diff --git a/src/metric/tests/.gitignore b/src/metric/tests/.gitignore
new file mode 100644
index 0000000..b73f619
--- /dev/null
+++ b/src/metric/tests/.gitignore
@@ -0,0 +1,7 @@
+.env
+data/
+images-cache/
+*.tar
+*.log
+.DS_Store
+
diff --git a/src/metric/tests/README.md b/src/metric/tests/README.md
new file mode 100644
index 0000000..719f400
--- /dev/null
+++ b/src/metric/tests/README.md
@@ -0,0 +1,159 @@
+# E2E Test - Argus Metric 部署测试
+## 概述
+
+本项目用于对 Argus Metric 模块进行端到端（E2E）部署测试。
+通过一键脚本可快速搭建 Prometheus、FTP、Grafana 等服务，验证 Metric 模块的完整部署与运行流程。
+
+## 一键构建与部署 Prometheus / FTP / Grafana
+### 1. 修改环境变量文件
+
+将示例配置文件复制为 .env 并根据实际情况修改：
+
+``` bash
+cp env.example .env
+```
+
+### 2. 一键启动服务
+
+执行以下命令完成环境初始化、镜像构建与服务启动：
+
+``` bash
+sudo bash start-all.sh
+```
+
+该脚本将自动完成：
+- 初始化目录结构（如 /private/argus/metric）
+- 构建各服务 Docker 镜像
+- 启动 Prometheus、FTP、Grafana 容器
+
+### 3. 检查容器日志
+
+可手动验证容器运行状态：
+
+``` bash
+docker logs argus-metric-ftp
+docker logs argus-metric-grafana
+docker logs argus-metric-prometheus
+```
+
+如日志输出中无 ERROR 或 supervisor 报错信息，则表示服务启动正常。
+
+## 客户端安装包打包与分发
+
+打包后服务端会将安装包发布至 FTP 共享目录，默认路径为：
+
+``` bash
+$DATA_ROOT/ftp/share
+```
+
+发布后的文件权限与 FTP 目录账户保持一致。
+
+### 1. 递增版本号
+``` bash
+bash scripts/version-manager.sh bump minor
+```
+该脚本会自动更新版本号（如 1.101.0 → 1.102.0）。
+
+### 2. 打包安装制品
+``` bash
+bash scripts/package_artifact.sh
+```
+执行后会在输出目录中生成压缩包或安装脚本。
+
+### 3. 发布制品至 FTP
+``` bash
+sudo bash scripts/publish_artifact.sh $VERSION --output-dir $OUTPUT_DIR --owner $UID:$GID
+```
+
+参数说明：
+
+参数	说明
+$VERSION	发布版本号（如 1.102.0）
+$OUTPUT_DIR	输出目录（默认 /private/argus/ftp/share）
+$UID:$GID	文件属主（用户ID:组ID）
+
+示例：
+
+``` bash
+sudo bash scripts/publish_artifact.sh 1.102.0 --output-dir /private/argus/ftp/share --owner 2133:2015
+```
+
+更多详情可参考 client-plugins/all-in-one/README.md。
+
+## 客户端安装（通过 FTP）
+
+客户端下载与安装步骤如下：
+
+``` bash
+curl -u ${USER}:${PASSWD} ftp://${FTP_SERVER}/setup.sh -o setup.sh
+chmod +x setup.sh
+sudo bash setup.sh --server ${FTP_SERVER} --user ${USER} --password ${PASSWD} --port ${PORT}
+```
+
+参数说明：
+
+参数	说明
+$FTP_SERVER	服务器 IP 地址
+$USER	默认 ftpuser
+$PASSWD	默认 ZGClab1234!
