build/build_images.sh

@@ -254,6 +254,54 @@ if [[ "$build_metric" == true ]]; then
   done
 fi
 
+# =======================================
+# Web & Alert module images
+# =======================================
+
+echo ""
+echo "Building Web and Alert module images..."
+
+# Pre-pull commonly used base images for stability
+web_alert_base_images=(
+  "node:20"
+  "ubuntu:24.04"
+)
+
+for base_image in "${web_alert_base_images[@]}"; do
+  if ! pull_base_image "$base_image"; then
+    build_failed=true
+  fi
+done
+
+web_builds=(
+  "Web Frontend|src/web/build_tools/frontend/Dockerfile|argus-web-frontend:latest|."
+  "Web Proxy|src/web/build_tools/proxy/Dockerfile|argus-web-proxy:latest|."
+)
+
+for build_spec in "${web_builds[@]}"; do
+  IFS='|' read -r image_label dockerfile_path image_tag build_context <<< "$build_spec"
+  if build_image "$image_label" "$dockerfile_path" "$image_tag" "$build_context"; then
+    images_built+=("$image_tag")
+  else
+    build_failed=true
+  fi
+  echo ""
+done
+
+alert_builds=(
+  "Alertmanager|src/alert/alertmanager/build/Dockerfile|argus-alertmanager:latest|."
+)
+
+for build_spec in "${alert_builds[@]}"; do
+  IFS='|' read -r image_label dockerfile_path image_tag build_context <<< "$build_spec"
+  if build_image "$image_label" "$dockerfile_path" "$image_tag" "$build_context"; then
+    images_built+=("$image_tag")
+  else
+    build_failed=true
+  fi
+  echo ""
+done
+
 echo "======================================="
 echo "📦 Build Summary"
 echo "======================================="

build/save_images.sh

@@ -71,6 +71,9 @@ declare -A images=(
     ["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-web-frontend:latest"]="argus-web-frontend-latest.tar"
+    ["argus-web-proxy:latest"]="argus-web-proxy-latest.tar"
+    ["argus-alertmanager:latest"]="argus-alertmanager-latest.tar"
 )
 
 # 函数：检查镜像是否存在

src/alert/alertmanager/build/Dockerfile

@@ -20,10 +20,10 @@ RUN wget https://github.com/prometheus/alertmanager/releases/download/v${ALERTMA
 
 ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
 
-ARG ARGUS_UID=2133
+ARG ARGUS_BUILD_UID=2133
-ARG ARGUS_GID=2015
+ARG ARGUS_BUILD_GID=2015
-ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID}
-ENV ARGUS_GID=${ARGUS_GID}
+ENV ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
 
 RUN mkdir -p /usr/share/alertmanager && \
     mkdir -p ${ALERTMANAGER_BASE_PATH} && \
@@ -33,16 +33,25 @@ RUN mkdir -p /usr/share/alertmanager && \
 
 # 创建 alertmanager 用户（可自定义 UID/GID）
 # 创建 alertmanager 用户组
-RUN groupadd -g ${ARGUS_GID} alertmanager
+RUN set -eux; \
+    if ! getent group "${ARGUS_BUILD_GID}" >/dev/null; then \
+        groupadd -g "${ARGUS_BUILD_GID}" alertmanager || true; \
+    fi; \
+    if id alertmanager >/dev/null 2>&1; then \
+        current_uid="$(id -u alertmanager)"; \
+        if [ "$current_uid" != "${ARGUS_BUILD_UID}" ] && ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
+            usermod -u "${ARGUS_BUILD_UID}" alertmanager; \
+        fi; \
+        usermod -g "${ARGUS_BUILD_GID}" alertmanager || true; \
+    else \
+        if ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
+            useradd -M -s /usr/sbin/nologin -u "${ARGUS_BUILD_UID}" -g "${ARGUS_BUILD_GID}" alertmanager; \
+        else \
+            echo "UID ${ARGUS_BUILD_UID} already exists; skip creating user 'alertmanager'"; \
+        fi; \
+    fi
 
-# 创建 alertmanager 用户并指定组
+RUN chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" /usr/share/alertmanager /alertmanager ${ALERTMANAGER_BASE_PATH} /private/argus/etc /usr/local/bin || true
-RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} alertmanager
-
-RUN chown -R alertmanager:alertmanager /usr/share/alertmanager && \
-    chown -R alertmanager:alertmanager /alertmanager && \
-    chown -R alertmanager:alertmanager ${ALERTMANAGER_BASE_PATH} && \
-    chown -R alertmanager:alertmanager /private/argus/etc && \
-    chown -R alertmanager:alertmanager /usr/local/bin
 
 # 配置内网 apt 源 (如果指定了内网选项)
 RUN if [ "$USE_INTRANET" = "true" ]; then \
@@ -86,4 +95,3 @@ EXPOSE 9093
 
 # 使用 supervisor 作为入口点
 CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
-

src/alert/alertmanager/build/build.sh

@@ -5,8 +5,8 @@ docker pull ubuntu:24.04
 source src/alert/tests/.env
 
 docker build \
-  --build-arg ARGUS_UID=${ARGUS_UID} \
+  --build-arg ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
-  --build-arg ARGUS_GID=${ARGUS_GID} \
+  --build-arg ARGUS_BUILD_GID=${ARGUS_BUILD_GID} \
   -f src/alert/alertmanager/build/Dockerfile \
   -t argus-alertmanager:latest .
 

src/alert/tests/.env

@@ -1,5 +1,5 @@
 DATA_ROOT=/home/argus/tmp/private/argus
-ARGUS_UID=1048
+ARGUS_BUILD_UID=1048
-ARGUS_GID=1048
+ARGUS_BUILD_GID=1048
 
 USE_INTRANET=false

src/alert/tests/docker-compose.yml

@@ -4,15 +4,15 @@ services:
       context: ../../../
       dockerfile: src/alert/alertmanager/build/Dockerfile
       args:
-        ARGUS_UID: ${ARGUS_UID:-2133}
+        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_GID: ${ARGUS_GID:-2015}
+        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
         USE_INTRANET: ${USE_INTRANET:-false}
     image: argus-alertmanager:latest
     container_name: argus-alertmanager
     environment:
       - ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
-      - ARGUS_UID=${ARGUS_UID:-2133}
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_GID=${ARGUS_GID:-2015}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
     ports:
       - "${ARGUS_PORT:-9093}:9093"
     volumes:

src/bind/build/Dockerfile

@@ -26,6 +26,7 @@ RUN apt-get update && \
     apt-get install -y \
     bind9 \
     bind9utils \
+    dnsutils \
     bind9-doc \
     supervisor \
     net-tools \

src/metric/client-plugins/all-in-one-demo/scripts/publish_artifact.sh

@@ -104,7 +104,26 @@ log_info "文件所有者: $OWNER"
 
 # 确保发布目录存在
 log_info "确保发布目录存在: $PUBLISH_DIR"
-sudo mkdir -p "$PUBLISH_DIR"
+mkdir -p "$PUBLISH_DIR"
+
+IFS=':' read -r OWNER_UID OWNER_GID <<< "$OWNER"
+if [[ -z "$OWNER_UID" || -z "$OWNER_GID" ]]; then
+    log_error "--owner 格式不正确，应为 uid:gid"
+    exit 1
+fi
+
+CURRENT_UID=$(id -u)
+CURRENT_GID=$(id -g)
+if [[ "$OWNER_UID" != "$CURRENT_UID" || "$OWNER_GID" != "$CURRENT_GID" ]]; then
+    if [[ "$CURRENT_UID" -ne 0 ]]; then
+        log_error "当前用户 (${CURRENT_UID}:${CURRENT_GID}) 无法设置所有者为 ${OWNER_UID}:${OWNER_GID}"
+        log_error "请以目标用户运行脚本或预先调整目录权限"
+        exit 1
+    fi
+    NEED_CHOWN=true
+else
+    NEED_CHOWN=false
+fi
 
 # 创建临时目录用于打包
 TEMP_PACKAGE_DIR="/tmp/argus-metric-package-$$"
@@ -208,26 +227,31 @@ fi
 TAR_NAME="argus-metric_$(echo $VERSION | tr '.' '_').tar.gz"
 log_info "创建发布包: $TAR_NAME"
 cd "$TEMP_PACKAGE_DIR"
-sudo tar -czf "$PUBLISH_DIR/$TAR_NAME" *
+tar -czf "$PUBLISH_DIR/$TAR_NAME" *
 cd - > /dev/null
 
-# 设置文件所有者
+if [[ "$NEED_CHOWN" == true ]]; then
-log_info "设置文件所有者为: $OWNER"
+    log_info "设置文件所有者为: $OWNER"
-sudo chown "$OWNER" "$PUBLISH_DIR/$TAR_NAME"
+    chown "$OWNER" "$PUBLISH_DIR/$TAR_NAME"
+fi
 
