部署 Dashboard 2.0 + Metrics 监控 Pods node 负载

ゝ一纸荒年。 2022-12-11 01:30 281阅读 0赞

> Kubernetes Dashboard 从v2.0.0-beta1版本开始，集成了一个 metrics-scraper 的组件，可以通过 Kubernetes 的 Metrics API 收集一些基础资源的监控信息，并在web页面展示。

这次就是想用 metrics-scraper 实现集群负载的监控 之后继续部署 HPA  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 1]

### 1 使用 openssl 签发证书 ###

mkdir certs
    openssl req -nodes -newkey rsa:2048 -keyout certs/dashboard.key -out certs/dashboard.csr -subj "/C=/ST=/L=/O=/OU=/CN=kubernetes-dashboard"
    openssl x509 -req -sha256 -days 10000 -in certs/dashboard.csr -signkey certs/dashboard.key -out certs/dashboard.crt

### 2 安装 Dashboard ###

# 1 创建 namespace
    kubectl create namespace kubernetes-dashboard
    # 2 导入证书
    kubectl create secret generic kubernetes-dashboard-certs --from-file=certs -n kubernetes-dashboard
    
    # 3 下载部署配置文件 如果下不下来，就自己fq 复制下来
    wget https://raw.githubusercontent.com/kubernetes/dashboard/v2.0.0-beta3/aio/deploy/recommended.yaml
    
    # 4 注释 recommended.yaml 中的 namespace 
    apiVersion: v1
    kind: Namespace
    metadata:
      name: kubernetes-dashboard
    
    
    # 5 注释 recommended.yaml 中的 Secret 这几行全部注释
    apiVersion: v1
    kind: Secret
    metadata:
      labels:
        k8s-app: kubernetes-dashboard
      name: kubernetes-dashboard-certs
      namespace: kubernetes-dashboard
    type: Opaque
    
    # 6 再 args 行 增加 一个 token-ttl 可以延长 token 登陆的过期时间
    
    args:
    - --token-ttl=604800
    
    # 7 修改 NodePort 这一部分 替换成 以下 代码 
    
    ---
    
    kind: Service
    apiVersion: v1
    metadata:
      labels:
        k8s-app: kubernetes-dashboard
      name: kubernetes-dashboard
      namespace: kubernetes-dashboard
    spec:
      type: NodePort
      ports:
        - port: 443
          targetPort: 8443
          nodePort: 30000
      selector:
        k8s-app: kubernetes-dashboard
    
    ---
    
    # 8 创建
    kubectl create -f recommended.yaml

### 3 创建 serviceAcount 和 token ###

# 新建 token-user.yaml 
    apiVersion: v1
    kind: ServiceAccount
    metadata:
      name: admin-user
      namespace: kube-system
    ---
    apiVersion: rbac.authorization.k8s.io/v1
    kind: ClusterRoleBinding
    metadata:
      name: admin-user
    roleRef:
      apiGroup: rbac.authorization.k8s.io
      kind: ClusterRole
      name: cluster-admin
    subjects:
    - kind: ServiceAccount
      name: admin-user
      namespace: kube-system
    
    
    # 创建用户
    
    kubectl create -f token-user.yaml
    
    # 查询 token
    kubectl -n kube-system describe secret $(kubectl -n kube-system get secret | grep admin-user | awk '{print $1}')
    # 使用 展示 的 token 字符串 登陆 dashboard

### 4 安装 metrics-server ###

metrics-server 是 Kubernetes 官方的集群资源利用率信息收集器，在 k8 1.8 版本 + Heaper 就不再支持了，所以安装 metrics-server

wget https://github.com/kubernetes-incubator/metrics-server/archive/v0.3.3.tar.gz
    
    tar zxvf v0.3.3.tar.gz
    
    
    
