Implementing Horizontal Pod Autoscaling

kubectl autoscale deploy web --min=2 --max=10 --cpu-percent=70

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata: { name: web }
spec:
  scaleTargetRef: { apiVersion: apps/v1, kind: Deployment, name: web }
  minReplicas: 2
  maxReplicas: 20
  metrics:
  - type: Resource
    resource: { name: cpu, target: { type: Utilization, averageUtilization: 70 } }
  - type: Resource
    resource: { name: memory, target: { type: AverageValue, averageValue: 512Mi } }

kubectl get hpa
kubectl get hpa web -o yaml

metrics:
- type: Resource
  resource:
    name: cpu
    target: { type: Utilization, averageUtilization: 70 }

metrics:
- type: Pods
  pods:
    metric: { name: requests_per_second }
    target: { type: AverageValue, averageValue: "100" }
- type: External
  external:
    metric:
      name: kafka_lag
      selector: { matchLabels: { topic: orders } }
    target: { type: Value, value: "1000" }

behavior:
  scaleUp:
    stabilizationWindowSeconds: 0
    policies:
    - { type: Percent, value: 100, periodSeconds: 15 }
    - { type: Pods,    value: 4,   periodSeconds: 15 }
    selectPolicy: Max

behavior:
  scaleDown:
    stabilizationWindowSeconds: 300   # default
    policies:
    - { type: Percent, value: 10, periodSeconds: 60 }