更新 install_k8s/install_k8s_ubuntu-final.sh

install_k8s/install_k8s_ubuntu-final.sh

@@ -1,29 +1,25 @@
 #!/bin/bash
 # ---------------------------------------------------------
-# Kubernetes (K8s) 高可用集群自动化脚本 (Ubuntu 专用 V5 完美防弹版)
+# Kubernetes (K8s) 高可用集群自动化脚本 (Ubuntu 终极可用版)
-# 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) =================
+# ================= 变量配置区 (执行前请核对以下 IP) =================
 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
+# 1. 高可用 VIP 配置 (你的 Keepalived 虚拟IP)
 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
+# 自动获取当前机器的主网卡名称
 VIP_INTERFACE=$(ip route | grep default | awk '{print $5}' | head -n 1) 
 
-# 2. Master 节点真实 IP 列表
+# 2. 你的三台 Master 节点真实 IP
 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}"
 # ===============================================================
 
@@ -31,127 +27,116 @@ RED='\033[0;31m'
 GREEN='\033[0;32m'
 YELLOW='\033[0;33m'
 NC='\033[0m'
+export DEBIAN_FRONTEND=noninteractive
 
 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}"
+    echo -e "${GREEN}==> 1. 开始初始化系统环境 (Ubuntu)...${NC}"
-    # 关闭防火墙
+    ufw disable 2>/dev/null
-    ufw disable
+    systemctl stop ufw 2>/dev/null && systemctl disable ufw 2>/dev/null
-    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 > /dev/null
-    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
+    # 【关键防坑】ip_nonlocal_bind 允许 HAProxy 强行绑定还未飘过来的 VIP
-    cat <<EOF | tee /etc/sysctl.d/k8s.conf
+    cat <<EOF | tee /etc/sysctl.d/k8s.conf > /dev/null
 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
+    sysctl --system > /dev/null
-    echo -e "${GREEN}==> 系统环境初始化完成。${NC}"
+    echo -e "${GREEN}==> 系统环境准备完毕。${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}"
+    echo -e "${GREEN}==> 2. 开始安装 Containerd (锁定 1.6.x 避开 2.x 的断层坑)...${NC}"
     
-    # 【核心修复】：强制解除之前的包锁定，防止卸载和重装失败
+    # 强行解锁并清理之前可能残留的坏包
     apt-mark unhold containerd containerd.io 2>/dev/null || true
-    
+    apt-get purge -y --allow-change-held-packages 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 autoremove -y > /dev/null
-    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 update -y > /dev/null
     apt-get install -y apt-transport-https ca-certificates curl software-properties-common gpg
 
-    # 配置阿里云 Docker 官方源
+    # 配置官方 Docker 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
+    apt-get update -y > /dev/null
 
-    # 动态获取 1.6.x 系列的最新版本号并强制安装
+    # 动态抓取 1.6.x 稳定版，防止 2.x 导致 kubeadm 崩溃
     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}"
+        echo -e "${RED}无法找到 containerd.io 1.6.x 版本，请检查网络！${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
-    
+    apt-mark hold containerd.io > /dev/null
-    # 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
+    # 【终极防坑】生成配置后，暴杀 disabled_plugins 屏蔽项，防止 CRI 插件装死
     mkdir -p /etc/containerd
     containerd config default | tee /etc/containerd/config.toml > /dev/null
+    sed -i '/disabled_plugins/d' /etc/containerd/config.toml
     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
+    systemctl restart containerd
+    systemctl enable containerd
 
-    # 配置 crictl，消除 socket 警告
+    # 消除 crictl 警告
-    cat <<EOF | tee /etc/crictl.yaml
+    cat <<EOF | tee /etc/crictl.yaml > /dev/null
 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}"
+    echo -e "${GREEN}==> Containerd (1.6.x) 安装配置完毕。${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}"
+    echo -e "${GREEN}==> 3. 开始安装 kubeadm, kubelet, kubectl...${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
+    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 > /dev/null
 