 # 清理临时目录
 rm -rf "$TEMP_PACKAGE_DIR"
 
 # 更新 LATEST_VERSION 文件
 log_info "更新 LATEST_VERSION 文件..."
-echo "$VERSION" | sudo tee "$PUBLISH_DIR/LATEST_VERSION" > /dev/null
+echo "$VERSION" > "$PUBLISH_DIR/LATEST_VERSION"
-sudo chown "$OWNER" "$PUBLISH_DIR/LATEST_VERSION"
+if [[ "$NEED_CHOWN" == true ]]; then
+    chown "$OWNER" "$PUBLISH_DIR/LATEST_VERSION"
+fi
 
 # 复制 DNS 配置文件到发布目录根目录（直接从 config 目录复制）
 if [[ -f "config/dns.conf" ]]; then
     log_info "复制 DNS 配置文件到发布目录根目录..."
-    sudo cp "config/dns.conf" "$PUBLISH_DIR/"
+    cp "config/dns.conf" "$PUBLISH_DIR/"
-    sudo chown "$OWNER" "$PUBLISH_DIR/dns.conf"
+    if [[ "$NEED_CHOWN" == true ]]; then
+        chown "$OWNER" "$PUBLISH_DIR/dns.conf"
+    fi
     log_success "DNS 配置文件复制完成: $PUBLISH_DIR/dns.conf"
 else
     log_warning "未找到 config/dns.conf 文件，跳过 DNS 配置文件复制"
@@ -236,8 +260,10 @@ fi
 # 复制 setup.sh 到发布目录
 if [[ -f "scripts/setup.sh" ]]; then
     log_info "复制 setup.sh 到发布目录..."
-    sudo cp "scripts/setup.sh" "$PUBLISH_DIR/"
+    cp "scripts/setup.sh" "$PUBLISH_DIR/"
-    sudo chown "$OWNER" "$PUBLISH_DIR/setup.sh"
+    if [[ "$NEED_CHOWN" == true ]]; then
+        chown "$OWNER" "$PUBLISH_DIR/setup.sh"
+    fi
 fi
 
 # 显示发布结果

src/metric/grafana/build/Dockerfile

@@ -65,6 +65,8 @@ COPY grafana.ini /tmp/grafana.ini
 COPY datasources/datasources.yml /tmp/datasources.yml
 COPY dashboards/dashboards.yml /tmp/dashboards.yml
 COPY dashboards/default_dashboard_by_hostname.json /tmp/default_dashboard.json
+COPY dashboards/default_cluster_dashboard.json /tmp/default_cluster_dashboard.json
+COPY dashboards/default_dashboard_by_instance.json /tmp/default_dashboard_by_instance.json
 
 # supervisor 配置
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf

src/metric/grafana/build/datasources/datasources.yml

@@ -8,7 +8,7 @@ datasources:
     type: prometheus
     access: proxy
     uid: eezk1zvkie4g0a
-    url: http://10.211.55.5:9090
+    url: http://prom.metric.argus.com:9090
     isDefault: true
     editable: true
     jsonData:

src/metric/grafana/build/start-grafana-supervised.sh

@@ -44,12 +44,18 @@ else
 fi
 
 # 复制数据源配置文件到挂载目录
-if [ -f "/tmp/datasources.yml" ]; then
+DS_OUT="/private/argus/metric/grafana/provisioning/datasources/datasources.yml"
-    echo "[INFO] Copying datasource configuration to /private/argus/metric/grafana/provisioning/datasources/"
+PROM_DOMAIN="prom.metric.argus.com:9090"
-    cp /tmp/datasources.yml /private/argus/metric/grafana/provisioning/datasources/datasources.yml
+
-    echo "[INFO] Datasource configuration copied successfully"
+if [ -f "/tmp/datasources.yml" ] && [ ! -f "$DS_OUT" ]; then
-elif [ -d "/private/argus/metric/grafana/provisioning/datasources" ] && [ "$(ls -A /private/argus/metric/grafana/provisioning/datasources)" ]; then
+    echo "[INFO] Initializing datasource provisioning file from /tmp"
-    echo "[INFO] Found existing datasource provisioning files in /private/argus/metric/grafana/provisioning/datasources"
+    cp /tmp/datasources.yml "$DS_OUT"
+fi
+
+# 统一将数据源 URL 规范为 prom.metric.argus.com:9090
+if [ -f "$DS_OUT" ]; then
+    sed -i -E "s#^\s*url:\s*http://[^[:space:]]+#    url: http://$PROM_DOMAIN#g" "$DS_OUT" || true
+    echo "[INFO] Datasource URL normalized to http://$PROM_DOMAIN"
 elif [ -d "/etc/grafana/provisioning/datasources" ] && [ "$(ls -A /etc/grafana/provisioning/datasources)" ]; then
     echo "[INFO] Found datasource provisioning files in /etc/grafana/provisioning/datasources"
     # 确保数据源配置目录权限正确
@@ -65,11 +71,33 @@ if [ -f "/tmp/dashboards.yml" ]; then
     echo "[INFO] Dashboard configuration copied successfully"
 fi
 
-# 复制默认仪表板到挂载目录
+# 复制默认仪表板到挂载目录（按需，不覆盖已存在文件）
-if [ -f "/tmp/default_dashboard.json" ]; then
+copy_dashboard_if_missing() {
-    echo "[INFO] Copying default dashboard to /private/argus/metric/grafana/provisioning/dashboards/"
+    local src="$1"; local dst_name="$2"
-    cp /tmp/default_dashboard.json /private/argus/metric/grafana/provisioning/dashboards/default_dashboard.json
+    local dst_dir="/private/argus/metric/grafana/provisioning/dashboards"
-    echo "[INFO] Default dashboard copied successfully"
+    local dst="$dst_dir/$dst_name"
+    if [ -f "$src" ]; then
+        if [ ! -f "$dst" ]; then
+            echo "[INFO] Installing dashboard: $dst_name"
+            cp "$src" "$dst"
+        else
+            echo "[INFO] Dashboard exists, skip: $dst_name"
+        fi
+    fi
+}
+
+copy_dashboard_if_missing "/tmp/default_dashboard.json" "default_dashboard.json"
+copy_dashboard_if_missing "/tmp/default_cluster_dashboard.json" "default_cluster_dashboard.json"
+copy_dashboard_if_missing "/tmp/default_dashboard_by_instance.json" "default_dashboard_by_instance.json"
+
+# 规范面板中的数据源字段：将字符串 "prometheus" 替换为 null（使用默认数据源）
+DB_DIR="/private/argus/metric/grafana/provisioning/dashboards"
+if [ -d "$DB_DIR" ]; then
+  for f in "$DB_DIR"/*.json; do
+    [ -f "$f" ] || continue
+    sed -i -E 's/"datasource"\s*:\s*"prometheus"/"datasource": null/g' "$f" || true
+  done
+  echo "[INFO] Normalized dashboard datasource to default (null)"
 fi
 
 # 启动 Grafana

src/sys/tests/docker-compose.yml

@@ -1,9 +1,5 @@
--version: "3.8"
-
 networks:
-  default:
+  sysnet:
-    external: true
-    name: argus-sys-net
     driver: bridge
     ipam:
       driver: default
@@ -15,7 +11,7 @@ services:
     image: ${BIND_IMAGE_TAG:-argus-bind9:latest}
     container_name: argus-bind-sys
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.2
     volumes:
       - ./private:/private
@@ -39,7 +35,7 @@ services:
       - ./private/argus/metric/prometheus:/private/argus/metric/prometheus
       - ./private/argus/etc:/private/argus/etc
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.10
     restart: unless-stopped
 
