k8s学习——K8S部署的坑

Nanan_an

已于 2023-11-27 00:20:08 修改

阅读量777

点赞数 1

文章标签： kubernetes 容器云原生

于 2023-11-17 11:40:50 首次发布

本文链接：https://blog.youkuaiyun.com/Nanan_an/article/details/134459509

版权

kubernetes-kubeadm init从私有仓库拉取镜像

kubernetes-kubeadm init从私有仓库拉取镜像_kubeadm init 从harbor拉取镜像-优快云博客

全网最详细完整【20分钟使用kubeadm+阿里云镜像源部署kubernetes 1.20.0集群】_阿里源原生的kubesphere怎么结合okg_永远吃不胖的运维攻城狮的博客-优快云博客

CentOS 7 yum更改Containerd配置

第一种
这里若出现containerd的问题

降低containerd的版本
对containerd的配置文件修改

#配置文件默认内容
 
#   Copyright 2018-2022 Docker Inc.
 
#   Licensed under the Apache License, Version 2.0 (the "License");
#   you may not use this file except in compliance with the License.
#   You may obtain a copy of the License at
 
#       http://www.apache.org/licenses/LICENSE-2.0
 
#   Unless required by applicable law or agreed to in writing, software
#   distributed under the License is distributed on an "AS IS" BASIS,
#   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#   See the License for the specific language governing permissions and
#   limitations under the License.
 
## 删除这里
disabled_plugins = ["cri"]
 
#root = "/var/lib/containerd"
#state = "/run/containerd"
#subreaper = true
#oom_score = 0
 
#[grpc]
#  address = "/run/containerd/containerd.sock"
#  uid = 0
#  gid = 0
 
#[debug]
#  address = "/run/containerd/debug.sock"
#  uid = 0
#  gid = 0
#  level = "info"

重装containerd
重新安装containerd

第二种

[root@k8s-master01 ~]# kubeadm init --apiserver-advertise-address=192.168.65.103 
[init] Using Kubernetes version: v1.28.4
[preflight] Running pre-flight checks
error execution phase preflight: [preflight] Some fatal errors occurred:
	[ERROR CRI]: container runtime is not running: output: time="2023-11-16T14:52:59+08:00" level=fatal msg="validate service connection: CRI v1 runtime API is not implemented for endpoint \"unix:///var/run/containerd/containerd.sock\": rpc error: code = Unimplemented desc = unknown service runtime.v1.RuntimeService"
, error: exit status 1
[preflight] If you know what you are doing, you can make a check non-fatal with `--ignore-preflight-errors=...`
To see the stack trace of this error execute with --v=5 or higher

错误关键字：

"validate service connection: CRI v1 runtime API is not implemented for endpoint \"unix:///var/run/containerd/containerd.sock\": rpc error: code = Unimplemented desc = unknown service runtime.v1.RuntimeService"
, error: exit status 1

查看日志：

# journalctl  -f -u containerd
-- Journal begins at Thu 2023-03-30 15:42:34 HKT. --
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.620700651+08:00" level=info msg="loading plugin \"io.containerd.tracing.processor.v1.otlp\"..." type=io.containerd.tracing.processor.v1
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.620817381+08:00" level=info msg="skip loading plugin \"io.containerd.tracing.processor.v1.otlp\"..." error="no OpenTelemetry endpoint: skip plugin" type=io.containerd.tracing.processor.v1
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.620920032+08:00" level=info msg="loading plugin \"io.containerd.internal.v1.tracing\"..." type=io.containerd.internal.v1
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.621035782+08:00" level=error msg="failed to initialize a tracing processor \"otlp\"" error="no OpenTelemetry endpoint: skip plugin"
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.621195952+08:00" level=info msg="loading plugin \"io.containerd.grpc.v1.cri\"..." type=io.containerd.grpc.v1
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.621572039+08:00" level=warning msg="failed to load plugin io.containerd.grpc.v1.cri" error="invalid plugin config: `systemd_cgroup` only works for runtime io.containerd.runtime.v1.linux"
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.622076402+08:00" level=info msg=serving... address=/run/containerd/containerd.sock.ttrpc
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.622318145+08:00" level=info msg=serving... address=/run/containerd/containerd.sock
Mar 31 15:15:55 debian systemd[1]: Started containerd container runtime.
Mar 31 15:15:55 debian containerd[5314]: time="2023-03-31T15:15:55.626592651+08:00" level=info msg="containerd successfully booted in 0.034138s"

提取错误：

ning msg="failed to load plugin io.containerd.grpc.v1.cri" error="invalid plugin config: `systemd_cgroup` only works for runtime io.containerd.runtime.v1.linux"

