script-tool/install_k8s/install_k8s_ubuntu-final.sh

#!/bin/bash
# ---------------------------------------------------------
# Kubernetes (K8s) 高可用集群自动化脚本 (Ubuntu 专用 V5 完美防弹版)
# 包含: 基础环境、组件安装、HAProxy+Keepalived VIP、K8s 初始化
# 修复: Containerd 2.x 兼容性、HAProxy 离线绑定崩溃、Crictl 警告
# 核心升级: 完美解决重复执行时的 apt-mark hold 包锁定死锁问题
# ---------------------------------------------------------

# ================= 变量配置区 (执行前务必修改) =================
K8S_VERSION="1.28.2-*"
POD_SUBNET="10.244.0.0/16"
SERVICE_SUBNET="10.96.0.0/12"

# 1. 高可用 VIP 配置
VIP="192.168.40.100"
VIP_PORT="16443"

# 自动获取当前机器的主网卡名称，避免 Keepalived 绑定失败
VIP_INTERFACE=$(ip route | grep default | awk '{print $5}' | head -n 1) 

# 2. Master 节点真实 IP 列表
MASTER01_IP="192.168.40.10"
MASTER02_IP="192.168.40.11"
MASTER03_IP="192.168.40.12"

# 控制平面入口地址
CONTROL_PLANE_ENDPOINT="${VIP}:${VIP_PORT}"
# ===============================================================

RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[0;33m'
NC='\033[0m'

if [ "$EUID" -ne 0 ]; then
  echo -e "${RED}请使用 root 权限运行此脚本！(sudo -i 或者 sudo ./script.sh)${NC}"
  exit 1
fi

# 1. 基础环境
function prepare_env() {
    echo -e "${GREEN}==> 开始初始化系统环境 (Ubuntu)...${NC}"
    # 关闭防火墙
    ufw disable
    systemctl stop ufw && systemctl disable ufw

    # 关闭 Swap
    swapoff -a
    sed -i '/ swap / s/^\(.*\)$/#\1/g' /etc/fstab

    # 加载内核模块
    cat <<EOF | tee /etc/modules-load.d/k8s.conf
overlay
br_netfilter
EOF
    modprobe overlay
    modprobe br_netfilter

    # 增加 ip_nonlocal_bind，允许 HAProxy 绑定还未漂移过来的 VIP
    cat <<EOF | tee /etc/sysctl.d/k8s.conf
net.bridge.bridge-nf-call-iptables  = 1
net.bridge.bridge-nf-call-ip6tables = 1
net.ipv4.ip_forward                 = 1
net.ipv4.ip_nonlocal_bind           = 1 
EOF
    sysctl --system
    echo -e "${GREEN}==> 系统环境初始化完成。${NC}"
}

# 2. 安装并锁定 Containerd 1.6.x
function install_containerd() {
    echo -e "${GREEN}==> 开始安装 Containerd (强制降级并锁定 1.6.x 稳定版)...${NC}"
    
    # 【核心修复】：强制解除之前的包锁定，防止卸载和重装失败
    apt-mark unhold containerd containerd.io 2>/dev/null || true
    
    # 清理可能存在的旧版本或不兼容的 2.x 版本 (加入允许修改 hold 包的参数以防万一)
    apt-get purge -y --allow-change-held-packages containerd containerd.io
    apt-get autoremove -y
    rm -rf /etc/containerd/ /var/run/containerd/ /run/containerd/

    apt-get update -y
    apt-get install -y apt-transport-https ca-certificates curl software-properties-common gpg

    # 配置阿里云 Docker 官方源
    install -m 0755 -d /etc/apt/keyrings
    rm -f /etc/apt/keyrings/docker.gpg
    curl -fsSL https://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg | gpg --dearmor --yes -o /etc/apt/keyrings/docker.gpg
    chmod a+r /etc/apt/keyrings/docker.gpg
    echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://mirrors.aliyun.com/docker-ce/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null

    apt-get update -y

    # 动态获取 1.6.x 系列的最新版本号并强制安装
    local VER=$(apt-cache madison containerd.io | grep ' 1.6.' | head -n 1 | awk -F '|' '{print $2}' | tr -d ' ')
    if [ -z "$VER" ]; then
        echo -e "${RED}无法找到 containerd.io 1.6.x 版本，请检查网络源！${NC}"
        exit 1
    fi
    echo -e "${YELLOW}匹配到稳定版本: ${VER}${NC}"
    apt-get install -y --allow-downgrades --allow-change-held-packages containerd.io=$VER
    
    # 锁定版本，防止无人值守更新将其升级到 2.x
    apt-mark hold containerd.io

    # 生成 1.6.x 兼容的默认配置
    mkdir -p /etc/containerd
    containerd config default | tee /etc/containerd/config.toml > /dev/null
    sed -i 's/SystemdCgroup = false/SystemdCgroup = true/' /etc/containerd/config.toml
    sed -i 's#registry.k8s.io/pause#registry.aliyuncs.com/google_containers/pause#g' /etc/containerd/config.toml

    systemctl daemon-reload
    systemctl enable --now containerd

    # 配置 crictl，消除 socket 警告
    cat <<EOF | tee /etc/crictl.yaml
runtime-endpoint: unix:///run/containerd/containerd.sock
image-endpoint: unix:///run/containerd/containerd.sock
timeout: 10
debug: false
EOF
    echo -e "${GREEN}==> Containerd 安装配置完成。${NC}"
}

