# Backup monitoring alerts. Managed by Ansible (roles/prometheus).
#
# Metrics are emitted by the backup role (roles/backup) into node_exporter's
# textfile collector. The default backup schedule is weekly, so a successful
# backup is expected at least once a week; alert only when nothing succeeded
# for twice that. Tune the threshold if backup_schedule changes.
groups:
  - name: backup
    rules:
      - alert: BackupStale
        expr: time() - backup_last_success_timestamp_seconds > 14 * 24 * 3600
        for: 1h
        labels:
          severity: warning
        annotations:
          summary: "Backup stale ({{ $labels.backup_job }} / {{ $labels.repo }})"
          description: >-
            Job '{{ $labels.backup_job }}' has not backed up repository
            '{{ $labels.repo }}' successfully on {{ $labels.instance }} in over
            14 days.

      - alert: BackupTimerSilent
        expr: time() - node_systemd_timer_last_trigger_seconds{name=~"backup@.*"} > 14 * 24 * 3600
        for: 1h
        labels:
          severity: warning
        annotations:
          summary: "Backup timer {{ $labels.name }} has not fired on {{ $labels.instance }}"
          description: >-
            Timer {{ $labels.name }} last triggered {{ $value | humanizeDuration }}
            ago.