+$PORT	FTP 服务端口（需与 .env 保持一致）
+
+示例：
+
+``` bash
+curl -u ftpuser:ZGClab1234! ftp://10.211.55.4/setup.sh -o setup.sh
+chmod +x setup.sh
+sudo bash setup.sh --server 10.211.55.4 --user ftpuser --password 'ZGClab1234!' --port 2122
+```
+
+更多细节可参考 client-plugins/all-in-one/README.md。
+
+## 模拟 Argus-Master 配置下发
+
+可通过手动写入 nodes.json 文件模拟 Argus-Master 对 Argus-Metric 的配置下发：
+
+[
+  {
+    "node_id": "A1",
+    "user_id": "sundapeng",
+    "ip": "10.211.55.4",
+    "hostname": "dev-sundapeng-nsche-wohen-pod-0",
+    "labels": ["label-a", "label-b"]
+  }
+]
+
+路径：
+
+``` bash
+${DATA_ROOT}/prometheus/nodes.json
+```
+
+Argus-Metric 中的 prometheus 模块会自动解析该文件，并将其拆分生成目标配置：
+
+``` bash
+${DATA_ROOT}/prometheus/targets/
+```
+
+## Grafana 手动配置（如未自动接入 Prometheus）
+
+如 Grafana 未自动导入 Prometheus 数据源，可手动执行以下操作：
+
+1. 添加数据源
+- 进入 Grafana → Data sources
+- 选择 Add data source → Prometheus
+- URL 填写：http://prometheus:9090(Docker 内部 DNS 地址)
+
+2. 导入测试 Dashboard
+- 打开 Grafana → Dashboards → Import
+- 上传或粘贴 test_grafana_dashboard.json
+
+## 查看监控数据
+Prometheus 访问以下地址查看节点活性：
+``` bash
+http://127.0.0.1:9091/targets
+```
+
+Grafana 访问以下地址查看监控大屏：
+``` bash
+http://127.0.0.1:3000/d/node_gpu_metrics/node-and-gpu-metrics
+```
\ No newline at end of file
diff --git a/src/metric/tests/check-paths.sh b/src/metric/tests/check-paths.sh
new file mode 100755
index 0000000..bc93897
--- /dev/null
+++ b/src/metric/tests/check-paths.sh
@@ -0,0 +1,106 @@
+#!/bin/bash
+
+# 路径检查脚本
+# 用于验证所有必要的构建目录是否存在
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+cd "$SCRIPT_DIR"
+
+echo "=========================================="
+echo "  路径检查脚本"
+echo "=========================================="
+echo ""
+echo "当前脚本目录: $SCRIPT_DIR"
+echo "当前工作目录: $(pwd)"
+echo ""
+
+# 检查配置文件
+echo "检查配置文件..."
+if [ -f "$SCRIPT_DIR/docker-compose.yml" ]; then
+    echo "  ✓ docker-compose.yml 存在"
+else
+    echo "  ✗ docker-compose.yml 不存在"
+fi
+
+if [ -f "$SCRIPT_DIR/.env" ]; then
+    echo "  ✓ .env 存在"
+elif [ -f "$SCRIPT_DIR/env.example" ]; then
+    echo "  ⚠ .env 不存在，但 env.example 存在"
+else
+    echo "  ✗ .env 和 env.example 都不存在"
+fi
+echo ""
+
+# 检查构建目录
+echo "检查构建目录..."
+BUILD_DIRS=(
+    "../ftp/build"
+    "../prometheus/build"
+    "../grafana/build"
+)
+
+all_exist=true
+for dir in "${BUILD_DIRS[@]}"; do
+    full_path="$SCRIPT_DIR/$dir"
+    if [ -d "$full_path" ]; then
+        echo "  ✓ $dir"
+        echo "    完整路径: $full_path"
+    else
+        echo "  ✗ $dir 不存在"
+        echo "    查找路径: $full_path"
+        all_exist=false
+    fi
+done
+echo ""
+
+# 检查 Dockerfile
+echo "检查 Dockerfile..."
+DOCKERFILES=(
+    "../ftp/build/Dockerfile"
+    "../prometheus/build/Dockerfile"
+    "../grafana/build/Dockerfile"
+)
+
+for dockerfile in "${DOCKERFILES[@]}"; do
+    full_path="$SCRIPT_DIR/$dockerfile"
+    if [ -f "$full_path" ]; then
+        echo "  ✓ $dockerfile"
+    else
+        echo "  ✗ $dockerfile 不存在"
+        echo "    查找路径: $full_path"
+        all_exist=false
+    fi
+done
+echo ""
+
+# 检查数据目录（可选）
+if [ -f "$SCRIPT_DIR/.env" ]; then
+    source "$SCRIPT_DIR/.env"
+    DATA_ROOT=${DATA_ROOT:-./data}
+    
+    echo "检查数据目录..."
+    echo "  数据根目录: $DATA_ROOT"
+    
+    if [ -d "$SCRIPT_DIR/$DATA_ROOT" ]; then
+        echo "  ✓ 数据目录存在"
+        ls -la "$SCRIPT_DIR/$DATA_ROOT" | head -10
+    else
+        echo "  ⚠ 数据目录不存在（首次运行时会自动创建）"
+    fi
+    echo ""
+fi
+
+# 总结
+echo "=========================================="
+if $all_exist; then
+    echo "  ✓ 所有必要的文件和目录都存在"
+    echo "  可以运行 ./start-all.sh 启动服务"
+else
+    echo "  ✗ 部分文件或目录缺失"
+    echo "  请检查项目结构是否完整"
+fi
+echo "=========================================="
+echo ""
+
diff --git a/src/metric/tests/docker-compose.yml b/src/metric/tests/docker-compose.yml
new file mode 100644
index 0000000..45ea0ac
--- /dev/null
+++ b/src/metric/tests/docker-compose.yml
@@ -0,0 +1,105 @@
+services:
+  ftp:
+    build:
+      context: ../ftp/build
+      dockerfile: Dockerfile
