "Self Monitoring: scale ui profile down", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "55FpH9Z_eovADMhI", + "title": "ui-backend l JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 49, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler l JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "xEYejbuN_ihYgDIf", + "title": "ui-backend xxl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 17, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "pI4cBsbM1M8ipZmy", + "title": "#xxlΒ ui-backend pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 17, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "9mpfX5xvPbEaCWua", + "title": "#Β ui-backend xl pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 33, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "kWo2dDriKRY9-afN", + "title": "ui-backend l (7GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 49, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 3900000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "HqQliohyDQ_Vy0bN", + "title": "ui-backend_l pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 49, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "5ITh7RHZnephSD1w", + "title": "ui-backend m JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 65, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler m JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "URzU3ppY6k2UML-d", + "title": "#Β ui-backend m pod ", + "width": 3, + "height": 16, + "x": 9, + "y": 65, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "eFeAEOSgVVmH200v", + "title": "ui-backend xl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 33, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "CHpb94eqcnliO2Uh", + "title": "ui-backend_xxxl filler pod ", + "width": 3, + "height": 17, + "x": 9, + "y": 0, + "type": "topList", + "config": { + "formatter": "number.compact", + "metricConfiguration": { + "lastValue": false, + "aggregation": "MEAN", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesPod", + "metricPath": [ + "Kubernetes", + "Kubernetes Pod" + ], + "grouping": [ + { + "maxResults": 50, + "by": { + "groupbyTag": "kubernetes.pod.label.instana.io/tenantUnit", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + "formatterSelected": false + } + }, + { + "id": "2wQ-GUz3aW5Fqg_9", + "title": "ui-backend xxl (22 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 17, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "min": 0, + "max": 11500000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Uk_ryemo2969NciQ", + "title": "ui-backend l CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 50, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_l", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "2UwrwSqOnHaqP3JV", + "title": "ui-backend m (3.9GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 65, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 2400000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "pVr9w24RHt9tTsDf", + "title": "ui-backend xxxl CPU total (bottom 5)", + "width": 3, + "height": 17, + "x": 3, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "N8Xva0FNuE8xMFPU", + "title": "ui-backend xxl CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 17, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "HQObdmKwmfb3y8aM", + "title": "ui-backend xxxl JVM mem used %", + "width": 3, + "height": 17, + "x": 6, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xxxl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "7q6c-cD1sHG4eBOr", + "title": "ui-backend xxxl (32 GB) profile mem", + "width": 3, + "height": 17, + "x": 0, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 22000000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xxxl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "L3BDLvVpoPZ63Oth", + "title": "ui-backend xl JVM mem used %", + "width": 3, + "height": 16, + "x": 6, + "y": 33, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "filler xl JVM mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "jvmRuntimePlatform", + "metricPath": [ + "Others", + "JVM", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usedPercentage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.pod.label.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Used Percentage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "FT1IE8Qu3G2udqv4", + "title": "ui-backend xl (11.5 GB) profile mem", + "width": 3, + "height": 16, + "x": 0, + "y": 33, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "bytes.detailed", + "renderer": "line", + "max": 7000000000, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MAX", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "Memory" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "formatter": "bytes.detailed", + "unit": "number", + "metric": "memory.usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_xl", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Usage", + "crossSeriesAggregation": "MAX" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + }, + { + "id": "IreOlj5wdxScZjx2", + "title": "ui-backend m CPU total (bottom 5)", + "width": 3, + "height": 16, + "x": 3, + "y": 62, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "containerd", + "metricPath": [ + "Container", + "Containerd Container", + "CPU" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "groupbyTag": "kubernetes.pod.name", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "ASC" + } + ], + "unit": "number", + "metric": "cpu.total_usage", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "tag.instana.io/profile", + "type": "TAG_FILTER", + "value": "ui_m", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "kubernetes.deployment.name", + "type": "TAG_FILTER", + "value": "ui-backend", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Total", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.detailed", + "renderer": "line", + "metrics": [] + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__usage_k8s_components.json b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__usage_k8s_components.json new file mode 100644 index 0000000..0abfc14 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/dashboards/self_monitoring__usage_k8s_components.json @@ -0,0 +1,3944 @@ +{ + "id": "d0rSOV5eTtule-9xMQfxAA", + "title": "Self Monitoring: Usage k8s components", + "accessRules": [ + { + "accessType": "READ_WRITE", + "relationType": "GLOBAL", + "relatedId": "" + }, + { + "accessType": "READ_WRITE", + "relationType": "USER", + "relatedId": "6745ceced26b6f000181586b" + } + ], + "widgets": [ + { + "id": "Du_4sxVlIEqSx5lx", + "title": "k8s-appdata-live-aggregator (8 x 16 GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 52, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-live-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-live-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-live-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-live-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-live-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "mxeZGURHhxMiVC5A", + "title": "k8s-tenantunit-highperf (32 X 128 GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "EiGZURGXLbYv8Y7Z", + "title": "k8s-beeinstant-aggregator (16 x 128 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 26, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "FETo0f3o3YpUWjOL", + "title": "k8s-appdata-health-aggregator (8 x 16 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 52, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-health-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-health-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-health-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-health-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-health-aggregator", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "Ddntp957Y0BlnVx6", + "title": "Node Capacity TenantUnits", + "width": 6, + "height": 13, + "x": 6, + "y": 13, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "max": 0, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "node" + }, + { + "label": "label.instanaGroup" + } + ], + "name": "kubernetes.node.label.instanaGroup", + "type": "STRING" + }, + "groupbyTag": "kubernetes.node.label.instanaGroup", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "SUM" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "bytes.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "grouping": [ + { + "maxResults": 5, + "by": { + "tagDefinition": { + "path": [ + { + "label": "Kubernetes" + }, + { + "label": "node" + }, + { + "label": "label.instanaGroup" + } + ], + "name": "kubernetes.node.label.instanaGroup", + "type": "STRING" + }, + "groupbyTag": "kubernetes.node.label.instanaGroup", + "groupbyTagEntity": "NOT_APPLICABLE", + "groupbyTagSecondLevelKey": "" + }, + "includeOthers": false, + "direction": "DESC" + } + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_mem", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.node.label.instanaGroup", + "type": "TAG_FILTER", + "value": "tenantUnit", + "entity": "NOT_APPLICABLE", + "operator": "CONTAINS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Capacity", + "crossSeriesAggregation": "SUM" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "HciVtbL5JxV1MlgT", + "title": "k8s-beeinstant-common (16 x 128 GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 26, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-common", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-common", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-common", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-common", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-beeinstant-common", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "PMAFTQMQbMe6Gvoj", + "title": "k8s-tenant-unit (32 x 256 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 0, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "uKuTFkTiC_rK9q3c", + "title": "k8s-sli-calls-filter (16 x 16 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 104, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-calls-filter", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-calls-filter", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-calls-filter", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-calls-filter", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-calls-filter", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "DKRlG9xccRjyYtVw", + "title": "k8s-serverless-acceptor (4 x 16GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-serverless-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "LAP1FdTDjKxhiM5W", + "title": "k8s-acceptor (8 x 20GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 39, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node Count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "K-II_hGvj9R05jeO", + "title": "k8s-tenantunit-highperf-XL (32 x 64 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 13, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf-xl", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf-xl", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf-xl", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf-xl", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tenantunit-highperf-xl", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "SQD_Ihw8KZJ4b94i", + "title": "k8s-bizops-writer (8 x 16 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 65, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-bizops-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-bizops-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-bizops-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-bizops-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-bizops-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "SIH4cIDBLKMpq8Ft", + "title": "Cluster Capacity", + "width": 6, + "height": 13, + "x": 6, + "y": 130, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "number.compact", + "renderer": "line", + "max": 0, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "SUM" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Requests", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "SUM" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "bytes.detailed", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Mem", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_mem", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Capacity", + "crossSeriesAggregation": "SUM" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Mem Requests", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_mem", + "timeShift": 0, + "tagFilterExpression": { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Memory Requests", + "crossSeriesAggregation": "SUM" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "AskpJ-opSVvdyaiz", + "title": "k8s-log-processor (8 x 32 GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "xGZlLDJdAuBRABoo", + "title": "k8s-sli-data-writer (8 X 18 GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 104, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-data-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-data-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-data-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-data-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-sli-data-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "D-a8hbhfJGRHRGvk", + "title": "k8s-core (8 x 64GB)", + "width": 6, + "height": 13, + "x": 6, + "y": 65, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-core", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-core", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-core", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-core", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "logicalOperator": "AND", + "elements": [ + { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-core", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + { + "name": "kubernetes.cluster.name", + "type": "TAG_FILTER", + "value": "saas-k8s-internal", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + } + ], + "type": "EXPRESSION" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "RsJgwnLBnBTYu6Ns", + "title": "k8s-appdataWriter (16 x 64)", + "width": 6, + "height": 13, + "x": 6, + "y": 39, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-appdata-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "mN2Q2uGqWx8YcU06", + "title": "k8s-tag-processor(8 x 32 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 117, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tag-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tag-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tag-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tag-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-tag-processor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "kNoDKz5dHPT1JhQ4", + "title": "k8s-eum-acceptor (16 X 20 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 78, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-eum-acceptor", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + }, + { + "id": "xylK60bd8bn7jrR4", + "title": "k8s-log-writer (8 x 16 GB)", + "width": 6, + "height": 13, + "x": 0, + "y": 91, + "type": "chart", + "config": { + "shareMaxAxisDomain": false, + "y1": { + "formatter": "percentage.detailed", + "renderer": "line", + "max": 1, + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "CPU" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "cpu.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Memory Used", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Memory" + ], + "formatter": "percentage.compact", + "unit": "number", + "metric": "memory.used", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "Used", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "y2": { + "formatter": "number.compact", + "renderer": "line", + "metrics": [ + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "Node count", + "source": "INFRASTRUCTURE_METRICS", + "type": "host", + "metricPath": [ + "Others", + "Host", + "Others" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "count", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [ + "DISTINCT_COUNT" + ], + "metricLabel": "Count", + "crossSeriesAggregation": "DISTINCT_COUNT" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU/node", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "cap_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Capacity", + "crossSeriesAggregation": "MEAN" + }, + { + "lastValue": false, + "color": "", + "compareToTimeShifted": false, + "threshold": { + "critical": "", + "warning": "", + "thresholdEnabled": false, + "operator": ">=" + }, + "aggregation": "MEAN", + "label": "CPU Request", + "source": "INFRASTRUCTURE_METRICS", + "type": "kubernetesNode", + "metricPath": [ + "Kubernetes", + "Kubernetes Node" + ], + "formatter": "number.compact", + "unit": "number", + "metric": "required_cpu", + "timeShift": 0, + "tagFilterExpression": { + "name": "zone", + "type": "TAG_FILTER", + "value": "k8s-log-writer", + "entity": "NOT_APPLICABLE", + "operator": "EQUALS" + }, + "allowedCrossSeriesAggregations": [], + "metricLabel": "CPU Requests", + "crossSeriesAggregation": "MEAN" + } + ], + "formatterSelected": true + }, + "type": "TIME_SERIES" + } + } + ], + "ownerId": "6745ceced26b6f000181586b", + "writable": true +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_job_queue_utilizatio.json b/packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_job_queue_utilizatio.json new file mode 100644 index 0000000..38147b9 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_job_queue_utilizatio.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Acceptor HTTP job queue is filling up [TF]", + "description": "The HTTP threads of this instance do not seem to be able to handle the number of incoming requests causing job queue to fill up. This may eventually result in rejected HTTP requests and Acceptor responding with HTTP status code ENHANCE_YOUR_CALM. Potential causes for this are the respective Acceptor instance receiving too much traffic or problems with the Kafka cluster.", + "query": "entity.kubernetes.deployment.name:\"acceptor\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "window": 60000, + "severity": 10, + "metricName": "metrics.gauges.org.eclipse.jetty.util.thread.QueuedThreadPool.dw.jobs-queue-utilization", + "aggregation": "avg", + "conditionOperator": ">", + "conditionValue": 0.5 + } + ] +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_span_error_rate.json b/packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_span_error_rate.json new file mode 100644 index 0000000..a6c2bc0 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/acceptor/acceptor_high_span_error_rate.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Acceptor spans_error_rate rate is too high [TF]", + "description": "This indicates problems with either too high load on the individual Acceptor node or problems with the Kafka cluster in this region and leads to gaps in metrics and calls for customers.", + "query": "entity.kubernetes.deployment.name:\"acceptor\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "window": 60000, + "severity": 10, + "metricName": "metrics.gauges.KPI.outgoing.spans.error_rate", + "aggregation": "avg", + "conditionOperator": ">", + "conditionValue": 0.05 + } + ] +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_infra_graph.json b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_infra_graph.json new file mode 100644 index 0000000..b1ad48c --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_infra_graph.json @@ -0,0 +1,18 @@ +{ + "name": "appdata-processor - Failed to heal online infra graph [TF]", + "description": "https://www.notion.so/instana/appdata-processor-Failure-to-heal-online-infra-graph-8daaf2073f0143f790607e78abb4a663", + "query": "entity.jvm.app.name:appdata-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.com.instana.graph.GraphStateMaintainer.num-rejected-full-updates", + "aggregation": "sum", + "window": 3600000, + "conditionOperator": ">=", + "conditionValue": 2, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_snapshots.json b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_snapshots.json new file mode 100644 index 0000000..4b0e00d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_failed_to_heal_online_snapshots.json @@ -0,0 +1,18 @@ +{ + "name": "appdata-processor - Failed to heal online snapshots [TF]", + "description": "https://www.notion.so/instana/appdata-processor-failed-to-heal-online-snapshots-c36dd6b9f2ec4a26ac4717d92c1911ba", + "query": "entity.jvm.app.name:appdata-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.com.instana.snapshot.cache.DefaultOnlineSnapshotCache.self-healing-errors", + "aggregation": "sum", + "window": 3600000, + "conditionOperator": ">=", + "conditionValue": 2, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_high_span_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_high_span_dropping.json new file mode 100644 index 0000000..646498c --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_high_span_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] appdata-processor is dropping > 25% spans [TF]", + "description": "This can lead to missing traces and results in wrong call counts. Possible reasons are an increase in ingress for the customer or that the component is running on an overloaded worker. If the traffic is reasonable (e.g. not spikes through load tests) consider scaling the spans profile for this TU up or scale out appdata-processor. See also https://www.notion.so/instana/appdata-processor-Spans-are-being-dropped-173977adc97d4e1b9b08bbbc7e56b8ec", + "query": "entity.jvm.app.name:appdata-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.incoming.span_messages.error_rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0.25, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_service_explosion.json b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_service_explosion.json new file mode 100644 index 0000000..23b4ec0 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/appdata-processor/appdata_processor_service_explosion.json @@ -0,0 +1,18 @@ +{ + "name": "appdata-processor - service explosion [TF]", + "description": "https://www.notion.so/instana/appdata-processor-Service-explosion-6794827fd9484a1cb557c06c7f7ce969", + "query": "entity.jvm.app.name:appdata-processor AND NOT entity.kubernetes.pod.label:\"instana.io/tenantUnit=cision-production\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.com.instana.spanprocessing.stream.appdatagraph.ServiceExplosionSafeguard.rejected", + "aggregation": "sum", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 100, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/butler/butler_jobs_queue_utilization.json b/packages/@instana-integration/instana-self-monitoring/events/butler/butler_jobs_queue_utilization.json new file mode 100644 index 0000000..11d41ea --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/butler/butler_jobs_queue_utilization.