Docker & Kubernetes with Spring Boot

# application.yml — enable probe endpoints
management:
  endpoint:
    health:
      probes:
        enabled: true
      group:
        liveness:
          include: livenessState
        readiness:
          include: readinessState, db, redis
  health:
    livenessstate:
      enabled: true
    readinessstate:
      enabled: true

# application.yml
server:
  shutdown: graceful                    # Wait for active requests to complete

spring:
  lifecycle:
    timeout-per-shutdown-phase: 30s     # Max 30s to drain

# Deployment — add preStop hook for safety
spec:
  containers:
    - name: myapp
      lifecycle:
        preStop:
          exec:
            command: ["sh", "-c", "sleep 5"]  # Wait for LB to deregister
  terminationGracePeriodSeconds: 45           # Must be > shutdown-phase + preStop

# application.yml
spring:
  cloud:
    kubernetes:
      config:
        enabled: true
        name: myapp-config         # ConfigMap name
        namespace: production
      secrets:
        enabled: true
        name: myapp-secrets        # Secret name
      reload:
        enabled: true              # Hot-reload on ConfigMap changes
        strategy: refresh          # Or restart_context for full reload
        mode: event                # Watch for changes (vs polling)

# ConfigMap (myapp-config.yaml)
apiVersion: v1
kind: ConfigMap
metadata:
  name: myapp-config
data:
  application.yml: |
    app:
      feature-flag: true
      cache-ttl: 300
      external-service-url: https://api.example.com

# Secret (myapp-secrets.yaml)
apiVersion: v1
kind: Secret
metadata:
  name: myapp-secrets
type: Opaque
stringData:
  spring.datasource.password: "s3cr3t-db-pass"
  app.jwt-secret: "hmac-256-secret-key"

resources:
  requests:
    memory: "512Mi"    # Guaranteed minimum
    cpu: "250m"        # 0.25 CPU cores
  limits:
    memory: "512Mi"    # Hard cap (OOM kill if exceeded)
    cpu: "1000m"       # Throttled if exceeded (not killed)

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: myapp-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: myapp
  minReplicas: 2
  maxReplicas: 10
  metrics:
    # CPU-based (default)
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70

    # Memory-based
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 80

    # Custom metric (requests per second via Prometheus)
    - type: Pods
      pods:
        metric:
          name: http_requests_per_second
        target:
          type: AverageValue
          averageValue: "1000"

  behavior:
    scaleUp:
      stabilizationWindowSeconds: 30    # React quickly
      policies:
        - type: Pods
          value: 2
          periodSeconds: 60             # Add max 2 pods per minute
    scaleDown:
      stabilizationWindowSeconds: 300   # Wait 5 min before scaling down
      policies:
        - type: Pods
          value: 1
          periodSeconds: 60             # Remove 1 pod per minute

apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp
spec:
  replicas: 3
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1          # 1 extra pod during rollout
      maxUnavailable: 0    # Never reduce below desired count
  template:
    spec:
      containers:
        - name: myapp
          image: myregistry/myapp:2.0.0
          ports:
            - containerPort: 8080
          startupProbe:
            httpGet:
              path: /actuator/health/liveness
              port: 8080
            initialDelaySeconds: 10
            periodSeconds: 5
            failureThreshold: 30       # 10 + (5×30) = 160s max startup
          livenessProbe:
            httpGet:
              path: /actuator/health/liveness
              port: 8080
            periodSeconds: 10
            failureThreshold: 3
          readinessProbe:
            httpGet:
              path: /actuator/health/readiness
              port: 8080
            periodSeconds: 5
            failureThreshold: 3
          resources:
            requests:
              memory: "512Mi"
              cpu: "250m"
            limits:
              memory: "512Mi"
              cpu: "1000m"
          env:
            - name: JAVA_TOOL_OPTIONS
              value: "-XX:MaxRAMPercentage=75.0 -XX:+UseG1GC"
          lifecycle:
            preStop:
              exec:
                command: ["sh", "-c", "sleep 5"]
      terminationGracePeriodSeconds: 45

# namespace.yaml
apiVersion: v1
kind: Namespace
metadata:
  name: myapp-prod
---
# configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: myapp-config
  namespace: myapp-prod
data:
  SPRING_PROFILES_ACTIVE: "prod"
  SERVER_PORT: "8080"
  MANAGEMENT_SERVER_PORT: "8081"
---
# secret.yaml
apiVersion: v1
kind: Secret
metadata:
  name: myapp-secrets
  namespace: myapp-prod
type: Opaque
stringData:
  SPRING_DATASOURCE_URL: "jdbc:postgresql://db-host:5432/myapp"
  SPRING_DATASOURCE_USERNAME: "app_user"
  SPRING_DATASOURCE_PASSWORD: "encrypted-password"
---
# deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp
  namespace: myapp-prod
  labels:
    app: myapp
    version: v2.0.0
spec:
  replicas: 3
  selector:
    matchLabels:
      app: myapp
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 0
  template:
    metadata:
      labels:
        app: myapp
        version: v2.0.0
      annotations:
        prometheus.io/scrape: "true"
        prometheus.io/port: "8081"
        prometheus.io/path: "/actuator/prometheus"
    spec:
      serviceAccountName: myapp-sa
      topologySpreadConstraints:
        - maxSkew: 1
          topologyKey: topology.kubernetes.io/zone
          whenUnsatisfiable: DoNotSchedule
          labelSelector:
            matchLabels:
              app: myapp
      containers:
        - name: myapp
          image: myregistry/myapp:2.0.0
          ports:
            - name: http
              containerPort: 8080
            - name: management
              containerPort: 8081
          envFrom:
            - configMapRef:
                name: myapp-config
            - secretRef:
                name: myapp-secrets
          env:
            - name: JAVA_TOOL_OPTIONS
              value: >-
                -XX:+UseContainerSupport
                -XX:MaxRAMPercentage=75.0
                -XX:+UseG1GC
                -XX:MaxGCPauseMillis=200
                -Dspring.config.additional-location=optional:configmap:myapp-config/
          startupProbe:
            httpGet:
              path: /actuator/health/liveness
              port: management
            initialDelaySeconds: 10
            periodSeconds: 5
            failureThreshold: 30
          livenessProbe:
            httpGet:
              path: /actuator/health/liveness
              port: management
            periodSeconds: 10
            failureThreshold: 3
          readinessProbe:
            httpGet:
              path: /actuator/health/readiness
              port: management
            periodSeconds: 5
            failureThreshold: 3
          resources:
            requests:
              memory: "512Mi"
              cpu: "250m"
            limits:
              memory: "512Mi"
              cpu: "1000m"
          lifecycle:
            preStop:
              exec:
                command: ["sh", "-c", "sleep 5"]
      terminationGracePeriodSeconds: 45
---
# service.yaml
apiVersion: v1
kind: Service
metadata:
  name: myapp-service
  namespace: myapp-prod
spec:
  selector:
    app: myapp
  ports:
    - name: http
      port: 80
      targetPort: http
    - name: management
      port: 8081
      targetPort: management
  type: ClusterIP
---
# hpa.yaml
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: myapp-hpa
  namespace: myapp-prod
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: myapp
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300