+      args:
+        FTP_UID: ${FTP_UID:-2133}
+        FTP_GID: ${FTP_GID:-2015}
+    image: argus-metric-ftp:latest
+    container_name: argus-ftp
+    restart: unless-stopped
+    environment:
+      - FTP_BASE_PATH=/private/argus/ftp
+      - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
+      - DOMAIN=${FTP_DOMAIN:-prom.ftp.argus.com}
+      - FTP_UID=${FTP_UID:-2133}
+      - FTP_GID=${FTP_GID:-2015}
+    ports:
+      - "${FTP_PORT:-21}:21"
+      - "${FTP_DATA_PORT:-20}:20"
+      - "21100-21110:21100-21110"
+    volumes:
+      - ${DATA_ROOT:-./data}/ftp:/private/argus/ftp
+      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
+    networks:
+      - argus-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  prometheus:
+    build:
+      context: ../prometheus/build
+      dockerfile: Dockerfile
+      args:
+        PROMETHEUS_UID: ${PROMETHEUS_UID:-2133}
+        PROMETHEUS_GID: ${PROMETHEUS_GID:-2015}
+        USE_INTRANET: ${USE_INTRANET:-false}
+    image: argus-metric-prometheus:latest
+    container_name: argus-prometheus
+    restart: unless-stopped
+    environment:
+      - PROMETHEUS_BASE_PATH=/private/argus/metric/prometheus
+      - PROMETHEUS_UID=${PROMETHEUS_UID:-2133}
+      - PROMETHEUS_GID=${PROMETHEUS_GID:-2015}
+    ports:
+      - "${PROMETHEUS_PORT:-9090}:9090"
+    volumes:
+      - ${DATA_ROOT:-./data}/prometheus:/private/argus/metric/prometheus
+      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
+    networks:
+      - argus-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  grafana:
+    build:
+      context: ../grafana/build
+      dockerfile: Dockerfile
+      args:
+        GRAFANA_UID: ${GRAFANA_UID:-2133}
+        GRAFANA_GID: ${GRAFANA_GID:-2015}
+    image: argus-metric-grafana:latest
+    container_name: argus-grafana
+    restart: unless-stopped
+    environment:
+      - GRAFANA_BASE_PATH=/private/argus/metric/grafana
+      - GRAFANA_UID=${GRAFANA_UID:-2133}
+      - GRAFANA_GID=${GRAFANA_GID:-2015}
+      - GF_SERVER_HTTP_PORT=3000
+      - GF_LOG_LEVEL=warn
+      - GF_LOG_MODE=console
+    ports:
+      - "${GRAFANA_PORT:-3000}:3000"
+    volumes:
+      - ${DATA_ROOT:-./data}/grafana:/private/argus/metric/grafana
+      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
+    networks:
+      - argus-network
+    depends_on:
+      - prometheus
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+networks:
+  argus-network:
+    driver: bridge
+    name: argus-network
+
+volumes:
+  ftp_data:
+    driver: local
+  prometheus_data:
+    driver: local
+  grafana_data:
+    driver: local
+
diff --git a/src/metric/tests/env.example b/src/metric/tests/env.example
new file mode 100644
index 0000000..9d72de2
--- /dev/null
+++ b/src/metric/tests/env.example
@@ -0,0 +1,26 @@
+# 用户和组配置
+FTP_UID=2133
+FTP_GID=2015
+PROMETHEUS_UID=2133
+PROMETHEUS_GID=2015
+GRAFANA_UID=2133
+GRAFANA_GID=2015
+
+# 数据根目录
+DATA_ROOT=/private/argus
+
+# FTP 配置
+FTP_PORT=2122
+FTP_DATA_PORT=2022
+FTP_PASSWORD=ZGClab1234!
+FTP_DOMAIN=prom.ftp.argus.com
+
+# Prometheus 配置
+PROMETHEUS_PORT=9090
+
+# Grafana 配置
+GRAFANA_PORT=3000
+
+# 网络配置
+USE_INTRANET=false
+
diff --git a/src/metric/tests/init-directories.sh b/src/metric/tests/init-directories.sh
new file mode 100755
index 0000000..df5d719
--- /dev/null
+++ b/src/metric/tests/init-directories.sh
@@ -0,0 +1,90 @@
+#!/bin/bash
+
+# 初始化目录脚本
+# 用于创建所有必要的数据目录并设置正确的权限
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+cd "$SCRIPT_DIR"
+
+# 加载 .env 文件（如果存在）
+if [ -f .env ]; then
+    echo "加载 .env 配置文件..."
+    source .env
+fi
+
+# 默认配置
+FTP_UID=${FTP_UID:-2133}
+FTP_GID=${FTP_GID:-2015}
+PROMETHEUS_UID=${PROMETHEUS_UID:-2133}
+PROMETHEUS_GID=${PROMETHEUS_GID:-2015}
+GRAFANA_UID=${GRAFANA_UID:-2133}
+GRAFANA_GID=${GRAFANA_GID:-2015}
+DATA_ROOT=${DATA_ROOT:-./data}
+
+echo "开始初始化目录结构..."
+echo "数据目录: ${DATA_ROOT}"
+echo ""
+
+# 创建 FTP 目录
+echo "创建 FTP 目录..."