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Butler HTTP thread pool is very busy [TF]", + "description": "The HTTP threads of this instance do not seem to be able to handle the number of incoming requests causing job queue to fill up. This may eventually result in OOPS page in web-UI. Potential cause for this is butler produce exceeded db access(queries) to PostgreSQL(butler) in rainbow. You might need to check the PostgreSQL in rainbow.", + "query": "entity.kubernetes.deployment.name:\"butler\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.org.eclipse.jetty.util.thread.QueuedThreadPool.dw.jobs-queue-utilization", + "aggregation": "avg", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 0.5, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/butler/butler_very_busy_http_thread_pool.json b/packages/@instana-integration/instana-self-monitoring/events/butler/butler_very_busy_http_thread_pool.json new file mode 100644 index 0000000..8e7e12f --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/butler/butler_very_busy_http_thread_pool.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Butler http thread is very busy [TF]", + "description": "The HTTP threads of this instance do not seem to be able to handle the number of incoming requests causing job queue to fill up. This may eventually result in OOPS page in web-UI. Potential cause for this is butler produce exceeded db access(queries) to PostgreSQL(butler) in rainbow. You might need to check the PostgreSQL in rainbow.", + "query": "entity.kubernetes.deployment.name:\"butler\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.org.eclipse.jetty.util.thread.QueuedThreadPool.dw.utilization-max", + "aggregation": "avg", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 0.9, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/cassandra/metrics_cassandra_unreachable_node.json b/packages/@instana-integration/instana-self-monitoring/events/cassandra/metrics_cassandra_unreachable_node.json new file mode 100644 index 0000000..101c108 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/cassandra/metrics_cassandra_unreachable_node.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] metrics-cassandra node unreachable for > 5m [TF]", + "description": "A node in the metrics-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards.", + "query": "(NOT entity.cassandra.cluster.name:\"*state*\") AND (NOT entity.cassandra.cluster.name:\"*profiles*\") AND (NOT entity.cassandra.cluster.name:\"*spans*\")", + "entityType": "cassandraCluster", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "unreachableNodeCount", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/cassandra/profiles_cassandra_unreachable_node.json b/packages/@instana-integration/instana-self-monitoring/events/cassandra/profiles_cassandra_unreachable_node.json new file mode 100644 index 0000000..44497b9 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/cassandra/profiles_cassandra_unreachable_node.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] profiles-cassandra node unreachable for > 5m [TF]", + "description": "A node in the profiles-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards.", + "query": "entity.cassandra.cluster.name:\"*profiles*\"", + "entityType": "cassandraCluster", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "unreachableNodeCount", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/cassandra/spans_cassandra_unreachable_node.json b/packages/@instana-integration/instana-self-monitoring/events/cassandra/spans_cassandra_unreachable_node.json new file mode 100644 index 0000000..b60f6dc --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/cassandra/spans_cassandra_unreachable_node.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] spans-cassandra node unreachable for > 5m [TF]", + "description": "A node in the spans-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards.", + "query": "entity.cassandra.cluster.name:\"*spans*\"", + "entityType": "cassandraCluster", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "unreachableNodeCount", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_unreachable_node.json b/packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_unreachable_node.json new file mode 100644 index 0000000..c903444 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_unreachable_node.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] state-cassandra node unreachable for > 5m [TF]", + "description": "A node in the state-cassandra cluster is not reachable since 5 minutes. This usually indicates overall load problems in the cluster or a issue with the underlying cloud VM. Try restarting the process and investigate overall cluster load afterwards.", + "query": "entity.cassandra.cluster.name:\"*state*\"", + "entityType": "cassandraCluster", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "unreachableNodeCount", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_write_latency.json b/packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_write_latency.json new file mode 100644 index 0000000..4a2cc0b --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/cassandra/state_cassandra_write_latency.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] state-cassandra write latency greater than 1 minute [TF]", + "description": "A node in the state-cassandra cluster is having very high write latency. This indicates a major issue which will affect\ndependent components like tag-processor. Try restarting the node.", + "query": "entity.cassandra.cluster.name:\"*state*\"", + "entityType": "cassandraNode", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "clientrequests.write.mean", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 60000, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_parts_per_partition.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_parts_per_partition.json new file mode 100644 index 0000000..21d2024 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_parts_per_partition.json @@ -0,0 +1,23 @@ +{ + "name": "ClickHouse - AP - Too many parts in one of the partitions of the XXX table [TF]", + "description": "https://www.notion.so/instana/ClickHouse-Too-many-parts-in-one-of-the-partitions-of-the-XXX-table-01b7add852d74a499ed0216115ed8804. ##Note: The 'conditionValue' (currently set to 830) is a sample reference for the variable 'active_parts_threshold'. Please adjust this value based on your specific environment.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "aggregation": "min", + "window": 60000, + "conditionOperator": ">=", + "conditionValue": 830, + "severity": 10, + "metricPattern": { + "prefix": "table_metric", + "postfix": "parts", + "operator": "any", + "placeholder": "" + } + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_rejected_inserts.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_rejected_inserts.json new file mode 100644 index 0000000..00a1aaa --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_rejected_inserts.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - AP - Too Many inserts are rejected [TF]", + "description": "The data is getting lost. Caused by 'Too many parts' exception due to high number of active data parts for partition. https://www.notion.so/instana/ClickHouse-Too-many-parts-in-one-of-the-partitions-of-the-XXX-table-01b7add852d74a499ed0216115ed8804. ##Note: The 'conditionValue' (currently set to 13500) is a sample reference for the variable 'clickhouse_rejected_inserts_threshold'. Please adjust this value based on your specific environment.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "clickHouseDatabase", + "expirationTime": 3600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "RejectedInserts", + "aggregation": "sum", + "window": 3600000, + "conditionOperator": ">", + "conditionValue": "13500", + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_simultaneous_queries.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_simultaneous_queries.json new file mode 100644 index 0000000..19316d6 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_ap_too_many_simultaneous_queries.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - AP - Too many simultaneous queries [TF]", + "description": "https://www.notion.so/instana/ClickHouse-Too-many-simultaneous-queries-8adf725a6c4c49088eee518b1af6880e", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "Query", + "aggregation": "min", + "window": 60000, + "conditionOperator": ">=", + "conditionValue": 120, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_distribution_queue_filling_up.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_distribution_queue_filling_up.json new file mode 100644 index 0000000..893dd25 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_distribution_queue_filling_up.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] ClickHouse - Distribution queue is filling up [TF]", + "description": "https://www.notion.so/instana/Clickhouse-Distribution-queue-is-filling-up-9453591a12df4a5bb9e27", + "query": "entity.type:clickhouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "DistributedFilesToInsert", + "aggregation": "min", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 1000, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_is_not_running_on_the_expected_hosts.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_is_not_running_on_the_expected_hosts.json new file mode 100644 index 0000000..66a47fc --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_is_not_running_on_the_expected_hosts.json @@ -0,0 +1,17 @@ +{ + "name": "[SREInfraSLO] ClickHouse is not running on the host. [TF]", + "description": "The ClickHouse process is not running on the underlying host. This can be caused by issues related to the replication process. Please check ClickHouse logs for any recurring exceptions / errors and if none are present you [start the ClickHouse recovery process](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/#recovery-after-failures).", + "query": "entity.zone:\"*clickhouse*\" AND NOT entity.zone:\"ZK*\"", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "entity_verification", + "severity": 10, + "matchingEntityType": "clickHouseDatabase", + "matchingOperator": "startsWith", + "matchingEntityLabel": "ClickHouse", + "offlineDuration": 120000 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme1n1_used.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme1n1_used.json new file mode 100644 index 0000000..fecf7f2 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme1n1_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Clickhouse disk fs./dev/nvme1n1.used more than 85% full. [TF]", + "description": "This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/nvme1n1.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/nvme1n1.used", + "aggregation": "max", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme2n1_used.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme2n1_used.json new file mode 100644 index 0000000..9f014ea --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme2n1_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Clickhouse disk fs./dev/nvme2n1.used more than 85% full. [TF]", + "description": "This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/nvme2n1.