@@ -58,6 +54,9 @@ services:
     ports:
       - "9200:9200"
     restart: unless-stopped
+    networks:
+      sysnet:
+        ipv4_address: 172.29.0.3
 
   kibana:
     image: argus-kibana:latest
@@ -74,6 +73,9 @@ services:
     ports:
       - "5601:5601"
     restart: unless-stopped
+    networks:
+      sysnet:
+        ipv4_address: 172.29.0.4
 
   node-a:
     image: ubuntu:22.04
@@ -106,6 +108,8 @@ services:
     ports:
       - "2020:2020"
     restart: unless-stopped
+    networks:
+      - sysnet
 
   node-b:
     image: ubuntu:22.04
@@ -138,6 +142,8 @@ services:
     ports:
       - "2021:2020"
     restart: unless-stopped
+    networks:
+      - sysnet
 
   ftp:
     image: argus-metric-ftp:latest
@@ -160,7 +166,7 @@ services:
       - /etc/localtime:/etc/localtime:ro
       - /etc/timezone:/etc/timezone:ro
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.40
     logging:
       driver: "json-file"
@@ -185,7 +191,7 @@ services:
       - /etc/localtime:/etc/localtime:ro
       - /etc/timezone:/etc/timezone:ro
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.41
     logging:
       driver: "json-file"
@@ -205,6 +211,9 @@ services:
       - GF_SERVER_HTTP_PORT=3000
       - GF_LOG_LEVEL=warn
       - GF_LOG_MODE=console
+      - GF_PATHS_PROVISIONING=/private/argus/metric/grafana/provisioning
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Viewer
     ports:
       - "${GRAFANA_PORT:-3000}:3000"
     volumes:
@@ -213,7 +222,7 @@ services:
       - /etc/localtime:/etc/localtime:ro
       - /etc/timezone:/etc/timezone:ro
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.42
     depends_on:
       - prometheus
@@ -224,7 +233,7 @@ services:
         max-file: "3"
 
   test-node:
-    image: argus-metric-test-node:latest
+    image: ubuntu:22.04
     container_name: argus-metric-test-node
     hostname: test-metric-node-001
     restart: unless-stopped
@@ -240,13 +249,21 @@ services:
       - FTP_USER=${FTP_USER:-ftpuser}
       - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
       - FTP_PORT=${FTP_PORT:-21}
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      - METRIC_NODE_ROLE=cpu
     volumes:
       - ./private/argus/agent:/private/argus/agent
+      - ./scripts/metric/test-node-entrypoint.sh:/usr/local/bin/metric-test-node-entrypoint.sh:ro
       - /etc/localtime:/etc/localtime:ro
       - /etc/timezone:/etc/timezone:ro
-    command: sleep infinity
+    entrypoint:
+      - /usr/local/bin/metric-test-node-entrypoint.sh
+    command:
+      - sleep
+      - infinity
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.50
     logging:
       driver: "json-file"
@@ -255,7 +272,8 @@ services:
         max-file: "3"
 
   test-gpu-node:
-    image: argus-metric-test-gpu-node:latest
+    profiles: ["gpu"]
+    image: nvidia/cuda:12.2.2-runtime-ubuntu22.04
     container_name: argus-metric-test-gpu-node
     hostname: test-metric-gpu-node-001
     restart: unless-stopped
@@ -278,13 +296,21 @@ services:
       - NVIDIA_VISIBLE_DEVICES=all
       - NVIDIA_DRIVER_CAPABILITIES=compute,utility
       - GPU_MODE=gpu
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      - METRIC_NODE_ROLE=gpu
     volumes:
       - ./private/argus/agent:/private/argus/agent
+      - ./scripts/metric/test-node-entrypoint.sh:/usr/local/bin/metric-test-node-entrypoint.sh:ro
       - /etc/localtime:/etc/localtime:ro
       - /etc/timezone:/etc/timezone:ro
-    command: sleep infinity
+    entrypoint:
+      - /usr/local/bin/metric-test-node-entrypoint.sh
+    command:
+      - sleep
+      - infinity
     networks:
-      default:
+      sysnet:
         ipv4_address: 172.29.0.51
     logging:
       driver: "json-file"

src/sys/tests/scripts/00_e2e_test.sh

@@ -3,6 +3,38 @@ set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
+ENABLE_GPU=false
+
+usage() {
+  cat <<'EOF'
+Usage: 00_e2e_test.sh [options]
+
+Options:
+  --enable-gpu   启用 GPU 相关拓扑与测试流程
+  -h, --help     显示帮助信息
+EOF
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --enable-gpu)
+      ENABLE_GPU=true
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage
+      exit 1
+      ;;
+  esac
+done
+
+export ARGUS_SYS_ENABLE_GPU=$ENABLE_GPU
+
 SCRIPTS=(
   "01_bootstrap.sh"
   "02_up.sh"
@@ -12,6 +44,11 @@ SCRIPTS=(
   "06_write_health_and_assert.sh"
   "07_logs_send_and_assert.sh"
   "08_restart_agent_reregister.sh"
+  "10_metric_publish.sh"
+  "11_metric_node_install.sh"
+  "12_metric_gpu_install.sh"
+  "13_metric_verify.sh"
+  "14_metric_cleanup.sh"
   "09_down.sh"
 )
 
@@ -23,4 +60,3 @@ for script in "${SCRIPTS[@]}"; do
 done
 
 echo "[SYS-E2E] All tests completed"
-

src/sys/tests/scripts/01_bootstrap.sh

@@ -22,6 +22,24 @@ ensure_image() {
 }
 
 echo "[INFO] Preparing directories..."
+ensure_writable_dir() {
+  local path="$1"
+  local parent
+  parent="$(dirname "$path")"
+  mkdir -p "$parent" 2>/dev/null || true
+  mkdir -p "$path" 2>/dev/null || true
+  if [[ ! -w "$path" ]]; then
+    docker run --rm -v "$parent:/target" ubuntu:24.04 bash -lc "chown -R $(id -u):$(id -g) /target" >/dev/null 2>&1 || true
+  fi
+  mkdir -p "$path"
+}
+
+# preflight: make base dirs writable if inherited from root-owned mounts
+ensure_writable_dir "$PRIVATE_CORE/argus"
+ensure_writable_dir "$PRIVATE_CORE/argus/metric"
+ensure_writable_dir "$PRIVATE_CORE/argus/metric/grafana"
+ensure_writable_dir "$PRIVATE_CORE/argus/metric/prometheus"
+
 mkdir -p \
   "$PRIVATE_CORE/argus/etc" \
   "$PRIVATE_CORE/argus/bind" \
@@ -57,6 +75,8 @@ chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" \
   "$PRIVATE_CORE/argus/agent" \
   "$PRIVATE_CORE/argus/etc" 2>/dev/null || true
 
+echo "[INFO] Using compose-managed network (auto-created by docker compose)"
+
 echo "[INFO] Distributing update-dns.sh for core services (bind/master/es/kibana)"
 BIND_UPDATE_SRC="$REPO_ROOT/src/bind/build/update-dns.sh"
 BIND_UPDATE_DEST="$PRIVATE_CORE/argus/etc/update-dns.sh"
@@ -75,8 +95,6 @@ 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 "$REPO_ROOT/src/agent" >/dev/null
@@ -91,19 +109,25 @@ fi
 echo "$AGENT_BIN" > "$TMP_DIR/agent_binary_path"
 
 # 检测GPU环境
-echo "[INFO] 检测GPU环境..."
+REQUEST_GPU=${ARGUS_SYS_ENABLE_GPU:-false}
 GPU_CHECK_SCRIPT="$REPO_ROOT/src/metric/tests/scripts/common/check-gpu.sh"
-if [ -f "$GPU_CHECK_SCRIPT" ]; then
+if [[ "$REQUEST_GPU" == "true" ]]; then
+  echo "[INFO] --enable-gpu 已启用，开始检测GPU环境..."
+  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"
+      echo "[INFO] GPU环境可用，将在 compose 中启用 test-gpu-node"
       GPU_AVAILABLE=true
     else
-        echo "[INFO] GPU环境不可用，跳过test-gpu-node容器"
+      echo "[ERROR] 未检测到可用 GPU，但指定了 --enable-gpu" >&2
-        GPU_AVAILABLE=false
+      exit 1
+    fi
+  else
+    echo "[ERROR] 未找到 GPU 检测脚本: $GPU_CHECK_SCRIPT" >&2
+    exit 1
   fi
 else
-    echo "[WARN] 未找到GPU检测脚本: $GPU_CHECK_SCRIPT，跳过GPU检测"
   GPU_AVAILABLE=false
+  echo "[INFO] GPU 支持未启用，跳过 GPU 检测"
 fi
 
 echo "[INFO] Writing .env with UID/GID and metric configuration"
@@ -112,7 +136,7 @@ ARGUS_BUILD_UID=$ARGUS_BUILD_UID
 ARGUS_BUILD_GID=$ARGUS_BUILD_GID
 
 # GPU 配置
-GPU_AVAILABLE=$GPU_AVAILABLE
+ENABLE_GPU=$GPU_AVAILABLE
 
 # FTP 配置
 FTP_PORT=21

src/sys/tests/scripts/02_up.sh

@@ -15,39 +15,51 @@ compose() {
 
 echo "[INFO] Bringing up system stack..."
 
