XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-24 02:17:00 +08:00
Code Issues Projects Releases Packages Wiki Activity

feat: Add rule to Kubernetes Job not starting (#436)

Browse source
This commit is contained in:
sipr-invivo 2024-10-28 22:24:10 +01:00 committed by GitHub
parent f9e683896f
commit bb75cb2c68
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
_data/rules.yml
View file

@ -1132,12 +1132,12 @@ groups:
description: "The indexing latency on Elasticsearch cluster is higher than the threshold." description: "The indexing latency on Elasticsearch cluster is higher than the threshold."
query: "elasticsearch_indices_indexing_index_time_seconds_total / elasticsearch_indices_indexing_index_total > 0.0005" query: "elasticsearch_indices_indexing_index_time_seconds_total / elasticsearch_indices_indexing_index_total > 0.0005"
severity: warning severity: warning
for: 10m for: 10m
- name: Elasticsearch High Indexing Rate - name: Elasticsearch High Indexing Rate
description: "The indexing rate on Elasticsearch cluster is higher than the threshold." description: "The indexing rate on Elasticsearch cluster is higher than the threshold."
query: "sum(rate(elasticsearch_indices_indexing_index_total[1m]))> 10000" query: "sum(rate(elasticsearch_indices_indexing_index_total[1m]))> 10000"
severity: warning severity: warning
for: 5m for: 5m
- name: Elasticsearch High Query Rate - name: Elasticsearch High Query Rate
description: "The query rate on Elasticsearch cluster is higher than the threshold." description: "The query rate on Elasticsearch cluster is higher than the threshold."
query: "sum(rate(elasticsearch_indices_search_query_total[1m])) > 100" query: "sum(rate(elasticsearch_indices_search_query_total[1m])) > 100"
@ -1147,14 +1147,14 @@ groups:
description: "The query latency on Elasticsearch cluster is higher than the threshold." description: "The query latency on Elasticsearch cluster is higher than the threshold."
query: "elasticsearch_indices_search_fetch_time_seconds / elasticsearch_indices_search_fetch_total > 1" query: "elasticsearch_indices_search_fetch_time_seconds / elasticsearch_indices_search_fetch_total > 1"
severity: warning severity: warning
for: 5m for: 5m
- name: Meilisearch - name: Meilisearch
exporters: exporters:
- name: Embedded exporter - name: Embedded exporter
slug: embedded-exporter slug: embedded-exporter
doc_url: https://github.com/orgs/meilisearch/discussions/625 doc_url: https://github.com/orgs/meilisearch/discussions/625
rules: rules:
- name: Meilisearch index is empty - name: Meilisearch index is empty
description: Meilisearch instance is down description: Meilisearch instance is down
query: 'meilisearch_index_docs_count == 0' query: 'meilisearch_index_docs_count == 0'
@ -2044,6 +2044,11 @@ groups:
description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete" description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete"
query: "kube_job_status_failed > 0" query: "kube_job_status_failed > 0"
severity: warning severity: warning
- name: Kubernetes Job not starting
summary: Kubernetes Job not starting ({{ $labels.namespace }}/{{ $labels.job_name }})
description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} did not start for 10 minutes"
query: "kube_job_status_active == 0 and kube_job_status_failed == 0 and kube_job_status_succeeded == 0 and (time() - kube_job_status_start_time) > 600"
severity: warning
- name: Kubernetes CronJob suspended - name: Kubernetes CronJob suspended
summary: Kubernetes CronJob suspended ({{ $labels.namespace }}/{{ $labels.cronjob }}) summary: Kubernetes CronJob suspended ({{ $labels.namespace }}/{{ $labels.cronjob }})
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended" description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended"