sbbb/base/storage/seaweedfs-alertrules.yaml

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: seaweedfs-alerts
  namespace: storage
  labels:
    role: alert-rules
    release: kube-prometheus-stack
spec:
  groups:
    - name: seaweedfs
      rules:
        - alert: SeaweedFSMasterDown
          expr: up{job=~".*seaweedfs.*", app="seaweedfs-master"} == 0
          for: 2m
          labels:
            severity: critical
          annotations:
            summary: "SeaweedFS master is down"
            description: "SeaweedFS master {{ $labels.namespace }}/{{ $labels.pod }} is down."

        - alert: SeaweedFSVolumeDown
          expr: up{job=~".*seaweedfs.*", app="seaweedfs-volume"} == 0
          for: 2m
          labels:
            severity: critical
          annotations:
            summary: "SeaweedFS volume server is down"
            description: "SeaweedFS volume server {{ $labels.namespace }}/{{ $labels.pod }} is down."

        - alert: SeaweedFSFilerDown
          expr: up{job=~".*seaweedfs.*", app="seaweedfs-filer"} == 0
          for: 2m
          labels:
            severity: critical
          annotations:
            summary: "SeaweedFS filer is down"
            description: "SeaweedFS filer {{ $labels.namespace }}/{{ $labels.pod }} is down."

        - alert: SeaweedFSDiskLow
          expr: (seaweedfs_disk_free_bytes / (seaweedfs_disk_free_bytes + seaweedfs_disk_used_bytes)) < 0.15
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "SeaweedFS disk space low"
            description: "SeaweedFS disk on {{ $labels.instance }} has less than 15% free space."

        - alert: SeaweedFSMirrorJobFailing
          expr: |
            kube_job_status_failed{namespace="storage", job_name=~"seaweedfs-s3-mirror.*"} > 0
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "SeaweedFS S3 mirror job failed"
            description: "Job {{ $labels.job_name }} failed. S3 backups to Scaleway are not running."

        - alert: SeaweedFSMirrorStale
          expr: |
            time() - kube_cronjob_status_last_successful_time{namespace="storage", cronjob="seaweedfs-s3-mirror"} > 7200
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "SeaweedFS S3 mirror hasn't succeeded in 2+ hours"
            description: "CronJob seaweedfs-s3-mirror last succeeded {{ $value | humanizeDuration }} ago."