ubuntu22.04系统kubeadm部署k8s高可用集群

一、shell脚本一键部署

#!/bin/bash
set -e


# 节点配置
MASTER1="192.168.177.125"
MASTER2="192.168.177.126"
MASTER3="192.168.177.127"
WORKER1="192.168.177.128"
KEEPALIVED_VIP="192.168.177.129"

# 当前主机IP
CURRENT_IP=$(hostname -I | awk '{print $1}')

# 判断当前节点角色
if [ "$CURRENT_IP" = "$MASTER1" ] || [ "$CURRENT_IP" = "$MASTER2" ] || [ "$CURRENT_IP" = "$MASTER3" ]; then
    NODE_ROLE="master"
elif [ "$CURRENT_IP" = "$WORKER1" ]; then
    NODE_ROLE="worker"
else
    echo "Error: Current IP $CURRENT_IP is not in the cluster plan."
    exit 1
fi

sudo apt update && sudo apt upgrade -y
sudo modprobe br_netfilter

echo "=== 内核模块检查 ==="
if ! lsmod | grep br_netfilter; then
  echo "错误：br_netfilter 模块未加载，即将重启系统..."
  logger -t k8s-install "br_netfilter 模块缺失，触发重启"
  sudo reboot
  exit 1  # 确保如果reboot失败会退出脚本
fi

# 1. 基础环境配置
function setup_basic_env() {
    echo ">>> Setting up basic environment..."
    # 禁用Swap
    swapoff -a
    sed -i '/swap/s/^/#/' /etc/fstab

    # 关闭防火墙
    systemctl stop ufw && systemctl disable ufw

    # 设置hosts解析
    cat >> /etc/hosts <<EOF
$MASTER1 master1
$MASTER2 master2
$MASTER3 master3
$WORKER1 worker1
EOF

    # 加载内核模块
    cat > /etc/modules-load.d/k8s.conf <<EOF
br_netfilter
EOF

    # 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
net.ipv4.ip_forward = 1
EOF
    sysctl --system
}


echo "=== 内核模块检查 ==="
if ! lsmod | grep br_netfilter; then
  echo "错误：br_netfilter 模块未加载，即将重启系统..."
  logger -t k8s-install "br_netfilter 模块缺失，触发重启"
  sudo reboot
  exit 1  # 确保如果reboot失败会退出脚本
fi


# 2. 安装容器运行时 (Containerd) - 使用阿里云镜像源
function install_containerd() {
    echo ">>> Installing Containerd..."
    apt-get update
    apt-get install -y ca-certificates curl gnupg lsb-release

    # 添加阿里云Docker GPG密钥
    mkdir -p /etc/apt/keyrings
    curl -fsSL https://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker-aliyun.gpg

    # 添加阿里云Docker仓库
    echo \
    "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker-aliyun.gpg] https://mirrors.aliyun.com/docker-ce/linux/ubuntu \
    $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker-aliyun.list > /dev/null

    # 安装Containerd
    apt-get update
    apt-get install -y containerd.io

    # 配置Containerd
    mkdir -p /etc/containerd
# 确保containerd配置正确
    sudo tee /etc/containerd/config.toml >/dev/null <<EOF
version = 2
[plugins."io.containerd.grpc.v1.cri"]
  sandbox_image = "registry.aliyuncs.com/google_containers/pause:3.9"
  [plugins."io.containerd.grpc.v1.cri".registry.mirrors]
    [plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
      endpoint = ["https://registry-1.docker.io"]
    [plugins."io.containerd.grpc.v1.cri".registry.mirrors."registry.k8s.io"]
      endpoint = ["https://registry.aliyuncs.com/google_containers"]
EOF
    systemctl restart containerd
}

# 3. 安装kubeadm/kubelet/kubectl - 使用阿里云镜像源
function install_k8s_tools() {
    echo ">>> Installing Kubernetes tools..."
    apt-get update && apt-get install -y apt-transport-https curl
    
    # 添加阿里云Kubernetes源
    curl -fsSL https://mirrors.aliyun.com/kubernetes/apt/doc/apt-key.gpg | apt-key add -
    cat > /etc/apt/sources.list.d/kubernetes-aliyun.list <<EOF
deb https://mirrors.aliyun.com/kubernetes/apt/ kubernetes-xenial main
EOF

    apt-get update
    apt-get install -y kubelet kubeadm kubectl
    apt-mark hold kubelet kubeadm kubectl
}

  
# 4. 配置Keepalived (仅Master节点)
function setup_keepalived() {
    if [ "$NODE_ROLE" != "master" ]; then
        return
    fi

    echo ">>> Configuring Keepalived on $CURRENT_IP..."
    apt-get install -y keepalived

