yindun
/
ansible-devops
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

更新 scripts/k8s-cluster-deploy.sh 

12
This commit is contained in:
joy 2025-10-31 09:41:35 +08:00
parent f50ea470fc
commit edb9ee6c28
1 changed files with 150 additions and 87 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

231
scripts/k8s-cluster-deploy.sh
View File

@ -9,34 +9,60 @@ YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m'
# 命令记录存储（用于最后汇总展示）
declare -a EXECUTED_COMMANDS=()
LOG_FILE="/var/log/k8s-deploy-$(date +%Y%m%d-%H%M%S).log"
# 打印函数
info() { echo -e "${YELLOW}[INFO]${NC} $1"; }
success() { echo -e "${GREEN}[SUCCESS]${NC} $1"; }
error() { echo -e "${RED}[ERROR]${NC} $1"; exit 1; }
step() { echo -e "\n${BLUE}===== $1 =====${NC}"; }
info() {
echo -e "${YELLOW}[INFO]${NC} $1" | tee -a "$LOG_FILE"
}
success() {
echo -e "${GREEN}[SUCCESS]${NC} $1" | tee -a "$LOG_FILE"
}
error() {
echo -e "${RED}[ERROR]${NC} $1" | tee -a "$LOG_FILE"
exit 1
}
step() {
echo -e "\n${BLUE}===== $1 =====${NC}" | tee -a "$LOG_FILE"
}
# 远程执行命令并记录
remote_exec() {
local ip=$1
local cmd=$2
local desc=${3:-"执行命令"}
info "在 $ip 上 $desc: ${YELLOW}$cmd${NC}"
EXECUTED_COMMANDS+=("在 $ip 上: $cmd")
# 执行远程命令并记录输出
if ! ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 "$REMOTE_USER@$ip" "$cmd" >> "$LOG_FILE" 2>&1; then
error "在 $ip 上执行命令失败: $cmd，请查看日志: $LOG_FILE"
fi
}
# 固定路径（可根据实际调整）
KUBEADM_CONF="/opt/k8s-install-conf/kubeadm-conf.yaml" # Master1的kubeadm配置文件
KUBEADM_CONF="/opt/k8s-install-conf/kubeadm-conf.yaml" # Master节点的kubeadm配置文件
INIT_RESULT_FILE="/opt/k8s-install-conf/kubeadm-init-result.txt" # 初始化结果保存文件
# 关键修改1：Calico v3.25官方YAML地址（替换原v3.26）
CALICO_YAML_OFFICIAL="https://docs.projectcalico.org/v3.25/manifests/calico.yaml"
# 本地临时Calico YAML路径（用于镜像替换）
LOCAL_CALICO_YAML="/tmp/calico-v3.25-modified.yaml"
# 关键修改2：华为云SWR镜像前缀（替换原docker.io/calico）
SWR_CALICO_PREFIX="swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/calico"
REMOTE_USER="root" # 远程节点登录用户
# ========================== 参数解析（核心：指定Master/Node IP） ==========================
# 初始化参数
# ========================== 参数解析 ==========================
MASTER_IPS=() # 3个Master节点IP（顺序：Master1, Master2, Master3）
NODE_IPS=() # Node节点IP列表（支持多个，用逗号分隔）
NODE_IPS=() # Node节点IP列表
parse_args() {
while [[ $# -gt 0 ]]; do
case "$1" in
--master-ips)
# 解析3个Master IP（格式："192.168.61.10,192.168.61.11,192.168.61.12"）
IFS=',' read -ra IPS <<< "$2"
if [[ ${#IPS[@]} -ne 3 ]]; then
error "--master-ips必须包含3个IP（逗号分隔），当前提供${#IPS[@]}个"
@ -45,14 +71,13 @@ parse_args() {
shift 2
;;
--node-ips)
# 解析Node IP列表（格式："192.168.61.20,192.168.61.21"）
IFS=',' read -ra IPS <<< "$2"
NODE_IPS=("${IPS[@]}")
shift 2
;;
--help)
echo "用法：$0 --master-ips <IP1,IP2,IP3> [--node-ips <IP1,IP2,...>]"
echo "功能：Master1初始化→远程Master/Node加入→Calico(v3.25+华为云SWR)部署"
echo "功能：部署K8s集群，包含3个Master节点和可选的Node节点"
echo "参数说明："
echo " --master-ips 必选，3个Master节点IP（顺序：Master1(初始化节点), Master2, Master3）"
