feat: 新增GPU测试节点argus-metric-test-gpu-node，测试安装包安装流程及与agent/master组件之间数据准确性；

refs #20

src/metric/tests/client-test-gpu-node/build/Dockerfile

@@ -0,0 +1,39 @@
+# 使用NVIDIA官方CUDA基础镜像 
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+# 设置时区
+ENV TZ=Asia/Shanghai
+
+RUN apt-get update -qq && \
+    apt-get install -y -qq \
+    tzdata \
+    curl \
+    wget \
+    gnupg2 \
+    software-properties-common \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# 配置时区
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+
+WORKDIR /app
+
+# 创建启动脚本，在运行时验证GPU
+COPY <<EOF /app/start.sh
+#!/bin/bash
+echo "检查GPU环境..."
+if command -v nvidia-smi &> /dev/null; then
+    nvidia-smi
+    echo "GPU环境正常"
+else
+    echo "警告: nvidia-smi 命令不可用，请确保容器运行时启用了GPU支持"
+fi
+exec "\$@"
+EOF
+
+RUN chmod +x /app/start.sh
+
+CMD ["/app/start.sh", "/bin/bash"]

src/metric/tests/docker-compose.yml

@@ -142,3 +142,44 @@ services:
         max-size: "10m"
         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
+    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:
+      - ${DATA_ROOT:-/private}/argus/agent:/private/argus/agent
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    command: sleep infinity
+    networks:
+      default:
+        ipv4_address: 172.30.0.51
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+

src/metric/tests/scripts/01_start_services.sh

@@ -21,6 +21,7 @@ docker ps | grep argus-ftp
 docker ps | grep argus-prometheus
 docker ps | grep argus-grafana
 docker ps | grep argus-metric-test-node
+docker ps | grep argus-metric-test-gpu-node
 
-echo "[01] 所有服务已启动"
+echo "[01] 基础服务已启动"
 

src/metric/tests/scripts/02_publish_artifact.sh

@@ -20,7 +20,7 @@ else
     echo "[02] 默认路径: $OUTPUT_DIR"
 fi
 
-OWNER="${FTP_UID:-2133}:${FTP_GID:-2015}"
+OWNER="${ARGUS_BUILD_UID:-2133}:${ARGUS_BUILD_GID:-2015}"
 
 cd "$PLUGIN_DIR"
 

src/metric/tests/scripts/04_test_gpu_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-gpu-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/metric/tests/scripts/common/start-all.sh

@@ -44,6 +44,7 @@ BUILD_DIRS=(
     "../prometheus/build"
     "../grafana/build"
     "client-test-node/build"
+    "client-test-gpu-node/build"
 )
 
 for dir in "${BUILD_DIRS[@]}"; do
@@ -87,7 +88,7 @@ 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")
+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 "${IMAGES[@]}"; do
@@ -126,6 +127,9 @@ else
                     "argus-metric-test-node:latest")
                         cache_file="${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 "$cache_file" ]; then
@@ -174,6 +178,9 @@ else
                     "argus-metric-test-node:latest")
                         docker save -o "${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/"
@@ -185,40 +192,12 @@ else
 fi
 
 echo ""
-echo "3. 启动服务..."
+echo "3. 启动基础服务..."
 cd "$TEST_DIR"
-docker compose up -d
+# 启动除GPU节点外的所有服务
+docker compose up -d ftp prometheus grafana test-node test-gpu-node
 
 echo ""
 echo "4. 等待服务启动..."
 sleep 5
 
-echo ""
-echo "5. 检查服务状态..."
-cd "$TEST_DIR"
-docker compose ps
-
-echo ""
-echo "=========================================="
-echo "  服务启动完成！"
-echo "=========================================="
-echo ""
-echo "服务访问地址："
-echo "  - FTP:        ftp://localhost:${FTP_PORT:-21}"
-echo "    用户名: ftpuser"
-echo "    密码:   ${FTP_PASSWORD:-ZGClab1234!}"
-echo ""
-echo "  - Prometheus: http://localhost:${PROMETHEUS_PORT:-9090}"
-echo ""
-echo "  - Grafana:    http://localhost:${GRAFANA_PORT:-3000}"
-echo "    用户名: admin"
-echo "    密码:   admin"
-echo ""
-echo "常用命令："
-echo "  查看日志:     docker compose logs -f [service]"
-echo "  停止服务:     docker compose stop"
-echo "  重启服务:     docker compose restart"
-echo "  停止并删除:   docker compose down"
-echo "  停止并删除卷: docker compose down -v"
-echo ""
-

src/metric/tests/scripts/save-images.sh

@@ -24,7 +24,8 @@ declare -A IMAGES=(
     ["argus-metric-ftp:latest"]="argus-ftp.tar"
     ["argus-metric-prometheus:latest"]="argus-prometheus.tar"
     ["argus-metric-grafana:latest"]="argus-grafana.tar"
-    ["ubuntu:22.04"]="test-node.tar"
+    ["argus-metric-test-node:latest"]="argus-test-node.tar"
+    ["argus-metric-test-gpu-node:latest"]="argus-test-gpu-node.tar"
 )
 
 # 检查镜像是否存在并保存