Improve KubernetesJobFailed alert

This commit is contained in:
Erki Aas
2026-09-18 10:55:41 +03:00
parent 3b6bc582a5
commit 4634d25320
+22 -2
View File
@@ -279,13 +279,33 @@ spec:
summary: Kubernetes container oom killer (instance {{ $labels.instance }}) summary: Kubernetes container oom killer (instance {{ $labels.instance }})
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesJobFailed - alert: KubernetesJobFailed
expr: kube_job_status_failed > 0 expr: |
(
kube_job_status_failed > 0
unless on (namespace, job_name)
kube_job_owner{owner_kind="CronJob", owner_is_controller="true"}
)
or
(
kube_job_status_failed > 0
and on (namespace, job_name)
(
kube_job_status_start_time
* on (namespace, job_name) group_left (owner_name)
kube_job_owner{owner_kind="CronJob", owner_is_controller="true"}
> on (namespace, owner_name) group_left ()
label_replace(
kube_cronjob_status_last_successful_time,
"owner_name", "$1", "cronjob", "(.*)"
)
)
)
for: 0m for: 0m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: Kubernetes Job failed (instance {{ $labels.instance }}) summary: Kubernetes Job failed (instance {{ $labels.instance }})
description: "Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesCronjobSuspended - alert: KubernetesCronjobSuspended
expr: kube_cronjob_spec_suspend != 0 expr: kube_cronjob_spec_suspend != 0
for: 0m for: 0m