XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 08:57:19 +08:00
Code Issues Projects Releases Packages Wiki Activity

fix k8s rule: longer alert check time

Browse source
This commit is contained in:
Samuel Berthe 2020-12-30 19:13:02 +01:00
parent a6bf7d1168
commit 3a352d08dc
No known key found for this signature in database
GPG key ID: 64863511FFBD0E3C
1 changed files with 8 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
_data/rules.yml
View file

@ -1200,10 +1200,15 @@ groups:
description: CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.
query: 'time() - kube_cronjob_next_schedule_time > 3600'
severity: warning
- name: Kubernetes job completion
description: Kubernetes Job failed to complete
query: 'kube_job_spec_completions - kube_job_status_succeeded > 0 or kube_job_status_failed > 0'
- name: Kubernetes job failed
description: Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
query: 'kube_job_status_failed > 0'
severity: critical
- name: Kubernetes job slow completion
description: Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.
query: 'kube_job_spec_completions - kube_job_status_succeeded > 0'
severity: critical
for: 12h
- name: Kubernetes API server errors
description: Kubernetes API server is experiencing high error rate
query: 'sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[2m])) / sum(rate(apiserver_request_count{job="apiserver"}[2m])) * 100 > 3'