改错：

containerd config default | sudo tee /etc/containerd/config.toml
修改 runtime_type 的值
sed -i  '96s/runtime_type.*/runtime_type = "io.containerd.runtime.v1.linux"/' /etc/containerd/config.toml

确认修改值

cat -n /etc/containerd/config.toml

    86	      [plugins."io.containerd.grpc.v1.cri".containerd.default_runtime]
    87	        base_runtime_spec = ""
    88	        cni_conf_dir = ""
    89	        cni_max_conf_num = 0
    90	        container_annotations = []
    91	        pod_annotations = []
    92	        privileged_without_host_devices = false
    93	        runtime_engine = ""
    94	        runtime_path = ""
    95	        runtime_root = ""
    96	        runtime_type = "io.containerd.runtime.v1.linux"

重启containerd

systemctl  restart containerd
journalctl  -f -u containerd

# journalctl  -f -u containerd
-- Journal begins at Thu 2023-03-30 15:42:34 HKT. --
Mar 31 16:47:50 master01 systemd[1]: Started containerd container runtime.
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.826347892+08:00" level=info msg="Start subscribing containerd event"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.826786123+08:00" level=info msg="Start recovering state"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.828864368+08:00" level=info msg="containerd successfully booted in 0.038659s"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.833400449+08:00" level=info msg="Start event monitor"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.833695542+08:00" level=info msg="Start snapshots syncer"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.833808203+08:00" level=info msg="Start cni network conf syncer for default"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.833906768+08:00" level=info msg="Start streaming server"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.834291549+08:00" level=info msg="ImageCreate event &ImageCreate{Name:sha256:221177c6082a88ea4f6240ab2450d540955ac6f4d5454f0e15751b653ebda165,Labels:map[string]string{io.cri-containerd.image: managed,},XXX_unrecognized:[],}"
Mar 31 16:47:50 master01 containerd[8116]: time="2023-03-31T16:47:50.835290401+08:00" level=info msg="ImageUpdate event &ImageUpdate{Name:registry.aliyuncs.com/google_containers/pause:3.7,Labels:map[string]string{io.cri-containerd.image: managed,},XXX_unrecognized:[],}"

https://zhuanlan.zhihu.com/p/618551600

kubeadm init 初始化问题

[init] Using Kubernetes version: v1.28.2
[preflight] Running pre-flight checks
	[WARNING Hostname]: hostname "node" could not be reached
	[WARNING Hostname]: hostname "node": lookup node on 8.8.8.8:53: no such host
error execution phase preflight: [preflight] Some fatal errors occurred:
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-apiserver.yaml]: /etc/kubernetes/manifests/kube-apiserver.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-controller-manager.yaml]: /etc/kubernetes/manifests/kube-controller-manager.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-scheduler.yaml]: /etc/kubernetes/manifests/kube-scheduler.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-etcd.yaml]: /etc/kubernetes/manifests/etcd.yaml already exists
	[ERROR Port-10250]: Port 10250 is in use
[preflight] If you know what you are doing, you can make a check non-fatal with `--ignore-preflight-errors=...`
To see the stack trace of this error execute with --v=5 or higher

这个错误信息表示在执行Kubernetes集群初始化时遇到了一些问题。具体来说，有以下几个问题：

主机名无法解析：无法解析主机名为"node"的IP地址（8.8.8.8）。这可能是因为网络配置问题或者DNS解析问题导致的。

# /etc/hosts
8.8.8.8 node

文件已存在：以下文件已经存在，导致初始化失败：

   - /etc/kubernetes/manifests/kube-apiserver.yaml
   - /etc/kubernetes/manifests/kube-controller-manager.yaml
   - /etc/kubernetes/manifests/kube-scheduler.yaml
   - /etc/kubernetes/manifests/etcd.yaml

端口占用：端口10250已经被占用。这可能是因为其他进程正在使用该端口，或者配置文件中指定了错误的端口号。

要解决这个问题，你可以尝试以下方法：

检查网络配置，确保主机名可以正确解析为IP地址。
删除已存在的文件，然后重新运行初始化命令。你可以使用以下命令删除这些文件：

sudo rm /etc/kubernetes/manifests/kube-apiserver.yaml
sudo rm /etc/kubernetes/manifests/kube-controller-manager.yaml
sudo rm /etc/kubernetes/manifests/kube-scheduler.yaml
sudo rm /etc/kubernetes/manifests/etcd.yaml

