Added alerts for failing connectors and tasks as these can not be aut…

…omatically recovered and need manual intervention. Signed-off-by: Laszlo I. Hunyady <[email protected]>
strimzi · Jul 8, 2024 · 943d27b · 943d27b
1 parent c8b5d9d
commit 943d27b
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 0 deletions.
diff --git a/examples/metrics/prometheus-install/prometheus-rules.yaml b/examples/metrics/prometheus-install/prometheus-rules.yaml
@@ -159,6 +159,20 @@ 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
+      labels:
+        severity: major
+      annotations:
+        summary: 'Kafka Connect Connector Failure'
+        description: 'Some connectors are failing, this can not be automatically recovered.'
+    - alert: ConnectFailedTask
+      expr: sum(kafka_connect_worker_connector_failed_task_count) > 0
+      labels:
+        severity: major
+      annotations:
+        summary: 'Kafka Connect Task Failure'
+        description: 'Some tasks are failing, this can not be automatically recovered.'
   - name: bridge
     rules:
     - alert: BridgeContainersDown

diff --git a/packaging/examples/metrics/prometheus-install/prometheus-rules.yaml b/packaging/examples/metrics/prometheus-install/prometheus-rules.yaml
@@ -159,6 +159,20 @@ 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
+      labels:
+        severity: major
+      annotations:
+        summary: 'Kafka Connect Connector Failure'
+        description: 'Some connectors are failing, this can not be automatically recovered.'
+    - alert: ConnectFailedTask
+      expr: sum(kafka_connect_worker_connector_failed_task_count) > 0
+      labels:
+        severity: major
+      annotations:
+        summary: 'Kafka Connect Task Failure'
+        description: 'Some tasks are failing, this can not be automatically recovered.'
   - name: bridge
     rules:
     - alert: BridgeContainersDown