-    apt-get update -y
+    apt-get update -y > /dev/null
     apt-get install -y --allow-downgrades --allow-change-held-packages kubelet kubeadm kubectl
-    apt-mark hold kubelet kubeadm kubectl
+    apt-mark hold kubelet kubeadm kubectl > /dev/null
 
     systemctl enable --now kubelet
-    echo -e "${GREEN}==> Kubernetes 组件安装完成。${NC}"
+    echo -e "${GREEN}==> K8s 核心组件安装完毕。${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}"
+    echo -e "${GREEN}==> 开始部署高可用 HAProxy & Keepalived (网卡: ${VIP_INTERFACE})...${NC}"
     apt-get install -y haproxy keepalived
 
-    cat <<EOF | tee /etc/haproxy/haproxy.cfg
+    cat <<EOF | tee /etc/haproxy/haproxy.cfg > /dev/null
 global
     log /dev/log local0
     log /dev/log local1 notice
@@ -179,7 +164,7 @@ backend kubernetes-master
     server master03 ${MASTER03_IP}:6443 check
 EOF
 
-    cat <<EOF | tee /etc/keepalived/keepalived.conf
+    cat <<EOF | tee /etc/keepalived/keepalived.conf > /dev/null
 ! Configuration File for keepalived
 global_defs {
    router_id LVS_DEVEL
@@ -212,24 +197,21 @@ EOF
 
     systemctl restart haproxy keepalived
     systemctl enable haproxy keepalived
-    echo -e "${GREEN}==> HAProxy 和 Keepalived 配置完成 (角色: ${STATE})。${NC}"
+    echo -e "${GREEN}==> 负载均衡组件部署完毕 (当前角色: ${STATE})。${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}"
+    echo -e "${YELLOW}==> 正在清理历史脏数据，确保纯净初始化...${NC}"
-    kubeadm reset -f
+    kubeadm reset -f > /dev/null 2>&1
-    rm -rf /etc/cni/net.d
+    rm -rf /etc/cni/net.d $HOME/.kube/config
-    rm -rf $HOME/.kube/config
+    ip link delete cni0 2>/dev/null || true
+    ip link delete flannel.1 2>/dev/null || true
     
-    echo -e "${GREEN}==> 检查 VIP 是否存活...${NC}"
+    echo -e "${GREEN}==> 验证基础服务健康状态...${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; }
+    ping -c 3 ${VIP} > /dev/null 2>&1 || { echo -e "${RED}致命错误: VIP (${VIP}) 无法连通，Keepalived未生效或存在IP冲突！${NC}"; exit 1; }
+    crictl ps > /dev/null 2>&1 || { echo -e "${RED}致命错误: Containerd 通道未就绪 (CRI报错)，请检查状态！${NC}"; exit 1; }
 
-    echo -e "${GREEN}==> 检查 Containerd 存活状态...${NC}"
+    echo -e "${GREEN}==> 开始初始化 Master01 集群...${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 \
@@ -240,7 +222,7 @@ function init_first_master() {
 
     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。${NC}"
+        echo -e "${GREEN}恭喜！集群初始化成功！请务必复制好上方的 kubeadm join 命令。${NC}"
         echo -e "${YELLOW}========================================================================${NC}"
         
         export KUBECONFIG=/etc/kubernetes/admin.conf
@@ -251,11 +233,11 @@ function init_first_master() {
         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}"
+        echo -e "${RED}初始化彻底失败！请检查上方输出。${NC}"
     fi
 }
 
-# 主路由逻辑
+# =============== 路由逻辑 ===============
 case "$1" in
     base)
         prepare_env
@@ -272,6 +254,10 @@ case "$1" in
         init_first_master
         ;;
     *)
-        echo -e "${YELLOW}用法: sudo $0 {base|init-vip-master|init-vip-backup|init-master}${NC}"
+        echo -e "${YELLOW}用法说明 (sudo ./install_k8s.sh <命令>):${NC}"
+        echo "  base            - 所有机器(包括Node)加集群前【必跑】，装依赖排雷"
+        echo "  init-vip-master - Master01执行，配置主负载均衡"
+        echo "  init-vip-backup - Master02/03执行，配置备用负载均衡"
+        echo "  init-master     - 仅Master01执行，进行最后的K8s集群初始化"
         exit 1
 esac