云服务器上部署Kubernetes集群（K8S）

master节点：master  

node节点：node1 

由于是ubuntu系统，参考两个博客配置

安装vmware搭建k8s集群（亲试无坑）-CSDN博客    该博客是centos系统，所以稍微有点区别结合另一篇博客一起参考

kubernetes集群部署-云社区-华为云   

# 启动chronyd服务
systemctl start chronyd
 
#设置chronyd服务开机自启
systemctl enable chronyd
 
# chronyd服务启动稍等几秒钟，就可以使用date命令验证时间了
date

可能报错：

root@hcss-ecs-ed4e:/# systemctl enable chronyd
Failed to enable unit: Refusing to operate on alias name or linked unit file: chronyd.service

解决步骤：

#先找其具体位置
root@hcss-ecs-ed4e:/# find /etc/systemd/system -name chronyd.service
/etc/systemd/system/chronyd.service
#尝试直接启用文件  仍报错  可能是个别名或链接到另一个单元文件
root@hcss-ecs-ed4e:/# systemctl enable /usr/lib/systemd/system/chronyd.service
Failed to enable unit: Unit file /usr/lib/systemd/system/chronyd.service does not exist.
#使用 file 命令查看文件实际类型  可以看到是一个链接
root@hcss-ecs-ed4e:/# file /etc/systemd/system/chronyd.service
/etc/systemd/system/chronyd.service: symbolic link to /lib/systemd/system/chrony.service
#再次直接启用其连接地址  成功  未报错
root@hcss-ecs-ed4e:/# systemctl enable /lib/systemd/system/chrony.service

禁用交换分区和防火墙

root@hcss-ecs-ed4e:/# swapoff -a
root@hcss-ecs-ed4e:/# swapon --show

root@hcss-ecs-ed4e:/# systemctl stop ufw
root@hcss-ecs-ed4e:/# systemctl disable ufw
Synchronizing state of ufw.service with SysV service script with /lib/systemd/systemd-sysv-install.
Executing: /lib/systemd/systemd-sysv-install disable ufw
Removed /etc/systemd/system/multi-user.target.wants/ufw.service.

 关于报错Port 10250 is in use解决办法：

[init] Using Kubernetes version: v1.28.2
[preflight] Running pre-flight checks
error execution phase preflight: [preflight] Some fatal errors occurred:
        [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

root@hcss-ecs-ed4e:/# systemctl restart kubelet
root@hcss-ecs-ed4e:/# netstat -ntpl | grep 10250
tcp6       0      0 :::10250                :::*                    LISTEN     718166/kubelet 
root@hcss-ecs-ed4e:/# kubeadm reset

root@ubt:/sudo systemctl restart kubelet
root@ubt:/newdir2/opt/hertzbeat/config# journalctl -f -u kubelet.service

几个排查错误命令

1.查看所有集群中所有pod

root@hcss-ecs-ed4e:/# kubectl get pod --all-namespaces -o wide
NAMESPACE              NAME                                         READY   STATUS    RESTARTS       AGE   IP              NODE            NOMINATED NODE   READINESS GATES
default                my-nginx-5ckf8                               1/1     Running   0              16h   10.244.2.7      ubt             <none>           <none>
default                my-nginx-69drn                               1/1     Running   0              16h   10.244.2.5      ubt             <none>           <none>
default                my-nginx-6r5gz                               1/1     Running   0              16h   10.244.2.9      ubt             <none>           <none>
default                my-nginx-7sjc8                               1/1     Running   0              16h   10.244.2.6      ubt             <none>           <none>
default                my-nginx-r2wdm                               1/1     Running   0              16h   10.244.2.4      ubt             <none>           <none>
default                my-nginx-swm2p                               1/1     Running   0              16h   10.244.2.8      ubt             <none>           <none>
kube-flannel           kube-flannel-ds-ptvqn                        1/1     Running   0              15h   192.168.7.218   hcss-ecs-ed4e   <none>           <none>
kube-flannel           kube-flannel-ds-z8mxj                        1/1     Running   0              15h   192.168.5.86    ubt             <none>           <none>
kube-system            coredns-66f779496c-478fx                     1/1     Running   0              23h   10.244.0.5      hcss-ecs-ed4e   <none>           <none>
kube-system            coredns-66f779496c-dvggf                     1/1     Running   0              23h   10.244.0.4      hcss-ecs-ed4e   <none>           <none>
kube-system            etcd-hcss-ecs-ed4e                           1/1     Running   3              23h   192.168.7.218   hcss-ecs-ed4e   <none>           <none>
kube-system            kube-apiserver-hcss-ecs-ed4e                 1/1     Running   0              16h   192.168.7.218   hcss-ecs-ed4e   <none>           <none>
kube-system            kube-controller-manager-hcss-ecs-ed4e        1/1     Running   5 (16h ago)    23h   192.168.7.218   hcss-ecs-ed4e   <none>           <none>
kube-system            kube-proxy-k4p7x                             1/1     Running   0              23h   192.168.7.218   hcss-ecs-ed4e   <none>           <none>
kube-system            kube-proxy-wvvvs                             1/1     Running   1              22h   192.168.5.86    ubt             <none>           <none>
kube-system            kube-scheduler-hcss-ecs-ed4e                 1/1     Running   5 (16h ago)    23h   192.168.7.218   hcss-ecs-ed4e   <none>           <none>
kubernetes-dashboard   dashboard-metrics-scraper-5b86c8dbf8-qdhh6   1/1     Running   0              16h   10.244.2.3      ubt             <none>           <none>
kubernetes-dashboard   kubernetes-dashboard-77db789568-wrhbs        1/1     Running   11 (15h ago)   16h   10.244.2.2      ubt             <none>           <none>


root@hcss-ecs-ed4e:/# kubectl get pod -owide --namespace kubernetes-dashboard
NAME                                         READY   STATUS    RESTARTS       AGE   IP           NODE   NOMINATED NODE   READINESS GATES
dashboard-metrics-scraper-5b86c8dbf8-qdhh6   1/1     Running   0              17h   10.244.2.3   ubt    <none>           <none>
kubernetes-dashboard-77db789568-wrhbs        1/1     Running   11 (15h ago)   17h   10.244.2.2   ubt    <none>           <none>


root@hcss-ecs-ed4e:/# kubectl get svc -A |grep kubernetes-dashboard
kubernetes-dashboard   dashboard-metrics-scraper   ClusterIP   10.111.211.15    <none>        8000/TCP                 18h
kubernetes-dashboard   kubernetes-dashboard        NodePort    10.102.46.49     <none>        443:31996/TCP            18h

2.查看日志

root@hcss-ecs-ed4e:/# kubectl logs kubernetes-dashboard-77db789568-wrhbs -n kubernetes-dashboard
Error from server: Get "https://192.168.5.86:10250/containerLogs/kubernetes-dashboard/kubernetes-dashboard-77db789568-wrhbs/kubernetes-dashboard": dial tcp 192.168.5.86:10250: connect: no route to host

3.重新加入集群

#master重新获取token
root@hcss-ecs-ed4e:/# kubeadm token create --print-join-command

#node 重置并加入
root@ubt:/# kubeadm reset
#scp将网络相关文件从master复制到node
root@ubt:/# scp root@master_ip:/etc/cni/net.d/*  /etc/cni/net.d/
#加入master  从master获取的token
root@ubt:/# kubeadm join ***** --token br1pv5.1m7l627il41efn2n --discovery-token-ca-cert-hash sha256:358dde62ac2155b0da48d74d62698fbdb25498a77436e93568c28a76e236c730