+sudo mkdir -p ${DATA_ROOT}/ftp/share
+sudo chown -R ${FTP_UID}:${FTP_GID} ${DATA_ROOT}/ftp
+sudo chmod -R 755 ${DATA_ROOT}/ftp
+
+# 创建 Prometheus 目录
+echo "创建 Prometheus 目录..."
+sudo mkdir -p ${DATA_ROOT}/prometheus/{data,rules,targets}
+
+# 创建默认的 targets 文件（先创建文件再改权限）
+if [ ! -f "${DATA_ROOT}/prometheus/targets/node_exporter.json" ]; then
+    echo "创建默认 node_exporter targets..."
+    echo '[
+  {
+    "targets": [],
+    "labels": {
+      "job": "node"
+    }
+  }
+]' | sudo tee ${DATA_ROOT}/prometheus/targets/node_exporter.json > /dev/null
+fi
+
+if [ ! -f "${DATA_ROOT}/prometheus/targets/dcgm_exporter.json" ]; then
+    echo "创建默认 dcgm_exporter targets..."
+    echo '[
+  {
+    "targets": [],
+    "labels": {
+      "job": "dcgm"
+    }
+  }
+]' | sudo tee ${DATA_ROOT}/prometheus/targets/dcgm_exporter.json > /dev/null
+fi
+
+# 统一设置 Prometheus 目录权限
+sudo chown -R ${PROMETHEUS_UID}:${PROMETHEUS_GID} ${DATA_ROOT}/prometheus
+sudo chmod -R 755 ${DATA_ROOT}/prometheus
+
+# 创建 Grafana 目录
+echo "创建 Grafana 目录..."
+sudo mkdir -p ${DATA_ROOT}/grafana/{data,logs,plugins,provisioning/datasources,provisioning/dashboards,data/sessions,data/dashboards,config}
+sudo chown -R ${GRAFANA_UID}:${GRAFANA_GID} ${DATA_ROOT}/grafana
+sudo chmod -R 755 ${DATA_ROOT}/grafana
+
+# 创建公共配置目录
+sudo mkdir -p ${DATA_ROOT}/etc
+sudo chown -R ${FTP_UID}:${FTP_GID} ${DATA_ROOT}/etc
+sudo chmod -R 755 ${DATA_ROOT}/etc
+
+echo "目录初始化完成！"
+echo ""
+echo "目录结构："
+echo "  ${DATA_ROOT}/"
+echo "  ├── ftp/           (UID:${FTP_UID}, GID:${FTP_GID})"
+echo "  ├── prometheus/    (UID:${PROMETHEUS_UID}, GID:${PROMETHEUS_GID})"
+echo "  ├── grafana/       (UID:${GRAFANA_UID}, GID:${GRAFANA_GID})"
+echo "  └── etc/           (UID:${FTP_UID}, GID:${FTP_GID})"
+echo ""
+echo "您现在可以运行 'docker-compose up -d' 来启动所有服务"
+
diff --git a/src/metric/tests/init-environment.sh b/src/metric/tests/init-environment.sh
new file mode 100755
index 0000000..38f23d3
--- /dev/null
+++ b/src/metric/tests/init-environment.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+
+################################################################################
+# Ubuntu 22.04 环境初始化脚本
+# 用途：安装开发测试环境所需的基础工具
+# 系统要求：Ubuntu 22.04
+# 使用方法：sudo ./init_environment.sh
+################################################################################
+
+set -e
+
+echo "==================================="
+echo "开始安装环境依赖..."
+echo "==================================="
+
+# 更新系统
+echo "[1/4] 更新系统包列表..."
+apt-get update -y
+
+# 安装基础工具
+echo "[2/4] 安装基础工具..."
+apt-get install -y \
+    vim \
+    curl \
+    wget \
+    git \
+    htop \
+    tree \
+    net-tools \
+    dnsutils \
+    iputils-ping \
+    telnet \
+    traceroute \
+    lsof \
+    unzip \
+    zip \
+    tar \
+    jq \
+    ca-certificates \
+    gnupg \
+    lsb-release \
+    software-properties-common \
+    apt-transport-https \
+    build-essential \
+    python3 \
+    python3-pip \
+    python3-venv \
+    tmux \
+    ncdu
+
+# 安装 Docker
+echo "[3/4] 安装 Docker..."
+
+# 卸载旧版本
+apt-get remove -y docker docker-engine docker.io containerd runc 2>/dev/null || true
+
+# 添加 Docker 官方 GPG key
+install -m 0755 -d /etc/apt/keyrings
+curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
+chmod a+r /etc/apt/keyrings/docker.gpg
+
+# 添加 Docker 仓库
+echo \
+  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \
+  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
+  tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+# 更新包列表并安装 Docker
+apt-get update -y
+apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
+
+# 启动 Docker 服务
+systemctl start docker
+systemctl enable docker
+
+# 添加当前用户到 docker 组
+if [ -n "$SUDO_USER" ]; then
+    usermod -aG docker "$SUDO_USER"
+    echo "✓ 用户 $SUDO_USER 已添加到 docker 组"
+fi
+
+# 清理
+echo "[4/4] 清理..."
+apt-get autoremove -y
+apt-get autoclean -y
+
+# 显示安装结果
+echo ""
+echo "==================================="
+echo "安装完成！"
+echo "==================================="
+echo ""
+echo "已安装："
+echo "  ✓ vim"
+echo "  ✓ curl, wget, git"
+echo "  ✓ Docker: $(docker --version)"
+echo "  ✓ Docker Compose: $(docker compose version)"
+echo "  ✓ Python: $(python3 --version)"
+echo "  ✓ 其他基础工具 (htop, tree, jq, tmux 等)"
+echo ""
+if [ -n "$SUDO_USER" ]; then
+    echo "提示：请重新登录以使 docker 组权限生效"
+fi
+echo ""
+
diff --git a/src/metric/tests/manage-images.sh b/src/metric/tests/manage-images.sh
new file mode 100755
index 0000000..b47150b
--- /dev/null
+++ b/src/metric/tests/manage-images.sh
@@ -0,0 +1,371 @@
+#!/bin/bash
+
+# Docker 镜像管理脚本
+# 支持构建、保存、加载、清理镜像
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+cd "$SCRIPT_DIR"
+
+# 检测 docker-compose 命令
+if command -v docker-compose &> /dev/null; then
+    DOCKER_COMPOSE="docker-compose"
+elif docker compose version &> /dev/null 2>&1; then
+    DOCKER_COMPOSE="docker compose"
+else
+    echo "错误: 未找到 docker-compose 或 docker compose 命令"
+    exit 1
+fi
+
+# 镜像缓存目录
+IMAGE_CACHE_DIR="./images-cache"
+mkdir -p "$IMAGE_CACHE_DIR"
+
+# 定义镜像列表
+IMAGES=(
+    "argus-metric-ftp:latest"
+    "argus-metric-prometheus:latest"
+    "argus-metric-grafana:latest"
+)
+
+# 镜像文件名映射
+declare -A IMAGE_FILES=(
+    ["argus-metric-ftp:latest"]="argus-ftp.tar"
+    ["argus-metric-prometheus:latest"]="argus-prometheus.tar"
+    ["argus-metric-grafana:latest"]="argus-grafana.tar"
+)
+
+# 检查镜像是否存在
+check_image_exists() {
+    local image=$1
+    if docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
+        return 0
+    else
+        return 1
+    fi
+}
+
+# 加载镜像
+load_image() {
+    local image=$1
+    local file="${IMAGE_CACHE_DIR}/${IMAGE_FILES[$image]}"
+    
+    if [ -f "$file" ]; then
+        echo "正在从缓存加载镜像: $image"
+        docker load -i "$file"
+        return 0
+    else
+        return 1
+    fi
+}
+
+# 保存镜像
+save_image() {
+    local image=$1
+    local file="${IMAGE_CACHE_DIR}/${IMAGE_FILES[$image]}"
+    
+    if check_image_exists "$image"; then
+        echo "正在保存镜像到缓存: $image"
+        docker save -o "$file" "$image"
+        echo "已保存: $file ($(du -h "$file" | cut -f1))"
+        return 0
+    else
+        echo "镜像不存在: $image"
+        return 1
+    fi
+}
+
+# 构建所有镜像
+build_all() {
+    echo "=========================================="
+    echo "  构建所有 Docker 镜像"
+    echo "=========================================="
+    echo ""
+    
+    local build_flag="${1:---no-cache}"
+    
+    echo "开始构建镜像..."
