prometheus-alerts.yaml

  - name: Backups
    rules:
    - alert: KumonoboruFailure
      expr: |
        up{job="systemd", unit="Kumonoboru", state="failed"} == 1
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: "Service failure detected in {{ $labels.instance }}"
        description: "The service '{{ $labels.instance }}' has a failed status"
        source: 'https://monitor.your-domain.com'

    - alert: KumonoboruTimerFailure
      expr: |
        up{job="systemd", unit="Kumonoboru", state="failed"} == 1
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: "Timer failure detected in {{ $labels.instance }}"
        description: "The timer '{{ $labels.instance }}' has a failed status"
        source: 'https://monitor.your-domain.com'

    - alert: SystemBackupFailed
      expr: |
        system_backup == 1
      labels:
        severity: critical
      annotations:
        summary: "System Backup has failed"
        description: "The repository {{ $labels.instance }} has failed the backup process"

    - alert: SystemBackupUnlockFailed
      expr: |
        system_backup == -1
      labels:
        severity: critical
      annotations:
        summary: "System Backup cannot proceed"
        description: "The repository {{ $labels.instance }} has failed to unlock. Backup cannot be performed"

    - alert: SystemBackupIntegrityFailed
      expr: |
        system_backup == -2
      labels:
        severity: critical
      annotations:
        summary: "System Backup containes error"
        description: "The repository {{ $labels.instance }} has failed an integrity check. Backup data may be corrupted"

    - alert: SystemBackupCleaningFailed
      expr: |
        system_backup == -3
      labels:
        severity: critical
      annotations:
        summary: "System Backup cannot be cleaned"
        description: "The repository {{ $labels.instance }} has failed the cleanup process. Backup may contain excess data"

    - alert: SystemBackupSucceeded
      expr: |
        system_backup == 0
      labels:
        severity: info
      annotations:
        summary: "System Backup has succeeded"
        description: "The repository {{ $labels.instance }} has succesfully completed the backup process"

    - alert: SystemBackupIntegritySucceeded
      expr: |
        system_backup == 2
      labels:
        severity: info 
      annotations:
        summary: "System Backup has no errors"
        description: "The repository {{ $labels.instance }} passed the integrity check"

    - alert: SystemBackupCleaningSucceeded
      expr: |
        system_backup == 3
      labels:
        severity: info
      annotations:
        summary: "System Backup has been cleaned"
        description: "The repository {{ $labels.instance }} has completed the cleanup process"