# 3. 安装 K8s 组件
function install_k8s_tools() {
    echo -e "${GREEN}==> 开始安装 kubeadm, kubelet, kubectl (使用阿里云新版 APT 源)...${NC}"
    
    # 【核心修复】：强制解除 K8s 组件的包锁定
    apt-mark unhold kubelet kubeadm kubectl 2>/dev/null || true

    mkdir -p /etc/apt/keyrings
    rm -f /etc/apt/keyrings/kubernetes-apt-keyring.gpg
    
    curl -fsSL https://mirrors.aliyun.com/kubernetes-new/core/stable/v1.28/deb/Release.key | gpg --dearmor -o /etc/apt/keyrings/kubernetes-apt-keyring.gpg
    echo "deb [signed-by=/etc/apt/keyrings/kubernetes-apt-keyring.gpg] https://mirrors.aliyun.com/kubernetes-new/core/stable/v1.28/deb/ /" | tee /etc/apt/sources.list.d/kubernetes.list

    apt-get update -y
    apt-get install -y --allow-downgrades --allow-change-held-packages kubelet kubeadm kubectl
    apt-mark hold kubelet kubeadm kubectl

    systemctl enable --now kubelet
    echo -e "${GREEN}==> Kubernetes 组件安装完成。${NC}"
}

# 4. 配置负载均衡 (HAProxy + Keepalived)
function setup_vip() {
    local STATE=$1
    local PRIORITY=$2
    
    echo -e "${GREEN}==> 开始配置 HAProxy 和 Keepalived (绑定的网卡: ${VIP_INTERFACE})...${NC}"
    apt-get install -y haproxy keepalived

    cat <<EOF | tee /etc/haproxy/haproxy.cfg
global
    log /dev/log local0
    log /dev/log local1 notice
    daemon

defaults
    mode                    tcp
    log                     global
    option                  tcplog
    timeout connect         10s
    timeout client          1m
    timeout server          1m

frontend kubernetes-apiserver
    bind ${VIP}:${VIP_PORT}
    mode tcp
    default_backend kubernetes-master

backend kubernetes-master
    mode tcp
    balance roundrobin
    option tcp-check
    server master01 ${MASTER01_IP}:6443 check
    server master02 ${MASTER02_IP}:6443 check
    server master03 ${MASTER03_IP}:6443 check
EOF

    cat <<EOF | tee /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
   router_id LVS_DEVEL
}
vrrp_script check_haproxy {
    script "killall -0 haproxy"
    interval 3
    weight -2
    fall 10
    rise 2
}
vrrp_instance VI_1 {
    state ${STATE}
    interface ${VIP_INTERFACE}
    virtual_router_id 51
    priority ${PRIORITY}
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 1111
    }
    virtual_ipaddress {
        ${VIP}
    }
    track_script {
        check_haproxy
    }
}
EOF

    systemctl restart haproxy keepalived
    systemctl enable haproxy keepalived
    echo -e "${GREEN}==> HAProxy 和 Keepalived 配置完成 (角色: ${STATE})。${NC}"
}

# 5. 初始化第一个 Master 节点
function init_first_master() {
    echo -e "${YELLOW}==> 正在清理可能残留的 K8s 脏数据...${NC}"
    kubeadm reset -f
    rm -rf /etc/cni/net.d
    rm -rf $HOME/.kube/config
    
    echo -e "${GREEN}==> 检查 VIP 是否存活...${NC}"
    ping -c 3 ${VIP} || { echo -e "${RED}警告: 无法 ping 通 VIP ${VIP}，请确保 Keepalived 正常启动且无 IP 冲突！${NC}"; exit 1; }

    echo -e "${GREEN}==> 检查 Containerd 存活状态...${NC}"
    crictl ps > /dev/null || { echo -e "${RED}警告: 无法连接 containerd，请检查服务状态！${NC}"; exit 1; }

    echo -e "${GREEN}==> 开始初始化第一个 Master 节点...${NC}"
    
    kubeadm init \
      --control-plane-endpoint="${CONTROL_PLANE_ENDPOINT}" \
      --upload-certs \
      --kubernetes-version=v1.28.2 \
      --pod-network-cidr=${POD_SUBNET} \
      --service-cidr=${SERVICE_SUBNET} \
      --image-repository=registry.aliyuncs.com/google_containers

    if [ $? -eq 0 ]; then
        echo -e "${YELLOW}========================================================================${NC}"
        echo -e "${GREEN}集群初始化成功！请妥善保存上面输出的 kubeadm join 命令。${NC}"
        echo -e "${YELLOW}========================================================================${NC}"
        
        export KUBECONFIG=/etc/kubernetes/admin.conf
        mkdir -p $HOME/.kube
        cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
        chown $(id -u):$(id -g) $HOME/.kube/config

        echo -e "${GREEN}==> 正在部署 Calico 网络插件...${NC}"
        kubectl apply -f https://raw.githubusercontent.com/projectcalico/calico/v3.26.1/manifests/calico.yaml
    else
        echo -e "${RED}集群初始化失败！请使用 'journalctl -xeu kubelet' 检查报错。${NC}"
    fi
}

# 主路由逻辑
case "$1" in
    base)
        prepare_env
        install_containerd
        install_k8s_tools
        ;;
    init-vip-master)
        setup_vip "MASTER" 100
        ;;
    init-vip-backup)
        setup_vip "BACKUP" 90
        ;;
    init-master)
        init_first_master
        ;;
    *)
        echo -e "${YELLOW}用法: sudo $0 {base|init-vip-master|init-vip-backup|init-master}${NC}"
        exit 1
esac