Kubernetes Horizontal Pod Autoscaler and resource management

# HPA v2 with multiple metrics
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: web-app-hpa
  namespace: production
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web-app
  minReplicas: 3
  maxReplicas: 20
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 80
    - type: Pods
      pods:
        metric:
          name: http_requests_per_second
        target:
          type: AverageValue
          averageValue: 1000
  behavior:
    scaleUp:
      stabilizationWindowSeconds: 60
      policies:
        - type: Percent
          value: 100
          periodSeconds: 60
        - type: Pods
          value: 4
          periodSeconds: 60
      selectPolicy: Max
    scaleDown:
      stabilizationWindowSeconds: 300
      policies:
        - type: Percent
          value: 10
          periodSeconds: 60

---
# Pod Disruption Budget
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: web-app-pdb
  namespace: production
spec:
  minAvailable: 2
  selector:
    matchLabels:
      app: web-app

---
# Resource Quota for namespace
apiVersion: v1
kind: ResourceQuota
metadata:
  name: production-quota
  namespace: production
spec:
  hard:
    requests.cpu: "20"
    requests.memory: 40Gi
    limits.cpu: "40"
    limits.memory: 80Gi
    pods: "100"
    services: "20"
    persistentvolumeclaims: "30"

---
# LimitRange for defaults
apiVersion: v1
kind: LimitRange
metadata:
  name: default-limits
  namespace: production
spec:
  limits:
    - type: Container
      default:
        cpu: 500m
        memory: 256Mi
      defaultRequest:
        cpu: 100m
        memory: 128Mi
      max:
        cpu: "2"
        memory: 2Gi
      min:
        cpu: 50m
        memory: 64Mi