Kubernetes Deployments: Rolling Updates and Best Practices

Deployment Configuration

apiVersion: apps/v1
kind: Deployment
metadata:
  name: api-server
  namespace: production
spec:
  replicas: 3
  selector:
    matchLabels:
      app: api-server
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1        # Max pods above desired (during update)
      maxUnavailable: 0   # Never take pods offline (zero-downtime)
  template:
    metadata:
      labels:
        app: api-server
        version: "1.2.3"
    spec:
      containers:
      - name: api
        image: myrepo/api:1.2.3
        ports:
        - containerPort: 3000
        # Resource limits are critical
        resources:
          requests:
            cpu: "250m"
            memory: "256Mi"
          limits:
            cpu: "500m"
            memory: "512Mi"
        # Health probes
        livenessProbe:
          httpGet:
            path: /health/live
            port: 3000
          initialDelaySeconds: 10
          periodSeconds: 10
          failureThreshold: 3
        readinessProbe:
          httpGet:
            path: /health/ready
            port: 3000
          initialDelaySeconds: 5
          periodSeconds: 5
          failureThreshold: 3
        # Graceful shutdown
        lifecycle:
          preStop:
            exec:
              command: ["/bin/sh", "-c", "sleep 5"]
        env:
        - name: DATABASE_URL
          valueFrom:
            secretKeyRef:
              name: app-secrets
              key: database-url
      terminationGracePeriodSeconds: 30

Health Check Endpoints

// Express health endpoints
app.get('/health/live', (req, res) => {
  // Liveness: is the process running?
  res.json({ status: 'ok', uptime: process.uptime() });
});

app.get('/health/ready', async (req, res) => {
  // Readiness: can it handle requests?
  try {
    await db.query('SELECT 1');  // DB check
    await redis.ping();           // Cache check
    res.json({ status: 'ready' });
  } catch (err) {
    res.status(503).json({ status: 'not ready', error: err.message });
  }
});

Horizontal Pod Autoscaler

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: api-server-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: api-server
  minReplicas: 2
  maxReplicas: 20
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 70
  - type: Resource
    resource:
      name: memory
      target:
        type: Utilization
        averageUtilization: 80
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300  # Wait 5min before scaling down
      policies:
      - type: Percent
        value: 50      # Scale down by max 50%
        periodSeconds: 60

Pod Disruption Budget

# Ensure minimum availability during node drain/upgrades
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: api-server-pdb
spec:
  minAvailable: 2   # Always keep at least 2 pods running
  selector:
    matchLabels:
      app: api-server

Blue-Green Deployment

# Blue (current)
apiVersion: apps/v1
kind: Deployment
metadata:
  name: api-blue
spec:
  replicas: 3
  template:
    metadata:
      labels:
        app: api
        version: blue
    spec:
      containers:
      - name: api
        image: myrepo/api:1.2.3

---
# Service switches between blue and green
apiVersion: v1
kind: Service
metadata:
  name: api-service
spec:
  selector:
    app: api
    version: blue  # Change to 'green' for cutover
  ports:
  - port: 80
    targetPort: 3000

Rolling updates with proper health checks and PDBs enable zero-downtime deployments.