+    $DOCKER_COMPOSE build $build_flag
+    
+    echo ""
+    echo "构建完成！"
+}
+
+# 保存所有镜像
+save_all() {
+    echo "=========================================="
+    echo "  保存所有 Docker 镜像到缓存"
+    echo "=========================================="
+    echo ""
+    
+    for image in "${IMAGES[@]}"; do
+        if save_image "$image"; then
+            echo "✓ $image"
+        else
+            echo "✗ $image (跳过)"
+        fi
+        echo ""
+    done
+    
+    echo "缓存目录: $IMAGE_CACHE_DIR"
+    echo "总大小: $(du -sh "$IMAGE_CACHE_DIR" | cut -f1)"
+}
+
+# 加载所有镜像
+load_all() {
+    echo "=========================================="
+    echo "  从缓存加载所有 Docker 镜像"
+    echo "=========================================="
+    echo ""
+    
+    local loaded=0
+    local skipped=0
+    
+    for image in "${IMAGES[@]}"; do
+        if check_image_exists "$image"; then
+            echo "镜像已存在，跳过: $image"
+            ((skipped++))
+        elif load_image "$image"; then
+            echo "✓ 已加载: $image"
+            ((loaded++))
+        else
+            echo "✗ 缓存不存在: $image"
+        fi
+        echo ""
+    done
+    
+    echo "加载: $loaded, 跳过: $skipped"
+}
+
+# 检查镜像状态
+status() {
+    echo "=========================================="
+    echo "  镜像状态"
+    echo "=========================================="
+    echo ""
+    
+    echo "Docker 镜像:"
+    for image in "${IMAGES[@]}"; do
+        if check_image_exists "$image"; then
+            local size=$(docker images --format "{{.Size}}" "$image" | head -1)
+            echo "  ✓ $image ($size)"
+        else
+            echo "  ✗ $image (未构建)"
+        fi
+    done
+    
+    echo ""
+    echo "缓存文件:"
+    if [ -d "$IMAGE_CACHE_DIR" ] && [ "$(ls -A $IMAGE_CACHE_DIR 2>/dev/null)" ]; then
+        for image in "${IMAGES[@]}"; do
+            local file="${IMAGE_CACHE_DIR}/${IMAGE_FILES[$image]}"
+            if [ -f "$file" ]; then
+                echo "  ✓ ${IMAGE_FILES[$image]} ($(du -h "$file" | cut -f1))"
+            else
+                echo "  ✗ ${IMAGE_FILES[$image]} (不存在)"
+            fi
+        done
+        echo ""
+        echo "缓存总大小: $(du -sh "$IMAGE_CACHE_DIR" | cut -f1)"
+    else
+        echo "  (无缓存文件)"
+    fi
+}
+
+# 清理缓存
+clean_cache() {
+    echo "=========================================="
+    echo "  清理镜像缓存"
+    echo "=========================================="
+    echo ""
+    
+    if [ -d "$IMAGE_CACHE_DIR" ] && [ "$(ls -A $IMAGE_CACHE_DIR 2>/dev/null)" ]; then
+        echo "缓存目录: $IMAGE_CACHE_DIR"
+        echo "大小: $(du -sh "$IMAGE_CACHE_DIR" | cut -f1)"
+        echo ""
+        read -p "确认删除所有缓存文件? (y/N): " -n 1 -r
+        echo
+        if [[ $REPLY =~ ^[Yy]$ ]]; then
+            rm -rf "$IMAGE_CACHE_DIR"/*.tar
+            echo "已清理缓存文件"
+        else
+            echo "已取消"
+        fi
+    else
+        echo "没有缓存文件"
+    fi
+}
+
+# 清理 Docker 镜像
+clean_images() {
+    echo "=========================================="
+    echo "  清理 Docker 镜像"
+    echo "=========================================="
+    echo ""
+    
+    local exists=0
+    for image in "${IMAGES[@]}"; do
+        if check_image_exists "$image"; then
+            exists=1
+            break
+        fi
+    done
+    
+    if [ $exists -eq 0 ]; then
+        echo "没有需要清理的镜像"
+        return
+    fi
+    
+    echo "将删除以下镜像:"
+    for image in "${IMAGES[@]}"; do
+        if check_image_exists "$image"; then
+            echo "  - $image"
+        fi
+    done
+    echo ""
+    
+    read -p "确认删除这些镜像? (y/N): " -n 1 -r
+    echo
+    if [[ $REPLY =~ ^[Yy]$ ]]; then
+        for image in "${IMAGES[@]}"; do
+            if check_image_exists "$image"; then
+                docker rmi "$image"
+                echo "已删除: $image"
+            fi
+        done
+    else
+        echo "已取消"
+    fi
+}
+
+# 智能准备镜像（自动检测并加载或构建）
+prepare() {
+    echo "=========================================="
+    echo "  智能准备 Docker 镜像"
+    echo "=========================================="
+    echo ""
+    
+    local need_build=()
+    local loaded=0
+    local existed=0
+    
+    for image in "${IMAGES[@]}"; do
+        if check_image_exists "$image"; then
+            echo "✓ 镜像已存在: $image"
+            ((existed++))
+        elif load_image "$image"; then
+            echo "✓ 已从缓存加载: $image"
+            ((loaded++))
+        else
+            echo "✗ 需要构建: $image"
+            need_build+=("$image")
+        fi
+    done
+    
+    echo ""
