k8s 自带监控metricsserver

k8s-自带监控metrics-server

1. k8s-自带监控metrics-server

• 查看资源集群状态

  • 查看master组件状态：

    kubectl get cs
    

  • 查看node状态：

    kubectl get node 
    

  • 查看Apiserver代理的URL：

    kubectl cluster-info
    

  • 查看集群详细信息：

    kubectl cluster-info dump
    

  • 查看资源信息：

    kubectl describe <资源> <名称>
    

  • 查看资源信息：

    kubectl get <资源>
    

• 监控集群资源利用率

  • 查看node资源消耗

    kubectl top node <node name>
    

  • 查看pod资源消耗

    kubectl top pod <pod name>
    

  执行时会提示错误：error: Metrics API not available

  这是因为这个命令需要由metric-server服务提供数据，而这个服务默认没有安装，还需要手动部署下。

• Metrics-server 工作流程图
  

  • Metrics Server是一个集群范围的资源使用情况的数据聚合器。作为一个应用部署在集群中。Metric server从每个节点上KubeletAPI收集指标，通过Kubernetes聚合器注册在Master APIServer中。
  • 为集群提供Node、Pods资源利用率指标
  • 项目地址：https://github.com/kubernetes-sigs/metrics-server

• Metrics-server 部署

  • 官网下载地址：https://github.com/kubernetes-sigs/metrics-server/releases/download/v0.3.7/components.yaml

  • 示例代码

    [root@k8s-master01 ~]# vim metrics-server.yaml 
    [root@k8s-master01 ~]# cat metrics-server.yaml 
    ---
    apiVersion: rbac.authorization.k8s.io/v1
    kind: ClusterRole
    metadata:
      name: system:aggregated-metrics-reader
      labels:
        rbac.authorization.k8s.io/aggregate-to-view: "true"
        rbac.authorization.k8s.io/aggregate-to-edit: "true"
        rbac.authorization.k8s.io/aggregate-to-admin: "true"
    rules:
    - apiGroups: ["metrics.k8s.io"]
      resources: ["pods", "nodes"]
      verbs: ["get", "list", "watch"]
    ---
    apiVersion: rbac.authorization.k8s.io/v1
    kind: ClusterRoleBinding
    metadata:
      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: RoleBinding
    metadata:
      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: apiregistration.k8s.io/v1
    kind: APIService
    metadata:
      name: v1beta1.metrics.k8s.io
    spec:
      service:
        name: metrics-server
        namespace: kube-system
      group: metrics.k8s.io
      version: v1beta1
      insecureSkipTLSVerify: true
      groupPriorityMinimum: 100
      versionPriority: 100
    ---
    apiVersion: v1
    kind: ServiceAccount
    metadata:
      name: metrics-server
      namespace: kube-system
    ---
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: metrics-server
      namespace: kube-system
      labels:
        k8s-app: metrics-server
    spec:
      selector:
        matchLabels:
          k8s-app: metrics-server
      template:
        metadata:
          name: metrics-server
          labels:
            k8s-app: metrics-server
        spec:
          serviceAccountName: metrics-server
          volumes:
          # mount in tmp so we can safely use from-scratch images and/or read-only containers
          - name: tmp-dir
            emptyDir: {}
          containers:
          - name: metrics-server
            image: lizhenliang/metrics-server:v0.3.7 
            imagePullPolicy: IfNotPresent
            args:
              - --cert-dir=/tmp
              - --secure-port=4443
              - --kubelet-insecure-tls
              - --kubelet-preferred-address-types=InternalIP
            ports:
            - name: main-port
              containerPort: 4443
              protocol: TCP
            securityContext:
              readOnlyRootFilesystem: true
              runAsNonRoot: true
              runAsUser: 1000
            volumeMounts:
            - name: tmp-dir
              mountPath: /tmp
          nodeSelector:
            kubernetes.io/os: linux
            kubernetes.io/arch: "amd64"
    ---
    apiVersion: v1
    kind: Service
    metadata:
      name: metrics-server
      namespace: kube-system
      labels:
        kubernetes.io/name: "Metrics-server"
        kubernetes.io/cluster-service: "true"
    spec:
      selector:
        k8s-app: metrics-server
      ports:
      - port: 443
        protocol: TCP
        targetPort: main-port
    ---
    apiVersion: rbac.authorization.k8s.io/v1
    kind: ClusterRole
    metadata:
      name: system:metrics-server
    rules:
    - apiGroups:
      - ""
      resources:
      - pods
      - nodes
      - nodes/stats
      - namespaces
      - configmaps
      verbs:
      - get
      - list
      - watch
    ---
    apiVersion: rbac.authorization.k8s.io/v1
    kind: ClusterRoleBinding
    metadata:
      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
    

  • 运行配置文件

    [root@k8s-master01 ~]# kubectl apply -f metrics-server.yaml 
    clusterrole.rbac.authorization.k8s.io/system:aggregated-metrics-reader created
    clusterrolebinding.rbac.authorization.k8s.io/metrics-server:system:auth-delegator created
    rolebinding.rbac.authorization.k8s.io/metrics-server-auth-reader created
    apiservice.apiregistration.k8s.io/v1beta1.metrics.k8s.io created
    serviceaccount/metrics-server created
    deployment.apps/metrics-server created
    service/metrics-server created
    clusterrole.rbac.authorization.k8s.io/system:metrics-server created
    clusterrolebinding.rbac.authorization.k8s.io/system:metrics-server created
    

  • 检查是否部署成功

    [root@k8s-master01 ~]# kubectl get apiservices |grep metrics
    kubectl get --raw /apis/metrics.k8s.io/v1beta1/nodesv1beta1.metrics.k8s.io                 kube-system/metrics-server   True        5m58s
    [root@k8s-master01 ~]# kubectl get --raw /apis/metrics.k8s.io/v1beta1/nodes
    {"kind":"NodeMetricsList","apiVersion":"metrics.k8s.io/v1beta1","metadata":{"selfLink":"/apis/metrics.k8s.io/v1beta1/nodes"},"items":[{"metadata":{"name":"k8s-node01","selfLink":"/apis/metrics.k8s.io/v1beta1/nodes/k8s-node01","creationTimestamp":"2021-08-31T08:47:28Z"},"timestamp":"2021-08-31T08:46:28Z","window":"30s","usage":{"cpu":"74966621n","memory":"1476144Ki"}},{"metadata":{"name":"k8s-node02","selfLink":"/apis/metrics.k8s.io/v1beta1/nodes/k8s-node02","creationTimestamp":"2021-08-31T08:47:28Z"},"timestamp":"2021-08-31T08:46:33Z","window":"30s","usage":{"cpu":"64642735n","memory":"1883488Ki"}},{"metadata":{"name":"k8s-master01","selfLink":"/apis/metrics.k8s.io/v1beta1/nodes/k8s-master01","creationTimestamp":"2021-08-31T08:47:28Z"},"timestamp":"2021-08-31T08:46:30Z","window":"30s","usage":{"cpu":"107193694n","memory":"2307884Ki"}}]}
    

    如果状态True并能返回数据说明Metrics Server服务工作正常。