---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  creationTimestamp: "2026-02-17T12:49:43Z"
  generation: 1
  labels:
    app.kubernetes.io/component: alert-router
    app.kubernetes.io/instance: main
    app.kubernetes.io/managed-by: cluster-monitoring-operator
    app.kubernetes.io/name: alertmanager
    app.kubernetes.io/part-of: openshift-monitoring
    app.kubernetes.io/version: 0.28.1
    prometheus: k8s
    role: alert-rules
  managedFields:
  - apiVersion: monitoring.coreos.com/v1
    fieldsType: FieldsV1
    fieldsV1:
      f:metadata:
        f:labels:
          .: {}
          f:app.kubernetes.io/component: {}
          f:app.kubernetes.io/instance: {}
          f:app.kubernetes.io/managed-by: {}
          f:app.kubernetes.io/name: {}
          f:app.kubernetes.io/part-of: {}
          f:app.kubernetes.io/version: {}
          f:prometheus: {}
          f:role: {}
      f:spec:
        .: {}
        f:groups:
          .: {}
          k:{"name":"alertmanager.rules"}:
            .: {}
            f:name: {}
            f:rules: {}
    manager: operator
    operation: Update
    time: "2026-02-17T12:49:43Z"
  name: alertmanager-main-rules
  namespace: openshift-monitoring
  resourceVersion: "9795"
  uid: 28aee620-d7ed-4c8e-a42a-3b10aee06fc0
spec:
  groups:
  - name: alertmanager.rules
    rules:
    - alert: AlertmanagerFailedReload
      annotations:
        description: Configuration has failed to load for {{ $labels.namespace }}/{{
          $labels.pod}}.
        runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-monitoring-operator/AlertmanagerFailedReload.md
        summary: Reloading an Alertmanager configuration has failed.
      expr: |
        # Without max_over_time, failed scrapes could create false negatives, see
        # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
        max_over_time(alertmanager_config_last_reload_successful{job=~"alertmanager-main|alertmanager-user-workload"}[5m]) == 0
      for: 10m
      labels:
        severity: critical
    - alert: AlertmanagerMembersInconsistent
      annotations:
        description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only
          found {{ $value }} members of the {{$labels.job}} cluster.
        summary: A member of an Alertmanager cluster has not found all other cluster
          members.
      expr: |
        # Without max_over_time, failed scrapes could create false negatives, see
        # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
          max_over_time(alertmanager_cluster_members{job=~"alertmanager-main|alertmanager-user-workload"}[5m])
        < on (namespace,service) group_left
          count by (namespace,service) (max_over_time(alertmanager_cluster_members{job=~"alertmanager-main|alertmanager-user-workload"}[5m]))
      for: 15m
      labels:
        severity: warning
    - alert: AlertmanagerFailedToSendAlerts
      annotations:
        description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed
          to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration
          }}.
        runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-monitoring-operator/AlertmanagerFailedToSendAlerts.md
        summary: An Alertmanager instance failed to send notifications.
      expr: |
        (
          rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload"}[15m])
        /
          ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload"}[15m])
        )
        > 0.01
      for: 5m
      labels:
        severity: warning
    - alert: AlertmanagerClusterFailedToSendAlerts
      annotations:
        description: The minimum notification failure rate to {{ $labels.integration
          }} sent from any instance in the {{$labels.job}} cluster is {{ $value |
          humanizePercentage }}.
        runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-monitoring-operator/AlertmanagerClusterFailedToSendAlerts.md
        summary: All Alertmanager instances in a cluster failed to send notifications
          to a critical integration.
      expr: |
        min by (namespace,service, integration) (
          rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[15m])
        /
          ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[15m]) > 0
        )
        > 0.01
      for: 5m
      labels:
        severity: warning
    - alert: AlertmanagerConfigInconsistent
      annotations:
        description: Alertmanager instances within the {{$labels.job}} cluster have
          different configurations.
        summary: Alertmanager instances within the same cluster have different configurations.
      expr: |
        count by (namespace,service) (
          count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job=~"alertmanager-main|alertmanager-user-workload"})
        )
        != 1
      for: 20m
      labels:
        severity: warning
    - alert: AlertmanagerClusterDown
      annotations:
        description: '{{ $value | humanizePercentage }} of Alertmanager instances
          within the {{$labels.job}} cluster have been up for less than half of the
          last 5m.'
        summary: Half or more of the Alertmanager instances within the same cluster
          are down.
      expr: |
        (
          count by (namespace,service) (
            avg_over_time(up{job=~"alertmanager-main|alertmanager-user-workload"}[5m]) < 0.5
          )
        /
          count by (namespace,service) (
            up{job=~"alertmanager-main|alertmanager-user-workload"}
          )
        )
        >= 0.5
      for: 5m
      labels:
        severity: warning