mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-24 02:17:00 +08:00
feat: Add rule to Kubernetes Job not starting (#436)
This commit is contained in:
parent
f9e683896f
commit
bb75cb2c68
1 changed files with 9 additions and 4 deletions
|
|
@ -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"
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue