Test alert

k8s/monitoring/templates/node-alerts.yaml

@@ -9,7 +9,26 @@ spec:
    groups:
   - name: node.alerts
     rules:
-    - alert: NodeHighCPU
+    - alert: InternalTestAlert
+      expr: vector(1)
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: "Internal Alert Pipeline Test"
+        description: "This alert is manually triggered to verify the Slack alerting pipeline."
+
+    - alert: NodeMissingWorkloadLabel
+      expr: |
+        count by (instance) (node_cpu_seconds_total) unless count by (instance) (node_cpu_seconds_total{workload=~".+"})
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Node missing workload label on metrics"
+        description: "Metrics for instance {{ "{{" }} $labels.instance {{ "}}" }} are missing the 'workload' label, which is required for NodeHighCPU alerts."
+
+    - alert: MediaNodeHighCPU
       expr: |
         (
           (1 - avg without (cpu, mode) (rate(node_cpu_seconds_total{mode="idle", workload="media"}[1m]))) * 100 > {{ .Values.cpuThresholdMedia | default 65 }}
@@ -23,4 +42,4 @@ spec:
         severity: warning
       annotations:
         summary: "High CPU usage on node {{ "{{" }} $labels.instance {{ "}}" }}"
-        description: "Node {{ "{{" }} $labels.instance {{ "}}" }} has CPU usage above threshold (current value: {{ "{{" }} $value | printf \"%.2f\" {{ "}}" }}%)"
+        description: "Node {{ "{{" }} $labels.instance {{ "}}" }} (workload: {{ "{{" }} $labels.workload {{ "}}" }}) has CPU usage above threshold (current value: {{ "{{" }} $value | printf \"%.2f\" {{ "}}" }}%)"

k8s/monitoring/values-production.yaml

@@ -170,6 +170,15 @@ kube-prometheus-stack:
         repeat_interval: 12h
         receiver: 'null'
         routes:
+        - match:
+            alertname: InternalTestAlert
+          receiver: 'slack-notifications'
+        - match:
+            alertname: MediaNodeHighCPU
+          receiver: 'slack-notifications'
+        - match:
+            alertname: NodeMissingWorkloadLabel
+          receiver: 'slack-notifications'
         - match:
             alertname: NodeHighCPU
           receiver: 'slack-notifications'