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/nvme2n1.used", + "aggregation": "max", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme3n1_used.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme3n1_used.json new file mode 100644 index 0000000..8740ac9 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_nvme3n1_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Clickhouse disk fs./dev/nvme3n1.used more than 85% full. [TF]", + "description": "This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/nvme3n1.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/nvme3n1.used", + "aggregation": "max", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdb_used.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdb_used.json new file mode 100644 index 0000000..8f2d9a5 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdb_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Clickhouse disk fs./dev/sdb.used more than 85% full. [TF]", + "description": "This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/sdb.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/sdb.used", + "aggregation": "max", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdc_used.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdc_used.json new file mode 100644 index 0000000..f74ee83 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_mount_points_full_sdc_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Clickhouse disk fs./dev/sdc.used more than 85% full. [TF]", + "description": "This is a critical alert and if no action, the Clickhouse Cluster can go down. A disk attached to a Clickhouse server at fs./dev/sdc.used is greater than 85%. This indicates that the disk is going to reach its maximum capacity. When triggered, please check the Clickhouse cluster capacity and coordinate with the rest of the team to decide to increase the disk or add more shards.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/sdc.used", + "aggregation": "max", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_queries_failing_due_to_memory_limit_exceeded.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_queries_failing_due_to_memory_limit_exceeded.json new file mode 100644 index 0000000..d041e11 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_queries_failing_due_to_memory_limit_exceeded.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - Queries failing due to memory limit exceeded [TF]", + "description": "https://www.notion.so/instana/ClickHouse-Queries-failing-due-to-memory-limit-exceeded-8f2a3e6daea2438eb97289c0892459f2", + "query": "entity.type:clickhouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "QueryMemoryLimitExceeded", + "aggregation": "sum", + "window": 120000, + "conditionOperator": ">", + "conditionValue": 50, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_read_only_mode.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_read_only_mode.json new file mode 100644 index 0000000..2d035d6 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_read_only_mode.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] ClickHouse replica is in read-only mode for > 1m [TF]", + "description": "This can occur if there is an unknown error during (re)initialization of sessions with Zookeeper, or during session reinitialization in ZK itself. Run the following command on the alerting ClickHouse node to verify that the replica is still in read-only mode. Initiate Clickhouse client first via root user using the following command: `clickhouse-client` Once client has started, use: `SELECT * FROM system.replicas WHERE is_readonly = 1 LIMIT 10;` If nothing points to more severe problems, try to **restart the ClickHouse node that contains the read-only replica.**", + "query": "entity.type:clickhouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "ReadonlyReplica", + "aggregation": "min", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_rejects_inserts.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_rejects_inserts.json new file mode 100644 index 0000000..7b95027 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_rejects_inserts.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - Inserts are rejected [TF]", + "description": "The data is getting lost. Caused by 'Too many parts' exception due to high number of active data parts for partition. https://www.notion.so/instana/ClickHouse-Too-many-parts-in-one-of-the-partitions-of-the-XXX-table-01b7add852d74a499ed0216115ed8804", + "query": "entity.type:clickhouse", + "entityType": "clickHouseDatabase", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "RejectedInserts", + "aggregation": "sum", + "window": 3600000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue30.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue30.json new file mode 100644 index 0000000..76ea4f2 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue30.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - Replica Max Insert Queue Filling Up [TF]", + "description": "There is an increase of files that are stockpiling at the Clickhouse level. The associated graph in SRE:Clickhouse-AP should highlight whether this is a collection of CH nodes, or if a single CH node is handling most of the files that are piling up. Additionally, Appdata-Writer errors may be present and may need investigation.", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "DistributedFilesToInsert", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 30, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue450.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue450.json new file mode 100644 index 0000000..c8e3f53 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replica_max_insert_queue450.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - Replica Max Insert Queue Filling Up [TF]", + "description": "There is an increase in insertions for a Clickhouse server, or multiple servers. There may also be an increase in Distributed Files to Insert. Additional items to check are Appdata-Writer Clickhouse Error Rates. For a development perspective of this error: https://www.notion.so/instana/ClickHouse-Replication-queue-is-filling-up-405a445e25be4316add4cca943bf9d20", + "query": "entity.type:clickhouse AND entity.zone:ClickHouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "ReplicasMaxInsertsInQueue", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 450, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replication_queue_filling_up.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replication_queue_filling_up.json new file mode 100644 index 0000000..a4f9832 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/clickhouse_replication_queue_filling_up.json @@ -0,0 +1,18 @@ +{ + "name": "ClickHouse - Replication queue is filling up [TF]", + "description": "https://www.notion.so/instana/ClickHouse-Replication-queue-filling-up-405a445e25be4316add4cca943bf9d20", + "query": "entity.type:clickhouse", + "entityType": "clickHouseDatabase", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "ReplicasMaxQueueSize", + "aggregation": "min", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 1000, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/clickhouse/zookeeper_clickhouse_is_not_running_on_the_expected_hosts.json b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/zookeeper_clickhouse_is_not_running_on_the_expected_hosts.json new file mode 100644 index 0000000..52fbdb4 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/clickhouse/zookeeper_clickhouse_is_not_running_on_the_expected_hosts.json @@ -0,0 +1,17 @@ +{ + "name": "[SREInfraSLO] Zookeeper is not running for Clickhouse. [TF]", + "description": "The Zookeeper process is not running on the underlying host. This will prevent Clickhouse from functioning untill it is restored.", + "query": "entity.zone:\"zk*clickhouse*\"", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "entity_verification", + "severity": 10, + "matchingEntityType": "zooKeeper", + "matchingOperator": "startsWith", + "matchingEntityLabel": "replica", + "offlineDuration": 120000 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards-elasticsearch.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards-elasticsearch.json new file mode 100644 index 0000000..0e40512 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards-elasticsearch.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Elasticsearch-NG has high number of unassigned shards [TF]", + "description": "Number of unassigned shards are increasing and is above 5. This can indicate underlying resource issue. There may not be enough elastic data nodes to assign the new shards.", + "query": "entity.service.name:elasticsearch", + "entityType": "elasticsearchCluster", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "unassigned_shards", + "aggregation": "avg", + "window": 1800000, + "conditionOperator": ">", + "conditionValue": 5, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards.json new file mode 100644 index 0000000..7e39777 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/ElasticSearch-NG_Unassigned_Shards.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Elasticsearch-NG has high number of unassigned shards [TF]", + "description": "Number of unassigned shards are increasing and is above 5. This can indicate underlying resource issue. There may not be enough elastic data nodes to assign the new shards.", + "query": "entity.service.name:global_metadata_ng", + "entityType": "elasticsearchCluster", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "unassigned_shards", + "aggregation": "avg", + "window": 1800000, + "conditionOperator": ">", + "conditionValue": 5, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_client_search_error_rate.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_client_search_error_rate.json new file mode 100644 index 0000000..58e2f15 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_client_search_error_rate.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] High ES Client Search Error Rate [TF]", + "description": "Searches from this component to ElasticSearch are failing at a high rate. ## Consequences - If this is a user facing component, users may be seeing errors on the UI - If this is a processing component, processing may not be proceeding as fast as necessary, or data may be out of sync, leading to incorrect information being shown on the UI ## Remediation - Check that ElasticSearch (NG) is healthy in this region. - Check that this component is able to connect to Elasticsearch - If the error rate is very high, and ES is otherwise healthy, a component restart may resolve the issue", + "query": "entity.dropwizard.gauge:com.instana.elastic.InstanaElasticsearchClient.SearchRequest.error_rate", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.elastic.InstanaElasticsearchClient.SearchRequest.error_rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme1n1_used.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme1n1_used.json new file mode 100644 index 0000000..826468d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme1n1_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch data disk utilized > 85% [TF]", + "description": "The elasticsearch disk usage for data is greater than 85%. This indicates the disk is getting closer to max capacity. This may require cleanup of disk space. If not addressed in time, it may cause the node to stop working and possibly leave the cluster.", + "query": "entity.selfType:elasticsearch", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/nvme1n1.used", + "aggregation": "max", + "window": 600000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme2n1_used.