检查端口占用情况，确保没有其他进程占用端口10250。如果有，请关闭占用该端口的进程或更改配置文件中的端口号。
如果以上方法都无法解决问题，你可以尝试忽略某些预检错误，使用--ignore-preflight-errors=...参数运行初始化命令。例如：

sudo kubeadm init --ignore-preflight-errors=Hostname,Port-10250

重新拉取kubeadm join

kubeadm token create --print-join-command

如果遇见如同和第一点的问题，就用第一个办法解决。

[root@k8s-node01 ~]# kubeadm join 192.168.65.103:6443 --token 8uunqo.rxib6b3gkwdoua43 --discovery-token-ca-cert-hash sha256:fba5
[preflight] Running pre-flight checks
f^Herror execution phase preflight: couldn't validate the identity of the API Server: could not find a JWS signature in the cluster-info ConfigMap for token ID "8uunqo"
To see the stack trace of this error execute with --v=5 or higher

错误：

error execution phase preflight: couldn't validate the identity of the API Server: could not find a JWS signature in the cluster-info ConfigMap for token ID "8uunqo"

解决方案，冲重新生成一个token。

重新生成token

重新生成token要在master节点上。

kubectl create secret generic token-to-join --from-literal=token="new-token"

这里的"new-token"，想当于密码，自己整一个就🆗。

基础操作命令

kubectl get nodes 查看join的node

kubectl create secret generic token-to-join --from-literal=token="new-token" 重新生成token

kubeadm init 初始化kubeadm

kubeadm token create --print-join-command重新拉取创建过的token

kubectl get pod --all-namespaces -o wide 获取所有命名空间中Pod信息的Kubernetes命令

kubectl apply -f kube-flannel.yml 运行yml文件

kubectl delete -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml 是一个用于删除Kubernetes集群中指定配置文件的指令。

kubectl -n kube-system logs <name>查看没起来的日志

重新应用配置：如果可能的话，尝试删除并重新应用Flannel的配置。这可以通过运行

kubectl delete -f kube-flannel.yml -n kube-system和

kubectl apply -f kube-flannel.yml -n kube-system
命令来完成。

kubectl describe pod <READINESS GATES > -n <INATED NODE> : 这个事查看pod的详细描述。

kubectl get deployments 获取部署

kubectl delete deployment <name> 删除部署

kubectl get service 获取服务

kubectl delete service <name> 删除服务

kubectl get namespaces 获取命名空间

# 查看当前集群的所有的节点
kubectl get node
# 显示 Node 的详细信息（一般用不着）
kubectl describe node node1

# 查看所有的pod
kubectl get pod --all-namespaces
# 查看pod的详细信息
kubectl get pods -o wide --all-namespaces

# 查看所有创建的服务
kubectl get service

# 查看所有的deploy
kubectl get deploy

# 重启 pod（这个方式会删除原来的pod，然后再重新生成一个pod达到重启的目的）
# 有yaml文件的重启
kubectl replace --force -f xxx.yaml
# 无yaml文件的重启
kubectl get pod <POD_NAME> -n <NAMESPACE> -o yaml | kubectl replace --force -f -

# 查看pod的详细信息
kubectl describe pod nfs-client-provisioner-65c77c7bf9-54rdp -n default

# 根据 yaml 文件创建Pod资源
kubectl apply -f pod.yaml
# 删除基于 pod.yaml 文件定义的Pod 
kubectl delete -f pod.yaml

# 查看容器的日志
kubectl logs <pod-name>
# 实时查看日志
kubectl logs -f <pod-name>
# 若 pod 只有一个容器，可以不加 -c
kubectl log  <pod-name> -c <container_name>
# 返回所有标记为 app=frontend 的 pod 的合并日志
kubectl logs -l app=frontend

# 通过bash获得 pod 中某个容器的TTY，相当于登录容器
# kubectl exec -it <pod-name> -c <container-name> -- bash
eg:
kubectl exec -it redis-master-cln81 -- bash

# 查看 endpoint 列表
kubectl get endpoints

# 查看已有的token
kubeadm token list

（以下这个没整出来，不建议看）

部署网络的坑（flannel网络）

参考这个：https://zhuanlan.zhihu.com/p/627310856

运行kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
会出现
1. The connection to the server localhost:8080 was refused - did you specify the right host or port?
这个我只在在node部署flannel组件遇到，这里使用第三种
2. ，
```
[root@k8s-master01 ~]# kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
namespace/kube-flannel unchanged
clusterrole.rbac.authorization.k8s.io/flannel unchanged
clusterrolebinding.rbac.authorization.k8s.io/flannel unchanged
serviceaccount/flannel unchanged
configmap/kube-flannel-cfg unchanged
daemonset.apps/kube-flannel-ds unchanged
```
1. 被墙了的话，换一种方式（我这里使用了这个方法）
```
curl -o kube-flannel.yml https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml

kubectl apply -f kube-flannel.yml 
```
这时候就 /root 路径下就出现这个kube-flannel.yml文件
1. 如果还是被墙的话，就本地部署
  这个顺序是先在/root创建一个
  kube-flannel.yml文件然后再执行
  kubectl apply -f kube-flannel.yml
  
