k3s: Pod-Monitoring in Grafana (Task 6.5)

kube-state-metrics (NodePort 30808) und ServiceAccount prometheus-infra (nur
nodes/metrics) im Cluster; Prometheus auf infra liest kubelet/cAdvisor per TLS
gegen die k3s-CA. Ziele per file_sd aus kubectl get nodes, cAdvisor auf die
nötigen Reihen begrenzt. Dashboard "k3s – Pods" (Vorgabe nex), Alerts K3s*
nur mit notify. Playbook monitoring-k3s.yml.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

deploy/prometheus/alerts.yml

@@ -47,3 +47,33 @@ groups:
         for: 15m
         labels: {severity: warning}
         annotations: {summary: "{{ $labels.instance }} {{ $labels.mountpoint }} < 10 % frei"}
+
+  # k3s (Task 6.5): nur melden, der Healer greift nicht ein (config/healer-rules.yaml, Aktion notify)
+  - name: knaster-k3s
+    rules:
+      - alert: K3sNodeNotReady
+        expr: kube_node_status_condition{condition="Ready", status="true"} == 0
+        for: 5m
+        labels: {severity: high}
+        annotations: {summary: "k3s-Knoten {{ $labels.node }} nicht bereit"}
+
+      - alert: K3sPodCrashLooping
+        expr: max by (namespace, pod, container) (kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff"}) == 1
+        for: 10m
+        labels: {severity: warning}
+        annotations: {summary: "{{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) startet immer wieder neu"}
+
+      - alert: K3sDeploymentUnavailable
+        expr: max by (namespace, deployment) (kube_deployment_spec_replicas) > max by (namespace, deployment) (kube_deployment_status_replicas_available)
+        for: 15m
+        labels: {severity: warning}
+        annotations: {summary: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} hat zu wenige bereite Pods"}
+
+      - alert: K3sContainerMemoryNearLimit
+        expr: >
+          max by (namespace, pod, container) (container_memory_working_set_bytes{job="cadvisor"})
+          / on (namespace, pod, container)
+          max by (namespace, pod, container) (kube_pod_container_resource_limits{resource="memory"}) > 0.9
+        for: 10m
+        labels: {severity: warning}
+        annotations: {summary: "{{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) über 90 % des Speicherlimits"}