Publish

_data/.#rules.yml

@@ -1 +0,0 @@
-samber@Sambers-MacBook.local.46405

_data/rules.yml

@@ -2044,6 +2044,15 @@ groups:
                 query: 'kube_node_status_condition{condition="Ready",status="true"} == 0'
                 severity: critical
                 for: 10m
+              - name: Kubernetes Node scheduling disabled
+                summary: Kubernetes node scheduling disabled (node {{ $labels.node }})
+                description: Node {{ $labels.node }} has been marked as unschedulable for more than 30 minutes.
+                query: 'kube_node_spec_taint{key="node.kubernetes.io/unschedulable"} == 1'
+                severity: warning
+                for: 30m
+                comments: |
+                  Kubernetes Node with disabled schedules are fine.
+                  This alarm can be useful to get warned if there are nodes which are longer unscheduled.
               - name: Kubernetes Node memory pressure
                 summary: Kubernetes memory pressure (node {{ $labels.node }})
                 description: "Node {{ $labels.node }} has MemoryPressure condition"

dist/rules/kubernetes/kubestate-exporter.yml

@@ -13,6 +13,15 @@ groups:
         summary: Kubernetes Node ready (node {{ $labels.node }})
         description: "Node {{ $labels.node }} has been unready for a long time\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
+    - alert: KubernetesNodeSchedulingDisabled
+      expr: 'kube_node_spec_taint{key="node.kubernetes.io/unschedulable"} == 1'
+      for: 30m
+      labels:
+        severity: warning
+      annotations:
+        summary: Kubernetes node scheduling disabled (node {{ $labels.node }})
+        description: "Node {{ $labels.node }} has been marked as unschedulable for more than 30 minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
     - alert: KubernetesNodeMemoryPressure
       expr: 'kube_node_status_condition{condition="MemoryPressure",status="true"} == 1'
       for: 2m