  kube-flannel.yml 文件内容

---
kind: Namespace
apiVersion: v1
metadata:
  name: kube-flannel
  labels:
    k8s-app: flannel
    pod-security.kubernetes.io/enforce: privileged
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
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
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
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
kind: ServiceAccount
metadata:
  labels:
    k8s-app: flannel
  name: flannel
  namespace: kube-flannel
---
kind: ConfigMap
apiVersion: v1
metadata:
  name: kube-flannel-cfg
  namespace: kube-flannel
  labels:
    tier: node
    k8s-app: flannel
    app: flannel
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"
      }
    }
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: kube-flannel-ds
  namespace: kube-flannel
  labels:
    tier: node
    app: flannel
    k8s-app: flannel
spec:
  selector:
    matchLabels:
      app: flannel
  template:
    metadata:
      labels:
        tier: node
        app: flannel
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: kubernetes.io/os
                operator: In
                values:
                - linux
      hostNetwork: true
      priorityClassName: system-node-critical
      tolerations:
      - operator: Exists
        effect: NoSchedule
      serviceAccountName: flannel
      initContainers:
      - name: install-cni-plugin
        image: registry.cn-zhangjiakou.aliyuncs.com/test-lab/coreos-flannel:amd64
        command:
        - cp
        args:
        - -f
        - /flannel
        - /opt/cni/bin/flannel
        volumeMounts:
        - name: cni-plugin
          mountPath: /opt/cni/bin
      - name: install-cni
        image: registry.cn-zhangjiakou.aliyuncs.com/test-lab/coreos-flannel:amd64
        command:
        - cp
        args:
        - -f
        - /etc/kube-flannel/cni-conf.json
        - /etc/cni/net.d/10-flannel.conflist
        volumeMounts:
        - name: cni
          mountPath: /etc/cni/net.d
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
      containers:
      - name: kube-flannel
        image: registry.cn-zhangjiakou.aliyuncs.com/test-lab/coreos-flannel:amd64
        command:
        - /opt/bin/flanneld
        args:
        - --ip-masq
        - --kube-subnet-mgr
        resources:
          requests:
            cpu: "100m"
            memory: "50Mi"
        securityContext:
          privileged: false
          capabilities:
            add: ["NET_ADMIN", "NET_RAW"]
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        - name: EVENT_QUEUE_DEPTH
          value: "5000"
        volumeMounts:
        - name: run
          mountPath: /run/flannel
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
        - name: xtables-lock
          mountPath: /run/xtables.lock
      volumes:
      - name: run
        hostPath:
          path: /run/flannel
      - name: cni-plugin
        hostPath:
          path: /opt/cni/bin
      - name: cni
        hostPath:
          path: /etc/cni/net.d
      - name: flannel-cfg
        configMap:
          name: kube-flannel-cfg
      - name: xtables-lock
        hostPath:
          path: /run/xtables.lock
          type: FileOrCreate

Kubernetes 安装flannel组件（本地 kube-flannel.yml 文件
 kube-flannel.yml(已修改镜像下载数据源)

运行后我们发现：没有Runing！！！！！
在这里插入图片描述

换成本地yaml内容
kubectl -n kube-system logs <name>查看没起来的日志

日志查看
kubectl -n kube-system logs kube-flannel-ds-amd64-8klng

E1117 11:13:50.358214       1 main.go:234] Failed to create SubnetManager: error retrieving pod spec for 'kube-system/kube-flannel-ds-jd6t6': pods "kube-flannel-ds-jd6t6" is forbidden: User "system:serviceaccount:kube-system:flannel" cannot get resource "pods" in API group "" in the namespace "kube-system"

大意就是：没权限

错误消息表明，用户 “system:serviceaccount:kube-system:flannel” 无法获取在
“kube-system” 命名空间中的 “pods” 资源。这通常是因为RBAC（Role-Based Access
Control）权限配置不正确。

可以用【kubectl get pods -n kube-system -o wide】可以清楚看出来是哪个节点/IP上pod或者镜像有问题

每一次更改kube-flannel.yml都要先
kubectl delete -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
然后再
kubectl apply -f kube-flannel.yml

