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

refs #29

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"

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

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

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

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 "[04] 检测GPU环境..."
-echo "[03] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
+# 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"

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

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..."
+echo "2. 检测GPU环境..."
-
+# 检测GPU环境
-# 检查镜像是否存在
+if bash "$SCRIPT_DIR/check-gpu.sh"; then
-IMAGE_CACHE_DIR="$TEST_DIR/images-cache"
+    echo "GPU环境可用，将启动GPU节点"
-IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest" "argus-metric-test-node:latest" "argus-metric-test-gpu-node:latest")
+    GPU_AVAILABLE=true
-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 $all_images_exist; then
-    echo "所有镜像已存在，跳过构建"
 else
-    echo "检测到缺失镜像，尝试从缓存加载..."
+    echo "GPU环境不可用，跳过GPU节点"
-    
+    GPU_AVAILABLE=false
-    # 尝试从缓存加载
-    loaded_from_cache=false
-    if [ -d "$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
 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..."

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"

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"

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
 

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"
+

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"

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"

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 "=========================================="