-# 检测GPU环境
+REQUEST_GPU=${ARGUS_SYS_ENABLE_GPU:-false}
-echo "[INFO] 检测GPU环境..."
+GPU_AVAILABLE=false
 GPU_CHECK_SCRIPT="$REPO_ROOT/src/metric/tests/scripts/common/check-gpu.sh"
-if [ -f "$GPU_CHECK_SCRIPT" ]; then
+
+if [[ "$REQUEST_GPU" == "true" ]]; then
+  echo "[INFO] --enable-gpu 生效，验证主机 GPU..."
+  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
+      echo "[INFO] GPU 检测通过，将启动 gpu profile"
     else
-        echo "[INFO] GPU环境不可用，将跳过GPU测试节点"
+      echo "[ERROR] 主机缺少可用 GPU，无法继续 --enable-gpu 流程" >&2
-        GPU_AVAILABLE=false
+      exit 1
+    fi
+  else
+    echo "[ERROR] 未找到 GPU 检测脚本: $GPU_CHECK_SCRIPT" >&2
+    exit 1
   fi
 else
-    echo "[WARN] 未找到GPU检测脚本: $GPU_CHECK_SCRIPT，跳过GPU检测"
+  echo "[INFO] 未启用 GPU 流程"
-    GPU_AVAILABLE=false
 fi
 
 pushd "$TEST_ROOT" >/dev/null
 compose -p argus-sys down --remove-orphans || true
 
+# 清理可能由 08 脚本创建的同名容器，避免 compose up 冲突
+for name in argus-node-b; do
+  if docker ps -aqf "name=^${name}$" >/dev/null 2>&1 && [[ -n "$(docker ps -aqf "name=^${name}$")" ]]; then
+    docker rm -f "$name" >/dev/null 2>&1 || true
+  fi
+done
+
 # 根据GPU可用性决定启动的服务
-if [ "$GPU_AVAILABLE" = true ]; then
+if [[ "$GPU_AVAILABLE" == true ]]; then
-    echo "[INFO] 启动所有服务（包括test-gpu-node）..."
+  echo "[INFO] 启动所有服务（包含 gpu profile）..."
-    compose -p argus-sys up -d
+  compose -p argus-sys --profile gpu up -d
 else
-    echo "[INFO] 启动基础服务（跳过test-gpu-node）..."
+  echo "[INFO] 启动基础服务（不含 gpu profile）..."
-    compose -p argus-sys up -d --scale test-gpu-node=0
+  compose -p argus-sys up -d
 fi
 
 popd >/dev/null
 
-if [ "$GPU_AVAILABLE" = true ]; then
+if [[ "$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)"
+  echo "[OK] Services started: master:32300 es:9200 kibana:5601 node-a:2020 node-b:2021 (gpu skipped)"
 fi
-

src/sys/tests/scripts/04_verify_dns_routing.sh

@@ -4,20 +4,15 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 
-compose() {
+# 直接根据 container_name 获取容器ID，避免 compose project 名称不一致导致查找失败
-  if docker compose version >/dev/null 2>&1; then
+cid_by_name() {
-    docker compose "$@"
+  docker ps -aqf "name=^$1$"
-  else
-    docker-compose "$@"
-  fi
-}
-
-service_id() {
-  compose -p argus-sys ps -q "$1"
 }
 
 echo "[INFO] Verifying DNS routing via bind..."
 
+pushd "$TEST_ROOT" >/dev/null
+
 # Check master IP file exists in shared private
 MASTER_FILE="$TEST_ROOT/private/argus/etc/master.argus.com"
 if [[ ! -f "$MASTER_FILE" ]]; then
@@ -28,7 +23,7 @@ MASTER_IP_HOST="$(cat "$MASTER_FILE" | tr -d '\r\n' || true)"
 echo "[INFO] master.argus.com file content: ${MASTER_IP_HOST}"
 
 # dig inside bind container
-BIN_ID="$(service_id bind)"
+BIN_ID="$(cid_by_name argus-bind-sys)"
 if [[ -n "$BIN_ID" ]]; then
   DIG_IP="$(docker exec "$BIN_ID" dig +short master.argus.com A | tail -n1 || true)"
   echo "[INFO] dig(master.argus.com) from bind container -> $DIG_IP"
@@ -39,8 +34,8 @@ else
   echo "[WARN] bind container not found; skip dig"
 fi
 
-for node in node-a node-b; do
+for node in argus-node-a argus-node-b; do
-  CID="$(service_id "$node")"
+  CID="$(cid_by_name "$node")"
   echo "[INFO] Checking resolution inside $node..."
   if ! docker exec "$CID" getent hosts master.argus.com >/dev/null 2>&1; then
     echo "[ERR] $node cannot resolve master.argus.com" >&2
@@ -50,5 +45,6 @@ for node in node-a node-b; do
   echo "[OK] $node resolved master.argus.com -> $RES"
 done
 
-echo "[OK] DNS routing verified"
+popd >/dev/null
 
+echo "[OK] DNS routing verified"

src/sys/tests/scripts/05_agent_register.sh

@@ -49,8 +49,35 @@ for _ in {1..60}; do
   fi
 done
 
+# 若仍未全部注册，尝试重启 node-b 并再等待一轮（兼容 DNS/启动时序抖动）
 if [[ ! -s "$TMP_DIR/node_id_a" || ! -s "$TMP_DIR/node_id_b" ]]; then
-  echo "[ERR] Agents did not register in time" >&2
+  echo "[WARN] node-a or node-b not registered in first window; restarting node-b and retrying..." >&2
+  # 仅重启 node-b，避免影响 es/kibana/master
+  if docker ps --format '{{.Names}}' | grep -q '^argus-node-b$'; then
+    docker restart argus-node-b >/dev/null 2>&1 || true
+  fi
+  # 再等待一轮（最多 120 秒）
+  > "$TMP_DIR/node_id_b"
+  for _ in {1..60}; do
+    sleep 2
+    resp=$(curl -fsS "$API_BASE/nodes" 2>/dev/null || true)
+    [[ -z "$resp" ]] && continue
+    if ! echo "$resp" | head -c1 | grep -q '\['; then
+      continue
+    fi
+    echo "$resp" > "$TMP_DIR/nodes_list.json"
+    ID_A=$(extract_node "$HOST_A" "$TMP_DIR/node_id_a" "$TMP_DIR/nodes_list.json" 2>/dev/null || true)
+    ID_B=$(extract_node "$HOST_B" "$TMP_DIR/node_id_b" "$TMP_DIR/nodes_list.json" 2>/dev/null || true)
+    if [[ -s "$TMP_DIR/node_id_a" && -s "$TMP_DIR/node_id_b" ]]; then
+      break
+    fi
+  done
+fi
+
+if [[ ! -s "$TMP_DIR/node_id_a" || ! -s "$TMP_DIR/node_id_b" ]]; then
+  echo "[ERR] Agents did not register in time (after retry)" >&2
+  echo "[HINT] Current /nodes response:" >&2
+  sed -n '1,200p' "$TMP_DIR/nodes_list.json" >&2 || true
   exit 1
 fi
 

src/sys/tests/scripts/07_logs_send_and_assert.sh

@@ -3,9 +3,19 @@ set -euo pipefail
 
 echo "[INFO] Sending logs via node-a/node-b and asserting ES counts..."
 
+# Robust count helper: tolerates 404/503 and non-JSON responses, returns integer >=0
 get_count() {
-  local idx="$1"
+  local idx="$1"; local tmp; tmp=$(mktemp)
-  curl -s "http://localhost:9200/${idx}/_count?ignore_unavailable=true&allow_no_indices=true" | sed -E 's/.*"count":([0-9]+).*/\1/' | awk 'NF{print $0;exit} END{if(NR==0)print 0}'
+  local code
+  code=$(curl -s -o "$tmp" -w "%{http_code}" "http://localhost:9200/${idx}/_count?ignore_unavailable=true&allow_no_indices=true" || true)
+  if [[ "$code" == "200" ]]; then
+    local val
+    val=$(jq -r '(.count // 0) | tonumber? // 0' "$tmp" 2>/dev/null || echo 0)
+    echo "$val"
+  else
+    echo 0
+  fi
+  rm -f "$tmp"
 }
 
 train0=$(get_count "train-*")
@@ -32,11 +42,26 @@ send_logs "$node_a" "host01"
 send_logs "$node_b" "host02"
 
 echo "[INFO] Waiting for ES to ingest..."
-sleep 10
+# Proactively refresh indices (ignore errors if not created yet)
+curl -s -X POST "http://localhost:9200/train-*/_refresh" >/dev/null 2>&1 || true
+curl -s -X POST "http://localhost:9200/infer-*/_refresh" >/dev/null 2>&1 || true
 
