k8s 1.21版本中安装metrics-server v0.5.1报错处理

安安csdn

已于 2022-06-06 23:48:03 修改

阅读量1k

点赞数

文章标签： kubernetes linux docker metrics-server

于 2022-06-06 23:47:10 首次发布

本文链接：https://blog.csdn.net/weixin_42072280/article/details/125156709

版权

环境

[root@master ~]# kubectl get node -owide
NAME    STATUS   ROLES    AGE     VERSION    INTERNAL-IP      EXTERNAL-IP   OS-IMAGE                KERNEL-VERSION           CONTAINER-RUNTIME
node0   Ready    <none>   4h10m   v1.21.10   192.168.56.169   <none>        CentOS Linux 7 (Core)   3.10.0-1160.el7.x86_64   containerd://1.6.2

# kubectl get pod -owide -A
NAMESPACE              NAME                                         READY   STATUS    RESTARTS   AGE     IP               NODE    NOMINATED NODE   READINESS GATES
kube-system            calico-kube-controllers-67878b879f-97lkh     1/1     Running   0          3h56m   192.168.56.169   node0   <none>           <none>
kube-system            calico-node-7nz6t                            1/1     Running   0          3h56m   192.168.56.169   node0   <none>           <none>
kube-system            coredns-5db6d786b9-wl6hd                     1/1     Running   0          3h56m   100.64.102.136   node0   <none>           <none>
kube-system            metrics-server-7c4b97b8d4-zt42p              0/1     Running   0          82s     100.64.102.145   node0   <none>           <none>
kubernetes-dashboard   dashboard-metrics-scraper-7b555c5c94-4lrqc   1/1     Running   0          3h56m   100.64.102.135   node0   <none>           <none>
kubernetes-dashboard   kubernetes-dashboard-94f5c6549-hdfjx         1/1     Running   0          3h56m   100.64.102.133   node0   <none>           <none>

