オンプレマシンのkubernetesでkubectl topが使えない

Question

CentOS Linux release 7.9.2009 (Core)
kubernetes 1.22.2

kubeadmを使用してkubernetesをインストールしましたがkubectl topコマンドが使えないです

[root@k8s-master ~]# kubeadm init --apiserver-advertise-address 192.168.1.10 --pod-network-cidr 10.240.0.0/16
[root@k8s-master ~]# kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
[root@k8s-master ~]# kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml
[root@k8s-master ~]# kubectl get pod -n kube-system
metrics-server-6dfddc5fb8-gkfxm      0/1     CrashLoopBackOff   7 (78s ago)   10m

ログはこんな感じ。

[root@k8s-master ~]# kubectl logs metrics-server-6dfddc5fb8-gkfxm -n kube-system
panic: unable to load configmap based request-header-client-ca-file: Get "https://10.96.0.1:443/api/v1/namespaces/kube-system/configmaps/extension-apiserver-authentication": dial tcp 10.96.0.1:443: i/o timeout

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:
  - pods
  - nodes
  - nodes/stats
  - namespaces
  - configmaps
  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=443
        - --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
        - --kubelet-use-node-status-port
        - --metric-resolution=15s
        image: k8s.gcr.io/metrics-server/metrics-server:v0.5.0
        imagePullPolicy: IfNotPresent
        livenessProbe:
          failureThreshold: 3
          httpGet:
            path: /livez
            port: https
            scheme: HTTPS
          periodSeconds: 10
        name: metrics-server
        ports:
        - containerPort: 443
          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:
          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

ネットワーク的な問題のような気がしますが全然解決でいなくてもう何時間か消費してます…
何処を直したらいいでしょうか？

Answer 1

https://github.com/kubernetes-sigs/metrics-server/blob/master/README.md#requirements

Metrics Serverのrequirementにもありますが、オンプレの場合metrics serverのDeploymentsに--kubelet-insecure-tlsのフラグを渡す必要があると思います。

Comments

[maki19]

大変遅くなってしまいましたが、言われたとおりにしたところエラーの内容が変わりました！少し前進した気がします！
Successfully assigned kube-system/metrics-server-5cd859f5c-t89rd to k8s-node1
Pulling image "k8s.gcr.io/metrics-server/metrics-server:v0.5.0"
Successfully pulled image "k8s.gcr.io/metrics-server/metrics-server:v0.5.0" in 2.696813755s
Liveness probe failed: Get "https://10.240.1.5:443/livez": context deadline exceeded
Readiness probe failed: Get "https://10.240.1.5:443/readyz": context deadline exceeded
Container metrics-server failed liveness probe, will be restarted
Created container metrics-server
Container image "k8s.gcr.io/metrics-server/metrics-server:v0.5.0" already present on machine
Started container metrics-server
Liveness probe failed: Get "https://10.240.1.5:443/livez": net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)

Readiness probe failed: Get "https://10.240.1.5:443/readyz": net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)

Back-off restarting failed container
となりました…力を貸していただければ幸いでございます。。。

どうか知識を貸していただければ幸いです。。。

[maki19]

kubectl logs metrics-server-5cd859f5c-t89rd -n kube-system
とした所
panic: unable to load configmap based request-header-client-ca-file: Get "https://10.96.0.1:443/api/v1/namespaces/kube-system/configmaps/extension-apiserver-authentication": dial tcp 10.96.0.1:443: i/o timeout

となっております