kubernetes中的附件组件Metrics-server与hpa资源实现对pod的自动扩容和缩容

一、概述

        Metrics-Server组件目的：获取集群中pod、节点等负载信息；

        hpa资源目的：通过metrics-server获取的pod负载信息，自动伸缩创建pod；

二、安装部署 Metrics-Server组件

安装目的，就是给k8s集群安装top命令

1、下载Metrics-Server资源清单

wget  https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/high-availability-1.21+.yaml

下载好的 high-availability-1.21+.yaml文件

apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    k8s-app: metrics-server
    rbac.authorization.k8s.io/aggregate-to-admin: "true"
    rbac.authorization.k8s.io/aggregate-to-edit: "true"
    rbac.authorization.k8s.io/aggregate-to-view: "true"
  name: system:aggregated-metrics-reader
rules:
- apiGroups:
  - metrics.k8s.io
  resources:
  - pods
  - nodes
  verbs:
  - get
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    k8s-app: metrics-server
  name: system:metrics-server
rules:
- apiGroups:
  - ""
  resources:
  - nodes/metrics
  verbs:
  - get
- apiGroups:
  - ""
  resources:
  - pods
  - nodes
  verbs:
  - get
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server-auth-reader
  namespace: kube-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
  name: metrics-server
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server:system:auth-delegator
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:auth-delegator
subjects:
- kind: ServiceAccount
  name: metrics-server
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    k8s-app: metrics-server
  name: system:metrics-server
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:metrics-server
subjects:
- kind: ServiceAccount
  name: metrics-server
  namespace: kube-system
---
apiVersion: v1
kind: Service
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
spec:
  ports:
  - name: https
    port: 443
    protocol: TCP
    targetPort: https
  selector:
    k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
spec:
  replicas: 2
  selector:
    matchLabels:
      k8s-app: metrics-server
  strategy:
    rollingUpdate:
      maxUnavailable: 1
  template:
    metadata:
      labels:
        k8s-app: metrics-server
    spec:
      affinity:
        podAntiAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
          - labelSelector:
              matchLabels:
                k8s-app: metrics-server
            namespaces:
            - kube-system
            topologyKey: kubernetes.io/hostname
      containers:
      - args:
        - --cert-dir=/tmp
        - --secure-port=10250
        - --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
        - --kubelet-use-node-status-port
        - --metric-resolution=15s
        image: registry.k8s.io/metrics-server/metrics-server:v0.7.1
        imagePullPolicy: IfNotPresent
        livenessProbe:
          failureThreshold: 3
          httpGet:
            path: /livez
            port: https
            scheme: HTTPS
          periodSeconds: 10
        name: metrics-server
        ports:
        - containerPort: 10250
          name: https
          protocol: TCP
        readinessProbe:
          failureThreshold: 3
          httpGet:
            path: /readyz
            port: https
            scheme: HTTPS
          initialDelaySeconds: 20
          periodSeconds: 10
        resources:
          requests:
            cpu: 100m
            memory: 200Mi
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            drop:
            - ALL
          readOnlyRootFilesystem: true
          runAsNonRoot: true
          runAsUser: 1000
          seccompProfile:
            type: RuntimeDefault
        volumeMounts:
        - mountPath: /tmp
          name: tmp-dir
      nodeSelector:
        kubernetes.io/os: linux
      priorityClassName: system-cluster-critical
      serviceAccountName: metrics-server
      volumes:
      - emptyDir: {}
        name: tmp-dir
---
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
spec:
  minAvailable: 1
  selector:
    matchLabels:
      k8s-app: metrics-server
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
  labels:
    k8s-app: metrics-server
  name: v1beta1.metrics.k8s.io
spec:
  group: metrics.k8s.io
  groupPriorityMinimum: 100
  insecureSkipTLSVerify: true
  service:
    name: metrics-server
    namespace: kube-system
  version: v1beta1
  versionPriority: 100

2、编辑Metrics-Server的资源清单

....     
       topologyKey: kubernetes.io/hostname
      containers:
      - args:
        #启动允许使用不安全的证书
        - --kubelet-insecure-tls
        - --cert-dir=/tmp
        - --secure-port=10250
        - --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
        - --kubelet-use-node-status-port
        - --metric-resolution=15s
        #image: registry.k8s.io/metrics-server/metrics-server:v0.7.1
        image: registry.aliyuncs.com/google_containers/metrics-server:v0.6.3
        imagePullPolicy: IfNotPresent
        livenessProbe:
          failureThreshold: 3
          httpGet:
            path: /livez

....

 3、创建Metrics-Server资源

[root@master study-demo]# kubectl apply -f high-availability-1.21+.yaml 
serviceaccount/metrics-server created
clusterrole.rbac.authorization.k8s.io/system:aggregated-metrics-reader created
clusterrole.rbac.authorization.k8s.io/system:metrics-server created
rolebinding.rbac.authorization.k8s.io/metrics-server-auth-reader created
clusterrolebinding.rbac.authorization.k8s.io/metrics-server:system:auth-delegator created
clusterrolebinding.rbac.authorization.k8s.io/system:metrics-server created
service/metrics-server created
deployment.apps/metrics-server created
poddisruptionbudget.policy/metrics-server created
apiservice.apiregistration.k8s.io/v1beta1.metrics.k8s.io created
 

4、查看安装结果 

4.1 查看pod

[root@master study-demo]# kubectl get pod --show-labels -A  | grep metrics

4.2 kubectl top node 命令查看节点信息

4.3 kubectl top pods -A 命令查看pod信息

三、hpa资源实现pod水平伸缩（自动扩缩容）

1. 当资源使用超过一定的范围，会自动扩容，但是扩容数量不会超过最大pod数量
2. 扩容时无延迟，只要监控资源超过阈值，则会自动创建pod
3. 当资源使用率恢复到阈值以下时，需要等待一段时间才会释放，大概5分钟

3.1 编写deployment资源清单

[root@master hpa-demo]# cat deployment.yaml 

apiVersion: apps/v1
kind: Deployment
metadata:
  name: dm-hpa
spec:
  replicas: 1
  selector:
    matchLabels:
      k8s: dolphin
  template:
    metadata:
      labels:
        k8s: dolphin
    spec:
      containers:
      - name: c1
        image: centos:7
        command:
        - tail
        - -f
        - /etc/hosts
        resources:
          requests:
            cpu: "50m"
          limits:
            cpu: "150m"
 

3.2 编写hpa资源清单绑定deployment

[root@master hpa-demo]# cat hpa.yaml 
apiVersion: autoscaling/v1
kind: HorizontalPodAutoscaler
metadata:
  name: hpa-tools
spec:
  maxReplicas: 10 # 扩容上线
  minReplicas: 2  # 缩容下限
  scaleTargetRef: # 扩缩容的目标
    apiVersion: "apps/v1"
    kind: Deployment
    name: dm-hpa
  targetCPUUtilizationPercentage: 95 #cpu阈值达到95%开始扩缩容
 

3.3 创建上面两个资源

[root@master hpa-demo]# kubectl apply -f deployment.yaml 
[root@master hpa-demo]# kubectl apply -f hpa.yaml 
 

3.4 查看hpa资源

可以看到我们deployment.yaml文件中的副本是1，创建hap绑定资源后，会根据hpa的配置，这里配置了2个，所以就创建了2个pod资源。

四、压测测试

1，进入pod，安装stress工具

· 进入pod容器

[root@master hpa]# kubectl exec dm-hpa-5bb4dd448d-ks2rt -it -- sh

· 安装aili源和epel源

sh-4.2# yum -y install wget

sh-4.2# wget -O /etc/yum.repos.d/CentOS-Base.repo https://mirrors.aliyun.com/repo/Centos-7.repo

sh-4.2# wget -O /etc/yum.repos.d/epel.repo https://mirrors.aliyun.com/repo/epel-7.repo

· 安装压测工具

sh-4.2#  yum -y install stress

2，开始使用命令压测pod

sh-4.2# stress --cpu 8 --io 4 --vm 2 --vm-bytes 128M --timeout 20m

3，查看hpa资源的负载情况

[root@master ~]# kubectl get hpa -o wide

可以看到：

1，我们创建的deploy资源只有一个副本；

2，我们创建的hpa资源之后，设置最小值是2，最大值是10 ；

3，我们在查看pod，可以看见，pod变成了2个；

4，我们进入容器，开始压测，将负载压测到超过95%；

5，再次查看pod，发现变成了3个，自动创建了一个；

6，关闭压测，5分钟后，pod有回归到了2个；

7，至此，hpa的pod自动伸缩，测试完毕；