refactor: metric e2e测试流程融合到 sys/tests 步骤中(test-gpu-node/check-service-installed);

refs #29
refactor: metric e2e测试流程融合到 sys/tests 步骤中（bootstrap/up/publish/installer）；
2025-10-21 09:31:29 +08:00 · 2025-10-20 17:59:17 +08:00 · 2025-10-20 15:30:07 +08:00 · 2025-10-20 14:58:12 +08:00 · 2025-10-20 14:18:15 +08:00 · 2025-10-20 09:45:32 +08:00
55 changed files with 1040 additions and 412 deletions
--- a/build/build_images.sh
+++ b/build/build_images.sh
@@ -10,6 +10,7 @@ Usage: $0 [OPTIONS]
 Options:
  --intranet        Use intranet mirror for log/bind builds
  --master-offline  Build master offline image (requires src/master/offline_wheels.tar.gz)
+  --metric          Build metric module images (ftp, prometheus, grafana, test nodes)
  --no-cache        Build all images without using Docker layer cache
  -h, --help        Show this help message

@@ -17,13 +18,15 @@ Examples:
  $0                             # Build with default sources
  $0 --intranet                  # Build with intranet mirror
  $0 --master-offline            # Additionally build argus-master:offline
-  $0 --intranet --master-offline
+  $0 --metric                    # Additionally build metric module images
+  $0 --intranet --master-offline --metric
 EOF
 }

 use_intranet=false
 build_master=true
 build_master_offline=false
+build_metric=true
 no_cache=false

 while [[ $# -gt 0 ]]; do
@@ -41,6 +44,10 @@ while [[ $# -gt 0 ]]; do
      build_master_offline=true
      shift
      ;;
+    --metric)
+      build_metric=true
+      shift
+      ;;
    --no-cache)
      no_cache=true
      shift
@@ -184,6 +191,33 @@ if [[ "$build_master" == true ]]; then
  popd >/dev/null
 fi

+if [[ "$build_metric" == true ]]; then
+  echo ""
+  echo "Building Metric module images..."
+  metric_root="$root/src/metric"
+  pushd "$metric_root/tests" >/dev/null
+  
+  # 检查docker-compose.yml是否存在
+  if [[ ! -f "docker-compose.yml" ]]; then
+    echo "docker-compose.yml not found in $metric_root/tests" >&2
+    build_failed=true
+  else
+    # 构建metric镜像
+    if docker compose build --no-cache; then
+      images_built+=("argus-metric-ftp:latest")
+      images_built+=("argus-metric-prometheus:latest")
+      images_built+=("argus-metric-grafana:latest")
+      images_built+=("argus-metric-test-node:latest")
+      images_built+=("argus-metric-test-gpu-node:latest")
+    else
+      echo "Failed to build metric module images"
+      build_failed=true
+    fi
+  fi
+  
+  popd >/dev/null
+fi
+
 echo "======================================="
 echo "📦 Build Summary"
 echo "======================================="
@@ -210,7 +244,6 @@ if [[ "$build_master_offline" == true ]]; then
  echo ""
  echo "🧳 Master offline wheels 已解压到 $master_offline_dir"
 fi
-
 echo ""
 echo "🚀 Next steps:"
 echo "   ./build/save_images.sh --compress          # 导出镜像"
--- a/build/save_images.sh
+++ b/build/save_images.sh
@@ -68,6 +68,11 @@ declare -A images=(
    ["argus-kibana:latest"]="argus-kibana-latest.tar"
    ["argus-bind9:latest"]="argus-bind9-latest.tar"
    ["argus-master:offline"]="argus-master-offline.tar"
+    ["argus-metric-ftp:latest"]="argus-metric-ftp-latest.tar"
+    ["argus-metric-prometheus:latest"]="argus-metric-prometheus-latest.tar"
+    ["argus-metric-grafana:latest"]="argus-metric-grafana-latest.tar"
+    ["argus-metric-test-node:latest"]="argus-metric-test-node-latest.tar"
+    ["argus-metric-test-gpu-node:latest"]="argus-metric-test-gpu-node-latest.tar"
 )

 # 函数：检查镜像是否存在
--- a/src/alert/README.md
+++ b/src/alert/README.md
@@ -1,13 +1,31 @@
 # Alertmanager

-## 启动示例
+## 构建
+1. 首先设置构建和部署的环境变量, 在项目根目录下执行：
+```bash
+cp src/alert/tests/.env.example src/alert/tests/.env
+```
+
+然后找到复制出来的.env文件，修改环境变量。
+
+2. 使用脚本构建，在项目根目录下执行：

 ```bash
-docker run -d --name alertmanager \
-  -p 9093:9093 \
-  -v /opt/alertmanager/data:/alertmanager \
-  argus-alert:latest
+bash src/alert/alertmanager/build/build.sh
+```
+
+构建成功后，会在项目根目录下生成argus-alertmanager-latest.tar
+
+## 部署
+
+提供docker-compose部署。在src/alert/tests目录下
+```bash
+docker-compose up -d
 ```

 ## 动态配置
-修改alertmanager.yml后，调用`/-/reload`接口可以重新加载配置
+配置文件放在`/private/argus/alert/alertmanager/alertmanager.yml`下，修改alertmanager.yml后，调用`http://alertmanager.alert.argus.com:9093/-/reload`接口(POST)可以重新加载配置.
+
+```bash
+curl -X POST http://localhost:9093/-/reload
+```
--- a/src/alert/alertmanager/build/Dockerfile
+++ b/src/alert/alertmanager/build/Dockerfile
@@ -19,8 +19,11 @@ RUN wget https://github.com/prometheus/alertmanager/releases/download/v${ALERTMA
    rm alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz

 ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
-ENV ARGUS_UID=2133
-ENV ARGUS_GID=2015
+
+ARG ARGUS_UID=2133
+ARG ARGUS_GID=2015
+ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_GID=${ARGUS_GID}

 RUN mkdir -p /usr/share/alertmanager && \
    mkdir -p ${ALERTMANAGER_BASE_PATH} && \
--- a/src/alert/alertmanager/build/build.sh
+++ b/src/alert/alertmanager/build/build.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+set -euo pipefail
+docker pull ubuntu:24.04
+
+source src/alert/tests/.env
+
+docker build \
+  --build-arg ARGUS_UID=${ARGUS_UID} \
+  --build-arg ARGUS_GID=${ARGUS_GID} \
+  -f src/alert/alertmanager/build/Dockerfile \
+  -t argus-alertmanager:latest .
+
+docker save -o argus-alertmanager-latest.tar argus-alertmanager:latest
--- a/src/alert/alertmanager/build/start-am-supervised.sh
+++ b/src/alert/alertmanager/build/start-am-supervised.sh
@@ -18,6 +18,7 @@ DOMAIN=alertmanager.alert.argus.com
 IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}')
 echo "current IP: ${IP}"
 echo "${IP}" > /private/argus/etc/${DOMAIN}
+chmod 755 /private/argus/etc/${DOMAIN}


 echo "[INFO] Starting Alertmanager process..."
--- a/src/alert/alertmanager/config/rule_files/README.md
+++ b/src/alert/alertmanager/config/rule_files/README.md
@@ -55,6 +55,6 @@ alerting:
  alertmanagers:
    - static_configs:
        - targets:
-            - "localhost:9093"   # Alertmanager 地址
+            - "alertmanager.alert.argus.com:9093"   # Alertmanager 地址

 ```
--- a/src/alert/tests/.env
+++ b/src/alert/tests/.env
@@ -0,0 +1,5 @@
+DATA_ROOT=/home/argus/tmp/private/argus
+ARGUS_UID=1048
+ARGUS_GID=1048
+
+USE_INTRANET=false
--- a/src/alert/tests/.env.example
+++ b/src/alert/tests/.env.example
@@ -0,0 +1,5 @@
+DATA_ROOT=/home/argus/tmp/private/argus
+ARGUS_UID=1048
+ARGUS_GID=1048
+
+USE_INTRANET=false
--- a/src/alert/tests/docker-compose.yml
+++ b/src/alert/tests/docker-compose.yml
@@ -1,4 +1,3 @@
-version: '3.8'
 services:
  alertmanager:
    build:
@@ -17,20 +16,21 @@ services:
    ports:
      - "${ARGUS_PORT:-9093}:9093"
    volumes:
-      - ${DATA_ROOT:-./data}/alertmanager:/private/argus/alert/alertmanager
+      - ${DATA_ROOT:-./data}/alert/alertmanager:/private/argus/alert/alertmanager
      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
    networks:
-      - argus-network
+      - argus-debug-net
    restart: unless-stopped
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"
+
 networks:
-  argus-network:
+  argus-debug-net:
    driver: bridge
-    name: argus-network
+    name: argus-debug-net

 volumes:
  alertmanager_data:
--- a/src/metric/tests/docker-compose.yml
+++ b/src/metric/tests/docker-compose.yml
@@ -5,13 +5,6 @@ networks:

 services:
  ftp:
-    build:
-      context: ../ftp/build
-      dockerfile: Dockerfile
-      args:
-        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
-        USE_INTRANET: ${USE_INTRANET:-false}
    image: argus-metric-ftp:latest
    container_name: argus-ftp
    restart: unless-stopped
@@ -41,13 +34,6 @@ services:
        max-file: "3"

  prometheus:
-    build:
-      context: ../prometheus/build
-      dockerfile: Dockerfile
-      args:
-        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
-        USE_INTRANET: ${USE_INTRANET:-false}
    image: argus-metric-prometheus:latest
    container_name: argus-prometheus
    restart: unless-stopped
@@ -73,12 +59,6 @@ services:
        max-file: "3"

  grafana:
-    build:
-      context: ../grafana/build
-      dockerfile: Dockerfile
-      args:
-        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
    image: argus-metric-grafana:latest
    container_name: argus-grafana
    restart: unless-stopped
@@ -109,9 +89,6 @@ services:
        max-file: "3"

  test-node:
-    build:
-      context: ./client-test-node/build
-      dockerfile: Dockerfile
    image: argus-metric-test-node:latest
    container_name: argus-metric-test-node
    hostname: test-metric-node-001
@@ -143,9 +120,6 @@ services:
        max-file: "3"

  test-gpu-node:
-    build:
-      context: ./client-test-gpu-node/build
-      dockerfile: Dockerfile
    image: argus-metric-test-gpu-node:latest
    container_name: argus-metric-test-gpu-node
    hostname: test-metric-gpu-node-001
--- a/src/metric/tests/scripts/01_start_services.sh
+++ b/src/metric/tests/scripts/01_start_services.sh
@@ -3,15 +3,8 @@ set -e

 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"

-# 解析参数
-REBUILD_FLAG=""
-if [[ "$1" == "--rebuild" || "$1" == "-r" ]]; then
-    REBUILD_FLAG="--rebuild"
-    echo "[01] 启用强制重新构建模式"
-fi
-
 echo "[01] 启动所有服务..."