-train1=$(get_count "train-*")
+# Retry up to 120s for counts to increase and reach threshold (>=4)
-infer1=$(get_count "infer-*")
+final=0
-final=$((train1 + infer1))
+threshold=4
+for attempt in {1..60}; do
+  train1=$(get_count "train-*")
+  infer1=$(get_count "infer-*")
+  final=$((train1 + infer1))
+  if (( final > base && final >= threshold )); then
+    break
+  fi
+  echo "[..] waiting ES counts increase to >=${threshold} ($attempt/60) current=${final} base=${base}"
+  # refresh indices again to speed up visibility
+  curl -s -X POST "http://localhost:9200/train-*/_refresh" >/dev/null 2>&1 || true
+  curl -s -X POST "http://localhost:9200/infer-*/_refresh" >/dev/null 2>&1 || true
+  sleep 2
+done
 echo "[INFO] final counts: train=${train1} infer=${infer1} total=${final}"
 
 if (( final <= base )); then
@@ -44,6 +69,7 @@ if (( final <= base )); then
   exit 1
 fi
 
+# Minimal threshold to be tolerant: expect at least 4 documents (2 train + 1 infer per node)
 if (( final < 4 )); then
   echo "[ERR] ES total below expected threshold: ${final} < 4" >&2
   exit 1

src/sys/tests/scripts/08_restart_agent_reregister.sh

@@ -58,10 +58,25 @@ docker rm -f argus-node-b >/dev/null 2>&1 || true
 
 AGENT_BIN_PATH="$(cat "$TMP_DIR/agent_binary_path")"
 
+# 选择 compose 管理的网络名（默认 argus-sys_sysnet）。
+detect_sysnet() {
+  if docker network inspect argus-sys_sysnet >/dev/null 2>&1; then
+    echo argus-sys_sysnet; return
+  fi
+  # 回退：从 master 容器推断所连网络（取第一个）
+  local n
+  n=$(docker inspect -f '{{range $k, $_ := .NetworkSettings.Networks}}{{println $k}}{{end}}' argus-master-sys 2>/dev/null | head -n1 || true)
+  if [[ -n "$n" ]]; then echo "$n"; return; fi
+  # 最后兜底：尝试项目默认网络（不保证有 IPAM）
+  echo argus-sys_default
+}
+SYSNET_NAME=$(detect_sysnet)
+echo "[INFO] Using docker network: $SYSNET_NAME"
+
 docker run -d \
   --name argus-node-b \
   --hostname dev-yyrshare-uuuu10-ep2f-pod-0 \
-  --network argus-sys-net \
+  --network "$SYSNET_NAME" \
   --ip 172.29.0.200 \
   --dns 172.29.0.2 \
   -e MASTER_ENDPOINT=http://master.argus.com:3000 \

src/sys/tests/scripts/09_down.sh

@@ -12,12 +12,33 @@ compose() {
   fi
 }
 
-docker rm -f argus-node-b >/dev/null 2>&1 || true
-
 pushd "$TEST_ROOT" >/dev/null
 compose -p argus-sys down --remove-orphans || true
+compose down --remove-orphans || true
 popd >/dev/null
 
+echo "[INFO] Force removing containers by name (if any)..."
+containers=(
+  argus-node-a
+  argus-node-b
+  argus-metric-test-node
+  argus-grafana
+  argus-kibana-sys
+  argus-master-sys
+  argus-bind-sys
+  argus-ftp
+  argus-es-sys
+  argus-prometheus
+)
+for c in "${containers[@]}"; do
+  id=$(docker ps -aqf "name=^${c}$" || true)
+  if [[ -n "$id" ]]; then
+    docker rm -f "$id" >/dev/null 2>&1 || true
+  fi
+done
+
+echo "[INFO] Removing compose networks (handled by compose down)"
+
 echo "[INFO] Cleaning private directories..."
 if [[ -d "$TEST_ROOT/private" ]]; then
   docker run --rm -v "$TEST_ROOT/private:/target" ubuntu:24.04 chown -R "$(id -u):$(id -g)" /target >/dev/null 2>&1 || true

src/sys/tests/scripts/10_metric_publish.sh

@@ -0,0 +1,66 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$TEST_ROOT/../../.." && pwd)"
+
+PLUGIN_DIR="$REPO_ROOT/src/metric/client-plugins/all-in-one-full"
+FTP_CONTAINER="argus-ftp"
+
+if [[ ! -d "$PLUGIN_DIR" ]]; then
+  echo "[SYS-METRIC] Metric client plugin directory not found: $PLUGIN_DIR" >&2
+  exit 1
+fi
+
+if [[ -f "$TEST_ROOT/.env" ]]; then
+  # shellcheck source=/dev/null
+  source "$TEST_ROOT/.env"
+fi
+
+OWNER="${ARGUS_BUILD_UID:-2133}:${ARGUS_BUILD_GID:-2015}"
+
+resolve_output_dir() {
+  local host_mount
+  if docker ps --format '{{.Names}}' | grep -q "^${FTP_CONTAINER}$"; then
+    host_mount=$(docker inspect "$FTP_CONTAINER" --format '{{range .Mounts}}{{if eq .Destination "/private/argus/ftp"}}{{.Source}}{{end}}{{end}}' 2>/dev/null || true)
+    if [[ -n "$host_mount" ]]; then
+      echo "$host_mount/share"
+      return 0
+    fi
+  fi
+  echo "$TEST_ROOT/private/argus/metric/ftp/share"
+}
+
+OUTPUT_DIR="$(resolve_output_dir)"
+mkdir -p "$OUTPUT_DIR"
+
+if [[ ! -w "$OUTPUT_DIR" ]]; then
+  echo "[SYS-METRIC] 无法写入 FTP 输出目录: $OUTPUT_DIR" >&2
+  echo "             请确认目录权限与 ARGUS_BUILD_UID/GID 一致" >&2
+  exit 1
+fi
+
+pushd "$PLUGIN_DIR" >/dev/null
+
+echo "[SYS-METRIC] Bumping metric artifact version..."
+bash scripts/version-manager.sh bump minor
+
+VERSION_FILE="config/VERSION"
+if [[ ! -f "$VERSION_FILE" ]]; then
+  echo "[SYS-METRIC] VERSION 文件缺失: $VERSION_FILE" >&2
+  exit 1
+fi
+
+VERSION=$(tr -d '\n' < "$VERSION_FILE")
+echo "[SYS-METRIC] 当前版本: $VERSION"
+
+echo "[SYS-METRIC] Packaging metric artifact..."
+bash scripts/package_artifact.sh --force
+
+echo "[SYS-METRIC] Publishing artifact to FTP share..."
+bash scripts/publish_artifact.sh "$VERSION" --output-dir "$OUTPUT_DIR" --owner "$OWNER"
+
+popd >/dev/null
+
+echo "[SYS-METRIC] Metric artifact published to $OUTPUT_DIR"

src/sys/tests/scripts/11_metric_node_install.sh

@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+if [[ -f "$TEST_ROOT/.env" ]]; then
+  # shellcheck source=/dev/null
+  source "$TEST_ROOT/.env"
+fi
+
+CONTAINER="argus-metric-test-node"
+
+if ! docker ps --format '{{.Names}}' | grep -q "^${CONTAINER}$"; then
+  echo "[SYS-METRIC] 容器 ${CONTAINER} 未运行，无法执行安装" >&2
+  exit 1
+fi
+
+FTP_HOST="${FTP_SERVER:-172.29.0.40}"
+FTP_USER="${FTP_USER:-ftpuser}"
+FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+FTP_PORT="${FTP_PORT:-21}"
+
+echo "[SYS-METRIC] 在 ${CONTAINER} 内执行安装 (FTP: ${FTP_HOST}:${FTP_PORT})"
+
+docker exec \
+  -e FTP_HOST="$FTP_HOST" \
+  -e FTP_USER="$FTP_USER" \
+  -e FTP_PASSWORD="$FTP_PASSWORD" \
+  -e FTP_PORT="$FTP_PORT" \
+  "$CONTAINER" bash -c '
+set -e
+
+if ! command -v curl &>/dev/null; then
+  echo "[SYS-METRIC] curl 未安装，开始安装依赖..."
+  apt-get update >/dev/null && apt-get install -y curl >/dev/null
+fi
+
+cd /tmp
+echo "[SYS-METRIC] 下载 setup.sh..."
+curl -u "${FTP_USER}:${FTP_PASSWORD}" "ftp://${FTP_HOST}:${FTP_PORT}/setup.sh" -o setup.sh
+
+echo "[SYS-METRIC] 执行安装..."
+chmod +x setup.sh
+bash setup.sh --server "${FTP_HOST}" --user "${FTP_USER}" --password "${FTP_PASSWORD}" --port "${FTP_PORT}"
+
+echo "[SYS-METRIC] 安装完成"
+'
+
+echo "[SYS-METRIC] Metric test node 安装流程完成"

