# 创建 pod 和 service
$ kubectl run php-apache --image=k8s.gcr.io/hpa-example --requests=cpu=200m --expose --port=80
service "php-apache" created
deployment "php-apache" created
​
# 创建 autoscaler
$ kubectl autoscale deployment php-apache --cpu-percent=50 --min=1 --max=10
deployment "php-apache" autoscaled
​
$ kubectl get hpa
NAME         REFERENCE                     TARGET    MINPODS   MAXPODS   REPLICAS   AGE
php-apache   Deployment/php-apache/scale   0% / 50%  1         10        1          18s
​
# 增加负载
$ kubectl run -i --tty load-generator --image=busybox /bin/sh
Hit enter for command prompt
$ while true; do wget -q -O- http://php-apache.default.svc.cluster.local; done
​
# 过一会就可以看到负载升高了
$ kubectl get hpa
NAME         REFERENCE                     TARGET      CURRENT   MINPODS   MAXPODS   REPLICAS   AGE
php-apache   Deployment/php-apache/scale   305% / 50%  305%      1         10        1          3m
​
# autoscaler 将这个 deployment 扩展为 7 个 pod
$ kubectl get deployment php-apache
NAME         DESIRED   CURRENT   UP-TO-DATE   AVAILABLE   AGE
php-apache   7         7         7            7           19m
​
# 删除刚才创建的负载增加 pod 后会发现负载降低，并且 pod 数量也自动降回 1 个
$ kubectl get hpa
NAME         REFERENCE                     TARGET       MINPODS   MAXPODS   REPLICAS   AGE
php-apache   Deployment/php-apache/scale   0% / 50%     1         10        1          11m
​
$ kubectl get deployment php-apache
NAME         DESIRED   CURRENT   UP-TO-DATE   AVAILABLE   AGE
php-apache   1         1         1            1           27m

apiVersion: autoscaling/v1
kind: HorizontalPodAutoscaler
metadata:
  name: php-apache
  namespace: default
spec:
  scaleTargetRef:
    apiVersion: apps/v1beta1
    kind: Deployment
    name: php-apache
  minReplicas: 1
  maxReplicas: 10
  metrics:
  - type: Resource
    resource:
      name: cpu
      targetAverageUtilization: 50
  - type: Pods
    pods:
      metricName: packets-per-second
      targetAverageValue: 1k
  - type: Object
    object:
      metricName: requests-per-second
      target:
        apiVersion: extensions/v1beta1
        kind: Ingress
        name: main-route
      targetValue: 10k
status:
  observedGeneration: 1
  lastScaleTime: <some-time>
  currentReplicas: 1
  desiredReplicas: 1
  currentMetrics:
  - type: Resource
    resource:
      name: cpu
      currentAverageUtilization: 0
      currentAverageValue: 0

$ kubectl describe hpa cm-test
Name:                           cm-test
Namespace:                      prom
Labels:                         <none>
Annotations:                    <none>
CreationTimestamp:              Fri, 16 Jun 2017 18:09:22 +0000
Reference:                      ReplicationController/cm-test
Metrics:                        (current / target)
  "http_requests" on pods:      66m / 500m
Min replicas:                   1
Max replicas:                   4
ReplicationController pods:     1 current / 1 desired
Conditions:
  Type                  Status  Reason                  Message
  ----                  ------  ------                  -------
  AbleToScale           True    ReadyForNewScale        the last scale time was sufficiently old as to warrant a new scale
  ScalingActive         True    ValidMetricFound        the HPA was able to successfully calculate a replica count from pods metric http_requests
  ScalingLimited        False   DesiredWithinRange      the desired replica count is within the acceptable range
Events: