一文看懂 Kubernetes 弹性伸缩

func (s ActivePods) Less(i, j int) bool {
    // 1. Unassigned < assigned
    // If only one of the pods is unassigned, the unassigned one is smaller
    if s[i].Spec.NodeName != s[j].Spec.NodeName && (len(s[i].Spec.NodeName) == 0 || len(s[j].Spec.NodeName) == 0) {
        return len(s[i].Spec.NodeName) == 0
    }
    // 2. PodPending < PodUnknown < PodRunning
    if podPhaseToOrdinal[s[i].Status.Phase] != podPhaseToOrdinal[s[j].Status.Phase] {
        return podPhaseToOrdinal[s[i].Status.Phase] < podPhaseToOrdinal[s[j].Status.Phase]
    }
    // 3. Not ready < ready
    // If only one of the pods is not ready, the not ready one is smaller
    if podutil.IsPodReady(s[i]) != podutil.IsPodReady(s[j]) {
        return !podutil.IsPodReady(s[i])
    }
    // TODO: take availability into account when we push minReadySeconds information from deployment into pods,
    //       see https://github.com/kubernetes/kubernetes/issues/22065
    // 4. Been ready for empty time < less time < more time
    // If both pods are ready, the latest ready one is smaller
    if podutil.IsPodReady(s[i]) && podutil.IsPodReady(s[j]) {
        readyTime1 := podReadyTime(s[i])
        readyTime2 := podReadyTime(s[j])
        if !readyTime1.Equal(readyTime2) {
            return afterOrZero(readyTime1, readyTime2)
        }
    }
    // 5. Pods with containers with higher restart counts < lower restart counts
    if maxContainerRestarts(s[i]) != maxContainerRestarts(s[j]) {
        return maxContainerRestarts(s[i]) > maxContainerRestarts(s[j])
    }
    // 6. Empty creation time pods < newer pods < older pods
    if !s[i].CreationTimestamp.Equal(&s[j].CreationTimestamp) {
        return afterOrZero(&s[i].CreationTimestamp, &s[j].CreationTimestamp)
    }
    return false
}

apiVersion: apps/v1 
kind: Deployment
metadata:
  name: nginx
  namespace: hpa
  labels:
    app: nginx
spec:
  replicas: 2
  selector:
    matchLabels:
      app: nginx  
  template:
    metadata:
      labels:
        app: nginx
    spec:
      containers:
      - name: nginx
        image: nginx:1.16.1
        ports:
        - containerPort: 80
        resources:
          requests:       # 必须设置，否则HPA无法运行
            cpu: 100m     # 设置容器运行时所需CPU资源
            memory: 200Mi # 设置容器运行时所需内存资源
          limits:         # 不是必须设置，但是设置后可以避免压测时占用过多资源
            cpu: 200m      # 限制容器CPU资源为200m,m 是毫核（milli-cores）的缩写，因此200m表示0.2核
            memory: 400Mi   # 限制容器内存资源为400Mi 
---
kind: Service
apiVersion: v1
metadata:
  name: nginx
  namespace: hpa
spec:
  type: NodePort
  selector:
    app: nginx
  ports:
  - protocol: TCP
    port: 80
    targetPort: 80

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: nginx-hpa
  namespace: hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: nginx
  minReplicas: 1  # Deployment可缩容的容器数量下限，需设置为大于等于1的整数
  maxReplicas: 10  # 该Deployment可扩容的容器数量上限，需大于minReplicas
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 50 # 目标资源的平均使用率，即资源使用量的平均值与其请求量之间的比例
  - type: Resource
    resource:
      name: memory
      target:
        type: Utilization
        averageUtilization: 50 # 目标资源的平均使用率，即资源使用量的平均值与其请求量之间的比例

behavior:
  scaleDown:
    stabilizationWindowSeconds: 300
  scaleUp:
    stabilizationWindowSeconds: 300

behavior:
  scaleUp:
    selectPolicy: Disabled

behavior:
  scaleDown:
    selectPolicy: Disabled