istio_based_hpa.yaml

apiVersion: autoscaling/v2beta1
kind: HorizontalPodAutoscaler
metadata:
  name: my-hpa
  namespace: sg-prod
  annotations:
    metric-config.object.istio-requests-total.prometheus/per-replica: "true"
    metric-config.object.istio-requests-total.prometheus/query: |
      sum(rate(istio_requests_total{reporter="destination", destination_workload="<deployment-name-here>"}[2m]))
spec:
  minReplicas: 10
  maxReplicas: 20
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: <deployment-name-here>
  metrics:
  - type: Object
    object:
      metricName: istio-requests-total
      target:
        apiVersion: v1
        kind: Pod
        name: <deployment-name-here>
      targetValue: 20 # adjust the QPS you want