echo " --node-ips 可选，Node节点IP列表（逗号分隔，如不指定则仅部署Master集群）"
@ -71,7 +96,7 @@ parse_args() {
error "缺少必选参数--master-ips（需指定3个Master节点IP）"
fi
# 提取Master1 IP（初始化节点）
# 提取Master IP
export MASTER1_IP="${MASTER_IPS[0]}"
export MASTER2_IP="${MASTER_IPS[1]}"
export MASTER3_IP="${MASTER_IPS[2]}"
@ -83,7 +108,31 @@ parse_args() {
}
# ========================== 步骤1：Master1初始化（核心） ==========================
# ========================== 免密登录检测 ==========================
check_ssh_access() {
step "前置检查：SSH免密登录验证"
local all_ips=("${MASTER_IPS[@]}" "${NODE_IPS[@]}")
local failed_ips=()
for ip in "${all_ips[@]}"; do
info "验证SSH免密登录：$REMOTE_USER@$ip"
if ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 -o BatchMode=yes "$REMOTE_USER@$ip" "echo 'SSH连通正常'" >/dev/null 2>&1; then
info "$ip SSH免密登录验证通过"
else
error "$ip SSH免密登录验证失败，请先执行: ssh-copy-id $REMOTE_USER@$ip 配置免密"
failed_ips+=("$ip")
fi
done
if [[ ${#failed_ips[@]} -gt 0 ]]; then
error "以下节点SSH免密登录配置失败: ${failed_ips[*]}"
fi
success "所有节点SSH免密登录验证通过"
}
# ========================== 步骤1：Master1初始化 ==========================
init_master1() {
step "Step 1：Master1节点初始化（$MASTER1_IP）"
@ -92,16 +141,18 @@ init_master1() {
error "Master1的kubeadm配置文件不存在：$MASTER1_IP:$KUBEADM_CONF（请先执行配置分发脚本）"
fi
# 执行kubeadm init（带证书上传，支持其他Master加入）
info "执行初始化命令：kubeadm init --upload-certs --config $KUBEADM_CONF"
# 执行kubeadm init
local init_cmd="kubeadm init --upload-certs --config $KUBEADM_CONF 2>&1"
info "执行初始化命令：$init_cmd"
info "初始化结果将保存到：$INIT_RESULT_FILE"
# 远程执行初始化，同时保存输出到本地文件
ssh "$REMOTE_USER@$MASTER1_IP" "kubeadm init --upload-certs --config $KUBEADM_CONF 2>&1" | tee "$INIT_RESULT_FILE"
local init_exit_code=${PIPESTATUS[0]} # 获取远程命令退出码
ssh "$REMOTE_USER@$MASTER1_IP" "$init_cmd" | tee "$INIT_RESULT_FILE"
local init_exit_code=${PIPESTATUS[0]}
if [[ $init_exit_code -ne 0 ]]; then
error "Master1初始化失败！查看详情：cat $INIT_RESULT_FILE"
fi
EXECUTED_COMMANDS+=("在 $MASTER1_IP 上初始化: $init_cmd")
success "Master1初始化完成，结果已保存到：$INIT_RESULT_FILE"
info "初始化输出预览（前20行）："
@ -123,51 +174,51 @@ config_master1_kubeconfig() {
)
for cmd in "${kube_cmds[@]}"; do
info "在Master1执行：$cmd"
ssh "$REMOTE_USER@$MASTER1_IP" "$cmd" || error "执行命令失败：$cmd"
remote_exec "$MASTER1_IP" "$cmd" "配置kubeconfig"
done
# 验证kubectl是否可用
info "验证kubectl：在Master1执行 kubectl get nodes"
ssh "$REMOTE_USER@$MASTER1_IP" "kubectl get nodes" || error "kubectl配置失败，无法获取节点信息"
remote_exec "$MASTER1_IP" "kubectl get nodes" "验证kubectl"
success "Master1 kubeconfig配置完成"
}
# ========================== 步骤3：提取join命令（从初始化结果中） ==========================
# ========================== 步骤3：提取join命令 ==========================
extract_join_commands() {
step "Step 3：从初始化结果中提取join命令"
# 检查结果文件是否存在
[[ -f "$INIT_RESULT_FILE" ]] || error "初始化结果文件不存在：$INIT_RESULT_FILE"
# 1. 提取Master节点join命令（含--control-plane和--certificate-key）
# 提取Master节点join命令
info "提取Master节点join命令"
local master_join_cmd