src/sys/tests/scripts/12_metric_gpu_install.sh

@@ -0,0 +1,64 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+ENABLE_GPU=${ARGUS_SYS_ENABLE_GPU:-false}
+
+if [[ "$ENABLE_GPU" != "true" ]]; then
+  echo "[SYS-METRIC] 未启用 GPU 流程，跳过 GPU 节点安装"
+  exit 0
+fi
+
+if [[ -f "$TEST_ROOT/.env" ]]; then
+  # shellcheck source=/dev/null
+  source "$TEST_ROOT/.env"
+fi
+
+CONTAINER="argus-metric-test-gpu-node"
+
+if ! docker ps --format '{{.Names}}' | grep -q "^${CONTAINER}$"; then
+  echo "[SYS-METRIC] 预期启动的 ${CONTAINER} 未运行" >&2
+  exit 1
+fi
+
+FTP_HOST="${FTP_SERVER:-172.29.0.40}"
+FTP_USER="${FTP_USER:-ftpuser}"
+FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+FTP_PORT="${FTP_PORT:-21}"
+
+echo "[SYS-METRIC] 在 GPU 节点执行安装 (FTP: ${FTP_HOST}:${FTP_PORT})"
+
+docker exec \
+  -e FTP_HOST="$FTP_HOST" \
+  -e FTP_USER="$FTP_USER" \
+  -e FTP_PASSWORD="$FTP_PASSWORD" \
+  -e FTP_PORT="$FTP_PORT" \
+  "$CONTAINER" bash -c '
+set -e
+
+if ! command -v nvidia-smi &>/dev/null; then
+  echo "[SYS-METRIC] GPU 节点缺少 nvidia-smi" >&2
+  exit 1
+fi
+
+nvidia-smi >/dev/null || true
+
+if ! command -v curl &>/dev/null; then
+  echo "[SYS-METRIC] curl 未安装，开始安装依赖..."
+  apt-get update >/dev/null && apt-get install -y curl >/dev/null
+fi
+
+cd /tmp
+echo "[SYS-METRIC] 下载 setup.sh..."
+curl -u "${FTP_USER}:${FTP_PASSWORD}" "ftp://${FTP_HOST}:${FTP_PORT}/setup.sh" -o setup.sh
+
+echo "[SYS-METRIC] 执行安装..."
+chmod +x setup.sh
+bash setup.sh --server "${FTP_HOST}" --user "${FTP_USER}" --password "${FTP_PASSWORD}" --port "${FTP_PORT}"
+
+echo "[SYS-METRIC] GPU 节点安装完成"
+'
+
+echo "[SYS-METRIC] Metric GPU 节点安装流程完成"

src/sys/tests/scripts/13_metric_verify.sh

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+echo "[SYS-METRIC] Verify: master"
+"$SCRIPT_DIR/13_metric_verify_master.sh"
+echo
+
+echo "[SYS-METRIC] Verify: prometheus"
+PROM_RETRIES=${PROM_VERIFY_RETRIES:-2}
+PROM_BACKOFF=${PROM_VERIFY_BACKOFF_SECONDS:-30}
+attempt=0
+while true; do
+  if "$SCRIPT_DIR/13_metric_verify_prometheus.sh"; then
+    break
+  fi
+  attempt=$((attempt+1))
+  if (( attempt > PROM_RETRIES )); then
+    echo "[ERR] prometheus verify failed after $PROM_RETRIES retries" >&2
+    exit 1
+  fi
+  echo "[WARN] prometheus verify failed; retry $attempt/$PROM_RETRIES after ${PROM_BACKOFF}s"
+  sleep "$PROM_BACKOFF"
+done
+echo
+
+echo "[SYS-METRIC] Verify: dataplane"
+"$SCRIPT_DIR/13_metric_verify_dataplane.sh"
+echo
+
+echo "[SYS-METRIC] Verify: grafana"
+"$SCRIPT_DIR/13_metric_verify_grafana.sh"
+echo
+
+echo "[SYS-METRIC] Verify: grafana panels"
+"$SCRIPT_DIR/13_metric_verify_grafana_panels.sh"
+echo
+
+echo "[SYS-METRIC] Metric verification completed"

src/sys/tests/scripts/13_metric_verify_dataplane.sh

@@ -0,0 +1,47 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+TMP_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)/tmp/metric-verify"
+mkdir -p "$TMP_DIR"
+
+PROM_BASE="http://localhost:9090/api/v1"
+INSTANCE="${METRIC_TEST_INSTANCE:-172.29.0.50:9100}"
+IP_ONLY="${INSTANCE%%:*}"
+
+echo "[VERIFY:DATA] node exporter metrics present in container"
+docker exec argus-metric-test-node bash -lc "curl -fsS --max-time 5 http://localhost:9100/metrics | head -n 5" > "$TMP_DIR/node_metrics_head.txt" || { echo "[ERR] cannot fetch node exporter metrics" >&2; exit 1; }
+if ! grep -E "node_(exporter_build_info|time_seconds)" -q "$TMP_DIR/node_metrics_head.txt"; then
+  echo "[WARN] head did not show expected lines; continuing (exporter may output later lines)"
+fi
+echo "[OK] node exporter endpoint reachable"
+
+echo "[VERIFY:DATA] Prometheus has recent sample for build_info"
+curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=node_exporter_build_info{job=\"node\",ip=\"$IP_ONLY\"}" > "$TMP_DIR/prom_ne_build_info_1.json"
+
+python3 - "$TMP_DIR/prom_ne_build_info_1.json" <<'PY'
+import json,sys,time
+j=json.load(open(sys.argv[1]))
+res=j.get('data',{}).get('result',[])
+assert res, 'no result for node_exporter_build_info'
+ts=float(res[0]['value'][0])
+now=time.time()
+assert now-ts<180, f"sample too old: now={now} ts={ts}"
+print(int(ts))
+PY
+T1=$?
+sleep 30
+curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=node_exporter_build_info{job=\"node\",ip=\"$IP_ONLY\"}" > "$TMP_DIR/prom_ne_build_info_2.json"
+
+TS1=$(python3 - "$TMP_DIR/prom_ne_build_info_1.json" <<'PY'
+import json,sys
+print(float(json.load(open(sys.argv[1]))['data']['result'][0]['value'][0]))
+PY
+)
+TS2=$(python3 - "$TMP_DIR/prom_ne_build_info_2.json" <<'PY'
+import json,sys
+print(float(json.load(open(sys.argv[1]))['data']['result'][0]['value'][0]))
+PY
+)
+awk -v a="$TS1" -v b="$TS2" 'BEGIN{ if (b>=a) exit 0; else exit 1 }' || { echo "[ERR] sample timestamp did not advance" >&2; exit 1; }
+echo "[OK] sample timestamp advanced"
+echo "[DONE] dataplane verify"

src/sys/tests/scripts/13_metric_verify_grafana.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+PROM_DOMAIN="prom.metric.argus.com:9090"
+GRAF="http://localhost:3000"
+
+echo "[VERIFY:GRAFANA] /api/health"
+TMP_FILE="$(cd "$(dirname "$0")"/.. && pwd)/tmp/metric-verify/graf_health.json"
+mkdir -p "$(dirname "$TMP_FILE")"
+curl -fsS --max-time 10 "$GRAF/api/health" -o "$TMP_FILE" || { echo "[ERR] failed to GET /api/health" >&2; exit 1; }
+python3 - "$TMP_FILE" <<'PY'
+import sys,json
+with open(sys.argv[1],'r',encoding='utf-8') as f:
+    j=json.load(f)
+assert j.get('database')=='ok', f"health not ok: {j}"
+print('OK')
+PY
+
+echo "[VERIFY:GRAFANA] datasource URL uses domain: $PROM_DOMAIN"
+DS_FILE="/private/argus/metric/grafana/provisioning/datasources/datasources.yml"
+if ! docker exec argus-grafana sh -lc "test -f $DS_FILE"; then
+  DS_FILE="/etc/grafana/provisioning/datasources/datasources.yml"
+fi
+docker exec argus-grafana sh -lc "grep -E 'url:\s*http://$PROM_DOMAIN' '$DS_FILE'" >/dev/null 2>&1 || { echo "[ERR] datasource not pointing to $PROM_DOMAIN" >&2; exit 1; }
+echo "[OK] datasource points to domain"
+
+echo "[VERIFY:GRAFANA] bind resolution inside grafana"
+tries=0
+until docker exec argus-grafana getent hosts prom.metric.argus.com >/dev/null 2>&1; do
+  tries=$((tries+1))
+  if (( tries > 24 )); then
+    echo "[ERR] grafana cannot resolve prom.metric.argus.com" >&2
+    exit 1
+  fi
+  echo "[..] waiting DNS propagation in grafana ($tries/24)"; sleep 5
+done
+echo "[OK] domain resolves"
+
+echo "[DONE] grafana verify"

