How to set up a horizontal autoscaler for pods on a physical server?

To set up horizontal autoscaling (Horizontal Pod Autoscaler, HPA) on a physical server (bare-metal) in Kubernetes, you need to follow several steps:

1. Ensure that the Metrics Server is configured in the cluster — it collects CPU and memory metrics necessary for HPA to function.

2. Configure resource monitoring for pods and nodes — without cloud infrastructure, you should use local solutions, such as Prometheus with HPA adapters.

3. Create an HPA object, specifying target metrics and minimum/maximum replica counts. For example:

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: example-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: example-deployment
  minReplicas: 2
  maxReplicas: 10
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 50

4. Ensure the HPA controller and metrics are working correctly — on bare-metal, additional configuration of RBAC and network policies may be required.

5. Test autoscaling under load and monitor behavior.

Important: on a physical server, there are no cloud APIs for scaling, so HPA only works at the pod level, and node scaling must be done manually or with other tools.