+    echo "统计: 已存在 $existed, 已加载 $loaded, 需构建 ${#need_build[@]}"
+    
+    if [ ${#need_build[@]} -gt 0 ]; then
+        echo ""
+        echo "需要构建以下镜像:"
+        for image in "${need_build[@]}"; do
+            echo "  - $image"
+        done
+        echo ""
+        
+        read -p "是否现在构建? (Y/n): " -n 1 -r
+        echo
+        if [[ ! $REPLY =~ ^[Nn]$ ]]; then
+            build_all ""
+            echo ""
+            read -p "是否保存新构建的镜像到缓存? (Y/n): " -n 1 -r
+            echo
+            if [[ ! $REPLY =~ ^[Nn]$ ]]; then
+                save_all
+            fi
+        fi
+    else
+        echo ""
+        echo "所有镜像已就绪！"
+    fi
+}
+
+# 显示帮助
+show_help() {
+    cat << EOF
+Docker 镜像管理工具
+
+用法: $0 <command>
+
+命令:
+  prepare          智能准备镜像（推荐）- 自动检测、加载或构建
+  build            构建所有镜像
+  build-cache      使用缓存构建
+  save             保存所有镜像到缓存
+  load             从缓存加载所有镜像
+  status           查看镜像状态
+  clean-cache      清理缓存文件
+  clean-images     清理 Docker 镜像
+  clean-all        清理缓存和镜像
+  help             显示此帮助信息
+
+示例:
+  # 智能准备（首次使用或镜像丢失时）
+  $0 prepare
+  
+  # 构建并保存镜像
+  $0 build
+  $0 save
+  
+  # 从缓存加载镜像
+  $0 load
+  
+  # 查看状态
+  $0 status
+
+镜像缓存目录: $IMAGE_CACHE_DIR/
+EOF
+}
+
+# 主逻辑
+case "${1:-help}" in
+    prepare)
+        prepare
+        ;;
+    build)
+        build_all "--no-cache"
+        ;;
+    build-cache)
+        build_all ""
+        ;;
+    save)
+        save_all
+        ;;
+    load)
+        load_all
+        ;;
+    status)
+        status
+        ;;
+    clean-cache)
+        clean_cache
+        ;;
+    clean-images)
+        clean_images
+        ;;
+    clean-all)
+        clean_cache
+        clean_images
+        ;;
+    help|--help|-h)
+        show_help
+        ;;
+    *)
+        echo "错误: 未知命令 '$1'"
+        echo ""
+        show_help
+        exit 1
+        ;;
+esac
+
diff --git a/src/metric/tests/start-all.sh b/src/metric/tests/start-all.sh
new file mode 100755
index 0000000..b0ceb72
--- /dev/null
+++ b/src/metric/tests/start-all.sh
@@ -0,0 +1,199 @@
+#!/bin/bash
+
+# 一键启动脚本
+# 用于初始化目录、构建镜像并启动所有服务
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+cd "$SCRIPT_DIR"
+
+echo "=========================================="
+echo "  Argus Metrics 一键启动脚本"
+echo "=========================================="
+echo ""
+echo "当前工作目录: $SCRIPT_DIR"
+echo ""
+
+# 检查 Docker 和 Docker Compose
+if ! command -v docker &> /dev/null; then
+    echo "错误: 未找到 docker 命令，请先安装 Docker"
+    exit 1
+fi
+
+# 检测 docker-compose 命令（兼容新旧版本）
+COMPOSE_FILE="$SCRIPT_DIR/docker-compose.yml"
+if command -v docker-compose &> /dev/null; then
+    DOCKER_COMPOSE="docker-compose -f $COMPOSE_FILE"
+    echo "使用: docker-compose"
+elif docker compose version &> /dev/null 2>&1; then
+    DOCKER_COMPOSE="docker compose -f $COMPOSE_FILE"
+    echo "使用: docker compose"
+else
+    echo "错误: 未找到 docker-compose 或 docker compose 命令"
+    exit 1
+fi
+echo "Compose 文件: $COMPOSE_FILE"
+echo ""
+
+# 检查必要的构建目录
+echo "检查构建目录..."
+BUILD_DIRS=(
+    "../ftp/build"
+    "../prometheus/build"
+    "../grafana/build"
+)
+
+for dir in "${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: $dir"
+    fi
+done
+echo ""
+
+# 检查并创建 .env 文件
+if [ ! -f .env ]; then
+    echo "未找到 .env 文件，从 env.example 创建..."
+    cp env.example .env
+    echo "已创建 .env 文件，请根据需要修改配置"
+fi
+
+# 加载环境变量
+source .env
+
+echo "1. 初始化目录结构..."
+bash "$SCRIPT_DIR/init-directories.sh"
+
+echo ""
+echo "2. 准备 Docker 镜像..."
+
+# 检查镜像是否存在
+IMAGE_CACHE_DIR="./images-cache"
+IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana: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 $all_images_exist; then
+    echo "所有镜像已存在，跳过构建"
+else
+    echo "检测到缺失镜像，尝试从缓存加载..."
+    
+    # 尝试从缓存加载
+    loaded_from_cache=false
+    if [ -d "$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="${IMAGE_CACHE_DIR}/argus-grafana.tar"
+                        ;;
+                esac
+                
+                if [ -f "$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: $(pwd)"
+        cd "$SCRIPT_DIR"
+        $DOCKER_COMPOSE build
+        
+        # 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"
+                        ;;
+                esac
+            done
+            echo "镜像已保存到: $IMAGE_CACHE_DIR/"
+        fi
+    elif $loaded_from_cache; then
+        echo ""
+        echo "所有镜像已从缓存加载完成！"
+    fi
+fi
+
+echo ""
+echo "3. 启动服务..."
+cd "$SCRIPT_DIR"
+$DOCKER_COMPOSE up -d
+
+echo ""
+echo "4. 等待服务启动..."
+sleep 5
+
+echo ""
+echo "5. 检查服务状态..."
