ceph monitoring

ceph_alerts.yml

apiVersion: 1
groups:
- folder: ceph-alerts
  interval: 10s
  name: cluster health
  orgId: 1
  rules:
  - annotations:
      description: The cluster state has been HEALTH_ERROR for more than 5 minutes.
        Please check 'ceph health detail' for more information.
      summary: Ceph is in the ERROR state
    condition: A
    data:
    - datasourceUid: ceph
      model:
        disableTextWrap: false
        editorMode: code
        expr: ceph_health_status == 2
        fullMetaSearch: false
        includeNullMetadata: true
        instant: true
        intervalMs: 10000
        legendFormat: __auto
        maxDataPoints: 43200
        range: false
        refId: A
        useBackend: false
      refId: A
      relativeTimeRange:
        from: 300
        to: 0
    execErrState: Error
    for: 5m
    isPaused: false
    labels:
      oid: 1.3.6.1.4.1.50495.1.2.1.2.1
      severity: critical
      type: ceph_default
    noDataState: OK
    title: CephHealthError
    uid: ceph-ceph_health_error
  - annotations:
      description: The cluster state has been HEALTH_WARN for more than 15 minutes.
        Please check 'ceph health detail' for more information.
      summary: Ceph is in the WARNING state
    condition: A
    data:
    - datasourceUid: ceph
      model:
        disableTextWrap: false
        editorMode: code
        expr: ceph_health_status == 1
        fullMetaSearch: false
        includeNullMetadata: true
        instant: true
        intervalMs: 10000
        legendFormat: __auto
        maxDataPoints: 43200
        range: false
        refId: A
        useBackend: false
      refId: A
      relativeTimeRange:
        from: 300
        to: 0
    execErrState: Error
    for: 15m
    isPaused: false
    labels:
      severity: warning
      type: ceph_default
    noDataState: OK
    title: CephHealthWarning
    uid: ceph-ceph_health_warning