src/sys/tests/scripts/13_metric_verify_grafana_panels.sh

@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+TMP_DIR="$TEST_ROOT/tmp/metric-verify"
+mkdir -p "$TMP_DIR"
+
+GRAF="http://localhost:3000"
+HOSTNAME="${METRIC_TEST_HOSTNAME:-test-metric-node-001}"
+
+echo "[VERIFY:GRAF-PANELS] resolve Prometheus datasource UID via Grafana"
+DS_JSON="$TMP_DIR/graf_ds.json"
+curl -fsS --max-time 10 "$GRAF/api/datasources" >"$DS_JSON"
+DS_UID=$(python3 - "$DS_JSON" <<'PY'
+import json,sys
+arr=json.load(open(sys.argv[1]))
+for ds in arr:
+    if (ds.get('type')=='prometheus'):
+        print(ds.get('uid',''))
+        break
+PY
+)
+if [[ -z "$DS_UID" ]]; then echo "[ERR] no prometheus datasource found in grafana" >&2; exit 1; fi
+echo "[OK] Prometheus DS UID=$DS_UID"
+
+proxy_query() {
+  local q="$1"; local out="$2"
+  curl -fsS --max-time 10 --get "$GRAF/api/datasources/proxy/uid/$DS_UID/api/v1/query" \
+    --data-urlencode "query=$q" >"$out"
+}
+
+assert_vector_recent_nonempty() {
+  local json="$1"; local max_age_sec="${2:-180}"
+  python3 - <<'PY' "$json" "$max_age_sec"
+import json,sys,time
+doc=json.load(open(sys.argv[1]))
+if doc.get('status')!='success':
+    raise SystemExit('prom status != success')
+res=doc.get('data',{}).get('result',[])
+assert res, 'empty result'
+ts=float(res[0]['value'][0])
+assert time.time()-ts < float(sys.argv[2]), f'timestamp too old: {ts}'
+print(int(ts))
+PY
+}
+
+echo "[VERIFY:GRAF-PANELS] Dashboard: Node and GPU Metrics — System Load"
+Q_NODE_LOAD="node_load1{hostname=\"$HOSTNAME\"}"
+proxy_query "$Q_NODE_LOAD" "$TMP_DIR/graf_panel_node_load.json"
+assert_vector_recent_nonempty "$TMP_DIR/graf_panel_node_load.json" 300 >/dev/null
+echo "[OK] node_load1 has recent sample via Grafana proxy"
+
+echo "[VERIFY:GRAF-PANELS] Dashboard: Cluster Dashboard — Node online count"
+Q_NODE_ONLINE='count(count by(hostname) (up{job="node"} == 1))'
+proxy_query "$Q_NODE_ONLINE" "$TMP_DIR/graf_panel_node_online.json"
+python3 - "$TMP_DIR/graf_panel_node_online.json" <<'PY'
+import json,sys
+doc=json.load(open(sys.argv[1]))
+assert doc.get('status')=='success', 'prom status not success'
+res=doc.get('data',{}).get('result',[])
+assert res, 'no series for node online count'
+val=float(res[0]['value'][1])
+assert val>=1, f'node online < 1: {val}'
+print('OK',val)
+PY
+echo "[OK] cluster node online count >= 1 via Grafana proxy"
+
+echo "[DONE] grafana panels verify"
+

src/sys/tests/scripts/13_metric_verify_master.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+TMP_DIR="$TEST_ROOT/tmp/metric-verify"
+mkdir -p "$TMP_DIR"
+
+MASTER_BASE="http://localhost:32300/api/v1/master"
+HOSTNAME="${METRIC_TEST_HOSTNAME:-test-metric-node-001}"
+
+curl_json() { curl -fsS --max-time 5 "$1"; }
+
+echo "[VERIFY:MASTER] list nodes and locate target hostname=$HOSTNAME"
+ALL_NODES_JSON="$TMP_DIR/master_nodes.json"
+
+# 重试等待节点出现在 /nodes 列表（最多 120s）
+NODE_ID=""
+for attempt in {1..24}; do
+  curl_json "$MASTER_BASE/nodes" > "$ALL_NODES_JSON" || true
+  NODE_ID=$(python3 - "$ALL_NODES_JSON" "$HOSTNAME" <<'PY'
+import json,sys
+try:
+    nodes=json.load(open(sys.argv[1]))
+except Exception:
+    nodes=[]
+name=sys.argv[2]
+for n in nodes:
+    if n.get('name')==name:
+        print(n.get('id',''))
+        break
+PY
+  )
+  if [[ -n "$NODE_ID" ]]; then break; fi
+  echo "[..] waiting node to appear in /nodes ($attempt/24)"; sleep 5
+done
+
+if [[ -z "$NODE_ID" ]]; then
+  echo "[ERR] master /nodes 中未找到 $HOSTNAME（等待超时）" >&2
+  echo "[HINT] 当前 /nodes 列表如下:" >&2
+  sed -n '1,160p' "$ALL_NODES_JSON" >&2 || true
+  exit 1
+fi
+echo "[OK] node id=$NODE_ID"
+
+echo "[VERIFY:MASTER] get node detail and assert fields"
+DETAIL1_JSON="$TMP_DIR/master_node_${NODE_ID}_detail_1.json"
+curl_json "$MASTER_BASE/nodes/$NODE_ID" > "$DETAIL1_JSON"
+
+# 基础字段与健康项检查（不强制立即 online）
+python3 - "$DETAIL1_JSON" "$HOSTNAME" <<'PY'
+import json,sys,datetime
+j=json.load(open(sys.argv[1]))
+host=sys.argv[2]
+assert j.get('name')==host, f"name mismatch: {j.get('name')} != {host}"
+status=j.get('status')
+assert status in ('initialized','online','offline'), f"unexpected status: {status}"
+md=j.get('meta_data',{})
+assert md.get('hostname',j.get('name'))==host, 'meta_data.hostname mismatch'
+assert 'last_report' in j and j['last_report'], 'last_report missing'
+h=j.get('health',{})
+for key in ('metric-node-exporter','metric-fluent-bit','metric-argus-agent'):
+    if key in h:
+        assert h[key].get('status')=='healthy', f"{key} not healthy: {h[key]}"
+print('OK')
+PY
+
+# 轮询等待 last_report 前进并最终转为 online（最多 90s），容忍短暂 5xx/网络错误
+attempt=0
+T_PRE=0
+until [[ $attempt -ge 18 ]]; do
+  sleep 5
+  DETAIL_CUR="$TMP_DIR/master_node_${NODE_ID}_detail_cur.json"
+  if ! curl_json "$MASTER_BASE/nodes/$NODE_ID" > "$DETAIL_CUR" 2>/dev/null; then
+    echo "[..] retrying node detail fetch ($attempt/18)"; ((attempt++)); continue
+  fi
+  read -r STATUS_CUR T_CUR < <(python3 - "$DETAIL_CUR" <<'PY'
+import json,sys,datetime
+j=json.load(open(sys.argv[1]))
+st=j.get('status','')
+ts=j.get('last_report','')
+if ts.endswith('Z'): ts=ts.replace('Z','+00:00')
+try:
+    t=float(datetime.datetime.fromisoformat(ts).timestamp())
+except Exception:
+    t=0.0
+print(st)
+print(t)
+PY
+  )
+  if awk -v a="$T_PRE" -v b="$T_CUR" 'BEGIN{exit !(b>a)}'; then
+    T_PRE="$T_CUR"
+  fi
+  if [[ "$STATUS_CUR" == "online" ]]; then
+    echo "[OK] status online and last_report progressed"
+    break
+  fi
+  ((attempt++))
+done
+if (( attempt >= 18 )) && [[ "$STATUS_CUR" != "online" ]]; then
+  echo "[WARN] status did not reach online within timeout; continuing"
+fi
+
+echo "$NODE_ID" > "$TMP_DIR/node_id_metric"
+echo "[DONE] master verify"

