Added alerts for failing connectors and tasks (#10315)

Signed-off-by: Laszlo I. Hunyady <[email protected]>
strimzi · Jul 11, 2024 · e5d158c · e5d158c
1 parent 5900318
commit e5d158c
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,7 @@
 
 ## 0.43.0
 
+* Added alerts for Connectors/Tasks in failed state.
 
 ## 0.42.0
 

diff --git a/packaging/examples/metrics/prometheus-install/prometheus-rules.yaml b/packaging/examples/metrics/prometheus-install/prometheus-rules.yaml
@@ -159,6 +159,22 @@ spec:
       annotations:
         summary: 'All Kafka Connect containers down or in CrashLookBackOff status'
         description: 'All Kafka Connect containers have been down or in CrashLookBackOff status for 3 minutes'
+    - alert: ConnectFailedConnector
+      expr: sum(kafka_connect_connector_status{status="failed"}) > 0
+      for: 5m
+      labels:
+        severity: major
+      annotations:
+        summary: 'Kafka Connect Connector Failure'
+        description: 'One or more connectors have been in failed state for 5 minutes,'
+    - alert: ConnectFailedTask
+      expr: sum(kafka_connect_worker_connector_failed_task_count) > 0
+      for: 5m
+      labels:
+        severity: major
+      annotations:
+        summary: 'Kafka Connect Task Failure'
+        description: 'One or more tasks have been in failed state for 5 minutes.'
   - name: bridge
     rules:
     - alert: BridgeContainersDown