fix: added rule to check galera backups succedded

henrywhitaker3 · Mar 9, 2024 · 9969e8b · 9969e8b
1 parent 0feced8
commit 9969e8b
Showing 1 changed file with 8 additions and 0 deletions.
diff --git a/argo/cluster/monitoring/kube-prometheus-stack/chart/rules/misc.yaml b/argo/cluster/monitoring/kube-prometheus-stack/chart/rules/misc.yaml
@@ -115,6 +115,14 @@ spec:
             severity: critical
           annotations:
             summary: Galera cluster size is not equal to the number of replicase
+        - alert: GaleraBackupFailed
+          expr: |
+            sum(kube_job_status_failed{namespace="databases", job_name=~"mariabackup.*"}) > 0
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Galera backup job failed
         - alert: MysqlDown
           expr: mysql_up{service!~"srep.*"} == 0
           for: 0m