    # 先等等，这里你直接 安装 可能会有问题 ，我们看下 metrics-server-0.3.3/deploy/1.8+/ 下的 
    # metrics-server-deployment.yaml 这个文件 替换成如下的样子
    ---
    apiVersion: v1
    kind: ServiceAccount
    metadata:
      name: metrics-server
      namespace: kube-system
    ---
    apiVersion: extensions/v1beta1
    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 # 从这里开始替换
    # image: k8s.gcr.io/metrics-server-amd64:v0.3.3
            image: registry.aliyuncs.com/google_containers/metrics-server-amd64:v0.3.3
            args:
              - --kubelet-insecure-tls
              - --kubelet-preferred-address-types=InternalIP
            imagePullPolicy: Always
            volumeMounts:
            - name: tmp-dir
              mountPath: /tmp

执行安装

# 安装
    kubectl apply -f metrics-server-0.3.3/deploy/1.8+/
    
    # 查看 metrics server pods 
    [root@k8s-master certs]# kubectl -n kube-system get pods -l k8s-app=metrics-server
    NAME                              READY   STATUS    RESTARTS   AGE
    metrics-server-7745fd5ddd-dn7p6   1/1     Running   0          5h
    
    [root@k8s-master certs]# kubectl get svc -n kube-system metrics-server
    NAME             TYPE        CLUSTER-IP     EXTERNAL-IP   PORT(S)   AGE
    metrics-server   ClusterIP   10.96.218.78   <none>        443/TCP   5h

如果你这里 查看 pods 像下面这样：

[root@k8s-master metrics-server-0.3.3]# kubectl -n kube-system get pods -l k8s-app=metrics-server
    NAME                             READY   STATUS             RESTARTS   AGE
    metrics-server-678cc5687-l2tjn   0/1     ImagePullBackOff   0          5m
    
    # 可以 查看详细/输出/日志信息
    
    [root@k8s-master metrics-server-0.3.3]# kubectl logs -f metrics-server-7745fd5ddd-dn7p6 -n kube-system
    
    Error from server (BadRequest): container "metrics-server" in pod "metrics-server-678cc5687-l2tjn" is waiting to start: trying and failing to pull image
    ...
    unable to fully scrape metrics from source kubelet_summary:k8s-node1: unable to fetch metrics from Kubelet k8s-node1 (k8s-node1): Get https://k8s-node1:10250/stats/summary/: dial tcp: lookup k8s-node1 on 10.96.0.10:53: no such host]
    ...
    # 这种是 DNS 解析 的异常带来的问题，我们之前配置过的 /etc/hosts
    
    172.16.0.175      k8s-master
    172.16.0.100      k8s-node1
    172.16.0.147      k8s-node2
    
    # 无法被 metrics-server 所找到 ，这里我们可以添加一个--kubelet-insecure-tls参数跳过证书校验： metrics-server-deployment.yaml 这个文件 
    
    - name: metrics-server
    # image: k8s.gcr.io/metrics-server-amd64:v0.3.3
            image: registry.aliyuncs.com/google_containers/metrics-server-amd64:v0.3.3
            args:
              - --kubelet-insecure-tls
              - --kubelet-preferred-address-types=InternalIP
            # imagePullPolicy: Always
            imagePullPolicy: Always

重新安装 ，查看日志 ，完成  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 2]

### 5 kubectl top nodes 查看效果 ###

\[root@k8s-master certs\]\# kubectl top nodes  
NAME CPU(cores) CPU% MEMORY(bytes) MEMORY%  
ecs-ca42 117m 2% 2968Mi 38%  
k8s-node1 665m 16% 4231Mi 54%  
k8s-node2 691m 17% 4149Mi 53%  
k8s-node3 654m 16% 5227Mi 67%  
k8s-node4 641m 16% 4458Mi 57%  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 3]

### 6 打开 dashboard 查看 ###

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 4]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center]: /images/20221123/40e31c3f66f64d548c8f9f8f34abd3b1.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20221123/080237fc5f504d82a3c9db17ee92d1b4.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 2]: /images/20221123/9e91c9bf12024438b8e162228946129f.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 3]: /images/20221123/3c0a704b17b84dc6b5dab1d5e873e13e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4MDE4Mjgz_size_16_color_FFFFFF_t_70_pic_center 4]: /images/20221123/c3dec760df72470fad29dbe957cc6347.png