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme2n1_used.json new file mode 100644 index 0000000..ec649c8 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_nvme2n1_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch data disk utilized > 85% [TF]", + "description": "The elasticsearch disk usage for data is greater than 85%. This indicates the disk is getting closer to max capacity. This may require cleanup of disk space. If not addressed in time, it may cause the node to stop working and possibly leave the cluster.", + "query": "entity.selfType:elasticsearch", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/nvme2n1.used", + "aggregation": "max", + "window": 600000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdb_used.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdb_used.json new file mode 100644 index 0000000..142e4bf --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdb_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch data disk utilized > 85% [TF]", + "description": "The elasticsearch disk usage for data is greater than 85%. This indicate the disk is getting closer to max capacity. This may require to cleanup the disk space. If this is not fixed on time, it may cause the node stop working and possible leave the cluster.", + "query": "entity.selfType:elasticsearch", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/sdb.used", + "aggregation": "max", + "window": 600000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdc_used.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdc_used.json new file mode 100644 index 0000000..3e12f8d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_data_disk_full_sdc_used.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch data disk utilized > 85% [TF]", + "description": "The elasticsearch disk usage for data is greater than 85%. This indicates the disk is getting closer to max capacity. This may require cleanup of disk space. If not addressed in time, it may cause the node to stop working and possibly leave the cluster.", + "query": "entity.selfType:elasticsearch", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/sdc.used", + "aggregation": "max", + "window": 600000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_is_not_running_on_the_expected_hosts.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_is_not_running_on_the_expected_hosts.json new file mode 100644 index 0000000..5bc1f04 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_is_not_running_on_the_expected_hosts.json @@ -0,0 +1,17 @@ +{ + "name": "[SREInfraSLO] Elasticsearch is not running on the host. [TF]", + "description": "The Elasticsearch process is not running on the underlying host. Please check Elasticsearch logs for any recurring exceptions / errors and if none are present restart the process", + "query": "entity.zone:\"elasticsearch*\"", + "entityType": "host", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "entity_verification", + "severity": 10, + "matchingEntityType": "elasticsearchNode", + "matchingOperator": "startsWith", + "matchingEntityLabel": "global_metadata_ng", + "offlineDuration": 120000 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status-elasticsearch.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status-elasticsearch.json new file mode 100644 index 0000000..0cb98fc --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status-elasticsearch.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch is in red status [TF]", + "description": "Elasticsearch is in red status. This indicates that at least one primary shard and all of its replicas are not allocated to a node, meaning that some data is unavailable. Please check this issue as it will impact read/write operations.", + "query": "entity.service.name:elasticsearch", + "entityType": "elasticsearchCluster", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "cluster_status", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 2, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status.json new file mode 100644 index 0000000..0d761ee --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_red_status.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch is in red status [TF]", + "description": "Elasticsearch is in red status. This indicates that at least one primary shard and all of its replicas are not allocated to a node, meaning that some data is unavailable. Please check this issue as it will impact read/write operations.", + "query": "entity.service.name:global_metadata_ng", + "entityType": "elasticsearchCluster", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "cluster_status", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">=", + "conditionValue": 2, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_root_disk_full.json b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_root_disk_full.json new file mode 100644 index 0000000..54485bd --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/elasticsearch/elasticsearch_root_disk_full.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] elasticsearch root disk utilized > 85% [TF]", + "description": "The elasticsearch disk usage for root is greater than 85%. This indicate the disk is getting closer to max capacity around 20G. This may require to cleanup the disk space. If this is not fixed on time, it may cause the node stop working and possible leave the cluster.", + "query": "entity.selfType:elasticsearch", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "fs./dev/root.used", + "aggregation": "max", + "window": 600000, + "conditionOperator": ">=", + "conditionValue": 0.85, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/cpu_usage_ratio_requests_instana_k8s_pod_filler.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/cpu_usage_ratio_requests_instana_k8s_pod_filler.json new file mode 100644 index 0000000..999a942 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/cpu_usage_ratio_requests_instana_k8s_pod_filler.json @@ -0,0 +1,18 @@ +{ + "name": "[DEVTUSLO] Instana filler pod CPU usage to CPU requests > 200% [TF]", + "description": "This Instana filler pod's CPU usage is over twice the CPU requests for more than 1h. This either indicates that the pod has too little requests and should be resized or that there is a problem with an upstream component (e.g. spike in usage on a specific pod).", + "query": "entity.type:kubernetesPod AND entity.kubernetes.pod.name:\"*filler*\"", + "entityType": "kubernetesPod", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "cpuUsageToRequestedRatio", + "aggregation": "avg", + "window": 3600000, + "conditionOperator": ">", + "conditionValue": 2, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_rollup_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_rollup_dropping.json new file mode 100644 index 0000000..aa73543 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_rollup_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping > 10% Cassandra rollups [TF]", + "description": "Rollups are being dropped before being written to Metrics Cassandra. This can be caused by too high load on the worker node or high processing pressure on the filler. ## Consequences This means there will be gaps in historical data for metrics. ## Remediation - Increase the TU toggle `config.rollup.cassandra.downstream.threads` (Default is 1. Shouldn't be more than 4). To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.processing.rollups.cassandra.error_rate", + "aggregation": "avg", + "window": 1800000, + "conditionOperator": ">", + "conditionValue": 0.10, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_writes_failing.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_writes_failing.json new file mode 100644 index 0000000..6ec03df --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_cassandra_writes_failing.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler writes to Cassandra are failing [TF]", + "description": "There is a high error rate when trying to write rollups to Cassandra. This can be caused by bugs (e.g. unsupported rollups used) or *a lot more likely* a broken connection between `filler` and Metrics Cassandra or general Metrics Cassandra problems. ## Consequences Alerting and live metrics viewing in the UI will be affected. ## Remediation - Check whether Cassandra is accessible from `filler`. - Otherwise report to team Infrastructure. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.outgoing.rollups.cassandra.error_rate", + "aggregation": "avg", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 0.10, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_error_rate.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_error_rate.json new file mode 100644 index 0000000..b87752a --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_error_rate.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] filler is failing to publish group member data [TF]", + "description": "Sending group members to the group processing instance is failing at a high rate. This probably indicates a serious issue with the kafka producer. ## Consequences Group entities will not be updated ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=5ilU_JJoTuWHKd9uz1PKXQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=WnDP6tKCTTOKCBIeR9Dx1w) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=1eqIS6ThSrud09h-fZzLRA) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=n1ruCLQvQhm--a1IbkXxyw)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.filler.topology.downstream.GroupMemberKafkaDownstream.kafka-producer.record-error-rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 5, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_lag.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_lag.json new file mode 100644 index 0000000..b919992 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_group_members_lag.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] group member metrics data are delayed [TF]", + "description": "Group member aggregation is being processed with a long delay - this means group member metrics are very delayed This is a sign that GroupMemberDataSource in Filler cannot keep up with the number data messages are written to the group_members topic. ## Consequences Group member metrics and entities might be dropped and may display an incorrect data ## Remediation - scale saas_instanaops_*_group_members topic to multiple partitions to allow multiple Filler instances to consume the group members topic To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=5ilU_JJoTuWHKd9uz1PKXQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=WnDP6tKCTTOKCBIeR9Dx1w) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=1eqIS6ThSrud09h-fZzLRA) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=n1ruCLQvQhm--a1IbkXxyw)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.com.instana.filler.stream.source.GroupMemberDataSource.group-member-age-dropped", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 5, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_info_event_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_info_event_dropping.json new file mode 100644 index 0000000..208532f --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_info_event_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping info events [TF]", + "description": "Events are being dropped before being published to the events kafka topic. ## Consequences This will cause alerts not to be triggered. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. - Check the logs to see if any unexpected errors have occurred. - If the metric `com.instana.filler.raw-messages.processed` has dropped to zero, no messages are flowing and `filler`. - Take a heap dump and inform team Infrastructure - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.processing.info_event.error_rate", + "aggregation": "avg", + "window": 120000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_kafka_rollup_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_kafka_rollup_dropping.json new file mode 100644 index 0000000..1bf270d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_kafka_rollup_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping > 10% Kafka rollups [TF]", + "description": "Rollups are being dropped before being written to Kafka. This can be caused by too high load on the worker node or high processing pressure on the filler. ## Consequences Alerting and live metrics viewing in the UI will be affected. ## Remediation - Increasing the TU toggle `config.rollup.kafka.downstream.threads` (Default is 1. Shouldn't be more than 4). To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.processing.rollups.kafka.error_rate", + "aggregation": "avg", + "window": 1800000, + "conditionOperator": ">", + "conditionValue": 0.10, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_lag.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_lag.json new file mode 100644 index 0000000..ffae355 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_lag.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler raw message lag > 5 seconds [TF]", + "description": "Filler raw message processing is lagging. The lag has been greater than five seconds for the last fifteen minutes. ## Consequences We are ingesting both tags and metrics more slowly than we should. Data will not become available in Instana in a timely fashion or might be dropped. ## Remediation Steps to take _until remediation_ - Upsize the metrics profile for the TU. - Move this filler to the highperf nodepool. - Move off other high-load components running on the same worker. - Scale out the filler.", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.timers.com.instana.filler.topology.RawMessagesStreamInitializer.time-difference.99th", + "aggregation": "avg", + "window": 900000, + "conditionOperator": ">", + "conditionValue": 5000, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_metric_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_metric_dropping.json new file mode 100644 index 0000000..8ac9d74 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_metric_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping metrics [TF]", + "description": "Metrics are being dropped before being published to Beeinstana and Cassandra. ## Consequences This will cause metrics not to be ingested. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. This is not valid for self-hosted installations. - Check the logs to see if any unexpected errors have occurred. - Check Beeinstana logs - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.processing.metric.error_rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_outdated_snapshots.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_outdated_snapshots.json new file mode 100644 index 0000000..e30f179 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_outdated_snapshots.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] filler outdated snapshots [TF]", + "description": "There is a difference in the snapshot cache and the snapshot state from ElasticSearch. ## Consequences If this condition persists, it could lead to outdated entities. ## Remediation - Check ElasticSearch cluster load. - If this is specific to this tenant, possibly there are too many online snapshots. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=WgHDS_DRRSWjVYOzKoojeg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=gjymdolcRCmhsSBDYa9tEw) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=d4cBzHW5Se-zzmtgQ9SLsw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=OYEqU6yTTFmsdkhnuPNidQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.com.instana.filler.service.snapshot.cache.ConsistentSnapshotCacheImpl.failed-snapshot-refreshes", + "aggregation": "avg", + "window": 1800000, + "conditionOperator": ">", + "conditionValue": 0.1667, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_events_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_events_dropping.json new file mode 100644 index 0000000..b942f51 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_events_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping raw events [TF]", + "description": "Raw events are being dropped before being published to the raw_events kafka topic. ## Consequences This will cause alerts not to be triggered. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. - Check the logs to see if any unexpected errors have occurred. - If the metric `com.instana.filler.raw-messages.processed` has dropped to zero, no messages are flowing and `filler`. - Take a heap dump and inform team Infrastructure - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.KPI.processing.raw_events.requested", + "aggregation": "avg", + "window": 120000, + "conditionOperator": "=", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_message_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_message_dropping.json new file mode 100644 index 0000000..296fb4d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_message_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping > 15% raw messages [TF]", + "description": "Raw messages, i.e. messages coming from agents, are being dropped. This is a sign that `filler` is running with too little resources or on a over-utilized host. ## Consequences This will cause gaps in metrics dashboards, broken alerting and permanent online/offline events. ## Remediation Steps to take _until remediation_ - Upsize the metrics profile for the TU. - Move this filler to the highperf nodepool. - Move off other high-load components running on the same worker. - Scale out the filler. If all the above have been done, then the filler is likely hitting limits in the snapshot processing pipeline. The infra team is working on improving limits and performance for the snapshot processing pipeline, but please inform team infra for further investigations. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.incoming.raw_messages.error_rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0.15, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_metrics_error_rate.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_metrics_error_rate.json new file mode 100644 index 0000000..a97cb5f --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_raw_metrics_error_rate.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] filler is failing to publish raw metric data [TF]", + "description": "Sending raw metrics to kafka (for beeinstana ingestion) is failing at a high rate. This probably indicates a serious issue with the kafka producer. ## Consequences Metrics will be lost. ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.filler.topology.downstream.KafkaRawMetricsDownstream.kafka-producer.record-error-rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 5, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_change_dropping.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_change_dropping.json new file mode 100644 index 0000000..159941f --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_change_dropping.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler is dropping snapshot changes [TF]", + "description": "Snapshot changes are being dropped before being written to ElasticSearch. This is a sign that `filler` is running with too little resources or on a over-utilized host. ## Consequences All reporting entities in this TU will go offline and there will effectively be no infrastructure monitoring. ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.KPI.processing.snapshot.requested", + "aggregation": "avg", + "window": 120000, + "conditionOperator": "=", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_processing.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_processing.json new file mode 100644 index 0000000..86182f1 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_snapshot_processing.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] filler is not processing any snapshot data [TF]", + "description": "Filler is not processing any entity heartbeats, which means it is not processing any snapshots. ## Consequences All reporting entities in this TU will go offline and there will effectively be no infrastructure monitoring. ## Remediation - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=R-BySNacQiGmIwSXpvAVqQ) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=eppNF3E5SIGcUYw1-DCEUQ) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDWDz6P_RU-5zwQ37IioFw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=Ml9uzhNNRqu5_QJQ3AZoYQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.filler.stream.FillerPipelineInitializer.heartbeats", + "aggregation": "sum", + "window": 120000, + "conditionOperator": "=", + "conditionValue": 0, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_expiring_snapshots.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_expiring_snapshots.json new file mode 100644 index 0000000..315e36d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_expiring_snapshots.json @@ -0,0 +1,18 @@ +{ + "name": "[EXPTUSLO] filler stopped synchronizing ES search index [TF]", + "description": "Check for unexpired snapshots has not successfully run. ## Consequences If this condition persists, it could lead to DFQ searches not returning correct results ## Remediation - Check ElasticSearch cluster load. - Check `filler` logs. To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=WgHDS_DRRSWjVYOzKoojeg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=gjymdolcRCmhsSBDYa9tEw) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=d4cBzHW5Se-zzmtgQ9SLsw) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=OYEqU6yTTFmsdkhnuPNidQ)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 1800000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.searchsnapshots.service.SearchStoreThroughCache.time-since-last-check-for-unexpired-snapshots", + "aggregation": "max", + "window": 1800000, + "conditionOperator": ">", + "conditionValue": 600000, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_fetching.json b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_fetching.json new file mode 100644 index 0000000..e8db295 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/fillers/filler_stopped_fetching.json @@ -0,0 +1,18 @@ +{ + "name": "[SRETUSLO] filler stopped fetching raw messages [TF]", + "description": "Metrics may not have been flowing for several minutes. ## Consequences If this condition persists, it will result in loss of metrics. ## Remediation - If you see this error for several fillers in one region this indicates problems with the Kafka cluster. - Check the logs to see if any unexpected errors have occurred. - If the metric `com.instana.filler.raw-messages.processed` has dropped to zero, no messages are flowing in `filler`. - Take a heap dump and inform team Infrastructure - Restart `filler` To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=C3eN96Z8RyOJ7ycpgHkK5Q) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=NXPy2nCSSeOsiKS2Rd6O-g) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=XvhTJitbRAmM3hhMOOKPbQ) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=4YntvQ3eSsaJ-BUXgoB2Wg)", + "query": "entity.jvm.app.name:filler AND NOT entity.kubernetes.deployment.name:techzone-observability-filler", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.kafka-consumer.fetch-rate.rawmessages", + "aggregation": "avg", + "window": 600000, + "conditionOperator": "<", + "conditionValue": 0.10, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/groundskeeper/synthetics_groundskeeper_datacenter_activation_error.json b/packages/@instana-integration/instana-self-monitoring/events/groundskeeper/synthetics_groundskeeper_datacenter_activation_error.json new file mode 100644 index 0000000..3a6b02b --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/groundskeeper/synthetics_groundskeeper_datacenter_activation_error.