master_join_cmd=$(grep -A 3 "You can now join any number of control-plane nodes by running the following command on each as root" "$INIT_RESULT_FILE" | grep -v "You can now" | tr -d '\n' | sed 's/ */ /g')
[[ -z "$master_join_cmd" ]] && error "未从初始化结果中提取到Master join命令"
# 补充--config参数（其他Master也需用自己的配置文件）
# 补充--config参数
master_join_cmd="$master_join_cmd --config $KUBEADM_CONF"
export MASTER_JOIN_CMD="$master_join_cmd"
EXECUTED_COMMANDS+=("Master节点加入命令: $MASTER_JOIN_CMD")
success "Master join命令提取完成："
echo -e "${YELLOW}${MASTER_JOIN_CMD}${NC}"
# 2. 提取Node节点join命令
# 提取Node节点join命令
info "提取Node节点join命令"
local node_join_cmd
node_join_cmd=$(grep -A 2 "Then you can join any number of worker nodes by running the following on each as root" "$INIT_RESULT_FILE" | grep -v "Then you can" | tr -d '\n' | sed 's/ */ /g')
[[ -z "$node_join_cmd" ]] && error "未从初始化结果中提取到Node join命令"
export NODE_JOIN_CMD="$node_join_cmd"
EXECUTED_COMMANDS+=("Node节点加入命令: $NODE_JOIN_CMD")
success "Node join命令提取完成："
echo -e "${YELLOW}${NODE_JOIN_CMD}${NC}"
}
# ========================== 步骤4：远程其他Master节点加入 ==========================
# ========================== 步骤4：其他Master节点加入 ==========================
join_other_masters() {
step "Step 4：远程Master2（$MASTER2_IP）和Master3（$MASTER3_IP）加入集群"
# 定义要加入的Master节点列表（排除Master1）
# 定义要加入的Master节点列表
local other_masters=("$MASTER2_IP" "$MASTER3_IP")
for master_ip in "${other_masters[@]}"; do
@ -175,28 +226,32 @@ join_other_masters() {
# 检查该Master的kubeadm配置文件是否存在
if ! ssh "$REMOTE_USER@$master_ip" "test -f $KUBEADM_CONF"; then
error "Master $master_ip的kubeconfig配置文件不存在：$KUBEADM_CONF"
error "Master $master_ip的配置文件不存在：$KUBEADM_CONF"
fi
# 远程执行join命令
info "在$master_ip执行join命令：$MASTER_JOIN_CMD"
ssh "$REMOTE_USER@$master_ip" "$MASTER_JOIN_CMD" || error "Master $master_ip加入失败"
remote_exec "$master_ip" "$MASTER_JOIN_CMD" "执行加入集群命令"
# 配置该Master的kubeconfig（否则无法本地执行kubectl）
info "配置$master_ip的kubeconfig"
ssh "$REMOTE_USER@$master_ip" "mkdir -p \$HOME/.kube && cp -i /etc/kubernetes/admin.conf \$HOME/.kube/config && chown \$(id -u):\$(id -g) \$HOME/.kube/config"
# 配置该Master的kubeconfig
local kube_config_cmds=(
"mkdir -p \$HOME/.kube"
"cp -i /etc/kubernetes/admin.conf \$HOME/.kube/config"
"chown \$(id -u):\$(id -g) \$HOME/.kube/config"
)
for cmd in "${kube_config_cmds[@]}"; do
remote_exec "$master_ip" "$cmd" "配置kubeconfig"
done
success "Master $master_ip加入集群并配置完成"
done
# 验证所有Master节点状态
info "验证所有Master节点状态（从Master1执行）"
ssh "$REMOTE_USER@$MASTER1_IP" "kubectl get nodes | grep master" || error "Master节点状态验证失败"
remote_exec "$MASTER1_IP" "kubectl get nodes | grep master" "验证Master节点状态"
success "所有Master节点加入完成"
}
# ========================== 步骤5：远程Node节点加入（可选） ==========================
# ========================== 步骤5：Node节点加入 ==========================
join_nodes() {
if [[ ${#NODE_IPS[@]} -eq 0 ]]; then
info "未指定Node节点，跳过Node加入步骤"
@ -208,30 +263,29 @@ join_nodes() {
for node_ip in "${NODE_IPS[@]}"; do
info "处理Node节点：$node_ip"
# 检查Node节点是否已安装基础组件（kubeadm、kubelet、containerd）
if ! ssh "$REMOTE_USER@$node_ip" "command -v kubeadm &>/dev/null && command -v kubelet &>/dev/null && systemctl is-active --quiet containerd"; then
# 检查Node节点是否已安装基础组件
local check_cmd="command -v kubeadm &>/dev/null && command -v kubelet &>/dev/null && systemctl is-active --quiet containerd"
if ! ssh "$REMOTE_USER@$node_ip" "$check_cmd"; then
error "Node $node_ip未安装基础组件（需先安装kubeadm、kubelet、containerd）"
fi
# 远程执行Node join命令
info "在$node_ip执行join命令：$NODE_JOIN_CMD"
ssh "$REMOTE_USER@$node_ip" "$NODE_JOIN_CMD" || error "Node $node_ip加入失败"
remote_exec "$node_ip" "$NODE_JOIN_CMD" "执行加入集群命令"
success "Node $node_ip加入集群完成"
done
# 验证所有节点状态
info "验证所有节点状态（从Master1执行）"
ssh "$REMOTE_USER@$MASTER1_IP" "kubectl get nodes" || error "节点状态验证失败"
remote_exec "$MASTER1_IP" "kubectl get nodes" "验证所有节点状态"
success "所有Node节点加入完成"
}
# ========================== 步骤6：部署Calico网络插件（v3.25+华为云SWR） ==========================
# ========================== 步骤6：部署Calico网络插件 ==========================
deploy_calico() {
step "Step 6：部署Calico v3.25（华为云SWR镜像）"
# 子步骤1：下载Calico v3.25官方YAML到本地
# 下载Calico YAML到本地
info "下载Calico v3.25官方YAML：$CALICO_YAML_OFFICIAL"
if command -v wget &>/dev/null; then
wget -q -O "$LOCAL_CALICO_YAML" "$CALICO_YAML_OFFICIAL" || error "wget下载Calico YAML失败"
@ -243,9 +297,8 @@ deploy_calico() {
[[ -f "$LOCAL_CALICO_YAML" ]] || error "Calico YAML下载失败，文件不存在"
success "Calico YAML下载完成（本地路径：$LOCAL_CALICO_YAML）"
# 子步骤2：替换YAML中的所有镜像地址为华为云SWR（核心修改）
# 替换YAML中的所有镜像地址为华为云SWR
info "替换镜像地址为华为云SWR：$SWR_CALICO_PREFIX"
# 替换3个核心镜像（cni、node、kube-controllers，均为v3.25.0版本）
sed -i "s#docker.io/calico/cni:v3.25.0#${SWR_CALICO_PREFIX}/cni:v3.25.0#g" "$LOCAL_CALICO_YAML"
sed -i "s#docker.io/calico/node:v3.25.0#${SWR_CALICO_PREFIX}/node:v3.25.0#g" "$LOCAL_CALICO_YAML"
sed -i "s#docker.io/calico/kube-controllers:v3.25.0#${SWR_CALICO_PREFIX}/kube-controllers:v3.25.0#g" "$LOCAL_CALICO_YAML"
@ -255,27 +308,27 @@ deploy_calico() {
grep -n "image:" "$LOCAL_CALICO_YAML" | head -n 10 || error "Calico YAML中未找到镜像配置，替换失败"
success "Calico镜像地址替换完成"
# 子步骤3：将修改后的YAML上传到Master1节点
# 将修改后的YAML上传到Master1节点
local remote_calico_yaml="/opt/k8s-install-conf/calico-v3.25-swr.yaml"
info "上传修改后的YAML到Master1：$remote_calico_yaml"
scp -o StrictHostKeyChecking=no "$LOCAL_CALICO_YAML" "$REMOTE_USER@$MASTER1_IP:$remote_calico_yaml" || error "YAML上传失败"
EXECUTED_COMMANDS+=("上传Calico配置到 $MASTER1_IP: scp $LOCAL_CALICO_YAML $REMOTE_USER@$MASTER1_IP:$remote_calico_yaml")
success "YAML上传完成"
# 子步骤4：在Master1执行Calico部署
info "执行部署命令：kubectl apply -f $remote_calico_yaml"
ssh "$REMOTE_USER@$MASTER1_IP" "kubectl apply -f $remote_calico_yaml" || error "Calico部署失败"
# 在Master1执行Calico部署
local deploy_cmd="kubectl apply -f $remote_calico_yaml"
remote_exec "$MASTER1_IP" "$deploy_cmd" "执行Calico部署"
# 子步骤5：等待Calico Pod启动（最多等待5分钟）
# 等待Calico Pod启动
info "等待Calico Pod启动（最多5分钟）..."