-bash "$SCRIPT_DIR/common/start-all.sh" $REBUILD_FLAG
+bash "$SCRIPT_DIR/common/start-all.sh"

 echo "[01] 等待服务就绪..."
 sleep 5
--- a/src/metric/tests/scripts/04_test_gpu_node_install.sh
+++ b/src/metric/tests/scripts/04_test_gpu_node_install.sh
@@ -1,6 +1,9 @@
 #!/bin/bash
 set -e

+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+COMMON_DIR="$SCRIPT_DIR/common"
+
 FTP_SERVER="${FTP_SERVER:-172.30.0.40}"
 FTP_USER="${FTP_USER:-ftpuser}"
 FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
@@ -8,26 +11,37 @@ FTP_PORT="${FTP_PORT:-21}"

 FTP_HOST="${FTP_SERVER}"

-echo "[03] 进入测试节点执行安装..."
-echo "[03] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
+echo "[04] 检测GPU环境..."
+# 检测GPU环境
+if bash "$COMMON_DIR/check-gpu.sh"; then
+    echo "[04] GPU环境可用，继续执行GPU节点安装"
+    GPU_AVAILABLE=true
+else
+    echo "[04] GPU环境不可用，跳过GPU节点安装"
+    GPU_AVAILABLE=false
+    exit 0
+fi
+
+echo "[04] 进入测试节点执行安装..."
+echo "[04] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"

 docker exec argus-metric-test-gpu-node bash -c "
 set -e

 if ! command -v curl &>/dev/null; then
-    echo '[03] curl 未安装，正在安装...'
+    echo '[04] curl 未安装，正在安装...'
    apt-get update && apt-get install -y curl
 fi

 cd /tmp
-echo '[03] 下载 setup.sh...'
+echo '[04] 下载 setup.sh...'
 curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_HOST}:${FTP_PORT}/setup.sh -o setup.sh

-echo '[03] 执行安装...'
+echo '[04] 执行安装...'
 chmod +x setup.sh
 bash setup.sh --server ${FTP_HOST} --user ${FTP_USER} --password '${FTP_PASSWORD}' --port ${FTP_PORT}

-echo '[03] 安装完成'
+echo '[04] 安装完成'
 "

-echo "[03] 完成"
+echo "[04] 完成"
--- a/src/metric/tests/scripts/common/check-gpu.sh
+++ b/src/metric/tests/scripts/common/check-gpu.sh
@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# GPU环境检测脚本
+# 检测系统是否有NVIDIA GPU硬件
+
+set -e
+
+# 检测函数
+check_gpu_support() {
+    echo "检测GPU环境..."
+    
+    # 方法1: 检测GPU设备文件
+    if ls /dev/nvidia* &>/dev/null; then
+        echo "✓ 检测到NVIDIA GPU设备文件"
+        return 0
+    fi
+    
+    # 方法2: 检测lspci中的NVIDIA设备（Linux）
+    if command -v lspci &> /dev/null; then
+        if lspci | grep -i nvidia &> /dev/null; then
+            echo "✓ 检测到NVIDIA GPU硬件"
+            return 0
+        fi
+    fi
+    
+    # 方法3: 检测nvidia-smi
+    if command -v nvidia-smi &> /dev/null; then
+        if nvidia-smi &> /dev/null; then
+            echo "✓ 检测到NVIDIA GPU硬件"
+            return 0
+        fi
+    fi
+    
+    echo "✗ 未检测到NVIDIA GPU硬件"
+    return 1
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "  GPU环境检测"
+    echo "=========================================="
+    echo ""
+    
+    if check_gpu_support; then
+        echo ""
+        echo "结果: GPU环境可用"
+        exit 0
+    else
+        echo ""
+        echo "结果: GPU环境不可用，将跳过GPU相关服务"
+        exit 1
+    fi
+}
+
+# 如果直接运行此脚本
+if [ "${BASH_SOURCE[0]}" = "${0}" ]; then
+    main "$@"
+fi
--- a/src/metric/tests/scripts/common/start-all.sh
+++ b/src/metric/tests/scripts/common/start-all.sh
@@ -1,7 +1,8 @@
 #!/bin/bash

 # 一键启动脚本
-# 用于初始化目录、构建镜像并启动所有服务
+# 用于初始化目录并启动所有服务
+# 镜像构建已移至 build/build_images.sh

 set -e

@@ -9,12 +10,6 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
 cd "$TEST_DIR"

-# 解析参数
-FORCE_REBUILD=false
-if [[ "$1" == "--rebuild" ]]; then
-    FORCE_REBUILD=true
-fi
-
 echo "=========================================="
 echo "  Argus Metrics 一键启动脚本"
 echo "=========================================="
@@ -37,26 +32,6 @@ echo "使用: docker compose"
 echo "Compose 文件: $TEST_DIR/docker-compose.yml"
 echo ""

-# 检查必要的构建目录
-echo "检查构建目录..."
-BUILD_DIRS=(
-    "../ftp/build"
-    "../prometheus/build"
-    "../grafana/build"
-    "client-test-node/build"
-    "client-test-gpu-node/build"
-)
-
-for dir in "${BUILD_DIRS[@]}"; do
-    if [ ! -d "$dir" ]; then
-        echo "错误: 构建目录不存在: $dir"
-        echo "完整路径: $(cd "$(dirname "$dir")" 2>/dev/null && pwd)/$(basename "$dir")"
-        exit 1
-    else
-        echo "  ✓ 找到: $dir"
-    fi
-done
-echo ""

 # 检查并创建 .env 文件
 if [ ! -f .env ]; then
@@ -84,118 +59,65 @@ echo "1. 初始化目录结构..."
 bash "$SCRIPT_DIR/init-directories.sh"

 echo ""
-echo "2. 准备 Docker 镜像..."
-
-# 检查镜像是否存在
-IMAGE_CACHE_DIR="$TEST_DIR/images-cache"
-IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest" "argus-metric-test-node:latest" "argus-metric-test-gpu-node:latest")
-all_images_exist=true
-
-for image in "${IMAGES[@]}"; do
-    if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
-        all_images_exist=false
-        break
-    fi
-done
-
-if $FORCE_REBUILD; then
-    echo "强制重新构建镜像（--rebuild 模式）..."
-    cd "$TEST_DIR"
-    docker compose build --no-cache
-    echo "镜像重新构建完成"
-elif $all_images_exist; then
-    echo "所有镜像已存在，跳过构建"
+echo "2. 检测GPU环境..."
+# 检测GPU环境
+if bash "$SCRIPT_DIR/check-gpu.sh"; then
+    echo "GPU环境可用，将启动GPU节点"
+    GPU_AVAILABLE=true
 else
-    echo "检测到缺失镜像，尝试从缓存加载..."
-    
-    # 尝试从缓存加载
-    loaded_from_cache=false
-    if [ -d "$IMAGE_CACHE_DIR" ]; then
-        for image in "${IMAGES[@]}"; do
-            if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
-                # 镜像不存在，尝试加载
-                case "$image" in
-                    "argus-metric-ftp:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-ftp.tar"
-                        ;;
-                    "argus-metric-prometheus:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-prometheus.tar"
-                        ;;
-                    "argus-metric-grafana:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-grafana.tar"
-                        ;;
-                    "argus-metric-test-node:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-test-node.tar"
-                        ;;
-                    "argus-metric-test-gpu-node:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-test-gpu-node.tar"
-                        ;;
-                esac
-                
-                if [ -f "$cache_file" ]; then
-                    echo "  从缓存加载: $image"
-                    docker load -i "$cache_file"
-                    loaded_from_cache=true
-                fi
-            fi
-        done
-    fi
-    
-    # 检查加载后是否还有缺失的镜像
-    need_build=false
-    for image in "${IMAGES[@]}"; do
-        if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
-            need_build=true
-            break
-        fi
-    done
-    
-    if $need_build; then
-        echo ""
-        echo "部分镜像缺失，开始构建..."
-        echo "工作目录: $(pwd)"
-        cd "$TEST_DIR"
-        docker compose build --no-cache
-        
-        # 询问是否保存镜像
-        echo ""
-        read -p "是否保存镜像到缓存以便下次快速启动? (Y/n): " -n 1 -r
-        echo
-        if [[ ! $REPLY =~ ^[Nn]$ ]]; then
-            mkdir -p "$IMAGE_CACHE_DIR"
-            echo "保存镜像到缓存..."
-            for image in "${IMAGES[@]}"; do
-                case "$image" in
-                    "argus-metric-ftp:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-ftp.tar" "$image" && echo "  已保存: argus-ftp.tar"
-                        ;;
-                    "argus-metric-prometheus:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-prometheus.tar" "$image" && echo "  已保存: argus-prometheus.tar"
-                        ;;
-                    "argus-metric-grafana:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-grafana.tar" "$image" && echo "  已保存: argus-grafana.tar"
-                        ;;
-                    "argus-metric-test-node:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-test-node.tar" "$image" && echo "  已保存: argus-test-node.tar"
-                        ;;
-                    "argus-metric-test-gpu-node:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-test-gpu-node.tar" "$image" && echo "  已保存: argus-test-gpu-node.tar"
-                        ;;
-                esac
-            done
-            echo "镜像已保存到: $IMAGE_CACHE_DIR/"
-        fi
-    elif $loaded_from_cache; then
-        echo ""
-        echo "所有镜像已从缓存加载完成！"
-    fi
+    echo "GPU环境不可用，跳过GPU节点"
+    GPU_AVAILABLE=false
 fi

 echo ""
-echo "3. 启动基础服务..."