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Synthetics Datacenter Activation Errors [TF]", + "description": "This indicates problems in the Synthetics Datacenter Activation / Managed Location Deployment process.", + "query": "entity.kubernetes.deployment.name:\"groundskeeper\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.synthetics.datacenter.activation.errors", + "aggregation": "max", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_high_io_wait.json b/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_high_io_wait.json new file mode 100644 index 0000000..f694e06 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_high_io_wait.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Kafka node is showing high I/O wait times [TF]", + "description": "A Kafka node is showing high wait times for a longer period of time. This can indicate underlying hardware issues (in case of local SSDS), a general load issue with the Kafka cluster in that region or a load increase for a certain customers whos partitions are located on that node. In case of hardware failures, replace the node in questions. Otherwise look into balancing topics acros the cluster to spread the load.", + "query": "entity.zone:Kafka", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "cpu.wait", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0.15, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_open_files.json b/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_open_files.json new file mode 100644 index 0000000..a859df3 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_open_files.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Kafka node is approaching max open files [TF]", + "description": "A Kafka node has too many open files. This can result in a crash or restart of one or more kafka nodes in the cluster. Collect logs, check the kafka service on the host is running, and restart if necessary.", + "query": "entity.zone:Kafka", + "entityType": "host", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "openFiles.used", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0.9, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_under_replicated_partitions.json b/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_under_replicated_partitions.json new file mode 100644 index 0000000..f41fd74 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/kafka/kafka_under_replicated_partitions.json @@ -0,0 +1,18 @@ +{ + "name": "[SREInfraSLO] Kafka node has under replicated topic partitions [TF]", + "description": "There are under replicated topic partitions on a Kafka node for a longer period of time. This can indicate one or more Kafka nodes are down or the Kafka cluster is overloaded and followers can't catch up from leaders. In case of hardware failures, replace the node in questions. If it's cluster overloaded, consider to expand Kafka cluster. If the node is overloaded(significant topics on the node) instead of the whole cluster, try to balance the topics across the cluster.", + "query": "entity.zone:Kafka", + "entityType": "kafka", + "expirationTime": 60000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "broker.underReplicatedPartitions", + "aggregation": "avg", + "window": 600000, + "conditionOperator": ">", + "conditionValue": 0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/log-health-processor/lhp_lagging_incoming_logs.json b/packages/@instana-integration/instana-self-monitoring/events/log-health-processor/lhp_lagging_incoming_logs.json new file mode 100644 index 0000000..d239862 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/log-health-processor/lhp_lagging_incoming_logs.json @@ -0,0 +1,18 @@ +{ + "name": "[DevSLO] Incoming logs are lagging [TF]", + "description": "LHP is significantly lagging to consume from `enriched_logs` topic. This can result in `false positives` (e.g. wrong unusual low number of logs detected) or `false negatives` (no detection) in Smart-Alerts. Even when the dropping metrics indicate a low dropping rate of logs, depending on the lag and Smart Alert rule, this can mean that there is hidden dropping, either by hitting the Kafka retention limits, or by the fact that the logs are consumed too late to be considered. **Action Item:** Check the internal dashboard for dropping and lag of logs, and whether the bottleneck is the processing capacity of LHP, or originating upstream.", + "query": "entity.jvm.app.name:log-health-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.histograms.KPI.incoming.enriched_logs.message-age-ms.99th", + "aggregation": "avg", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 180000, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_one_percent_of_test_results.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_one_percent_of_test_results.json new file mode 100644 index 0000000..c34f5f7 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_one_percent_of_test_results.json @@ -0,0 +1,19 @@ +{ + "name": "[DevSLO] synthetics-health-processor is dropping test results [TF]", + "description": "`synthetics-health-processor is dropping more than 1% of incoming test results.`\n\n`Action Item:`\nCheck the internal dashboard for dropping, and whether this is just due to a general increase in incoming test results:\n- if `yes`: Ask SRE to scale-out\n- if `no`: Investigate whether a performance problem or bug was introduced", + "query": "entity.jvm.app.name:synthetics-health-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "triggering": true, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.incoming.results.error_rate", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.01, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_test_results.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_test_results.json new file mode 100644 index 0000000..3a47ccc --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_dropping_test_results.json @@ -0,0 +1,19 @@ +{ + "name": "[DevSLO] synthetics-health-processor is dropping test results [TF]", + "description": "`synthetics-health-processor is dropping more than 10% of incoming test results.` `Action Item:`Check the internal dashboard for dropping, and whether this is just due to a general increase in incoming test results: - if `yes`: Ask SRE to scale-out - if `no`: Investigate whether a performance problem or bug was introduced", + "query": "entity.jvm.app.name:synthetics-health-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "triggering": true, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.incoming.results.error_rate", + "aggregation": "avg", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 0.10, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_not_receiving_test_results.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_not_receiving_test_results.json new file mode 100644 index 0000000..7ab0c5d --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_is_not_receiving_test_results.json @@ -0,0 +1,19 @@ +{ + "name": "[DevSLO] synthetics-health-processor is not receiving test results [TF]", + "description": "`synthetics-health-processor is not receiving test results.` `Action Item:` Most likely there is a problem in synthetics-health-processor or in the components upstream: - As a quick fix, ask SRE to restart - Investigate whether a problem or bug was introduced in synthetics-health-processor or upstream components", + "query": "entity.jvm.app.name:synthetics-health-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "triggering": true, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.KPI.incoming.results.calls", + "aggregation": "sum", + "window": 300000, + "conditionOperator": "=", + "conditionValue": 0.0, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_kafka_failing.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_kafka_failing.json new file mode 100644 index 0000000..72ef733 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/shp_kafka_failing.json @@ -0,0 +1,18 @@ +{ + "name": "[SLO] Writes of health events to Kafka are failing [TF]", + "description": "Failed writes of health events to Kafka means loss of events in the events product area and loss of alerts send out to the alert channels. Check the logs and the network between this node and the Kafka nodes.", + "query": "entity.jvm.app.name:synthetics-health-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.outgoing.events.error_rate", + "aggregation": "avg", + "window": 60000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_addon_license_error.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_addon_license_error.json new file mode 100644 index 0000000..dc604c9 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_addon_license_error.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Synthetics Acceptor Addon License Errors [TF]", + "description": "This indicates problems with the Synthetics Acceptor receiving data from a Managed location for a TU that does not have a synthetic addon license purchased.", + "query": "entity.kubernetes.deployment.name:\"synthetics-acceptor\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.synthetics.license.addons.error_rate", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_external_storage_write_error.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_external_storage_write_error.json new file mode 100644 index 0000000..fc7b3e0 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_acceptor_external_storage_write_error.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Synthetics Acceptor External Storage Write Errors [TF]", + "description": "This indicates problems with the Synthetics Acceptor inserting data to the External Storage.", + "query": "entity.kubernetes.deployment.name:\"synthetics-acceptor\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.synthetics.s3.store.error_rate", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] + } \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_queued_calls.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_queued_calls.json new file mode 100644 index 0000000..c5120d4 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_queued_calls.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Synthetics Reader ClickHouse Queued Calls [TF]", + "description": "This indicates problems with the Synthetics Reader queuing calls to retrieve data from ClickHouse. ## Consequences This will cause Synthetics Tests and Locations pages to timeout without showing any data. ## Remediation - If the metric `metrics.gauges.clickHouse.clustered.queuedCalls` is high, the execution time of all calls will increase causing timeouts: - Take a thread dump of the `synthetics-reader` pods and inform team Synthetics - Restart `synthetics-reader`", + "query": "entity.kubernetes.deployment.name:\"synthetics-reader\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.clickHouse.clustered.queuedCalls", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.30, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_select_failure.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_select_failure.json new file mode 100644 index 0000000..47f4b0c --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_clickhouse_select_failure.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Synthetics Reader ClickHouse Select Failures [TF]", + "description": "This indicates problems with the Synthetics Reader retrieving data from ClickHouse.", + "query": "entity.kubernetes.deployment.name:\"synthetics-reader\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.clickHouse.clustered.select.error_rate", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_external_storage_read_error.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_external_storage_read_error.json new file mode 100644 index 0000000..57981be --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_reader_external_storage_read_error.json @@ -0,0 +1,18 @@ +{ + "name": "[DevSLO] - Synthetics Reader External Storage Read Errors [TF]", + "description": "This indicates problems with the Synthetics Reader retrieving data from the External Storage.", + "query": "entity.kubernetes.deployment.name:\"synthetics-reader\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.KPI.synthetics.s3.get.error_rate", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} \ No newline at end of file diff --git a/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_writer_clickhouse_insert_failure.json b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_writer_clickhouse_insert_failure.json new file mode 100644 index 0000000..46d3f20 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/synthetics/synthetics_writer_clickhouse_insert_failure.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] Synthetics Writer ClickHouse Insert Failures [TF]", + "description": "This indicates problems with the Synthetics Writer inserting data in ClickHouse.", + "query": "entity.kubernetes.deployment.name:\"synthetics-writer\"", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 300000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.meters.com.instana.clickhouse.client.ClickHouseHttpClient.insert.errors", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 10 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_cleanup_stalled.json b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_cleanup_stalled.json new file mode 100644 index 0000000..abd9304 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_cleanup_stalled.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] tag-processor is not cleaning up tag sets [TF]", + "description": "Tag processor is is not running the cleanup of tag sets. ## Consequences Changes which have been dropped will not be fixed and updates to tag sets will not be reflected. This could cause some entities to not show up in searches and smart alerts based on these tags become unreliable and have false alerts. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Cassandra and Kafka. - Consider a rolling restart of pods - Inform engineering", + "query": "entity.jvm.app.name:tag-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.timers.com.instana.tags.synchronization.DefaultTagPropagationStateCleaner.state-age.rate", + "aggregation": "avg", + "window": 600000, + "conditionOperator": "=", + "conditionValue": 0.0, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_snapshots.json b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_snapshots.json new file mode 100644 index 0000000..d6cfd38 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_snapshots.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] tag-processor is dropping snapshot updates [TF]", + "description": "Tag processor is dropping records when reading the `snapshots` topic to reduce latency. This means tag-processor is having trouble keeping up with the number of snapshot updates for some TUs. ## Consequences As long as this occurs, there may be delays in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka. - Consider increasing the number of tag-processor instances to keep up with increased load. You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.SnapshotUpdateDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg)", + "query": "entity.jvm.app.name:tag-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "com.instana.tags.processing.SnapshotUpdateDropper.error_rate{tenantUnit=\"all\"}", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.01, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_propagation_actions.json b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_propagation_actions.json new file mode 100644 index 0000000..f3dac1c --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_propagation_actions.json @@ -0,0 +1,18 @@ +{ + "name": "[DEVSLO] tag-processor is dropping tag propagation actions [TF]", + "description": "Tag processor is having trouble keeping up with tag changes and tag propagation for some TUs. ## Consequences As long as this occurs, there may be delays in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka or State Cassandra. - Consider increasing the number of tag-processor instances to keep up with increased load. You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.TagPropagationActionDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg)", + "query": "entity.jvm.app.name:tag-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.tags.processing.TagPropagationActionDropper.error_rate{tenantUnit=\"all\"}", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.05, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_sets.json b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_sets.json new file mode 100644 index 0000000..d0d1d7e --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tag_sets.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] tag-processor is dropping tag set updates [TF]", + "description": "Tag processor is having trouble writing tag sets into Elasticsearch for some TUs. ## Consequences As long as this occurs, there may be delays in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka or Elasticsearch. - Consider increasing the number of tag-processor instances to keep up with increased load. You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.TagSetUpdateDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg)", + "query": "entity.jvm.app.name:tag-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.tags.processing.TagSetUpdateDropper.error_rate{tenantUnit=\"all\"}", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.01, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tagged_metrics.json b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tagged_metrics.json new file mode 100644 index 0000000..c673925 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_dropping_tagged_metrics.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] tag-processor is dropping tagged metrics [TF]", + "description": "Tag processor is having trouble keeping up with the number of tagged metrics that are being published from some TUs. ## Consequences As long as this occurs, there may be delays in multi-dimensional metrics in custom dashboards and Analyze Infrastructure for some TUs. ## Remediation Steps to take _until remediation_ - Verify that there are no issues with Kafka. - Consider increasing the number of tag-processor instances to keep up with increased load. - Consider decreasing the filler tagged metric publish count You can go to an individual tag-processor dropiwizard dashboard to see which TUs are affected (check the `com.instana.tags.processing.TaggedMetricDropper..error_rate` metrics) To get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg)", + "query": "entity.jvm.app.name:tag-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.gauges.com.instana.tags.processing.TaggedMetricDropper.error_rate{tenantUnit=\"all\"}", + "aggregation": "avg", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 0.01, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_snapshot_lag.json b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_snapshot_lag.json new file mode 100644 index 0000000..088873a --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/events/tag-processor/tag_processor_snapshot_lag.json @@ -0,0 +1,18 @@ +{ + "name": "[SRESLO] tag-processor is lagging [TF]", + "description": "Updates written to ES are not live - we have some lag in some part of the tag-processor pipeline.\n\nThis can come from:\n- latency writing into ES\n- latency in State Cassandra\n- latency writing to Kafka\n- High GC or High CPU from too many upstream updates\n\n## Consequences\nThere will be delays and possibly data-loss for changes that are occurring in customer environments in Custom Dashboards or Infrastructure Analyze.\n\n## Remediation\nSteps to take _until remediation_\n- Consider adjusting the dropping configuration e.g. decrease `config.tag.processor.start.dropping.age.ms` to enforce more dropping and reduce lag.\n- Verify that there are no issues with Kafka or Elasticsearch.\n- Consider increasing the number of tag-processor instances to keep up with increased load.\n\nTo get more context: [πŸ”΅](https://blue-instanaops.instana.io/#/customDashboards/view;dashboardId=l6yRfqedQn-t_GqhGVHYmg) [🟒](https://green-instanaops.instana.io/#/customDashboards/view;dashboardId=9VDfDX1UQ7yAMuBj14CK7A) [πŸ”΄](https://red-instanaops.instana.io/#/customDashboards/view;dashboardId=jDwGyhY8SAq88FJXvtsqIg) [🟠](https://orange-instanaops.instana.io/#/customDashboards/view;dashboardId=YalysPDKRoGpzuagPYtWwg)", + "query": "entity.jvm.app.name:tag-processor", + "entityType": "dropwizardApplicationContainer", + "expirationTime": 600000, + "rules": [ + { + "ruleType": "threshold", + "metricName": "metrics.timers.com.instana.tags.writing.TagSetWriter.tagset-age.mean", + "aggregation": "min", + "window": 300000, + "conditionOperator": ">", + "conditionValue": 300000, + "severity": 5 + } + ] +} diff --git a/packages/@instana-integration/instana-self-monitoring/package.json b/packages/@instana-integration/instana-self-monitoring/package.json new file mode 100644 index 0000000..c40bd51 --- /dev/null +++ b/packages/@instana-integration/instana-self-monitoring/package.json @@ -0,0 +1,18 @@ +{ + "name": "@instana-integration/instana-self-monitoring", + "version": "1.0.0", + "description": "This integration package provides dashboards and event monitoring to support self-monitoring for Instana’s internal systems.", + "author": "IBM", + "license": "MIT", + "scripts": {}, + "publishConfig": { + "access": "public" + }, + "keywords": [ + "instana self-monitoring", + "IBM", + "instana", + "custom dashboards", + "event definitions" + ] +} \ No newline at end of file