Files
argus/src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/package.sh
yuyr 34cb239bf4 完成H20服务器部署及重启测试 (#51)
当前部署情况
- h1: 部署server & client
- h2: 部署client
- 部署2025-11-25
- 部署目录:  /home2/argus/server  ,  /home2/argus/client
- 部署使用账号:argus

网络拓扑:
- h1 作为docker swarm manager
- h2 作为worker加入docker swarm
- docker swarm 上创建overlay network

访问方式:
- 通过ssh到h1服务器,端口转发 20006-20011 端口到笔记本本地;
- 门户网址:http://localhost:20006/dashboard

部署截图:
![image.png](/attachments/86c1a7af-dacc-4ba7-a182-f7cefd4e6427)
![image.png](/attachments/06f20852-771c-4264-b031-e6acd0f6ea1c)
![image.png](/attachments/091ab5a8-95bf-466f-a394-3255dcb49735)

注意事项:
- server各容器使用域名作为overlay network上alias别名,实现域名访问,当前版本禁用bind作为域名解析,原因是容器重启后IP变化场景bind机制复杂且不稳定。
- client 构建是内置安装包,容器启动时执行安装流程,后续重启容器跳过安装步骤。
- UID/GID:部署使用 argus账号 uid=2133, gid=2015。

Reviewed-on: #51
Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>
Reviewed-by: xuxt <xuxt@zgclab.edu.cn>
Reviewed-by: huhy <husteryezi@163.com>
2025-11-25 15:54:29 +08:00

98 lines
2.1 KiB
Bash
Executable File

#!/bin/bash
set -e
# 颜色定义
GREEN='\033[0;32m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
log_info() {
echo -e "${BLUE}[INFO]${NC} $1"
}
log_success() {
echo -e "${GREEN}[SUCCESS]${NC} $1"
}
# 获取当前目录
CURRENT_DIR=$(pwd)
PACKAGE_NAME="dcgm-exporter-$(date +%Y%m%d-%H%M%S)"
PACKAGE_FILE="${PACKAGE_NAME}.tar.gz"
log_info "开始打包 DCGM Exporter 安装包..."
# 检查必要文件
log_info "检查必要文件..."
required_files=(
"install.sh"
"uninstall.sh"
"bin/dcgm-exporter"
"bin/datacenter-gpu-manager_3.3.9_amd64.deb"
"check_health.sh"
)
missing_files=()
for file in "${required_files[@]}"; do
if [[ ! -f "$file" ]]; then
missing_files+=("$file")
fi
done
if [[ ${#missing_files[@]} -gt 0 ]]; then
echo "缺少以下文件:"
for file in "${missing_files[@]}"; do
echo " - $file"
done
exit 1
fi
# 防御:阻止将 Git LFS 指针文件打包
for f in bin/dcgm-exporter bin/datacenter-gpu-manager_3.3.9_amd64.deb; do
if head -n1 "$f" 2>/dev/null | grep -q '^version https://git-lfs.github.com/spec/v1$'; then
echo "[ERROR] $f 是 Git LFS 指针文件,未还原为真实制品"
echo " 请在仓库根目录执行: git lfs fetch --all && git lfs checkout"
exit 1
fi
done
log_success "所有必要文件检查完成"
# 创建临时目录
TEMP_DIR=$(mktemp -d)
log_info "创建临时目录: $TEMP_DIR"
# 复制文件到临时目录
cp -r . "$TEMP_DIR/$PACKAGE_NAME"
# 进入临时目录
cd "$TEMP_DIR"
# 创建压缩包
log_info "创建压缩包: $PACKAGE_FILE"
tar -czf "$PACKAGE_FILE" "$PACKAGE_NAME"
# 移动压缩包到原目录
mv "$PACKAGE_FILE" "$CURRENT_DIR/"
# 清理临时目录
rm -rf "$TEMP_DIR"
# 返回原目录
cd "$CURRENT_DIR"
# 显示结果
log_success "打包完成!"
echo
echo "安装包文件: $PACKAGE_FILE"
echo "文件大小: $(du -h "$PACKAGE_FILE" | cut -f1)"
echo
echo "使用方法:"
echo "1. 将 $PACKAGE_FILE 传输到目标服务器"
echo "2. 解压: tar -xzf $PACKAGE_FILE"
echo "3. 进入目录: cd $PACKAGE_NAME"
echo "4. 运行安装: sudo ./install.sh"
echo
echo "注意: 请确保 config/default-counters.csv 文件存在"