+echo "3. 检查 Docker 镜像..."
+
+# 检查必要的镜像是否存在
+BASE_IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest" "argus-metric-test-node:latest")
+GPU_IMAGES=("argus-metric-test-gpu-node:latest")
+
+# 先检查基础镜像
+missing_images=()
+for image in "${BASE_IMAGES[@]}"; do
+    if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
+        missing_images+=("$image")
+    fi
+done
+
+# 检查GPU镜像（如果GPU环境可用）
+if [ "$GPU_AVAILABLE" = true ]; then
+    for image in "${GPU_IMAGES[@]}"; do
+        if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
+            missing_images+=("$image")
+        fi
+    done
+fi
+
+if [ ${#missing_images[@]} -gt 0 ]; then
+    echo "以下镜像缺失，请先运行 build/build_images.sh 构建镜像："
+    for image in "${missing_images[@]}"; do
+        echo "   • $image"
+    done
+    echo ""
+    echo "构建命令："
+    echo "   ./build/build_images.sh --metric"
+    exit 1
+else
+    echo "所有必要镜像已存在"
+fi
+
+echo ""
+echo "4. 启动基础服务..."
 cd "$TEST_DIR"
-# 启动除GPU节点外的所有服务
-docker compose up -d ftp prometheus grafana test-node test-gpu-node
+
+# 根据GPU环境决定启动的服务
+if [ "$GPU_AVAILABLE" = true ]; then
+    echo "启动所有服务（包括GPU节点）..."
+    docker compose up -d ftp prometheus grafana test-node test-gpu-node
+else
+    echo "启动基础服务（跳过GPU节点）..."
+    docker compose up -d ftp prometheus grafana test-node
+fi

 echo ""
 echo "4. 等待服务启动..."
--- a/src/sys/tests/docker-compose.yml
+++ b/src/sys/tests/docker-compose.yml
@@ -1,7 +1,8 @@
-version: "3.8"
+-version: "3.8"

 networks:
  default:
+    external: true
    name: argus-sys-net
    driver: bridge
    ipam:
@@ -137,3 +138,156 @@ services:
    ports:
      - "2021:2020"
    restart: unless-stopped
+
+  ftp:
+    image: argus-metric-ftp:latest
+    container_name: argus-ftp
+    restart: unless-stopped
+    environment:
+      - TZ=Asia/Shanghai
+      - FTP_BASE_PATH=/private/argus/ftp
+      - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
+      - DOMAIN=${FTP_DOMAIN:-ftp.metric.argus.com}
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    ports:
+      - "${FTP_PORT:-21}:21"
+      - "${FTP_DATA_PORT:-20}:20"
+      - "21100-21110:21100-21110"
+    volumes:
+      - ./private/argus/metric/ftp:/private/argus/ftp
+      - ./private/argus/etc:/private/argus/etc
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    networks:
+      default:
+        ipv4_address: 172.29.0.40
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  prometheus:
+    image: argus-metric-prometheus:latest
+    container_name: argus-prometheus
+    restart: unless-stopped
+    environment:
+      - TZ=Asia/Shanghai
+      - PROMETHEUS_BASE_PATH=/private/argus/metric/prometheus
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    ports:
+      - "${PROMETHEUS_PORT:-9090}:9090"
+    volumes:
+      - ./private/argus/metric/prometheus:/private/argus/metric/prometheus
+      - ./private/argus/etc:/private/argus/etc
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    networks:
+      default:
+        ipv4_address: 172.29.0.41
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  grafana:
+    image: argus-metric-grafana:latest
+    container_name: argus-grafana
+    restart: unless-stopped
+    environment:
+      - TZ=Asia/Shanghai
+      - GRAFANA_BASE_PATH=/private/argus/metric/grafana
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      - GF_SERVER_HTTP_PORT=3000
+      - GF_LOG_LEVEL=warn
+      - GF_LOG_MODE=console
+    ports:
+      - "${GRAFANA_PORT:-3000}:3000"
+    volumes:
+      - ./private/argus/metric/grafana:/private/argus/metric/grafana
+      - ./private/argus/etc:/private/argus/etc
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    networks:
+      default:
+        ipv4_address: 172.29.0.42
+    depends_on:
+      - prometheus
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  test-node:
+    image: argus-metric-test-node:latest
+    container_name: argus-metric-test-node
+    hostname: test-metric-node-001
+    restart: unless-stopped
+    privileged: true
+    depends_on:
+      - ftp
+      - prometheus
+    environment:
+      - TZ=Asia/Shanghai
+      - DEBIAN_FRONTEND=noninteractive
+      - FTP_DOMAIN=${FTP_DOMAIN:-ftp.metric.argus.com}
+      - FTP_SERVER=${FTP_SERVER:-172.29.0.40}
+      - FTP_USER=${FTP_USER:-ftpuser}
+      - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
+      - FTP_PORT=${FTP_PORT:-21}
+    volumes:
+      - ./private/argus/agent:/private/argus/agent
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    command: sleep infinity
+    networks:
+      default:
+        ipv4_address: 172.29.0.50
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  test-gpu-node:
+    image: argus-metric-test-gpu-node:latest
+    container_name: argus-metric-test-gpu-node
+    hostname: test-metric-gpu-node-001
+    restart: unless-stopped
+    privileged: true
+    runtime: nvidia
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: 
+                - gpu
+    depends_on:
+      - ftp
+      - prometheus
+    environment:
+      - TZ=Asia/Shanghai
+      - DEBIAN_FRONTEND=noninteractive
+      - NVIDIA_VISIBLE_DEVICES=all
+      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+      - GPU_MODE=gpu
+    volumes:
+      - ./private/argus/agent:/private/argus/agent
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    command: sleep infinity
+    networks:
+      default:
+        ipv4_address: 172.29.0.51
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
--- a/src/sys/tests/scripts/01_bootstrap.sh
+++ b/src/sys/tests/scripts/01_bootstrap.sh
@@ -27,17 +27,34 @@ mkdir -p \
  "$PRIVATE_CORE/argus/bind" \
  "$PRIVATE_CORE/argus/master" \
  "$PRIVATE_CORE/argus/metric/prometheus" \
+  "$PRIVATE_CORE/argus/metric/ftp/share" \
+  "$PRIVATE_CORE/argus/metric/grafana/data" \
+  "$PRIVATE_CORE/argus/metric/grafana/logs" \
+  "$PRIVATE_CORE/argus/metric/grafana/plugins" \
+  "$PRIVATE_CORE/argus/metric/grafana/provisioning/datasources" \
+  "$PRIVATE_CORE/argus/metric/grafana/provisioning/dashboards" \
+  "$PRIVATE_CORE/argus/metric/grafana/data/sessions" \
+  "$PRIVATE_CORE/argus/metric/grafana/data/dashboards" \
+  "$PRIVATE_CORE/argus/metric/grafana/config" \
+  "$PRIVATE_CORE/argus/metric/prometheus/data" \
+  "$PRIVATE_CORE/argus/metric/prometheus/rules" \
+  "$PRIVATE_CORE/argus/metric/prometheus/targets" \
+  "$PRIVATE_CORE/argus/agent" \
  "$PRIVATE_CORE/argus/log/elasticsearch" \
  "$PRIVATE_CORE/argus/log/kibana" \
  "$PRIVATE_NODEA/argus/agent/dev-yyrshare-nbnyx10-cp2f-pod-0/health" \
  "$PRIVATE_NODEB/argus/agent/dev-yyrshare-uuuu10-ep2f-pod-0/health" \
  "$TMP_DIR"

-# Align ownership for supervisor-managed services (ES/Kibana expect UID/GID inside container)
+# Align ownership for supervisor-managed services (ES/Kibana/Grafana expect UID/GID inside container)
 echo "[INFO] Fixing ownership for core private directories..."
 chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" \
  "$PRIVATE_CORE/argus/log/elasticsearch" \
  "$PRIVATE_CORE/argus/log/kibana" \
+  "$PRIVATE_CORE/argus/metric/grafana" \
+  "$PRIVATE_CORE/argus/metric/prometheus" \
+  "$PRIVATE_CORE/argus/metric/ftp" \
+  "$PRIVATE_CORE/argus/agent" \
  "$PRIVATE_CORE/argus/etc" 2>/dev/null || true

 echo "[INFO] Distributing update-dns.sh for core services (bind/master/es/kibana)"
@@ -55,6 +72,11 @@ ensure_image "argus-elasticsearch:latest"
 ensure_image "argus-kibana:latest"
 ensure_image "argus-bind9:latest"
 ensure_image "argus-master:latest"
+ensure_image "argus-metric-ftp:latest"
+ensure_image "argus-metric-prometheus:latest"
+ensure_image "argus-metric-grafana:latest"
+ensure_image "argus-metric-test-node:latest"
+ensure_image "argus-metric-test-gpu-node:latest"

 echo "[INFO] Building agent binary..."
 pushd "$REPO_ROOT/src/agent" >/dev/null
@@ -68,10 +90,44 @@ if [[ ! -x "$AGENT_BIN" ]]; then
 fi
 echo "$AGENT_BIN" > "$TMP_DIR/agent_binary_path"

-echo "[INFO] Writing .env with UID/GID"
+# 检测GPU环境
+echo "[INFO] 检测GPU环境..."
+GPU_CHECK_SCRIPT="$REPO_ROOT/src/metric/tests/scripts/common/check-gpu.sh"
+if [ -f "$GPU_CHECK_SCRIPT" ]; then
+    if bash "$GPU_CHECK_SCRIPT" >/dev/null 2>&1; then
+        echo "[INFO] GPU环境可用，将启动test-gpu-node容器"
+        GPU_AVAILABLE=true
+    else
+        echo "[INFO] GPU环境不可用，跳过test-gpu-node容器"
+        GPU_AVAILABLE=false
+    fi
+else
+    echo "[WARN] 未找到GPU检测脚本: $GPU_CHECK_SCRIPT，跳过GPU检测"
+    GPU_AVAILABLE=false
+fi
+
+echo "[INFO] Writing .env with UID/GID and metric configuration"
 cat > "$TEST_ROOT/.env" <<EOF
 ARGUS_BUILD_UID=$ARGUS_BUILD_UID
 ARGUS_BUILD_GID=$ARGUS_BUILD_GID
+
+# GPU 配置
+GPU_AVAILABLE=$GPU_AVAILABLE
+
+# FTP 配置
+FTP_PORT=21
+FTP_DATA_PORT=20
+FTP_PASSWORD=ZGClab1234!
