diff --git a/_data/rules.yml b/_data/rules.yml index ee6a302..715f181 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -2219,6 +2219,11 @@ groups: 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 failing + summary: Kubernetes CronJob failing ({{ $labels.namespace }}/{{ $labels.cronjob }}) + description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is failing" + query: "(kube_cronjob_status_last_schedule_time > kube_cronjob_status_last_successful_time) AND (kube_cronjob_status_active == 0) AND (kube_cronjob_spec_suspend == 0)" + severity: critical - name: Kubernetes CronJob suspended summary: Kubernetes CronJob suspended ({{ $labels.namespace }}/{{ $labels.cronjob }}) description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended"