gistfile1.txt

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    app: kube-prometheus-stack
    release: prometheus
  name: job-failure-test
spec:
  groups:
    - name: CronJobAlert
      rules:
        - record: job_cronjob:kube_job_status_start_time:max
          expr: |-
            label_replace(
              label_replace(
                max(
                  kube_job_status_start_time
                  * ON(exported_job) GROUP_RIGHT()
                  kube_job_labels{label_cronjob!=""}
                ) BY (exported_job, label_cronjob)
                == ON(label_cronjob) GROUP_LEFT()
                max(
                  kube_job_status_start_time
                  * ON(exported_job) GROUP_RIGHT()
                  kube_job_labels{label_cronjob!=""}
                ) BY (label_cronjob),
                "job", "$1", "exported_job", "(.+)"),
              "cronjob", "$1", "label_cronjob", "(.+)")
        - record: job_cronjob:kube_job_status_failed:sum
          expr: |-
            clamp_max(
              job_cronjob:kube_job_status_start_time:max,
            1)
            * ON(job) GROUP_LEFT()
            label_replace(
              label_replace(
                (kube_job_status_failed != 0),
                "job", "$1", "exported_job", "(.+)"),
              "cronjob", "$1", "label_cronjob", "(.+)")
        - alert: CronJobFailed
          labels:
            severity: error
          for: 1m
          expr: |-
            job_cronjob:kube_job_status_failed:sum
            * ON(cronjob) GROUP_RIGHT()
            kube_cronjob_labels
            > 0