Add MachineHealthCheckUnterminatedShortCircuitSRE alert

openshift · Apr 25, 2024 · d2f40f4 · d2f40f4
1 parent 18af189
commit d2f40f4
Showing 1 changed file with 14 additions and 0 deletions.
diff --git a/install/0000_90_machine-api-operator_04_alertrules.yaml b/install/0000_90_machine-api-operator_04_alertrules.yaml
@@ -78,3 +78,17 @@ spec:
             description: |
               The number of unhealthy machines has exceeded the `maxUnhealthy` limit for the check, you should check
               the status of machines in the cluster.
+    - name: machine-health-check-unterminated-short-circuit-sre
+      rules:
+        - alert: MachineHealthCheckUnterminatedShortCircuitSRE
+          expr: |
+            mapi_machinehealthcheck_short_circuit == 1
+          for: 30m
+          labels:
+            severity: critical
+          annotations:
+            summary: "machine health check {{ $labels.name }} has been disabled by short circuit for more than 30 minutes"
+            description: |
+              The number of unhealthy machines has exceeded the `maxUnhealthy` limit for the check, you should check
+              the status of machines in the cluster.
+