+FTP_DOMAIN=ftp.metric.argus.com
+
+# Prometheus 配置
+PROMETHEUS_PORT=9090
+
+# Grafana 配置
+GRAFANA_PORT=3000
+
+# 网络配置
+USE_INTRANET=false
 EOF

 echo "[OK] Bootstrap completed"
--- a/src/sys/tests/scripts/02_up.sh
+++ b/src/sys/tests/scripts/02_up.sh
@@ -3,6 +3,7 @@ set -euo pipefail

 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$TEST_ROOT/../../.." && pwd)"

 compose() {
  if docker compose version >/dev/null 2>&1; then
@@ -13,10 +14,40 @@ compose() {
 }

 echo "[INFO] Bringing up system stack..."
+
+# 检测GPU环境
+echo "[INFO] 检测GPU环境..."
+GPU_CHECK_SCRIPT="$REPO_ROOT/src/metric/tests/scripts/common/check-gpu.sh"
+if [ -f "$GPU_CHECK_SCRIPT" ]; then
+    if bash "$GPU_CHECK_SCRIPT" >/dev/null 2>&1; then
+        echo "[INFO] GPU环境可用，将启动GPU测试节点"
+        GPU_AVAILABLE=true
+    else
+        echo "[INFO] GPU环境不可用，将跳过GPU测试节点"
+        GPU_AVAILABLE=false
+    fi
+else
+    echo "[WARN] 未找到GPU检测脚本: $GPU_CHECK_SCRIPT，跳过GPU检测"
+    GPU_AVAILABLE=false
+fi
+
 pushd "$TEST_ROOT" >/dev/null
 compose -p argus-sys down --remove-orphans || true
-compose -p argus-sys up -d
+
+# 根据GPU可用性决定启动的服务
+if [ "$GPU_AVAILABLE" = true ]; then
+    echo "[INFO] 启动所有服务（包括test-gpu-node）..."
+    compose -p argus-sys up -d
+else
+    echo "[INFO] 启动基础服务（跳过test-gpu-node）..."
+    compose -p argus-sys up -d --scale test-gpu-node=0
+fi
+
 popd >/dev/null

-echo "[OK] Services started: master:32300 es:9200 kibana:5601 node-a:2020 node-b:2021"
+if [ "$GPU_AVAILABLE" = true ]; then
+    echo "[OK] Services started: master:32300 es:9200 kibana:5601 node-a:2020 node-b:2021 test-gpu-node:172.29.0.51"
+else
+    echo "[OK] Services started: master:32300 es:9200 kibana:5601 node-a:2020 node-b:2021 (test-gpu-node skipped)"
+fi

--- a/src/sys/tests/scripts/05_publish_artifact.sh
+++ b/src/sys/tests/scripts/05_publish_artifact.sh
@@ -0,0 +1,61 @@
+#!/bin/bash
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+TEST_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$TEST_DIR/../../.." && pwd)"
+PLUGIN_DIR="$REPO_ROOT/src/metric/client-plugins/all-in-one-full"
+
+# 加载 .env
+if [ -f "$TEST_DIR/.env" ]; then
+    source "$TEST_DIR/.env"
+fi
+
+# 检测容器挂载目录
+if docker ps --format '{{.Names}}' | grep -q '^argus-ftp$'; then
+    FTP_MOUNT=$(docker inspect argus-ftp --format '{{range .Mounts}}{{if eq .Destination "/private/argus/ftp"}}{{.Source}}{{end}}{{end}}')
+    OUTPUT_DIR="${FTP_MOUNT}/share"
+    echo "[02] 容器挂载: $OUTPUT_DIR"
+else
+    OUTPUT_DIR="${DATA_ROOT:-$TEST_DIR/private}/ftp/share"
+    echo "[02] 默认路径: $OUTPUT_DIR"
+fi
+
+OWNER="${ARGUS_BUILD_UID:-2133}:${ARGUS_BUILD_GID:-2015}"
+
+cd "$PLUGIN_DIR"
+
+echo "[02] 递增版本号..."
+bash scripts/version-manager.sh bump minor
+
+VERSION_FILE="config/VERSION"
+if [ ! -f "$VERSION_FILE" ]; then
+    echo "[02] 错误: 未找到 $VERSION_FILE"
+    exit 1
+fi
+
+VERSION=$(cat "$VERSION_FILE" | tr -d '[:space:]')
+echo "[02] 新版本: $VERSION"
+
+echo "[02] 构建安装包..."
+bash scripts/package_artifact.sh --force
+
+echo "[02] 发布到 FTP: $OUTPUT_DIR"
+sudo bash scripts/publish_artifact.sh "$VERSION" --output-dir "$OUTPUT_DIR" --owner "$OWNER"
+
+echo "[02] 设置文件权限..."
+# 设置所有者
+sudo chown -R "$OWNER" "$OUTPUT_DIR"
+# 设置目录权限为 755 (rwxr-xr-x)
+sudo find "$OUTPUT_DIR" -type d -exec chmod 755 {} \;
+# 设置文件权限为 644 (rw-r--r--)
+sudo find "$OUTPUT_DIR" -type f -exec chmod 644 {} \;
+# 特别处理 .sh 文件，给予执行权限 755
+sudo find "$OUTPUT_DIR" -type f -name "*.sh" -exec chmod 755 {} \;
+echo "[02] 权限设置完成 (UID:GID=$OWNER, dirs=755, files=644, scripts=755)"
+
+echo "[02] 发布完成，验证文件..."
+ls -lh "$OUTPUT_DIR"
+
+echo "[02] 完成"
+
--- a/src/sys/tests/scripts/06_test_node_install.sh
+++ b/src/sys/tests/scripts/06_test_node_install.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+set -e
+
+FTP_SERVER="${FTP_SERVER:-172.30.0.40}"
+FTP_USER="${FTP_USER:-ftpuser}"
+FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+FTP_PORT="${FTP_PORT:-21}"
+
+FTP_HOST="${FTP_SERVER}"
+
+echo "[03] 进入测试节点执行安装..."
+echo "[03] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
+
+docker exec argus-metric-test-node bash -c "
+set -e
+
+if ! command -v curl &>/dev/null; then
+    echo '[03] curl 未安装，正在安装...'
+    apt-get update && apt-get install -y curl
+fi
+
+cd /tmp
+echo '[03] 下载 setup.sh...'
+curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_HOST}:${FTP_PORT}/setup.sh -o setup.sh
+
+echo '[03] 执行安装...'
+chmod +x setup.sh
+bash setup.sh --server ${FTP_HOST} --user ${FTP_USER} --password '${FTP_PASSWORD}' --port ${FTP_PORT}
+
+echo '[03] 安装完成'
+"
+
+echo "[03] 完成"
--- a/src/sys/tests/scripts/07_test_gpu_node_install.sh
+++ b/src/sys/tests/scripts/07_test_gpu_node_install.sh
@@ -0,0 +1,55 @@
+#!/bin/bash
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$TEST_ROOT/../../.." && pwd)"
+
+FTP_SERVER="${FTP_SERVER:-172.29.0.40}"
+FTP_USER="${FTP_USER:-ftpuser}"
+FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+FTP_PORT="${FTP_PORT:-21}"
+
+FTP_HOST="${FTP_SERVER}"
+
+echo "[04] 检测GPU环境..."
+# 检测GPU环境
+GPU_CHECK_SCRIPT="$REPO_ROOT/metric/tests/scripts/common/check-gpu.sh"
+if [ -f "$GPU_CHECK_SCRIPT" ]; then
+    if bash "$GPU_CHECK_SCRIPT"; then
+        echo "[04] GPU环境可用，继续执行GPU节点安装"
+        GPU_AVAILABLE=true
+    else
+        echo "[04] GPU环境不可用，跳过GPU节点安装"
+        GPU_AVAILABLE=false
+        exit 0
+    fi
+else
+    echo "[04] 未找到GPU检测脚本: $GPU_CHECK_SCRIPT，跳过GPU节点安装"
+    GPU_AVAILABLE=false
+    exit 0
+fi
+
+echo "[04] 进入测试节点执行安装..."
+echo "[04] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
+
+docker exec argus-metric-test-gpu-node bash -c "
+set -e
+
+if ! command -v curl &>/dev/null; then
+    echo '[04] curl 未安装，正在安装...'
+    apt-get update && apt-get install -y curl
+fi
+
+cd /tmp
+echo '[04] 下载 setup.sh...'
+curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_HOST}:${FTP_PORT}/setup.sh -o setup.sh
+
+echo '[04] 执行安装...'
+chmod +x setup.sh
+bash setup.sh --server ${FTP_HOST} --user ${FTP_USER} --password '${FTP_PASSWORD}' --port ${FTP_PORT}
+
+echo '[04] 安装完成'
+"
+
+echo "[04] 完成"
--- a/src/sys/tests/scripts/08_check_services_installed.sh
+++ b/src/sys/tests/scripts/08_check_services_installed.sh
@@ -0,0 +1,96 @@
+#!/bin/bash
+set -e
+
+echo "[04] 验证安装结果 - 检查监控端口..."
+echo "=========================================="
+
+# 检查容器是否运行
+if ! docker ps --format '{{.Names}}' | grep -q '^argus-metric-test-node$'; then
+    echo "错误: 容器 argus-metric-test-node 未运行"
+    exit 1
+fi
+
+ERRORS=0
+
+# ==================== 检查监听端口 ====================
+echo ""
+echo "[1] 检查监听端口..."
