Kubernetes on GKE Autopilot,
broken on purpose

# The demo app (as first applied, version 1.0): Google's public sample "hello-app". 3 replicas, each asking for 250m CPU and 512Mi memory.
apiVersion: apps/v1
kind: Deployment
metadata:
  name: hello
spec:
  replicas: 3
  selector:
    matchLabels:
      app: hello
  template:
    metadata:
      labels:
        app: hello
    spec:
      containers:
      - name: hello
        image: us-docker.pkg.dev/google-samples/containers/gke/hello-app:1.0
        ports:
        - containerPort: 8080
        resources:
          requests:
            cpu: 250m
            memory: 512Mi
        readinessProbe:
          httpGet:
            path: /
            port: 8080

# The demo app: Google's public sample "hello-app". 3 replicas, each asking for 250m CPU and 512Mi memory.
apiVersion: apps/v1
kind: Deployment
metadata:
  name: hello
spec:
  replicas: 3
  selector:
    matchLabels:
      app: hello
  template:
    metadata:
      labels:
        app: hello
    spec:
      containers:
      - name: hello
        image: us-docker.pkg.dev/google-samples/containers/gke/hello-app:2.0
        ports:
        - containerPort: 8080
        resources:
          requests:
            cpu: 250m
            memory: 512Mi
        readinessProbe:
          httpGet:
            path: /
            port: 8080

# One stable address in front of the pods, exposed to the internet through a Google Cloud load balancer.
apiVersion: v1
kind: Service
metadata:
  name: hello
spec:
  type: LoadBalancer
  selector:
    app: hello
  ports:
  - port: 80
    targetPort: 8080

# Horizontal Pod Autoscaler: keep average CPU near 50% of the request, between 3 and 10 pods.
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: hello
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: hello
  minReplicas: 3
  maxReplicas: 10
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 50

# Temporary traffic generator for the scaling demo (deleted afterwards).
apiVersion: apps/v1
kind: Deployment
metadata:
  name: load-generator
spec:
  replicas: 4
  selector:
    matchLabels:
      app: load-generator
  template:
    metadata:
      labels:
        app: load-generator
    spec:
      containers:
      - name: load
        image: busybox:1.36
        command: ["sh", "-c", "while true; do wget -q -O- http://hello > /dev/null; done"]
        resources:
          requests:
            cpu: 250m
            memory: 256Mi

# Troubleshooting demo 1: an app that exits because a required setting is missing -> CrashLoopBackOff.
apiVersion: v1
kind: Pod
metadata:
  name: payments-worker
spec:
  containers:
  - name: worker
    image: busybox:1.36
    command: ["sh", "-c", "echo 'Starting payments-worker v1.4.2'; echo 'Connecting to database...'; echo 'ERROR: DATABASE_URL is not set'; exit 1"]
    resources:
      requests:
        cpu: 250m
        memory: 256Mi

# Troubleshooting demo 2: a container that uses more memory than its 256Mi limit -> OOMKilled.
apiVersion: v1
kind: Pod
metadata:
  name: report-builder
spec:
  restartPolicy: Never
  containers:
  - name: builder
    image: busybox:1.36
    command: ["sh", "-c", "echo 'Loading 600 MB report into memory...'; head -c 600m /dev/zero | tail"]
    resources:
      requests:
        cpu: 250m
        memory: 256Mi
      limits:
        memory: 256Mi