cluster

Infrastructure files for Nordgedanken and Midnightthoughts.
git clone git://archive.git.mtrnord.blog/MTRNord/cluster.git
Log | Files | Refs | README

velero-alerts.yaml (1487B)

      1 apiVersion: monitoring.coreos.com/v1
      2 kind: PrometheusRule
      3 metadata:
      4   name: velero-alerts
      5   namespace: velero
      6   labels:
      7     release: prometheus-stack
      8 spec:
      9   groups:
     10     - name: velero
     11       rules:
     12         - alert: VeleroBackupPartialFailure
     13           expr: |
     14             increase(velero_backup_partial_failure_total{schedule!=""}[6h]) > 0
     15             and on(schedule)
     16             (time() - velero_backup_last_successful_timestamp{schedule!=""}) > 21600
     17           for: 15m
     18           labels:
     19             severity: warning
     20           annotations:
     21             summary: "Velero backup partially failed and no recent success"
     22             description: "Schedule {{ $labels.schedule }} has partial failures and no successful backup in the last 6 hours."
     23 
     24         - alert: VeleroBackupFailure
     25           expr: |
     26             increase(velero_backup_failure_total{schedule!=""}[1h]) > 0
     27           for: 5m
     28           labels:
     29             severity: critical
     30           annotations:
     31             summary: "Velero backup failed"
     32             description: "Schedule {{ $labels.schedule }} backup failed in the last hour."
     33 
     34         - alert: VeleroBackupMissing
     35           expr: |
     36             time() - velero_backup_last_successful_timestamp{schedule!=""} > 90000
     37           for: 1h
     38           labels:
     39             severity: critical
     40           annotations:
     41             summary: "Velero backup missing for 25h"
     42             description: "Schedule {{ $labels.schedule }} has no successful backup in the last 25 hours."