local wait_time=0
while true; do
# 检查calico-system命名空间下所有Pod是否Running
local pod_status
pod_status=$(ssh "$REMOTE_USER@$MASTER1_IP" "kubectl get pods -n calico-system -o jsonpath='{.items[*].status.phase}' 2>/dev/null")
if [[ "$pod_status" =~ ^(Running\ )*Running$ && -n "$pod_status" ]]; then
break
fi
if [[ $wait_time -ge 300 ]]; then # 5分钟=300秒
if [[ $wait_time -ge 300 ]]; then
error "Calico Pod启动超时（5分钟），请手动检查：kubectl get pods -n calico-system"
fi
sleep 10
@ -283,58 +336,68 @@ deploy_calico() {
info "已等待${wait_time}秒，Calico Pod状态：$pod_status"
done
# 子步骤6：验证Calico状态
info "验证Calico状态（从Master1执行）"
ssh "$REMOTE_USER@$MASTER1_IP" "kubectl get pods -n calico-system" || error "Calico状态验证失败"
# 额外验证网络插件是否就绪
ssh "$REMOTE_USER@$MASTER1_IP" "kubectl get nodes -o wide | grep -E 'STATUS|Ready'" || error "节点网络未就绪"
# 验证Calico状态
remote_exec "$MASTER1_IP" "kubectl get pods -n calico-system" "验证Calico状态"
remote_exec "$MASTER1_IP" "kubectl get nodes -o wide | grep -E 'STATUS|Ready'" "验证节点网络状态"
success "Calico v3.25（华为云SWR）部署完成，集群网络已就绪"
# 子步骤7：清理本地临时YAML文件
# 清理本地临时YAML文件
info "清理本地临时文件：$LOCAL_CALICO_YAML"
rm -f "$LOCAL_CALICO_YAML" || info "本地文件清理失败，可手动删除"
}
# ========================== 主流程：串联所有步骤 ==========================
# ========================== 步骤7：展示执行的所有命令 ==========================
show_executed_commands() {
step "Step 7：执行命令汇总"
echo -e "${YELLOW}以下是部署过程中执行的关键命令：${NC}"
echo -e "----------------------------------------------------------------------"
local count=1
for cmd in "${EXECUTED_COMMANDS[@]}"; do
echo -e "${count}. ${cmd}"
((count++))
done
echo -e "----------------------------------------------------------------------"
}
# ========================== 主流程 ==========================
main() {
# 记录开始时间
local start_time=$(date +%s)
# 1. 解析参数
parse_args "$@"
# 2. 前置检查：确保SSH免密登录正常
step "前置检查：SSH免密登录验证"
local all_ips=("${MASTER_IPS[@]}" "${NODE_IPS[@]}")
for ip in "${all_ips[@]}"; do
info "验证SSH免密登录：$REMOTE_USER@$ip"
if ! ssh -o StrictHostKeyChecking=no "$REMOTE_USER@$ip" "echo 'SSH连通正常' >/dev/null"; then
error "SSH免密登录失败：$ip（请先执行 ssh-copy-id $REMOTE_USER@$ip 配置免密）"
fi
done
success "所有节点SSH免密登录验证通过"
# 2. 检查SSH免密登录
check_ssh_access
# 3. 执行核心步骤
init_master1 # Master1初始化
config_master1_kubeconfig # Master1配置kubeconfig
extract_join_commands # 提取join命令
join_other_masters # 其他Master加入
join_nodes # Node加入（可选）
deploy_calico # 部署Calico（v3.25+SWR）
init_master1
config_master1_kubeconfig
extract_join_commands
join_other_masters
join_nodes
deploy_calico
# 4. 集群部署完成总结
# 4. 展示执行的命令
show_executed_commands
# 5. 集群部署完成总结
step "集群部署完成总结"
local end_time=$(date +%s)
local duration=$((end_time - start_time))
echo -e "${GREEN}========================================"
echo -e "K8s集群部署全流程完成！"
echo -e "部署耗时：$((duration/60))分$((duration%60))秒"
echo -e "关键信息："
echo -e " 1. Calico版本：v3.25（镜像源：华为云SWR）"
echo -e " 2. 集群节点状态：ssh $REMOTE_USER@$MASTER1_IP 'kubectl get nodes'"
echo -e " 3. Calico状态：ssh $REMOTE_USER@$MASTER1_IP 'kubectl get pods -n calico-system'"
echo -e " 4. 初始化结果：$INIT_RESULT_FILE"
echo -e " 5. 部署日志：$LOG_FILE"
echo -e "========================================"
}
# 启动主流程
main "$@"
chmod +x k8s-cluster-deploy.sh
# 部署3个Master + 2个Node（替换为你的IP）
#bash k8s-cluster-deploy.sh --master-ips 192.168.61.10,192.168.61.11,192.168.61.12 --node-ips 192.168.61.20,192.168.61.21