refactor: metric e2e测试流程融合到 sys/tests 步骤中（bootstrap/up/publish/installer）；

refs #29

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

@@ -13,10 +13,33 @@ compose() {
 }
 
 echo "[INFO] Bringing up system stack..."
+
+# 加载环境变量
+if [ -f "$TEST_ROOT/.env" ]; then
+    source "$TEST_ROOT/.env"
+    echo "[INFO] 已加载环境变量，GPU_AVAILABLE=$GPU_AVAILABLE"
+else
+    echo "[WARN] 未找到.env文件，默认GPU不可用"
+    GPU_AVAILABLE=false
+fi
+
 pushd "$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 +1,47 @@
+#!/bin/bash
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+COMMON_DIR="$SCRIPT_DIR/common"
+
+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="${FTP_SERVER}"
+
+echo "[04] 检测GPU环境..."
+# 检测GPU环境
+if bash "$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 '[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"