    # 生成Keepalived配置
    PRIORITY=100
    if [ "$CURRENT_IP" = "$MASTER1" ]; then
        PRIORITY=150
    elif [ "$CURRENT_IP" = "$MASTER2" ]; then
        PRIORITY=120
    fi

    cat > /etc/keepalived/keepalived.conf <<EOF
vrrp_script chk_kubeapi {
    script "nc -zv localhost 6443"
    interval 2
    weight -5
    fall 3
    rise 2
}

vrrp_instance VI_1 {
    state BACKUP
    interface ens33
    virtual_router_id 51
    priority $PRIORITY
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 42
    }
    virtual_ipaddress {
        $KEEPALIVED_VIP
    }
    track_script {
        chk_kubeapi
    }
}
EOF

    systemctl enable keepalived && systemctl start keepalived
}

# 5. 初始化Master节点 (仅第一个Master)
function init_master() {
    if [ "$CURRENT_IP" != "$MASTER1" ]; then
        return
    fi

    echo ">>> Initializing first master node..."
    kubeadm init \
        --control-plane-endpoint="$KEEPALIVED_VIP:6443" \
        --upload-certs \
        --pod-network-cidr=10.244.0.0/16 \
        --apiserver-advertise-address=$CURRENT_IP \
        --image-repository registry.aliyuncs.com/google_containers  # 使用阿里云镜像仓库

    # 配置kubectl
    mkdir -p $HOME/.kube
    cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
    chown $(id -u):$(id -g) $HOME/.kube/config

    # 保存join命令
    JOIN_CMD=$(kubeadm token create --print-join-command)
    echo "Worker join command: $JOIN_CMD" > /root/join-command.txt
    
    CERT_KEY=$(kubeadm init phase upload-certs --upload-certs | tail -1)
    echo "Master join command: kubeadm join $KEEPALIVED_VIP:6443 --token $(echo $JOIN_CMD | awk '{print $5}') --discovery-token-ca-cert-hash $(echo $JOIN_CMD | awk '{print $7}') --control-plane --certificate-key $CERT_KEY" >> /root/join-command.txt
}

# 6. 加入其他Master节点
function join_masters() {
    if [ "$CURRENT_IP" = "$MASTER1" ] || [ "$NODE_ROLE" != "master" ]; then
        return
    fi

    echo ">>> Joining as additional master node..."
    if [ -f "/tmp/join-command.txt" ]; then
        bash /tmp/join-command.txt
    else
        echo "Error: Join command not found. Please copy /root/join-command.txt from master1 to /tmp/join-command.txt"
        exit 1
    fi
}

# 7. 加入Worker节点
function join_workers() {
    if [ "$NODE_ROLE" != "worker" ]; then
        return
    fi

    echo ">>> Joining as worker node..."
    if [ -f "/tmp/join-command.txt" ]; then
        bash /tmp/join-command.txt
    else
        echo "Error: Join command not found. Please copy /root/join-command.txt from master1 to /tmp/join-command.txt"
        exit 1
    fi
}

# 8. 安装网络插件 (仅第一个Master) - 使用国内镜像
function install_network_plugin() {
    if [ "$CURRENT_IP" != "$MASTER1" ]; then
        return
    fi

    echo ">>> Installing Flannel network plugin..."
    # 使用国内镜像源下载flannel配置
    curl -o kube-flannel.yml https://ghproxy.com/https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
    sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' kube-flannel.yml  # 替换镜像源
    kubectl apply -f kube-flannel.yml
}

# 9. 验证集群状态 (仅第一个Master)
function verify_cluster() {
    if [ "$CURRENT_IP" != "$MASTER1" ]; then
        return
    fi

    echo ">>> Verifying cluster status..."
    sleep 30  # 等待组件启动
    kubectl get nodes
    kubectl get pods -n kube-system
}

# 主执行流程
setup_basic_env
install_containerd
install_k8s_tools
setup_keepalived

if [ "$NODE_ROLE" = "master" ]; then
    if [ "$CURRENT_IP" = "$MASTER1" ]; then
        init_master
        install_network_plugin
        verify_cluster
    else
        join_masters
    fi
else
    join_workers
fi

echo ">>> Kubernetes cluster setup completed on $CURRENT_IP!"

使用说明：
脚本适配：

替换脚本中的 , 和 为 kubeadm init 输出的实际值

确保所有节点可以互相SSH访问（用于复制join命令）

执行顺序：

先在 master1 (192.168.177.125) 上运行脚本

从 master1 获取 /root/join-command.txt 中的命令

在其他节点上运行脚本前，先修改 join_masters() 和 join_workers() 函数中的join命令

网络接口：

脚本默认使用 ens33 作为Keepalived网络接口，请根据实际网卡名修改

VIP验证：

部署完成后，在任一Master节点执行 ip a 查看VIP是否绑定

测试VIP漂移：停止当前持有VIP的Master节点的keepalived服务，观察VIP是否迁移

完整流程：

bash

在master1上执行

chmod +x deploy_k8s_ha.sh
bash -xe ./deploy_k8s_ha.sh

获取join命令

cat /root/join-command.txt

在其他节点上执行前，修改脚本中的join命令部分

然后分别在其他节点执行

./deploy_k8s_ha.sh
此脚本实现了完整的自动化部署，包括：

基础环境配置

Containerd安装

Kubernetes组件安装

Keepalived高可用配置

多Master节点加入

Worker节点加入

网络插件部署

二、部署其他节点

从master1节点复制join命令到其他节点
scp root@192.168.177.125:/root/join-command.txt /tmp/
在其他节点上执行脚本
./k8s-ha-setup.sh