K8S集群网络插件部署问题解决方案

问题概述：

在通过shell脚本部署K8S集群的过程中，网络插件kube-flannel.yml部署出现了问题，拉取
image: docker.io/flannel/flannel-cni-plugin:v1.1.2
image: docker.io/flannel/flannel:v0.22.0
这2个镜像一直timeout，通过kubectl get pod去查看STATUS为Init:ImagePullBackOff，再通过kubectl describe pod去查看报错Error: ErrImagePull，很明显拉取镜像失败，这个默认的镜像仓库在国外被墙掉了，那么网络插件就无法部署，K8S集群状态就不正常了。

问题现象：

各节点状态

[root@hq-t-temp-centos7 ~]# kubectl get nodes
NAME              STATUS   ROLES           AGE   VERSION
k8smaster         NotReady    control-plane   20h   v1.28.2
test-k8s-node01   NotReady    <none>          20h   v1.28.2
test-k8s-node02   NotReady    <none>          20h   v1.28.2

journalctl报错信息

Container runtime network not ready" networkReady="NetworkReady=false reason:NetworkPluginNotRead

kuboard界面节点状态信息

container runtime network not ready: NetworkReady=false reason:NetworkPluginNotReady message:docker: network plugin is not ready: cni config uninitialized

解决方案

通过手动下载flannel相关镜像load到本地，然后重新打tag，并上传到自建的镜像仓库，可以是本地的，也可以是公网的，我这里使用的是阿里云的，上传完成后，再改一下kube-flannel.yml进行部署（kubectl apply -f kube-flannel.yml）。
我的阿里云镜像仓库地址（公共）：
registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel:v0.21.5
registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel-cni-plugin:v1.1.2

阿里云的镜像仓库上传的时候需要自行建立2个仓库名，分别是flannel-cni-plugin和flannel，参考步骤：

docker load -i flannel.tar 
docker images
#REPOSITORY                                                           TAG        IMAGE ID       CREATED         SIZE
#flannel/flannel                                                      v0.21.5    a6c0cb5dbd21   15 months ago   68.9MB
docker tag a6c0cb5dbd21 registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel:v0.21.5
docker push registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel:v0.21.5

完整的kube-flannel.yml配置如下：

apiVersion: v1
kind: Namespace
metadata:
  labels:
    k8s-app: flannel
    pod-security.kubernetes.io/enforce: privileged
  name: kube-flannel
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    k8s-app: flannel
  name: flannel
  namespace: kube-flannel
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    k8s-app: flannel
  name: flannel
rules:
- apiGroups:
  - ""
  resources:
  - pods
  verbs:
  - get
- apiGroups:
  - ""
  resources:
  - nodes
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - nodes/status
  verbs:
  - patch
- apiGroups:
  - networking.k8s.io
  resources:
  - clustercidrs
  verbs:
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    k8s-app: flannel
  name: flannel
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: flannel
subjects:
- kind: ServiceAccount
  name: flannel
  namespace: kube-flannel
---
apiVersion: v1
data:
  cni-conf.json: |
    {
      "name": "cbr0",
      "cniVersion": "0.3.1",
      "plugins": [
        {
          "type": "flannel",
          "delegate": {
            "hairpinMode": true,
            "isDefaultGateway": true
          }
        },
        {
          "type": "portmap",
          "capabilities": {
            "portMappings": true
          }
        }
      ]
    }
  net-conf.json: |
    {
      "Network": "10.244.0.0/16",
      "Backend": {
        "Type": "vxlan"
      }
    }
kind: ConfigMap
metadata:
  labels:
    app: flannel
    k8s-app: flannel
    tier: node
  name: kube-flannel-cfg
  namespace: kube-flannel
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    app: flannel
    k8s-app: flannel
    tier: node
  name: kube-flannel-ds
  namespace: kube-flannel
spec:
  selector:
    matchLabels:
      app: flannel
      k8s-app: flannel
  template:
    metadata:
      labels:
        app: flannel
        k8s-app: flannel
        tier: node
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: kubernetes.io/os
                operator: In
                values:
                - linux
      containers:
      - args:
        - --ip-masq
        - --kube-subnet-mgr
        command:
        - /opt/bin/flanneld
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        - name: EVENT_QUEUE_DEPTH
          value: "5000"
        image: registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel:v0.21.5
        name: kube-flannel
        resources:
          requests:
            cpu: 100m
            memory: 50Mi
        securityContext:
          capabilities:
            add:
            - NET_ADMIN
            - NET_RAW
          privileged: false
        volumeMounts:
        - mountPath: /run/flannel
          name: run
        - mountPath: /etc/kube-flannel/
          name: flannel-cfg
        - mountPath: /run/xtables.lock
          name: xtables-lock
      hostNetwork: true
      initContainers:
      - args:
        - -f
        - /flannel
        - /opt/cni/bin/flannel
        command:
        - cp
        image: registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel-cni-plugin:v1.1.2
        name: install-cni-plugin
        volumeMounts:
        - mountPath: /opt/cni/bin
          name: cni-plugin
      - args:
        - -f
        - /etc/kube-flannel/cni-conf.json
        - /etc/cni/net.d/10-flannel.conflist
        command:
        - cp
        image: registry.cn-hangzhou.aliyuncs.com/liuk8s/flannel:v0.21.5
        name: install-cni
        volumeMounts:
        - mountPath: /etc/cni/net.d
          name: cni
        - mountPath: /etc/kube-flannel/
          name: flannel-cfg
      priorityClassName: system-node-critical
      serviceAccountName: flannel
      tolerations:
      - effect: NoSchedule
        operator: Exists
      volumes:
      - hostPath:
          path: /run/flannel
        name: run
      - hostPath:
          path: /opt/cni/bin
        name: cni-plugin
      - hostPath:
          path: /etc/cni/net.d
        name: cni
      - configMap:
          name: kube-flannel-cfg
        name: flannel-cfg
      - hostPath:
          path: /run/xtables.lock
          type: FileOrCreate
        name: xtables-lock