feat: initial alert rules

rules/nodes.yaml

@@ -0,0 +1,55 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: k8s-node-rules
+  namespace: monitoring
+  labels:
+    release: monitoring
+spec:
+  groups:
+    - name: nodes.critical
+      rules:
+        - alert: NodeNotReady
+          expr: kube_node_status_condition{condition="Ready",status="true"} == 0
+          for: 15m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Node NotReady"
+            description: "Le node {{ $labels.node }} est NotReady depuis 15 minutes."
+
+        - alert: NodeMemoryPressure
+          expr: kube_node_status_condition{condition="MemoryPressure",status="true"} == 1
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Node en MemoryPressure"
+            description: "Le node {{ $labels.node }} est en MemoryPressure."
+
+        - alert: NodeDiskPressure
+          expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Node en DiskPressure"
+            description: "Le node {{ $labels.node }} est en DiskPressure."
+
+        - alert: NodeHighCPU
+          expr: 100 - (avg by(node) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "CPU node élevé"
+            description: "CPU du node {{ $labels.node }} > 85%."
+
+        - alert: NodeHighMemory
+          expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 90
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "RAM node élevée"
+            description: "RAM du node {{ $labels.node }} > 90%."