Kubernetes : Horizontal Pod Autoscaler2024/06/07

Configure Horizontal Pod Autoscaler to set auto scaling to Pods.

This example is based on the environment like follows.

+----------------------+   +----------------------+
|  [ ctrl.srv.world ]  |   |   [ dlp.srv.world ]  |
|     Manager Node     |   |     Control Plane    |
+-----------+----------+   +-----------+----------+
        eth0|10.0.0.25             eth0|10.0.0.30
            |                          |
------------+--------------------------+-----------
            |                          |
        eth0|10.0.0.51             eth0|10.0.0.52
+-----------+----------+   +-----------+----------+
| [ node01.srv.world ] |   | [ node02.srv.world ] |
|     Worker Node#1    |   |     Worker Node#2    |
+----------------------+   +----------------------+

[1]	Deploy Metrics Server, refer to here.
[2]	This is an example of Deployment to set Horizontal Pod Autoscaler.

root@ctrl:~#

vi my-nginx.yml

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    run: my-nginx
  name: my-nginx
spec:
  replicas: 1
  selector:
    matchLabels:
      run: my-nginx
  template:
    metadata:
      labels:
        run: my-nginx
    spec:
      containers:
      - image: nginx
        name: my-nginx
        resources:
          # requests : set minimum required resources when creating pods
          requests:
            # 250m : 0.25 CPU
            cpu: 250m
            memory: 64Mi
          # set maximum resorces
          limits:
            cpu: 500m
            memory: 128Mi

root@ctrl:~#

vi hpa.yml

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: my-nginx-hpa
  namespace: default
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    # target Deployment name
    name: my-nginx
  minReplicas: 1
  # maximum number of replicas
  maxReplicas: 4
  metrics:
  - type: Resource
    resource:
      # scale if target CPU utilization is over 20%
      name: cpu
      target:
        type: Utilization
        averageUtilization: 20

root@ctrl:~#

kubectl apply -f my-nginx.yml -f hpa.yml

deployment.apps/my-nginx created
horizontalpodautoscaler.autoscaling/my-nginx-hpa created

root@ctrl:~#

kubectl get pods

NAME                       READY   STATUS    RESTARTS   AGE
my-nginx-9ccccd89c-bfhf2   1/1     Running   0          6s

root@ctrl:~#

kubectl top pod

NAME                       CPU(cores)   MEMORY(bytes)
my-nginx-9ccccd89c-bfhf2   0m           7Mi

root@ctrl:~#

kubectl get hpa

NAME           REFERENCE             TARGETS       MINPODS   MAXPODS   REPLICAS   AGE
my-nginx-hpa   Deployment/my-nginx   cpu: 0%/20%   1         4         1          64s

# run some processes to put stress in a pod manually and see current state of pods again

root@ctrl:~#

kubectl get hpa

NAME           REFERENCE             TARGETS         MINPODS   MAXPODS   REPLICAS   AGE
my-nginx-hpa   Deployment/my-nginx   cpu: 123%/20%   1         4         1          3m26s

# pods have been scaled for settings

root@ctrl:~#

kubectl get pods

NAME                       READY   STATUS    RESTARTS   AGE
my-nginx-9ccccd89c-4chtm   1/1     Running   0          28s
my-nginx-9ccccd89c-bfhf2   1/1     Running   0          3m43s
my-nginx-9ccccd89c-xtj7q   1/1     Running   0          28s
my-nginx-9ccccd89c-zxmdc   1/1     Running   0          28s

root@ctrl:~#

kubectl top pod

NAME                       CPU(cores)   MEMORY(bytes)
my-nginx-9ccccd89c-4chtm   0m           7Mi
my-nginx-9ccccd89c-bfhf2   499m         8Mi
my-nginx-9ccccd89c-xtj7q   0m           7Mi
my-nginx-9ccccd89c-zxmdc   0m           7Mi

Matched Content