monitoring-alerts.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: todo-app-monitor
  namespace: todo-app
  labels:
    app: todo-app
spec:
  selector:
    matchLabels:
      app.kubernetes.io/instance: todo-app
  endpoints:
  - port: http
    interval: 30s
    path: /metrics
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: todo-app-alerts
  namespace: todo-app
spec:
  groups:
  - name: todo-app.rules
    rules:
    - alert: HighPodRestarts
      expr: increase(kube_pod_container_status_restarts_total{namespace="todo-app"}[15m]) > 5
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: "High number of pod restarts in todo-app namespace"
        description: "More than 5 pod restarts in 15 minutes detected in {{ $labels.pod }}"

    - alert: PodNotReady
      expr: kube_pod_status_ready{namespace="todo-app",condition="false"} == 1
      for: 5m
      labels:
        severity: critical
      annotations:
        summary: "Pod in todo-app namespace is not ready"
        description: "{{ $labels.pod }} in namespace {{ $labels.namespace }} has been not ready for more than 5 minutes"

    - alert: HighCPUUsage
      expr: 100 * (kube_pod_container_resource_requests{resource="cpu",unit="core",namespace="todo-app"} - node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{}) / kube_pod_container_resource_requests{resource="cpu",unit="core",namespace="todo-app"} > 80
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: "High CPU usage in todo-app namespace"
        description: "CPU usage is above 80% for {{ $labels.pod }}"