kalilurrahman/kr-claudiator-skills/deployment-strategies

apiVersion: apps/v1
kind: Deployment
spec:
  replicas: 10
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 2        # Allow 2 extra pods during rollout
      maxUnavailable: 0  # Never reduce below 10 healthy pods
  template:
    spec:
      containers:
        - name: api
          image: api:v2.1.0
          readinessProbe:
            httpGet:
              path: /health
              port: 8080
            initialDelaySeconds: 10
            periodSeconds: 5
            failureThreshold: 3
          # Readiness probe must pass before traffic routes to new pod

# Monitor rolling deployment
kubectl rollout status deployment/api -n production
kubectl get pods -n production -w
 
# Rollback if something's wrong
kubectl rollout undo deployment/api -n production
kubectl rollout undo deployment/api --to-revision=3 -n production

# Two identical environments; switch traffic at load balancer
 
# blue-deployment.yaml (current production)
apiVersion: apps/v1
kind: Deployment
metadata:
  name: api-blue
  labels:
    slot: blue
spec:
  replicas: 5
  selector:
    matchLabels: { slot: blue }
  template:
    metadata:
      labels: { app: api, slot: blue, version: v2.0.0 }
    spec:
      containers:
        - name: api
          image: api:v2.0.0
 
---
# green-deployment.yaml (new version — staged)
apiVersion: apps/v1
kind: Deployment
metadata:
  name: api-green
spec:
  replicas: 5
  selector:
    matchLabels: { slot: green }
  template:
    metadata:
      labels: { app: api, slot: green, version: v2.1.0 }
 
---
# service.yaml — switch by changing selector
apiVersion: v1
kind: Service
metadata:
  name: api
spec:
  selector:
    app: api
    slot: blue  # ← change to 'green' to switch traffic
  ports:
    - port: 80
      targetPort: 8080

# Blue-green switch
kubectl patch service api -p '{"spec":{"selector":{"slot":"green"}}}'
 
# Instant rollback
kubectl patch service api -p '{"spec":{"selector":{"slot":"blue"}}}'

apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
  name: api
spec:
  replicas: 20
  strategy:
    canary:
      steps:
        - setWeight: 5      # 5% of traffic to canary
        - pause: {duration: 10m}
        - analysis:
            templates:
              - templateName: error-rate-check
        - setWeight: 20     # 20% after passing analysis
        - pause: {duration: 10m}
        - setWeight: 50
        - pause: {duration: 5m}
        - setWeight: 100    # Full rollout if no issues
 
      canaryService: api-canary
      stableService: api-stable
      trafficRouting:
        nginx:
          stableIngress: api-stable-ingress
 
---
apiVersion: argoproj.io/v1alpha1
kind: AnalysisTemplate
metadata:
  name: error-rate-check
spec:
  metrics:
    - name: error-rate
      successCondition: result < 0.01   # <1% error rate
      failureCondition: result > 0.05
      provider:
        prometheus:
          query: |
            sum(rate(http_requests_total{status=~"5..",version="canary"}[5m]))
            / sum(rate(http_requests_total{version="canary"}[5m]))

# LaunchDarkly / Unleash / homegrown
from launchdarkly_client import Context
def get_price(product_id: str, user_id: str) -> dict:
    context = Context.builder(user_id).kind("user").build()
    
    # Gradually roll out new pricing algorithm
    use_new_pricing = ld_client.variation(
        "new-pricing-algorithm", context, default=False
    )
    
    if use_new_pricing:
        return new_pricing_engine.calculate(product_id)
    else:
        return legacy_pricing_engine.calculate(product_id)
# Percentage rollout: 0% → 5% → 25% → 50% → 100%
# Kill switch: set to 0% immediately if issues found
# No deployment needed to rollback — toggle the flag