+echo "----------------------------------------"
+CHECK_RESULT=$(docker exec argus-metric-test-node bash -c '
+if command -v netstat >/dev/null 2>&1; then
+    echo "使用 netstat 检查端口:"
+    if netstat -tlnp 2>/dev/null | grep -E ":(9100|9400|2020)"; then
+        echo "✓ 找到监控端口"
+        exit 0
+    else
+        echo "✗ 未找到监控端口 (9100/9400/2020)"
+        exit 1
+    fi
+elif command -v ss >/dev/null 2>&1; then
+    echo "使用 ss 检查端口:"
+    if ss -tlnp 2>/dev/null | grep -E ":(9100|9400|2020)"; then
+        echo "✓ 找到监控端口"
+        exit 0
+    else
+        echo "✗ 未找到监控端口 (9100/9400/2020)"
+        exit 1
+    fi
+elif command -v lsof >/dev/null 2>&1; then
+    echo "使用 lsof 检查端口:"
+    if lsof -i :9100 -i :9400 -i :2020 2>/dev/null | grep LISTEN; then
+        echo "✓ 找到监控端口"
+        exit 0
+    else
+        echo "✗ 未找到监控端口 (9100/9400/2020)"
+        exit 1
+    fi
+else
+    echo "? 没有可用的端口检查工具 (netstat/ss/lsof)，跳过此检查"
+    exit 0
+fi
+')
+echo "$CHECK_RESULT"
+# 只有在明确失败时才计入错误（exit 1），没有工具（exit 0）不算错误
+if echo "$CHECK_RESULT" | grep -q "✗ 未找到监控端口"; then
+    ERRORS=$((ERRORS + 1))
+fi
+
+# ==================== 测试端口连通性 ====================
+echo ""
+echo "[2] 测试端口连通性..."
+echo "----------------------------------------"
+docker exec argus-metric-test-node bash -c '
+if command -v curl >/dev/null 2>&1; then
+    FAILED=0
+    for port in 9100 9400 2020; do
+        echo -n "端口 $port: "
+        if curl -s --connect-timeout 2 "http://localhost:$port/metrics" > /dev/null 2>&1; then
+            echo "✓ 可访问 (/metrics)"
+        elif curl -s --connect-timeout 2 "http://localhost:$port/" > /dev/null 2>&1; then
+            echo "✓ 可访问 (根路径)"
+        else
+            echo "✗ 不可访问"
+            FAILED=$((FAILED + 1))
+        fi
+    done
+    exit $FAILED
+else
+    echo "? curl 不可用，跳过连通性测试"
+    exit 0
+fi
+' || ERRORS=$((ERRORS + 1))
+
+echo ""
+echo "=========================================="
+if [ $ERRORS -eq 0 ]; then
+    echo "✓ [04] 验证完成 - 所有端口检查通过"
+else
+    echo "✗ [04] 验证失败 - 发现 $ERRORS 个问题"
+    echo ""
+    echo "调试建议："
+    echo "  1. 进入容器检查: docker exec -it argus-metric-test-node bash"
+    echo "  2. 查看进程: docker exec argus-metric-test-node ps aux"
+    echo "  3. 查看日志: docker exec argus-metric-test-node cat /tmp/argus_install.log"
+    exit 1
+fi
+echo "=========================================="
--- a/src/sys/tests/scripts/09_write_health_and_assert.sh
+++ b/src/sys/tests/scripts/09_write_health_and_assert.sh
--- a/src/sys/tests/scripts/10_logs_send_and_assert.sh
+++ b/src/sys/tests/scripts/10_logs_send_and_assert.sh
--- a/src/sys/tests/scripts/11_restart_agent_reregister.sh
+++ b/src/sys/tests/scripts/11_restart_agent_reregister.sh
--- a/src/sys/tests/scripts/12_down.sh
+++ b/src/sys/tests/scripts/12_down.sh
--- a/src/web/README.md
+++ b/src/web/README.md
@@ -1,12 +1,34 @@
 # Argus-web

-架构：React + Vite + Mantine
+前端页面架构：React + Vite + Mantine

+该模块分为两个部分，argus-web-frontend和argus-web-proxy。其中argus-web-frontend负责前端页面展示，argus-web-proxy负责反向代理，实现对其他网站的反向代理功能

-## 打包部署
+## 构建
+在构建前需要设置构建和部署的环境变量。根目录下运行：
+```bash
+cp src/web/tests/.env.example src/web/tests/.env
+```
+修改.env的内容。
+
+### argus-web-frontend
 根目录下运行
 ```bash
 bash src/web/buld_tools/frontend/build.sh
 ```
+构建成功后，会在根目录下有一个打包好的tar包argus-web-frontend-latest.tar。

+### argus-web-proxy
+根目录下运行
+```bash
+bash src/web/build_tools/proxy/build.sh
+```
+构建成功后，会在根目录下有一个打包好的tar包argus-web-proxy-latest.tar。

+## 部署
+
+提供docker-compose部署。在src/web/tests目录下
+```bash
+docker-compose up -d
+```
+会同时启动argus-web-frontend和argus-web-proxy两个容器服务。
--- a/src/web/build_tools/frontend/Dockerfile
+++ b/src/web/build_tools/frontend/Dockerfile
@@ -24,8 +24,10 @@ RUN apt-get update && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

 ENV FRONTEND_BASE_PATH=/private/argus/web/frontend
-ENV ARGUS_UID=2133
-ENV ARGUS_GID=2015
+ARG ARGUS_UID=2133
+ARG ARGUS_GID=2015
+ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_GID=${ARGUS_GID}

 RUN mkdir -p ${FRONTEND_BASE_PATH} && \
    mkdir -p /private/argus/etc
@@ -82,7 +84,7 @@ COPY src/web/build_tools/frontend/health-check.sh /usr/local/bin/health-check.sh
 RUN chmod +x /usr/local/bin/health-check.sh

 # 暴露端口
-EXPOSE 80
+EXPOSE 8080

 # 保持 root 用户，由 supervisor 控制 user 切换
 USER root
--- a/src/web/build_tools/frontend/build.sh
+++ b/src/web/build_tools/frontend/build.sh
@@ -1,4 +1,10 @@
 docker pull node:20
 docker pull ubuntu:24.04
-docker build -f src/web/build_tools/frontend/Dockerfile -t argus-web:0.1.1 .
-rm -f argus-web-0.1.1.tar && sudo docker image save argus-web:0.1.1 > argus-web-0.1.1.tar
+
+source src/web/tests/.env
+
+docker build \
+  --build-arg ARGUS_UID=${ARGUS_UID} \
+  --build-arg ARGUS_GID=${ARGUS_GID} \
+  -f src/web/build_tools/frontend/Dockerfile -t argus-web-frontend:latest .
+docker save -o argus-web-frontend-latest.tar argus-web-frontend:latest
--- a/src/web/build_tools/frontend/health-check.sh
+++ b/src/web/build_tools/frontend/health-check.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 set -euo pipefail

-URL="http://127.0.0.1:80"
+URL="http://127.0.0.1:8080"

 echo "[INFO] Starting Argus web health check loop for $URL..."

--- a/src/web/build_tools/frontend/nginx.conf
+++ b/src/web/build_tools/frontend/nginx.conf
@@ -12,7 +12,7 @@ http {

    # React 前端服务
    server {
-        listen 80;
+        listen 8080;
        server_name web.argus.com;

        root /usr/share/nginx/html;
@@ -25,32 +25,4 @@ http {
    }


-    # Master 服务，需要增加 CORS 支持
-    server {
-    listen 80;
-    server_name master.argus.com;
-
-    location / {
-        proxy_pass http://master.argus.com;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-
-        # CORS 支持
-        add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
-        add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
-        add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
-
-        if ($request_method = OPTIONS) {
-            add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
-            add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
-            add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
-            add_header 'Content-Length' 0;
-            add_header 'Content-Type' 'text/plain';
-            return 204;
-        }
-    }
-}
-
 }
--- a/src/web/build_tools/frontend/start-web-supervised.sh
+++ b/src/web/build_tools/frontend/start-web-supervised.sh
@@ -8,20 +8,12 @@ DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
 DOMAIN=web.argus.com
 WEB_DOMAIN_FILE="${DNS_DIR}/${DOMAIN}"
 RUNTIME_USER="${ARGUS_RUNTIME_USER:-argus}"
-RUNTIME_UID="${ARGUS_BUILD_UID:-2133}"
-RUNTIME_GID="${ARGUS_BUILD_GID:-2015}"
+RUNTIME_UID="${ARGUS_UID:-2133}"
+RUNTIME_GID="${ARGUS_GID:-2015}"

 mkdir -p "$DNS_DIR"
 chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true

-if [[ -x "$DNS_SCRIPT" ]]; then
-  echo "[INFO] Running update-dns.sh before master starts"
-  # 若脚本存在则执行，保证容器使用 bind 作为 DNS
-  "$DNS_SCRIPT" || echo "[WARN] update-dns.sh execution failed"
-else
-  echo "[WARN] DNS update script not found or not executable: $DNS_SCRIPT"
-fi
-

 # 记录容器 IP
 IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}' || true)
@@ -32,6 +24,7 @@ if [[ -n "${IP}" ]]; then
 else
  echo "[WARN] Failed to detect web IP via ifconfig"
 fi
+chmod 755 "$WEB_DOMAIN_FILE"

 echo "[INFO] Launching nginx..."

--- a/src/web/build_tools/proxy/Dockerfile
+++ b/src/web/build_tools/proxy/Dockerfile
@@ -8,8 +8,10 @@ RUN apt-get update && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

 ENV FRONTEND_BASE_PATH=/private/argus/web/proxy
-ENV ARGUS_UID=2133
-ENV ARGUS_GID=2015
+ARG ARGUS_UID=2133
+ARG ARGUS_GID=2015
+ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_GID=${ARGUS_GID}

 RUN mkdir -p ${FRONTEND_BASE_PATH} && \
    mkdir -p /private/argus/etc
--- a/src/web/build_tools/proxy/build.sh
+++ b/src/web/build_tools/proxy/build.sh
@@ -0,0 +1,9 @@
+docker pull ubuntu:24.04
+
+source src/web/tests/.env
+
+docker build \
+    --build-arg ARGUS_UID=${ARGUS_UID} \
+    --build-arg ARGUS_GID=${ARGUS_GID} \
+    -f src/web/build_tools/proxy/Dockerfile -t argus-web-proxy:latest .