报错信息

查看metrics-server的pod信息：

[root@master ~]# kubectl describe pod metrics-server-7c4b97b8d4-zt42p -n kube-system
Name:                 metrics-server-7c4b97b8d4-zt42p
Namespace:            kube-system
Priority:             2000000000
Priority Class Name:  system-cluster-critical
Node:                 node0/192.168.56.169
Start Time:           Mon, 06 Jun 2022 19:14:43 +0800
Labels:               k8s-app=metrics-server
                      pod-template-hash=7c4b97b8d4
Annotations:          <none>
Status:               Running
IP:                   100.64.102.145
IPs:
  IP:           100.64.102.145
Controlled By:  ReplicaSet/metrics-server-7c4b97b8d4
Containers:
  metrics-server:
    Container ID:  containerd://70a65f2becaaed20e835d58d8cf4f4e02fb285e9d3942dbafddeceb2083fd520
    Image:         xxxx/metrics-server:v0.5.1
    Image ID:      xxxx/metrics-server@sha256:a84baf65a4a3163799ab19307c7fc21c1473ac5e4044f25df398719cf7c58279
    Port:          443/TCP
    Host Port:     0/TCP
    Args:
      --cert-dir=/tmp
      --secure-port=443
      --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
      --kubelet-use-node-status-port
      --metric-resolution=15s
    State:          Running
      Started:      Mon, 06 Jun 2022 19:14:45 +0800
    Ready:          False
    Restart Count:  0
    Requests:
      cpu:        100m
      memory:     200Mi
    Liveness:     http-get https://:https/livez delay=0s timeout=1s period=10s #success=1 #failure=3
    Readiness:    http-get https://:https/readyz delay=20s timeout=1s period=10s #success=1 #failure=3
    Environment:  <none>
    Mounts:
      /tmp from tmp-dir (rw)
      /var/run/secrets/kubernetes.io/serviceaccount from metrics-server-token-hv5cx (ro)
Conditions:
  Type              Status
  Initialized       True
  Ready             False
  ContainersReady   False
  PodScheduled      True
Volumes:
  tmp-dir:
    Type:       EmptyDir (a temporary directory that shares a pod's lifetime)
    Medium:
    SizeLimit:  <unset>
  metrics-server-token-hv5cx:
    Type:        Secret (a volume populated by a Secret)
    SecretName:  metrics-server-token-hv5cx
    Optional:    false
QoS Class:       Burstable
Node-Selectors:  kubernetes.io/os=linux
Tolerations:     node.kubernetes.io/not-ready:NoExecute op=Exists for 300s
                 node.kubernetes.io/unreachable:NoExecute op=Exists for 300s
Events:
  Type     Reason     Age                            From               Message
  ----     ------     ----                           ----               -------
  Normal   Scheduled  93s                            default-scheduler  Successfully assigned kube-system/metrics-server-7c4b97b8d4-zt42p to node0
  Normal   Pulled     11s                            kubelet            Container image "10.188.250.8/kubebtest/metrics-server:v0.5.1" already present on machine
  Normal   Created    10s                            kubelet            Created container metrics-server
  Normal   Started    10s                            kubelet            Started container metrics-server
  Warning  Unhealthy  <invalid> (x7 over <invalid>)  kubelet            Readiness probe failed: HTTP probe failed with statuscode: 500
[root@master ~]#
[root@master ~]#
[root@master ~]#
[root@master ~]# kubectl logs metrics-server-7c4b97b8d4-zt42p -n kube-system
I0606 11:14:45.636137       1 serving.go:341] Generated self-signed cert (/tmp/apiserver.crt, /tmp/apiserver.key)
E0606 11:14:46.689009       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:14:46.733054       1 secure_serving.go:202] Serving securely on [::]:443
I0606 11:14:46.734167       1 requestheader_controller.go:169] Starting RequestHeaderAuthRequestController
I0606 11:14:46.734244       1 shared_informer.go:240] Waiting for caches to sync for RequestHeaderAuthRequestController
I0606 11:14:46.734630       1 dynamic_serving_content.go:130] Starting serving-cert::/tmp/apiserver.crt::/tmp/apiserver.key
I0606 11:14:46.734641       1 tlsconfig.go:240] Starting DynamicServingCertificateController
I0606 11:14:46.734931       1 configmap_cafile_content.go:202] Starting client-ca::kube-system::extension-apiserver-authentication::client-ca-file
I0606 11:14:46.735259       1 shared_informer.go:240] Waiting for caches to sync for client-ca::kube-system::extension-apiserver-authentication::client-ca-file
I0606 11:14:46.735645       1 configmap_cafile_content.go:202] Starting client-ca::kube-system::extension-apiserver-authentication::requestheader-client-ca-file
I0606 11:14:46.735679       1 shared_informer.go:240] Waiting for caches to sync for client-ca::kube-system::extension-apiserver-authentication::requestheader-client-ca-file
I0606 11:14:46.839072       1 shared_informer.go:247] Caches are synced for client-ca::kube-system::extension-apiserver-authentication::requestheader-client-ca-file
I0606 11:14:46.839231       1 shared_informer.go:247] Caches are synced for RequestHeaderAuthRequestController
I0606 11:14:46.839564       1 shared_informer.go:247] Caches are synced for client-ca::kube-system::extension-apiserver-authentication::client-ca-file
E0606 11:15:01.675388       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:15:13.234527       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
E0606 11:15:16.670256       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:15:23.236475       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
E0606 11:15:31.676283       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:15:33.234068       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
I0606 11:15:43.235745       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
E0606 11:15:46.677634       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:15:53.236178       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
E0606 11:16:01.676373       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:16:03.235592       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
I0606 11:16:13.236974       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
E0606 11:16:16.676874       1 scraper.go:139] "Failed to scrape node" err="Get \"https://192.168.56.169:11250/stats/summary?only_cpu_and_memory=true\": x509: cannot validate certificate for 192.168.56.169 because it doesn't contain any IP SANs" node="node0"
I0606 11:16:23.239367       1 server.go:188] "Failed probe" probe="metric-storage-ready" err="not metrics to serve"
[root@master ~]#

解决办法

在deployment中添加：

- --kubelet-insecure-tls  #添加

如下图：

在这里插入图片描述
重新apply资源，过一会，pod就正常了，metrics-server的日志也就正常了！

参考

metrics-server版本：v0.5.1 github官方地址
 K8s部署metric-server页面不显示，报错unable to fully scrape metrics

附件（metrics-server版本：v0.5.1 ）

Installation

kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/download/v0.5.1/components.yaml

[root@master ~]# cat components-v0.5.1.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:
  - 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
        - --kubelet-insecure-tls  #添加
        - --metric-resolution=15s
        #image: k8s.gcr.io/metrics-server/metrics-server:v0.5.1
        image: xxxx/metrics-server:v0.5.1
        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