mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-26 11:27:00 +08:00
feat: Add rule to Kubernetes Job not starting
This commit is contained in:
parent
c41fda1d92
commit
ae5aeb9f53
1 changed files with 9 additions and 4 deletions
|
|
@ -2044,6 +2044,11 @@ groups:
|
|||
description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete"
|
||||
query: "kube_job_status_failed > 0"
|
||||
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
|
||||
summary: Kubernetes CronJob suspended ({{ $labels.namespace }}/{{ $labels.cronjob }})
|
||||
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended"
|
||||
|
|
|
|||
Loading…
Reference in a new issue