-
Notifications
You must be signed in to change notification settings - Fork 372
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
52 additions
and
52 deletions.
There are no files selected for viewing
104 changes: 52 additions & 52 deletions
104
ansible/roles/stack-monitor-stateful/templates/alertrules.kafkalag.yml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,107 +1,107 @@ | ||
groups: | ||
- name: alertrules.kafka_lag | ||
rules: | ||
- alert: secor {{ kafka_topic_prefix }}.events.deviceprofile.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.events.deviceprofile.backup"} > {{ events_deviceprofile_backup_threshold }} | ||
- alert: secor {{ env_name }}.events.deviceprofile.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.events.deviceprofile.backup"} > {{ events_deviceprofile_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.events.deviceprofile.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.events.deviceprofile.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.channel.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.channel.backup"} > {{ telemetry_channel_backup_threshold }} | ||
description: '{{ env_name }}.events.deviceprofile.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.events.deviceprofile.backup | ||
- alert: secor {{ env_name }}.telemetry.channel.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.channel.backup"} > {{ telemetry_channel_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.channel.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.channel.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.derived.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.derived.backup"} > {{ telemetry_derived_backup_threshold }} | ||
description: '{{ env_name }}.telemetry.channel.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.channel.backup | ||
- alert: secor {{ env_name }}.telemetry.derived.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.derived.backup"} > {{ telemetry_derived_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.derived.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.derived.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.failed.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.failed.backup"} > {{ telemetry_failed_backup_threshold }} | ||
description: '{{ env_name }}.telemetry.derived.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.derived.backup | ||
- alert: secor {{ env_name }}.telemetry.failed.backup group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.failed.backup"} > {{ telemetry_failed_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.failed.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.failed.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.ingestion.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.ingestion.backup"} > {{ telemetry_ingestion_backup_threshold }} | ||
description: '{{ env_name }}.telemetry.failed.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.failed.backup | ||
- alert: secor {{ env_name }}.telemetry.ingestion.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.ingestion.backup"} > {{ telemetry_ingestion_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.ingestion.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.ingestion.backup | ||
- alert: secor {{ kafka_topic_prefix }}.graph.events.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.graph.events.backup"} > {{ graph_events_backup_threshold }} | ||
description: '{{ env_name }}.telemetry.ingestion.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.ingestion.backup | ||
- alert: secor {{ env_name }}.graph.events.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.graph.events.backup"} > {{ graph_events_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.graph.events.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.graph.events.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.raw.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.raw.backup"} > {{ telemetry_raw_backup_threshold }} | ||
description: '{{ env_name }}.graph.events.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.graph.events.backup | ||
- alert: secor {{ env_name }}.telemetry.raw.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.raw.backup"} > {{ telemetry_raw_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.raw.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.raw.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.unique.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.unique.backup"} > {{ telemetry_unique_backup_threshold }} | ||
description: '{{ env_name }}.telemetry.raw.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.raw.backup | ||
- alert: secor {{ env_name }}.telemetry.unique.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.unique.backup"} > {{ telemetry_unique_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.unique.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.unique.backup | ||
- alert: secor {{ kafka_topic_prefix }}.learning.failed.events.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.learning.failed.events.backup"} > {{ learning_failed_events_backup_threshold }} | ||
description: '{{ env_name }}.telemetry.unique.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.unique.backup | ||
- alert: secor {{ env_name }}.learning.failed.events.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.learning.failed.events.backup"} > {{ learning_failed_events_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.learning.failed.events.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.learning.failed.events.backup | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.denorm.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.denorm.backup"} > {{ telemetry_denorm_backup_threshold }} | ||
description: '{{ env_name }}.learning.failed.events.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.learning.failed.events.backup | ||
- alert: secor {{ env_name }}.telemetry.denorm.backup consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.denorm.backup"} > {{ telemetry_denorm_backup_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.denorm.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.denorm.backup | ||
- alert: secor {{ kafka_topic_prefix }}.pipeline_metrics consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.pipeline_metrics"} > {{ pipeline_metrics_threshold }} | ||
description: '{{ env_name }}.telemetry.denorm.backup consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.denorm.backup | ||
- alert: secor {{ env_name }}.pipeline_metrics consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.pipeline_metrics"} > {{ pipeline_metrics_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.pipeline_metrics consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.pipeline_metrics | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.extractor.failed consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.extractor.failed"} > {{ telemetry_extractor_failed_threshold }} | ||
description: '{{ env_name }}.pipeline_metrics consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.pipeline_metrics | ||
- alert: secor {{ env_name }}.telemetry.extractor.failed consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.extractor.failed"} > {{ telemetry_extractor_failed_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.extractor.failed consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.extractor.failed | ||
- alert: secor {{ kafka_topic_prefix }}.telemetry.assess consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ kafka_topic_prefix }}.telemetry.assess"} > {{ telemetry_assess_threshold }} | ||
description: '{{ env_name }}.telemetry.extractor.failed consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.extractor.failed | ||
- alert: secor {{ env_name }}.telemetry.assess consumer group lag | ||
expr: kafka_consumergroupzookeeper_lag_zookeeper{consumergroup="{{ env_name }}.telemetry.assess"} > {{ telemetry_assess_threshold }} | ||
for: 5m | ||
labels: | ||
severity: critical | ||
annotations: | ||
description: '{{ kafka_topic_prefix }}.telemetry.assess consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ kafka_topic_prefix }}.telemetry.assess | ||
description: '{{ env_name }}.telemetry.assess consumer group lag is {% raw %}{{$value}}{% endraw %} for partition: {% raw %}{{ $labels.partition }}{% endraw %}' | ||
summary: secor consumer group lag is more for {{ env_name }}.telemetry.assess |