+docker save -o argus-web-proxy-latest.tar argus-web-proxy:latest
--- a/src/web/build_tools/proxy/conf.d/alert.conf
+++ b/src/web/build_tools/proxy/conf.d/alert.conf
@@ -3,6 +3,7 @@ server {
    server_name alertmanager.alert.argus.com;

    location / {
-        proxy_pass http://alertmanager.alert.argus.com:9093;
+        set $alert_backend http://alertmanager.alert.argus.com:9093;
+        proxy_pass $alert_backend;
    }
 }
--- a/src/web/build_tools/proxy/conf.d/log.conf
+++ b/src/web/build_tools/proxy/conf.d/log.conf
@@ -4,7 +4,8 @@ server {
    server_name es.log.argus.com;

    location / {
-        proxy_pass http://es.log.argus.com;
+        set $es_backend http://es.log.argus.com:9200;
+        proxy_pass $es_backend;
    }
 }

@@ -14,6 +15,7 @@ server {
    server_name kibana.log.argus.com;

    location / {
-        proxy_pass http://kibana.log.argus.com;
+        set $kibana_backend http://kibana.log.argus.com:5601;
+        proxy_pass $kibana_backend;
    }
 }
--- a/src/web/build_tools/proxy/conf.d/master.conf
+++ b/src/web/build_tools/proxy/conf.d/master.conf
@@ -3,25 +3,25 @@ server {
    server_name master.argus.com;

    location / {
-        # proxy_pass http://master.argus.com;
-        proxy_pass http://master.argus.com;
-        # proxy_set_header Host $host;
-        # proxy_set_header X-Real-IP $remote_addr;
-        # proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        # proxy_set_header X-Forwarded-Proto $scheme;
+        set $master_backend http://master.argus.com:3000;
+        proxy_pass $master_backend;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;

-        # # CORS 支持
-        # add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
-        # add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
-        # add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
+        # CORS 支持
+        add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
+        add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
+        add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;

-        # if ($request_method = OPTIONS) {
-        #     add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
-        #     add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
-        #     add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
-        #     add_header 'Content-Length' 0;
-        #     add_header 'Content-Type' 'text/plain';
-        #     return 204;
-        # }
+        if ($request_method = OPTIONS) {
+            add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
+            add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
+            add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
+            add_header 'Content-Length' 0;
+            add_header 'Content-Type' 'text/plain';
+            return 204;
+        }
    }
 }
--- a/src/web/build_tools/proxy/conf.d/metric.conf
+++ b/src/web/build_tools/proxy/conf.d/metric.conf
@@ -4,16 +4,18 @@ server {
    server_name prometheus.metric.argus.com;

    location / {
-        proxy_pass http://prom.metric.argus.com;
+        set $prom_backend http://prom.metric.argus.com:9090;
+        proxy_pass $prom_backend;
    }
 }

-# # Grafana
-# server {
-#     listen 80;
-#     server_name grafana.metric.argus.com;
+# Grafana
+server {
+    listen 80;
+    server_name grafana.metric.argus.com;

-#     location / {
-#         proxy_pass http://grafana.metric.argus.com;
-#     }
-# }
+    location / {
+        set $grafana_backend http://grafana.metric.argus.com:3000;
+        proxy_pass $grafana_backend;
+    }
+}
--- a/src/web/build_tools/proxy/conf.d/web.conf
+++ b/src/web/build_tools/proxy/conf.d/web.conf
@@ -3,6 +3,7 @@ server {
    server_name web.argus.com;

    location / {
-        proxy_pass http://web.argus.com:80;
+        set $web_backend http://web.argus.com:8080;
+        proxy_pass $web_backend;
    }
 }
--- a/src/web/build_tools/proxy/nginx.conf.template
+++ b/src/web/build_tools/proxy/nginx.conf.template
@@ -5,14 +5,6 @@ events {
    worker_connections  1024;
 }

-server {
-    listen 80 default_server;
-    server_name _;
-
-    location / {
-        proxy_pass http://web.argus.com:80;
-    }
-}

 http {
    include       mime.types;
@@ -32,5 +24,16 @@ http {
    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
    proxy_set_header X-Forwarded-Proto $scheme;

+    server {
+        listen 80 default_server;
+        server_name _;
+
+        location / {
+            set $web_backend http://web.argus.com:8080;
+            proxy_pass $web_backend;
+        }
+    }
+
+
    include /etc/nginx/conf.d/*.conf;
 }
--- a/src/web/build_tools/proxy/start-proxy-supervised.sh
+++ b/src/web/build_tools/proxy/start-proxy-supervised.sh
@@ -9,8 +9,8 @@ DNS_CONF_PRIVATE="/private/argus/etc/dns.conf"
 DNS_CONF_SYSTEM="/etc/resolv.conf"
 DNS_DIR="/private/argus/etc"
 DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
-RUNTIME_UID="${ARGUS_BUILD_UID:-2133}"
-RUNTIME_GID="${ARGUS_BUILD_GID:-2015}"
+RUNTIME_UID="${ARGUS_UID:-2133}"
+RUNTIME_GID="${ARGUS_GID:-2015}"

 mkdir -p "$DNS_DIR"
 chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true
--- a/src/web/src/components/AlertFilters.jsx
+++ b/src/web/src/components/AlertFilters.jsx
@@ -8,10 +8,10 @@ export function AlertFilters({ filters, setFilters, nodeOptions }) {
        value={filters.severity}
        onChange={(value) => setFilters((f) => ({ ...f, severity: value }))}
        data={[
-          { value: "all", label: "全部" },
-          { value: "critical", label: "严重" },
-          { value: "warning", label: "警告" },
-          { value: "info", label: "信息" },
+          { value: "all", label: "all" },
+          { value: "critical", label: "critical" },
+          { value: "warning", label: "warning" },
+          { value: "info", label: "info" },
        ]}
        w={150}
      />
@@ -20,7 +20,7 @@ export function AlertFilters({ filters, setFilters, nodeOptions }) {
        value={filters.state}
        onChange={(value) => setFilters((f) => ({ ...f, state: value }))}
        data={[
-          { value: "all", label: "全部" },
+          { value: "all", label: "all" },
          { value: "active", label: "Active" },
          { value: "resolved", label: "Resolved" },
        ]}
--- a/src/web/src/components/AlertTable.jsx
+++ b/src/web/src/components/AlertTable.jsx
@@ -1,5 +1,6 @@
-import { Table, Group, ActionIcon, Button } from "@mantine/core";
-import { IconChevronUp, IconChevronDown } from "@tabler/icons-react";
+import { Table, Group, ActionIcon, Button, Code } from "@mantine/core";
+import { IconChevronUp, IconChevronDown, IconInfoCircle } from "@tabler/icons-react";
+import { useState } from "react";

 export function AlertTable({
  alerts,
@@ -16,6 +17,11 @@ export function AlertTable({
  formatRelativeTime,
 }) {
  const totalPages = Math.ceil(sortedAlerts.length / pageSize);
+  const [expandedRow, setExpandedRow] = useState(null);
+
+  const toggleExpand = (index) => {
+    setExpandedRow(expandedRow === index ? null : index);
+  };

  return (
    <>
@@ -47,24 +53,52 @@ export function AlertTable({
                </Group>
              </Table.Th>
            ))}
+            <Table.Th>更多信息</Table.Th>
          </Table.Tr>
        </Table.Thead>
+
        <Table.Tbody>
          {paginatedAlerts.map((alert, i) => (
-            <Table.Tr key={i} style={{ backgroundColor: getRowColor(alert) }}>
-              <Table.Td>{alert.labels?.alertname || "-"}</Table.Td>
-              <Table.Td>{alert.labels?.instance || "-"}</Table.Td>
-              <Table.Td style={{ color: getSeverityColor(alert.labels?.severity) }}>
-                {alert.labels?.severity || "info"}
-              </Table.Td>
-              <Table.Td>{getStateBadge(alert.status?.state)}</Table.Td>
-              <Table.Td title={alert.startsAt || "-"}>{formatRelativeTime(alert.startsAt)}</Table.Td>
-              <Table.Td title={alert.endsAt || "-"}>
-                {alert.endsAt ? new Date(alert.endsAt).toLocaleString() : "-"}
-              </Table.Td>
-              <Table.Td title={alert.updatedAt || "-"}>{formatRelativeTime(alert.updatedAt)}</Table.Td>
-              <Table.Td>{alert.annotations?.summary || "-"}</Table.Td>
-            </Table.Tr>
+            <>
+              <Table.Tr key={i} style={{ backgroundColor: getRowColor(alert) }}>
+                <Table.Td>{alert.labels?.alertname || "-"}</Table.Td>
+                <Table.Td>{alert.labels?.instance || "-"}</Table.Td>
+                <Table.Td style={{ color: getSeverityColor(alert.labels?.severity) }}>
+                  {alert.labels?.severity || "info"}
+                </Table.Td>
+                <Table.Td>{getStateBadge(alert.status?.state)}</Table.Td>
+                <Table.Td title={alert.startsAt || "-"}>{formatRelativeTime(alert.startsAt)}</Table.Td>
+                <Table.Td title={alert.endsAt || "-"}>
+                  {alert.endsAt ? new Date(alert.endsAt).toLocaleString() : "-"}
+                </Table.Td>
+                <Table.Td title={alert.updatedAt || "-"}>{formatRelativeTime(alert.updatedAt)}</Table.Td>
+                <Table.Td>{alert.annotations?.summary || "-"}</Table.Td>
+                <Table.Td>
+                  <ActionIcon
+                    onClick={() => toggleExpand(i)}
+                    variant="subtle"
+                    color="blue"
+                    title="显示/隐藏更多信息"
+                  >
+                    <IconInfoCircle size={18} />
+                  </ActionIcon>
