XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 00:47:18 +08:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'master' of github.com:samber/awesome-prometheus-alerts

Browse source
This commit is contained in:
Samuel Berthe 2022-12-04 23:12:05 +01:00
commit a381fb5e22
No known key found for this signature in database
GPG key ID: 64863511FFBD0E3C
2 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
_data/rules.yml
View file

@ -1692,8 +1692,9 @@ groups:
for: 2m
- name: Kubernetes Pod not healthy
description: Pod has been in a non-ready state for longer than 15 minutes.
query: 'min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0'
query: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0'
severity: critical
for: 15m
- name: Kubernetes pod crash looping
description: Pod {{ $labels.pod }} is crash looping
query: 'increase(kube_pod_container_status_restarts_total[1m]) > 3'

4
dist/rules/kubernetes/kubestate-exporter.yml vendored
View file

@ -149,8 +149,8 @@ groups:
description: "The maximum number of desired Pods has been hit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPodNotHealthy
expr: 'min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0'
for: 0m
expr: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0'
for: 15m
labels:
severity: critical
annotations: