解决步骤

因项目要求，需在k8s集群中使用 kubectl top node命令，但是一直报error: metrics not available yet错误。为了更好的复现问题，我们将本次解决问题的步骤整理如下。

环境说明

k8s版本：v1.23.5
k8s部署方式：kubeadm

##版本说明，当前的k8s版本为v1.23.5
[root@XXXX ~]# kubectl get node
NAME                        STATUS   ROLES    AGE    VERSION
test-worker1   Ready    <none>   160d   v1.23.5

问题现象

#1 查看node出错
[root@XXXX ~]# kubectl top node
error: metrics not available yet

#2 查看pod没问题 
[root@XXXXX ~]# kubectl top pod
NAME               CPU(cores)   MEMORY(bytes)   
XXX-48jgq   16m          75Mi            
XXX-55g2z   12m          82Mi            
XXX-6tj6c   8m           143Mi 

初次排查

# 查看metrics.k8s.io的api情况
kubectl get --raw /apis/metrics.k8s.io/v1beta1 | python -m json.tool
{
    "apiVersion": "v1",
    "groupVersion": "metrics.k8s.io/v1beta1",
    "kind": "APIResourceList",
    "resources": [
        {
            "kind": "NodeMetrics",
            "name": "nodes",
            "namespaced": false,
            "singularName": "",
            "verbs": [
                "get",
                "list"
            ]
        },
        {
            "kind": "PodMetrics",
            "name": "pods",
            "namespaced": true,
            "singularName": "",
            "verbs": [
                "get",
                "list"
            ]
        }
    ]
}

#2 查看apiservices 服务
kubectl describe apiservices v1beta1.metrics.k8s.io
Status:
  Conditions:
    Last Transition Time:  2023-11-07T16:16:24Z
    Message:               all checks passed
    Reason:                Passed
    Status:                True
    Type:                  Available

问题解决

部署metric-server，使用yaml方式进行部署，因为git下载不下来，我提前下载下来，然后换了阿里的镜像源，要注意metric-server和k8s版本的兼容性：

版本兼容性

根据图表，我们的k8s版本是1.23，因此我们使用metrics-server:v0.6.4

metric-server.yaml

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:
  selector:
    matchLabels:
      k8s-app: metrics-server
  strategy:
    rollingUpdate:
      maxUnavailable: 0
  template:
    metadata:
      labels:
        k8s-app: metrics-server
    spec:
      containers:
      - args:
        - --cert-dir=/tmp
        - --secure-port=4443
        - --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
        - --kubelet-use-node-status-port
        - --metric-resolution=15s
        - --kubelet-insecure-tls 
        image: registry.cn-hangzhou.aliyuncs.com/rainux/metrics-server:v0.6.4
        imagePullPolicy: IfNotPresent
        livenessProbe:
          failureThreshold: 3
          httpGet:
            path: /livez
            port: https
            scheme: HTTPS
          periodSeconds: 10
        name: metrics-server
        ports:
        - containerPort: 4443
          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
          readOnlyRootFilesystem: true
          runAsNonRoot: true
          runAsUser: 1000
        volumeMounts:
        - mountPath: /tmp
          name: tmp-dir
      nodeSelector:
        kubernetes.io/os: linux
      priorityClassName: system-cluster-critical
      serviceAccountName: metrics-server
      volumes:
      - emptyDir: {}
        name: tmp-dir
---
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

问题验证

#1 运行yaml文件
[root@k8s-master][~]
$kubectl create -f metrics-server.yaml

#2 问题验证
[root@XXXX][~]
$kubectl top node
NAME         CPU(cores)   CPU%   MEMORY(bytes)   MEMORY%   
k8s-master   194m         9%     1689Mi          35%       
     

[root@XXXX][~]
$kubectl top pod
NAME                                      CPU(cores)   MEMORY(bytes)   
cm-deploy-XXXX               0m           3Mi             
nfs-XXXXX   0m           13Mi