+                </Table.Td>
+              </Table.Tr>
+
+              {expandedRow === i && (
+                <Table.Tr key={`details-${i}`} style={{ backgroundColor: "#f9fafb" }}>
+                  <Table.Td colSpan={9}>
+                    <div style={{ fontSize: "0.85rem", lineHeight: 1.5 }}>
+                      {Object.entries(alert.labels || {}).map(([k, v]) => (
+                        <div key={k}>
+                          <Code color="blue">{k}</Code> ：{v}
+                        </div>
+                      ))}
+                    </div>
+                  </Table.Td>
+                </Table.Tr>
+              )}
+            </>
          ))}
        </Table.Tbody>
      </Table>
--- a/src/web/src/components/NodeDetailDrawer.jsx
+++ b/src/web/src/components/NodeDetailDrawer.jsx
@@ -1,4 +1,4 @@
-import { useState, useEffect } from "react"; 
+import { useState, useEffect } from "react";
 import {
  Drawer,
  Text,
@@ -102,11 +102,6 @@ export default function NodeDetailDrawer({ opened, nodeId, onClose }) {
          {/* 滚动内容 */}
          <ScrollArea style={{ flex: 1 }}>
            <Stack spacing="md">
-              {/* 配置信息 */}
-              <NodeConfigCard nodeId={node.id} config={node.config || {}} onSaved={() => fetchNodeDetail(node.id)} />
-
-              {/* 标签信息 */}
-              <NodeLabelCard nodeId={node.id} labels={Array.isArray(node.label) ? node.label : []} onSaved={() => fetchNodeDetail(node.id)} />

              {/* 元数据 */}
              <NodeMetaCard node={node} />
@@ -114,6 +109,12 @@ export default function NodeDetailDrawer({ opened, nodeId, onClose }) {
              {/* 健康信息 */}
              <NodeHealthCard node={node} />

+              {/* 配置信息 */}
+              <NodeConfigCard nodeId={node.id} config={node.config || {}} onSaved={() => fetchNodeDetail(node.id)} />
+
+              {/* 标签信息 */}
+              <NodeLabelCard nodeId={node.id} labels={Array.isArray(node.label) ? node.label : []} onSaved={() => fetchNodeDetail(node.id)} />
+
              {/* 其他基础信息展示 */}
              <Stack spacing="xs">
                <Text fw={500}>注册时间: <Text span c="dimmed">{new Date(node.register_time).toLocaleString()}</Text></Text>
--- a/src/web/src/components/NodeHealthCard.jsx
+++ b/src/web/src/components/NodeHealthCard.jsx
@@ -2,54 +2,62 @@ import { useState } from "react";
 import { Card, Text, Stack, Group, ActionIcon, Badge, Popover } from "@mantine/core";
 import { IconInfoCircle } from "@tabler/icons-react";

+
+// 子组件：单条健康信息
+function HealthItem({ moduleName, data }) {
+  const status = data?.status || "unknown";
+  const color = status === "healthy" ? "green" : status === "unhealthy" ? "red" : "gray";
+  const [opened, setOpened] = useState(false);
+
+  return (
+    <Group key={moduleName} spacing="xs" align="center">
+      <Text size="sm" fw={500}>{moduleName}</Text>
+      <Badge color={color} variant="light">{status}</Badge>
+      {(data?.error || data?.timestamp) && (
+        <Popover
+          opened={opened}
+          onClose={() => setOpened(false)}
+          position="bottom"
+          withArrow
+          shadow="sm"
+        >
+          <Popover.Target>
+            <ActionIcon
+              size="xs"
+              color="blue"
+              variant="light"
+              onClick={() => setOpened((o) => !o)}
+            >
+              <IconInfoCircle size={14} />
+            </ActionIcon>
+          </Popover.Target>
+          <Popover.Dropdown>
+            <Stack spacing={4}>
+              {data.error && <Text size="xs" c="red">Error: {data.error}</Text>}
+              {data.timestamp && (
+                <Text size="xs" c="dimmed">
+                  Updated: {new Date(data.timestamp).toLocaleString()}
+                </Text>
+              )}
+            </Stack>
+          </Popover.Dropdown>
+        </Popover>
+      )}
+    </Group>
+  );
+}
+
+// 主组件：健康信息卡片
 export default function NodeHealthCard({ node }) {
  const health = node.health || {};

-  const renderHealthItem = (moduleName, data) => {
-    const status = data?.status || "unknown";
-    const color = status === "healthy" ? "green" : status === "unhealthy" ? "red" : "gray";
-    const [opened, setOpened] = useState(false);
-
-    return (
-      <Group key={moduleName} spacing="xs" align="center">
-        <Text size="sm" fw={500}>{moduleName}</Text>
-        <Badge color={color} variant="light">{status}</Badge>
-        {(data?.error || data?.timestamp) && (
-          <Popover
-            opened={opened}
-            onClose={() => setOpened(false)}
-            position="bottom"
-            withArrow
-            shadow="sm"
-          >
-            <Popover.Target>
-              <ActionIcon size="xs" color="blue" variant="light" onClick={() => setOpened((o) => !o)}>
-                <IconInfoCircle size={14} />
-              </ActionIcon>
-            </Popover.Target>
-            <Popover.Dropdown>
-              <Stack spacing={4}>
-                {data.error && <Text size="xs" c="red">Error: {data.error}</Text>}
-                {data.timestamp && (
-                  <Text size="xs" c="dimmed">
-                    Updated: {new Date(data.timestamp).toLocaleString()}
-                  </Text>
-                )}
-              </Stack>
-            </Popover.Dropdown>
-          </Popover>
-        )}
-      </Group>
-    );
-  };
-
  return (
    <Card shadow="xs" radius="md" withBorder>
      <Text fw={600} mb="sm">健康信息</Text>
      <Stack spacing="xs">
-        {Object.entries(health).map(([moduleName, data]) =>
-          renderHealthItem(moduleName, data)
-        )}
+        {Object.entries(health).map(([moduleName, data]) => (
+          <HealthItem key={moduleName} moduleName={moduleName} data={data} />
+        ))}
      </Stack>
    </Card>
  );
--- a/src/web/src/components/NodeTable.jsx
+++ b/src/web/src/components/NodeTable.jsx
@@ -4,7 +4,7 @@ import { Link } from "react-router-dom";
 import NodeStatus from "./NodeStatus";
 import PaginationControl from "./PaginationControl";
 import { apiRequest } from "../config/request";
-import { MASTER_API } from "../config/api";
+import { MASTER_API, EXTERNAL_HOST } from "../config/api";

 export function NodeTable({
    withSearch = false,
@@ -56,13 +56,28 @@ export function NodeTable({
            <Table.Td>{node.version}</Table.Td>
            {withActions && (
                <Table.Td>
-                    <Button
-                        size="xs"
-                        variant="light"
-                        onClick={() => fetchDetail && fetchDetail(node.id)}
-                    >
-                        查看详情
-                    </Button>
+                    <Group spacing="xs">
+                        {/* 查看详情 */}
+                        <Button
+                            size="xs"
+                            variant="light"
+                            onClick={() => fetchDetail && fetchDetail(node.id)}
+                        >
+                            查看详情
+                        </Button>
+
+                        {/* Grafana Dashboard 链接 */}
+                        <Button
+                            size="xs"
+                            variant="outline"
+                            component="a"
+                            href={`${EXTERNAL_HOST.GRAFANA}/d/node_gpu_metrics/node-and-gpu-metrics?var-hostname=${encodeURIComponent(node.name)}`}
+                            target="_blank"
+                            rel="noopener noreferrer"
+                        >
+                            Grafana
+                        </Button>
+                    </Group>
                </Table.Td>
            )}
        </Table.Tr>
@@ -71,8 +86,6 @@ export function NodeTable({
    return (
        <Card shadow="sm" radius="md" p="lg">
            {/* 标题 + 查看更多 */}
-
-
            {(title || viewMoreLink) && (
                <Group position="apart" mb="sm">
                    {title && <Text fw={700} size="lg">{title}</Text>}
--- a/src/web/src/components/Sidebar.jsx
+++ b/src/web/src/components/Sidebar.jsx
@@ -12,7 +12,7 @@ export default function Sidebar() {
  const location = useLocation(); // 路由变化时会触发 Sidebar 重新渲染

  const links = [
-    { to: "/dashboard", label: "概览仪表盘", icon: <IconGauge size={16} /> },
+    { to: "/dashboard", label: "仪表盘", icon: <IconGauge size={16} /> },
    { to: "/nodeInfo", label: "节点信息", icon: <IconServer size={16} /> },
    { to: "/metrics", label: "指标详情", icon: <IconActivity size={16} /> },
    { to: "/logs", label: "日志详情", icon: <IconFileText size={16} /> },
--- a/src/web/src/config/api.js
+++ b/src/web/src/config/api.js
@@ -17,14 +17,14 @@ export const MASTER_API = {

 // 其他外部 API
 export const EXTERNAL_API = {
-  ALERTS_INFOS: "http://localhost:9093/api/v2/alerts",
+  ALERTS_INFOS: "http://alertmanager.alert.argus.com/api/v2/alerts",
 };

 // 外部服务 Host
 export const EXTERNAL_HOST = {
-  ALERTS: "http://localhost:9093",
+  ALERTS: "http://alertmanager.alert.argus.com",
  GRAFANA: "http://grafana.metric.argus.com",
+  GRAFANA_DASHBOARD: "http://grafana.metric.argus.com/d/cluster-dashboard/cluster-dashboard",
  PROMETHEUS: "http://prometheus.metric.argus.com",
-  ES: "http://es.log.argus.com",
-  KIBANA: "http://kibana.log.argus.com",
+  KIBANA: "http://kibana.log.argus.com/app/discover",
 };
--- a/src/web/src/config/entries.js
+++ b/src/web/src/config/entries.js
@@ -5,12 +5,11 @@ import kibanaLogo from "../assets/kibana.png";
 import { EXTERNAL_HOST } from "./api";