+cd "$SCRIPT_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: $DOCKER_COMPOSE down -v"
+echo ""
+
diff --git a/src/metric/tests/stop-all.sh b/src/metric/tests/stop-all.sh
new file mode 100755
index 0000000..6886160
--- /dev/null
+++ b/src/metric/tests/stop-all.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+
+# 停止所有服务脚本
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+cd "$SCRIPT_DIR"
+
+# 检测 docker-compose 命令（兼容新旧版本）
+COMPOSE_FILE="$SCRIPT_DIR/docker-compose.yml"
+if command -v docker-compose &> /dev/null; then
+    DOCKER_COMPOSE="docker-compose -f $COMPOSE_FILE"
+elif docker compose version &> /dev/null 2>&1; then
+    DOCKER_COMPOSE="docker compose -f $COMPOSE_FILE"
+else
+    echo "错误: 未找到 docker-compose 或 docker compose 命令"
+    exit 1
+fi
+
+echo "=========================================="
+echo "  停止 Argus Metrics 服务"
+echo "=========================================="
+echo ""
+
+# 检查是否有运行的容器
+if [ "$($DOCKER_COMPOSE ps -q)" ]; then
+    echo "停止所有服务..."
+    $DOCKER_COMPOSE stop
+    
+    echo ""
+    read -p "是否要删除容器? (y/N): " -n 1 -r
+    echo
+    if [[ $REPLY =~ ^[Yy]$ ]]; then
+        $DOCKER_COMPOSE down
+        echo "容器已删除"
+        
+        read -p "是否要删除数据卷? (y/N): " -n 1 -r
+        echo
+        if [[ $REPLY =~ ^[Yy]$ ]]; then
+            $DOCKER_COMPOSE down -v
+            echo "数据卷已删除"
+        fi
+    fi
+else
+    echo "没有运行的服务"
+fi
+
+echo ""
+echo "完成！"
+
diff --git a/src/metric/tests/test_grafana_dashboard.json b/src/metric/tests/test_grafana_dashboard.json
new file mode 100644
index 0000000..4a09e80
--- /dev/null
+++ b/src/metric/tests/test_grafana_dashboard.json
@@ -0,0 +1,629 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": 9,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Load",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 101,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "node_load1{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} load1",
+          "refId": "A"
+        },
+        {
+          "expr": "node_load5{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} load5",
+          "refId": "B"
+        },
+        {
+          "expr": "node_load15{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} load15",
+          "refId": "C"
+        }
+      ],
+      "title": "System Load",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "100 * (1 - avg by(hostname) (irate(node_cpu_seconds_total{mode=\"idle\",hostname=\"$hostname\"}[5m])))",
+          "legendFormat": "{{hostname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "CPU Usage",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "%",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 70
+              },
+              {
+                "color": "red",
+                "value": 90
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "100 * (1 - (node_memory_MemAvailable_bytes{hostname=\"$hostname\"} / node_memory_MemTotal_bytes{hostname=\"$hostname\"}))",
+          "legendFormat": "{{hostname}}",
+          "refId": "B"
+        }
+      ],
+      "title": "Node Memory Usage",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Bytes/s",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum by(hostname) (rate(node_disk_read_bytes_total{device!~\"^(loop|ram|sr0).*\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} read",
+          "refId": "A"
+        },
+        {
+          "expr": "sum by(hostname) (rate(node_disk_written_bytes_total{device!~\"^(loop|ram|sr0).*\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} write",
+          "refId": "B"
+        }
+      ],
+      "title": "Node Disk I/O (Bytes/s)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Bytes/s",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "id": 102,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum by(hostname)(rate(node_network_receive_bytes_total{device!~\"^(lo|docker.*)\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} RX",
+          "refId": "A"
+        },
+        {
+          "expr": "sum by(hostname)(rate(node_network_transmit_bytes_total{device!~\"^(lo|docker.*)\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} TX",
+          "refId": "B"
+        }
+      ],
+      "title": "Network Traffic",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Processes",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 200
+              },
+              {
+                "color": "red",
+                "value": 500
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "id": 104,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "node_procs_running{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} Running",
+          "refId": "A"
+        },
+        {
+          "expr": "node_procs_blocked{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} Blocked",
+          "refId": "B"
+        }
+      ],
+      "title": "Node Process Count",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "15s",
+  "schemaVersion": 39,
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "current": {
+          "selected": true,
+          "text": "node-exporter-A1",
+          "value": "node-exporter-A1"
+        },
+        "datasource": {
+          "type": "prometheus"
+        },
+        "definition": "label_values(node_cpu_seconds_total,hostname)",
+        "hide": 0,
+        "includeAll": false,
+        "label": "hostname",
+        "multi": false,
+        "name": "hostname",
+        "options": [],
+        "query": {
+          "qryType": 1,
+          "query": "label_values(node_cpu_seconds_total,hostname)",
+          "refId": "PrometheusVariableQueryEditor-VariableQuery"
+        },
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "type": "query"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-12h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Node and GPU Metrics",
+  "uid": "node_gpu_metrics",
+  "weekStart": ""
+}
\ No newline at end of file