lipl

部署高版本 k8s 集群

1.前期准备

#!/bin/bash

# 关闭防火墙
systemctl stop firewalld
systemctl disable firewalld

# 关闭 SELinux
setenforce 0 # 临时
sed -i 's/enforcing/disabled/' /etc/selinux/config # 永久

# 关闭 swap
swapoff -a # 临时
sed -ri 's/.*swap.*/#&/' /etc/fstab # 永久

# 设置主机名
hostnamectl set-hostname k8s-master
hostnamectl set-hostname k8s-node1
hostnamectl set-hostname k8s-node2

# 添加 hosts
cat >> /etc/hosts << EOF
192.168.100.194 k8s-master
192.168.100.195 k8s-node1
192.168.100.196 k8s-node2
EOF

# 调整内核参数
cat > /etc/sysctl.d/k8s.conf << EOF
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
EOF
sysctl --system # 生效

echo "配置完成！"

chmod +x configure.sh
./configure.sh

2.所有节点安装 docker-ce

#联网获取最新版 docker rpm 包
yumdownloader --resolve docker-ce

#--3台yum客户端安装docker，不指定版本就是最新版
yum install ./docker-ce*.rpm
#配置docker加速
cat > /etc/docker/daemon.json << EOF
{
    "registry-mirrors": [
        "https://docker.m.daocloud.io"
    ]
}
EOF
systemctl enable docker && systemctl start docker 设置开机自启并启动docker

3.安装cri-docker(docker与k8s通信的中程序：翻译官)

说明：从1.24版本开始k8s默认容器已经不是docker，如果要通过docker作为k8s的容器运行时需要安装组件，进行通信
# 下载
wget https://github.com/Mirantis/cri-dockerd/releases/download/v0.3.2/cri-dockerd-0.3.2-3.el7.x86_64.rpm
# 安装
rpm -ivh cri-dockerd-0.3.2-3.el7.x86_64.rpm
# 修改cri-docker镜像地址
vi /usr/lib/systemd/system/cri-docker.service
ExecStart=/usr/bin/cri-dockerd --container-runtime-endpoint fd:// --pod-infra-container-image=registry.aliyuncs.com/google_containers/pause:3.9
 
# 启动
systemctl enable cri-docker && systemctl start cri-docker

4.安装配置k8s的yum源，所有节点安装kubeadm、kubelet、kubectl

#k8syum 源

cat > /etc/yum.repos.d/kubernetes.repo << EOF
[kubernetes]
name=Kubernetes
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=0
repo_gpgcheck=0
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF

#yumdownloader --resolve kubelet-1.28.0 kubeadm-1.28.0 kubectl-1.28.0
systemctl enable kubelet

5.k8s镜像下载

--获取需要下载镜像的列表
kubeadm config images list 


--镜像下载
docker pull registry.aliyuncs.com/google_containers/kube-apiserver:v1.28.0
docker pull registry.aliyuncs.com/google_containers/kube-controller-manager:v1.28.0
docker pull registry.aliyuncs.com/google_containers/kube-scheduler:v1.28.0
docker pull registry.aliyuncs.com/google_containers/kube-proxy:v1.28.0
docker pull registry.aliyuncs.com/google_containers/etcd:3.5.9-0
docker pull registry.aliyuncs.com/google_containers/coredns:v1.10.1
docker pull registry.aliyuncs.com/google_containers/pause:3.9

部署k8s，master节点操作

# apiserver-advertise-address  配置k8s apiserver地址，用于监听、响应其他节点请求
# --service-cidr=10.96.0.0/12 配置k8s Service的IP范围
# --pod-network-cidr=10.244.0.0/16 配置k8s pod的IP范围
kubeadm init \
  --apiserver-advertise-address=192.168.100.194 \
  --image-repository registry.aliyuncs.com/google_containers \
  --kubernetes-version v1.28.0 \
  --service-cidr=10.96.0.0/12 \
  --pod-network-cidr=10.244.0.0/16 \
  --cri-socket=unix:///var/run/cri-dockerd.sock \
  --ignore-preflight-errors=all   #忽略错误，不然一直拉取外网镜像
 
--安装成功后master节点执行
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config

6.worker 节点加入集群

kubeadm join 10.44.100.194:6443 --token 6xkje6.g53th6yjstzv79e2 --discovery-token-ca-cert-hash sha256:803c78010edaa35ab481e05a1493ed832294cbfb45982fe2f82314a499d2fe5a  --cri-socket unix:///var/run/cri-dockerd.sock  

7.安装 flannel插件

wget https://github.com/flannel-io/flannel/releases/latest/download/kube-flannel.yml
cat kube-flannel.yml | grep image 下载所需镜像
docker pull docker.m.daocloud.io/flannel/flannel:v0.25.6
docker pull docker.m.daocloud.io/flannel/flannel-cni-plugin:v1.5.1-flannel2
保存镜像到tar包
docker save -o flannel_v0.25.6.tar docker.m.daocloud.io/flannel/flannel:v0.25.6
docker save -o flannel-cni-plugin_v1.5.1-flannel2.tar docker.m.daocloud.io/flannel/flannel-cni-plugin:v1.5.1-flannel2
导入镜像-所有节点
docker load -i flannel_v0.25.6.tar
docker load -i flannel-cni-plugin_v1.5.1-flannel2.tar
安装flannel
kubectl apply -f kube-flannel.yml

安装报错

附安装中的错误处理：

1）init初始化报错
[ERROR CRI]: container runtime is not running: output: time="2024-09-24T09:56:19+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"
原因：k8s自从v1.24后,默认容器运行时改成了containerd,containerd是一个CRI（containner runtime interface）组件，在容器运行时调用containerd组件来创建、运行、销毁容器
解决：disabled_plugins = ["cri"] 改为 disabled_plugins = []  &&然后重启systemctl restart containerd 
2）k8s安装失败后的重置
kubeadm reset
rm -rf /etc/kubernetes/*
rm -rf /root/.kube
3）Found multiple CRI endpoints on the host. Please define which one do you wish to use by setting the 'criSocket'
原因： 表明在环境中有多个容器运行时接口（containner runtime interface），k8s不确定用哪一个
解决：在kubeadm init时指定要使用的cri端点 --cri-socket unix:///var/run/cri-dockerd.sock
4）部署flannel 提示Init:ImagePullBackOff
原因：拉取失败，连接不到docker.io
编辑kube-flannel.yml文件，把image字段对应的docker.io改为docker.m.daocloud.io
重新部署：kubectl delete -f kube-flannel.yml&&kubectl apply -f kube-flannel.yml
5）从节点执行kubectl命令提示
E0927 09:56:12.002974 22410 memcache.go:265] couldn't get current server API group list: Get "http://localhost:8080/api?timeout=32s": dial tcp [::1]:8080: connect: connection refused
原因：k8s默认从~/.kube/config 配置文件获取访问kube-apiserver地址、证书、用户名等信息，如果没有配置文件会默认读取默认值localhost:8080,而本机的localhost:8080没有服务报错。
解决办法：mkdir ~/.kube
cp /etc/kubernetes/kubelet.conf ~/.kube/config