 export const metricsEntries = [
-  { label: "Grafana", href: EXTERNAL_HOST.GRAFANA, icon: grafanaLogo },
+  { label: "Grafana", href: EXTERNAL_HOST.GRAFANA_DASHBOARD, icon: grafanaLogo },
  { label: "Prometheus", href: EXTERNAL_HOST.PROMETHEUS, icon: prometheusLogo },
 ];

 export const logsEntries = [
-  { label: "Elasticsearch", href: EXTERNAL_HOST.ES, icon: esLogo },
  { label: "Kibana", href: EXTERNAL_HOST.KIBANA, icon: kibanaLogo },
 ];

--- a/src/web/src/pages/Alerts.jsx
+++ b/src/web/src/pages/Alerts.jsx
@@ -1,5 +1,5 @@
 import { useEffect, useState, useMemo } from "react";
-import { Stack, Title, Loader, Center, Group, Button, Badge, ActionIcon } from "@mantine/core";
+import { Stack, Title, Loader, Center, Group, Button, Badge, ActionIcon, Switch } from "@mantine/core";
 import { IconRefresh } from "@tabler/icons-react";
 import { apiRequest } from "../config/request";
 import { EXTERNAL_API } from "../config/api";
@@ -17,18 +17,20 @@ export default function Alerts() {
  const [page, setPage] = useState(1);
  const pageSize = 10;
  const [sortConfig, setSortConfig] = useState({ key: "startsAt", direction: "desc" });
+  const [autoRefresh, setAutoRefresh] = useState(true); // 默认开启自动刷新

  async function fetchAlerts() {
    setLoading(true);
    const data = await apiRequest(EXTERNAL_API.ALERTS_INFOS);
    if (data && Array.isArray(data)) {
      setAlerts(data);
-      const counts = { critical: 0, warning: 0, info: 0 };
+      const counts = { critical: 0, warning: 0, info: 0, total: 0 };
      data.forEach((alert) => {
        const sev = alert.labels?.severity || "info";
        if (sev === "critical") counts.critical++;
        else if (sev === "warning") counts.warning++;
        else counts.info++;
+        counts.total++;
      });
      setStats(counts);
    }
@@ -37,9 +39,14 @@ export default function Alerts() {

  useEffect(() => {
    fetchAlerts();
-    const timer = setInterval(fetchAlerts, 30000);
+
+    let timer;
+    if (autoRefresh) {
+      timer = setInterval(fetchAlerts, 30000);
+    }
+
    return () => clearInterval(timer);
-  }, []);
+  }, [autoRefresh]);

  // 节点选项
  const nodeOptions = useMemo(() => {
@@ -124,7 +131,14 @@ export default function Alerts() {
    <Stack spacing="lg" p="md">
      <Group position="apart">
        <Title order={2}>告警详情</Title>
-        <Button component="a" href="{EXTERNAL_HOST.ALERTS}" target="_blank" variant="outline">
+        <Switch
+          checked={autoRefresh}
+          onChange={(e) => setAutoRefresh(e.currentTarget.checked)}
+          label="自动刷新"
+          color="green"
+          size="sm"
+        />
+        <Button component="a" href={EXTERNAL_HOST.ALERTS} target="_blank" variant="outline">
          打开 Alertmanager
        </Button>
        <ActionIcon onClick={fetchAlerts} color="blue" variant="filled" size="lg" title="刷新">
--- a/src/web/src/pages/Dashboard.jsx
+++ b/src/web/src/pages/Dashboard.jsx
@@ -1,5 +1,5 @@
 import { useEffect, useState } from "react";
-import { Grid, Text } from "@mantine/core";
+import { Grid, Text, Stack, Title } from "@mantine/core";
 import { NodeTable } from "../components/NodeTable";
 import { HealthCard } from "../components/HealthCard";
 import { AlertStats } from "../components/AlertStats";
@@ -14,12 +14,13 @@ export default function Dashboard() {
    const [loading, setLoading] = useState(true);

    const countAlerts = (data) => {
-        const stats = { critical: 0, warning: 0, info: 0 };
+        const stats = { critical: 0, warning: 0, info: 0, total: 0 };
        data?.forEach((alert) => {
            const severity = alert.labels?.severity || "info";
            if (severity === "critical") stats.critical++;
            else if (severity === "warning") stats.warning++;
            else stats.info++;
+            stats.total++;
        });
        return stats;
    };
@@ -41,7 +42,7 @@ export default function Dashboard() {
                    status_statistics: healthRes?.status_statistics || [],
                });

-                setAlerts(countAlerts(alertsRes?.data || []));
+                setAlerts(countAlerts(alertsRes || []));
            } catch (err) {
                console.error("获取 Dashboard 数据失败:", err);
            } finally {
@@ -61,13 +62,16 @@ export default function Dashboard() {
    }

    return (
-        <Grid>
+        <Stack spacing="lg" p="md">
+            <Title order={1} mb="md">仪表盘</Title>
+            <Grid>

-            <Grid.Col span={6}><HealthCard health={health} /></Grid.Col>
-            <Grid.Col span={6}>
-                <AlertStats stats={alerts} layout="column" title="告警统计" link="/alerts" />
-            </Grid.Col>
-            <Grid.Col span={12}><NodeTable clusterData={cluster} title="集群节点" viewMoreLink="/nodeInfo" /></Grid.Col>
-        </Grid>
+                <Grid.Col span={6}><HealthCard health={health} /></Grid.Col>
+                <Grid.Col span={6}>
+                    <AlertStats stats={alerts} layout="column" title="告警统计" link="/alerts" />
+                </Grid.Col>
+                <Grid.Col span={12}><NodeTable clusterData={cluster} title="集群节点" viewMoreLink="/nodeInfo" /></Grid.Col>
+            </Grid>
+        </Stack>
    );
 }
--- a/src/web/src/pages/Metrics.jsx
+++ b/src/web/src/pages/Metrics.jsx
@@ -5,7 +5,7 @@ import { metricsEntries } from "../config/entries";
 export default function Metrics() {
  return (
    <Stack spacing="lg" p="md">
-      <Title order={2}>指标入口</Title>
+      <Title order={2}>指标详情</Title>
      <Grid gutter="lg">
        {metricsEntries.map((entry) => (
          <Grid.Col key={entry.href} span={{ base: 12, sm: 4, md: 3 }}>
--- a/src/web/src/pages/NodePage.jsx
+++ b/src/web/src/pages/NodePage.jsx
@@ -1,5 +1,5 @@
 import { useState } from "react";
-import { Grid } from "@mantine/core";
+import { Grid, Stack, Title } from "@mantine/core";
 import { apiRequest } from "../config/request";
 import { MASTER_API } from "../config/api";
 import { NodeTable } from "../components/NodeTable";
@@ -23,24 +23,30 @@ export default function NodePage() {
    };

    return (
-        <Grid gutter="lg">
-            {/* 左侧：节点表格 */}
-            <Grid.Col span={drawerOpen ? 8 : 12}>
-                <NodeTable
-                    withSearch
-                    withPagination
-                    withActions
-                    fetchDetail={fetchNodeDetail}
-                />
-            </Grid.Col>
+        <Stack spacing="lg" p="md">
+            <Title order={2} mb="md">
+                节点信息
+            </Title>

-            {/* 节点详情 Drawer */}
-            <NodeDetailDrawer
-                opened={drawerOpen}
-                onClose={() => setDrawerOpen(false)}
-                nodeId={selectedNodeId}
-                loading={detailLoading}
-            />
-        </Grid>
+            <Grid gutter="lg">
+                {/* 左侧：节点表格 */}
+                <Grid.Col span={drawerOpen ? 8 : 12}>
+                    <NodeTable
+                        withSearch
+                        withPagination
+                        withActions
+                        fetchDetail={fetchNodeDetail}
+                    />
+                </Grid.Col>
+
+                {/* 节点详情 Drawer */}
+                <NodeDetailDrawer
+                    opened={drawerOpen}
+                    onClose={() => setDrawerOpen(false)}
+                    nodeId={selectedNodeId}
+                    loading={detailLoading}
+                />
+            </Grid>
+        </Stack>
    );
 }
--- a/src/web/tests/.env.example
+++ b/src/web/tests/.env.example
@@ -0,0 +1,5 @@
+DATA_ROOT=/home/argus/tmp/private/argus
+ARGUS_UID=1048
+ARGUS_GID=1048
+
+USE_INTRANET=false
--- a/src/web/tests/docker-compose.yml
+++ b/src/web/tests/docker-compose.yml
@@ -1,4 +1,3 @@
-version: '3.8'
 services:
  web-frontend:
    build:
@@ -20,7 +19,7 @@ services:
      - ${DATA_ROOT:-./data}/web:/private/argus/web/frontend
      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
    networks:
-      - argus-network
+      - argus-debug-net
    restart: unless-stopped
    logging:
      driver: "json-file"
@@ -45,7 +44,7 @@ services:
    volumes:
      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
    networks:
-      - argus-network
+      - argus-debug-net
    restart: unless-stopped
    logging:
      driver: "json-file"
@@ -54,9 +53,8 @@ services:
        max-file: "3"

 networks:
-  argus-network:
-    driver: bridge
-    name: argus-network
+  argus-debug-net:
+    external: true

 volumes:
  web-frontend_data:
Author	SHA1	Message	Date
sundapeng.sdp	b0d451cbe7	refactor: metric e2e测试流程融合到 sys/tests 步骤中(test-gpu-node/check-service-installed); refs #29	2025-10-21 09:31:29 +08:00
sundapeng.sdp	835e81282f	refactor: metric e2e测试流程融合到 sys/tests 步骤中（bootstrap/up/publish/installer）； refs #29	2025-10-20 17:59:17 +08:00
sundapeng.sdp	c4582c99bc	feat: metric e2e 启动服务中判断是否当前服务器存在可用GPU，如无则跳过 test-gpu-node 容器创建和安装包的测试； refs #29	2025-10-20 15:30:07 +08:00
sundapeng.sdp	299765ed40	refactor: metric e2e docker-compose中移除构建参数；metric e2e启动服务脚本中移除构建逻辑，迁移至build模块； refs #29	2025-10-20 14:58:12 +08:00
sundapeng.sdp	a8bbf2d6e9	refactor: metric 模块中所需镜像构建融合到 build 模块； refs #29	2025-10-20 14:18:15 +08:00
xuxt	d1b89c0cf6	dev_1.0.0_xuxt_2 更新反向代理，打包镜像，以及README文档 (#28 ) Co-authored-by: xiuting.xu <xiutingxt.xu@gmail.com> Reviewed-on: #28 Reviewed-by: yuyr <yuyr@zgclab.edu.cn> Reviewed-by: huhy <husteryezi@163.com> Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>	2025-10-20 09:45:32 +08:00