1.环境信息
三台centos7.9虚机
192.168.56.102 node1 (2个cpu)
192.168.56.103 node2
192.168.56.104 node3
设置三台机器间免密登录
ssh-keygen -t rsa
~/.ssh/
cat ~/.ssh/id_rsa.pub > ~/.ssh/authorized_keys
chmod 700 ~/.ssh
chmod 600 ~/.ssh/authorized_keys
ssh-copy-id -i ~/.ssh/id_rsa.pub -p 22 root@node1修改主机名
hostname node1 //临时修改
hostnamectl set-hostname node1 //永久修改禁用防火墙
systemctl stop firewalld
systemctl disable firewalld禁用selinux
setenforce 0 //临时关闭
sed -i "s/SELINUX=enforcing/SELINUX=disabled/g" /etc/selinux/config //永久关闭禁用缓冲区
swapoff -a
/etc/fstab //注释swap安装docker
安装工具和驱动
yum install -y yum-utils device-mapper-persistent-data lvm2
添加yum源
yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
启用源
yum-config-manager --enable docker-ce-nightly
卸载历史版本
yum remove docker docker-common docker-selinux docker-engine docer-io
安装docker
yum install docker-ce-19.03.15 docker-ce-cli-19.03.15 containerd.io-19.03.15 -y //指定版本为19.03
启动docker
systemctl start docker
systemctl enable docker修改/etc/docker/daemon.json
{
"exec-opts": ["native.cgroupdriver=systemd"],
"registry-mirrors":["https://docker.mirrors.ustc.edu.cn"]
}
scp daemon.json root@node2:/etc/docker/
scp daemon.json root@node3:/etc/docker/
添加yum源
/etc/yum.repo.d/k8s.repo
[kubernetes]
name=kubernetes
enabled=1
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64/
gpgcheck=1
repo_gpgcheck=0
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg
https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpgyum clean all
yum makecache
2.安装k8s
yum search kubeadm --showduplicates
三个机器分别执行
yum install kubeadm-1.20.9-0 kubectl-1.20.9-0 kubelet-1.20.9-0 -y
systemctl start kubelet
systemctl enable kubelet在master节点上初始化
kubeadm init \
--apiserver-advertise-address 192.168.56.102 \
--image-repository registry.aliyuncs.com/google_containers \
--kubernetes-version v1.20.9 \
--service-cidr 10.1.0.0/16 \
--pod-network-cidr 10.244.0.0/16
---------------------------------------------------------------------
--apiserver-advertise-address 192.168.56.102 //主机的ip
--image-repository registry.aliyuncs.com/google_containers //各个组件镜像仓库
--kubernetes-version v1.20.9 //k8s版本
--service-cidr 10.1.0.0/16 //service网段
--pod-network-cidr 10.244.0.0/16 //pod的网段kubeadm init完成后
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
kubeadm join 192.168.56.102:6443 --token 9ei6kq.imr068aa8mvphhvt \
--discovery-token-ca-cert-hash sha256:07093c3ae6cddb40a32b9648522248d4b02bd27a0e4338f525031663c4fd2aa2kubectl get nodes
[root@localhost kubernetes]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
localhost.localdomain NotReady control-plane,master 17m v1.20.9kubectl get pod -A
NAMESPACE NAME READY STATUS RESTARTS AGE
kube-system coredns-7f89b7bc75-76xh8 0/1 Pending 0 19m
kube-system coredns-7f89b7bc75-pkzzm 0/1 Pending 0 19m
kube-system etcd-localhost.localdomain 1/1 Running 0 19m
kube-system kube-apiserver-localhost.localdomain 1/1 Running 0 19m
kube-system kube-controller-manager-localhost.localdomain 1/1 Running 0 19m
kube-system kube-proxy-7k48f 1/1 Running 0 19m
kube-system kube-scheduler-localhost.localdomain 1/1 Running 0 19m安装flannel网络插件
kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml3.大功告成
[root@localhost kubelet]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
localhost.localdomain Ready control-plane,master 31m v1.20.9
node2 NotReady 3m39s v1.20.9
node3 Ready 3m19s v1.20.9 4.遇见的错误
A. kebelet 启动不起来
原因是cgroup类型不对
在docker daemon.json中添加
"exec-opts": ["native.cgroupdriver=systemd"],然后还是起不来
journalctl -xeu kubelet | less
错误日志
localhost.localdomain kubelet[32128]: F0729 00:04:15.112170 32128 server.go:198] failed to load Kubelet config file /var/lib/kubelet/config.yaml, error failed to read kubelet config file "/var/lib/kubelet/config.yaml", error: open /var/lib/kubelet/config.yaml: no such file or directory需要在kubeadm init之后就可以起来了
B. 从节点没有admin.conf文件
mkdir -p $HOME/.kube
[root@localhost ~]# sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
cp: 无法获取"/etc/kubernetes/admin.conf" 的文件状态(stat): 没有那个文件或目录
[root@localhost ~]# sudo chown $(id -u):$(id -g) $HOME/.kube/config
chown: 无法访问"/root/.kube/config": 没有那个文件或目录从主节点scp一份过去
C. kube-flannel.yml文件获取不到的话，可以直接下载下来
kubectl apply 报错
The connection to the server localhost:8080 was refused - did you specify the right host or port?
echo "export KUBECONFIG=/etc/kubernetes/admin.conf" >> /etc/profile
source /etc/profile 即可D. docker启动不起来
错误之处
"exec-opts": ["native.cgroupdriver=systemd"], 写成了 -> "exe-opts": ["native.cgroupdriver=systemd"],E. master节点 kubeadm join信息丢失了
-----
kubeadm token create --print-join-command
-----
-----
kubeadm token list
kubeadm token create --ttl 0
openssl x509 -pubkey -in /etc/kubernetes/pki/ca.crt | openssl rsa -pubin -outform der 2>/dev/null | openssl dgst -sha256 -hex | sed 's/^.* //'
-----F. join出错
kubeadm join 192.168.56.105:6443 --token kby4kb.8pk6i96jyuyqy9q1 --discovery-token-ca-cert-hash sha256:55a6876fb90e37679db74823ab8d469dabbe59ffa5ec927f1e6dc2ea16483732
[preflight] Running pre-flight checks
[WARNING Service-Docker]: docker service is not enabled, please run 'systemctl enable docker.service'
[preflight] Reading configuration from the cluster...
[preflight] FYI: You can look at this config file with 'kubectl -n kube-system get cm kubeadm-config -o yaml'
error execution phase kubelet-start: a Node with name "localhost.localdomain" and status "Ready" already exists in the cluster. You must delete the existing Node or change the name of this new joining Node
To see the stack trace of this error execute with --v=5 or higher因为我的虚拟机是从同一台机器上克隆过来的，主机名都一样，所以需要修改一下主机名