重新应用配置：如果可能的话，尝试删除并重新应用Flannel的配置。这可以通过运行kubectl delete -f kube-flannel.yml -n kube-system和kubectl apply -f kube-flannel.yml -n kube-system命令来完成。

结论就是。我没整出来
但是是kube-flannel.yml文件的问题。没找到一个合适的kube-flannel.yml文件

k8s安装网络插件flannel 时出现报错Init:ImagePullBackOff 无法安装成功

重新初始化kubeadm init，重新加入节点，重新再来。

registry.k8s.io/pause:3.6

  Warning  FailedCreatePodSandBox  2m30s (x6 over 17m)  kubelet          
    Failed to create pod sandbox: rpc error: code = Unknown desc = failed to get sandbox image "registry.k8s.io/pause:3.6": 
    failed to pull image "registry.k8s.io/pause:3.6":
     failed to pull and unpack image "registry.k8s.io/pause:3.6": 
     failed to resolve reference "registry.k8s.io/pause:3.6": 
    failed to do request: Head "https://us-west2-docker.pkg.dev/v2/k8s-artifacts-prod/images/pause/manifests/3.6": 
    dial tcp 64.233.188.82:443: connect: connection refused

解决方案:
https://developer.aliyun.com/article/1344429#:~:text=修改 %2Fetc%2Fcontainerd%2Fconfig.toml 配置文件，执行命令如下所示： sed -i 's%2Fregistry.k8s.io%2Fpause%3A3.6%2Fregistry.aliyuncs.com%2Fgoogle_containers%2Fpause%3A3.9%2Fg',%2Fetc%2Fcontainerd%2Fconfig.toml 重启containerd systemctl restart containerd 3.再次查看容器运行情况可以发现，一些容器已经慢慢起来了： 4.解决完成。

如果没有 containerd

生成 containerd 的默认配置文件
containerd config default > /etc/containerd/config.toml
查看 sandbox 的默认镜像仓库在文件中的第几行
cat /etc/containerd/config.toml | grep -n “sandbox_image”

初始化删除代码

master

[root@k8s-master01 ~]# kubeadm init --apiserver-advertise-address=192.168.65.103 --image-repository registry.aliyuncs.com/google_containers --kubernetes-version v1.28.2 --service-cidr=10.96.0.0/12 --pod-network-cidr=10.244.0.0/16
[init] Using Kubernetes version: v1.28.2
[preflight] Running pre-flight checks
error execution phase preflight: [preflight] Some fatal errors occurred:
	[ERROR Port-6443]: Port 6443 is in use
	[ERROR Port-10259]: Port 10259 is in use
	[ERROR Port-10257]: Port 10257 is in use
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-apiserver.yaml]: /etc/kubernetes/manifests/kube-apiserver.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-controller-manager.yaml]: /etc/kubernetes/manifests/kube-controller-manager.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-scheduler.yaml]: /etc/kubernetes/manifests/kube-scheduler.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-etcd.yaml]: /etc/kubernetes/manifests/etcd.yaml already exists
	[ERROR Port-10250]: Port 10250 is in use
	[ERROR Port-2379]: Port 2379 is in use
	[ERROR Port-2380]: Port 2380 is in use
	[ERROR DirAvailable--var-lib-etcd]: /var/lib/etcd is not empty
[preflight] If you know what you are doing, you can make a check non-fatal with `--ignore-preflight-errors=...`
To see the stack trace of this error execute with --v=5 or higher

代码

从错误信息来看，主要是端口占用问题和文件已存在问题，以及etcd数据目录未清空问题。以下是一些可能的解决方案的示例代码：

解决端口占用问题：
你可以使用lsof命令来查看哪些进程正在使用特定的端口，然后根据需要关闭它们。在你的情况下，需要关闭使用6443、10259、10257、10250、2379和2380端口的进程。示例代码如下：

# 列出使用6443端口的进程并终止它们
lsof -i :6443 | awk '{print $2}' | xargs kill -9

# 重复以上步骤，替换端口为其他被占用的端口

解决文件已存在的问题：
你可以尝试删除已经存在的文件，然后再次运行kubeadm init命令。示例代码如下：

# 删除存在的文件
rm -rf /etc/kubernetes/manifests/kube-apiserver.yaml
rm -rf /etc/kubernetes/manifests/kube-controller-manager.yaml
rm -rf /etc/kubernetes/manifests/kube-scheduler.yaml
rm -rf /etc/kubernetes/manifests/etcd.yaml

解决etcd数据目录问题：
你需要清空etcd的数据目录。示例代码如下：

# 清空etcd的数据目录
rm -rf /var/lib/etcd/*

然后再次尝试运行kubeadm init命令。