src/sys/tests/scripts/13_metric_verify_prometheus.sh

@@ -0,0 +1,142 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+TMP_DIR="$TEST_ROOT/tmp/metric-verify"
+mkdir -p "$TMP_DIR"
+
+PROM_BASE="http://localhost:9090/api/v1"
+HOSTNAME="${METRIC_TEST_HOSTNAME:-test-metric-node-001}"
+
+nodes_json="$TEST_ROOT/private/argus/metric/prometheus/nodes.json"
+targets_json="$TEST_ROOT/private/argus/metric/prometheus/targets/node_exporter.json"
+
+echo "[VERIFY:PROM] nodes.json present and contains hostname=$HOSTNAME"
+[[ -f "$nodes_json" ]] || { echo "[ERR] $nodes_json missing" >&2; exit 1; }
+python3 - "$nodes_json" "$HOSTNAME" <<'PY'
+import json,sys
+arr=json.load(open(sys.argv[1]))
+host=sys.argv[2]
+assert any((i.get('hostname')==host) for i in arr), f"{host} not found in nodes.json"
+PY
+echo "[OK] nodes.json contains target"
+
+echo "[VERIFY:PROM] file_sd targets exist for nodes.json entries"
+[[ -f "$targets_json" ]] || { echo "[ERR] $targets_json missing" >&2; exit 1; }
+python3 - "$nodes_json" "$targets_json" "$HOSTNAME" >"$TMP_DIR/prom_targets_ip_inst.txt" <<'PY'
+import json,sys
+nodes=json.load(open(sys.argv[1]))
+file_sd=json.load(open(sys.argv[2]))
+host=sys.argv[3]
+targets=set()
+for item in file_sd:
+    for t in item.get('targets',[]): targets.add(t)
+# choose node matching hostname; fallback to first metric user node; otherwise first
+sel = None
+for n in nodes:
+    if n.get('hostname') == host:
+        sel = n
+        break
+if not sel:
+    for n in nodes:
+        if n.get('user_id') == 'metric':
+            sel = n
+            break
+if not sel and nodes:
+    sel = nodes[0]
+if not sel:
+    raise SystemExit('nodes.json empty or no suitable node found')
+ip = sel['ip']
+inst = f"{ip}:9100"
+print(ip)
+print(inst)
+PY
+IP_FIRST=$(sed -n '1p' "$TMP_DIR/prom_targets_ip_inst.txt")
+INSTANCE=$(sed -n '2p' "$TMP_DIR/prom_targets_ip_inst.txt")
+echo "[INFO] expecting instance in file_sd: $INSTANCE"
+
+# 尝试在 Prometheus 容器内主动刷新 targets（可选加速）
+if docker ps --format '{{.Names}}' | grep -q '^argus-prometheus$'; then
+  echo "[..] triggering update_targets inside argus-prometheus"
+  docker exec argus-prometheus bash -lc \
+    'python3 /usr/local/bin/update_targets.py --config /private/argus/metric/prometheus/nodes.json --targets-dir /private/argus/metric/prometheus/targets >/dev/null 2>&1 || true'
+fi
+
+# 给 Prometheus 一次初始 scrape 周期
+sleep 10
+
+# 若短暂未生成，进行重试（最多 180s），期间多次触发刷新
+retry=0
+until jq -r '.[].targets[]' "$targets_json" 2>/dev/null | grep -q "^${IP_FIRST}:9100$"; do
+  if (( retry >= 36 )); then
+    echo "[ERR] ${IP_FIRST}:9100 not present in file_sd after timeout" >&2
+    echo "[HINT] current targets file content:" >&2
+    sed -n '1,200p' "$targets_json" >&2 || true
+    exit 1
+  fi
+  if (( retry % 3 == 0 )) && docker ps --format '{{.Names}}' | grep -q '^argus-prometheus$'; then
+    docker exec argus-prometheus bash -lc \
+      'python3 /usr/local/bin/update_targets.py --config /private/argus/metric/prometheus/nodes.json --targets-dir /private/argus/metric/prometheus/targets >/dev/null 2>&1 || true'
+  fi
+  echo "[..] waiting file_sd refresh ($retry/36)"; sleep 5; ((retry++))
+done
+
+# 改为以 PromQL up 指标作为健康依据，避免 targets 页面状态抖动
+echo "[VERIFY:PROM] up{job=\"node\",ip=\"$IP_FIRST\"} > 0"
+attempt=0
+until (( attempt >= 60 )); do
+  curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=up{job=\"node\",ip=\"$IP_FIRST\"}" > "$TMP_DIR/prom_up_inst_active.json" || true
+  if python3 - "$TMP_DIR/prom_up_inst_active.json" <<'PY'
+import json,sys
+try:
+    j=json.load(open(sys.argv[1]))
+except Exception:
+    raise SystemExit(1)
+res=j.get('data',{}).get('result',[])
+if res:
+    try:
+        val=float(res[0]['value'][1])
+        if val>0: raise SystemExit(0)
+    except Exception:
+        pass
+raise SystemExit(1)
+PY
+  then
+    echo "[OK] up > 0 (control-plane scrape works)"; break
+  fi
+  if (( attempt % 6 == 0 )) && docker ps --format '{{.Names}}' | grep -q '^argus-prometheus$'; then
+    docker exec argus-prometheus bash -lc \
+      'python3 /usr/local/bin/update_targets.py --config /private/argus/metric/prometheus/nodes.json --targets-dir /private/argus/metric/prometheus/targets >/dev/null 2>&1 || true'
+  fi
+  echo "[..] waiting up{job=\"node\",ip=\"$IP_FIRST\"} > 0 ($attempt/60)"; sleep 5; ((attempt++))
+done
+if (( attempt >= 60 )); then
+  echo "[ERR] up{job=\"node\",ip=\"$IP_FIRST\"} did not become > 0" >&2
+  exit 1
+fi
+
+echo "[VERIFY:PROM] instant up query > 0"
+curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=up{job=\"node\",ip=\"$IP_FIRST\"}" > "$TMP_DIR/prom_up_inst.json"
+python3 - "$TMP_DIR/prom_up_inst.json" <<'PY'
+import json,sys
+j=json.load(open(sys.argv[1]))
+res=j.get('data',{}).get('result',[])
+assert res, 'empty result for up{job="node",instance=...}'
+val=float(res[0]['value'][1])
+assert val>0, f"up value not > 0: {val}"
+PY
+echo "[OK] up > 0"
+
+echo "[VERIFY:PROM] count(up{job=\"node\"}==1) >= 1"
+curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=count(up{job=\"node\"}==1)" > "$TMP_DIR/prom_up_count.json"
+python3 - "$TMP_DIR/prom_up_count.json" <<'PY'
+import json,sys
+j=json.load(open(sys.argv[1]))
+res=j.get('data',{}).get('result',[])
+assert res, 'empty result for count(up{job="node"}==1)'
+val=float(res[0]['value'][1])
+assert val>=1, f"count < 1: {val}"
+PY
+echo "[OK] up count satisfied"
+echo "[DONE] prometheus verify"

src/sys/tests/scripts/14_metric_cleanup.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+FTP_SHARE="$TEST_ROOT/private/argus/metric/ftp/share"
+
+if [[ -d "$FTP_SHARE" ]]; then
+  echo "[SYS-METRIC] 清理 FTP 发布产物..."
+  rm -f "$FTP_SHARE"/argus-metric_*.tar.gz 2>/dev/null || true
+  rm -f "$FTP_SHARE"/LATEST_VERSION 2>/dev/null || true
+  rm -f "$FTP_SHARE"/dns.conf "$FTP_SHARE"/setup.sh 2>/dev/null || true
+else
+  echo "[SYS-METRIC] FTP 目录不存在，跳过清理"
+fi
+
+echo "[SYS-METRIC] Metric 清理完成"

src/sys/tests/scripts/metric/test-node-entrypoint.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+AGENT_ROOT=${AGENT_ROOT:-/private/argus/agent}
+PREPARED_FLAG="/tmp/.metric_node_prepared"
+
+export DEBIAN_FRONTEND=${DEBIAN_FRONTEND:-noninteractive}
+
+if [[ ! -f "$PREPARED_FLAG" ]]; then
+  apt-get update -qq
+  apt-get install -y -qq \
+    curl \
+    net-tools \
+    iproute2 \
+    lsof \
+    procps \
+    ca-certificates \
+    gnupg2 || {
+      echo "[metric-node] Failed to install base packages" >&2
+      exit 1
+    }
+
+  mkdir -p "$(dirname "$PREPARED_FLAG")"
+  touch "$PREPARED_FLAG"
+fi
+
+if [[ -n "${TZ:-}" ]]; then
+  ln -snf "/usr/share/zoneinfo/${TZ}" /etc/localtime 2>/dev/null || true
+  echo "$TZ" > /etc/timezone 2>/dev/null || true
+fi
+
+mkdir -p "$AGENT_ROOT"
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$AGENT_ROOT" 2>/dev/null || true
+
+if [[ "${METRIC_NODE_ROLE:-cpu}" == "gpu" ]]; then
+  if ! command -v nvidia-smi >/dev/null 2>&1; then
+    echo "[metric-node] nvidia-smi not available but GPU role requested" >&2
+    exit 1
+  fi
+  nvidia-smi || true
+fi
+
+exec "$@"

src/sys/tests/scripts/node_entrypoint.sh

@@ -46,7 +46,9 @@ fi
 # Start Fluent Bit in background (will block, so run via bash -lc &)
 if [[ -x /private/start-fluent-bit.sh ]]; then
   log "starting fluent-bit"
-  bash -lc '/private/start-fluent-bit.sh' &
+  sysctl -w fs.inotify.max_user_instances=512 >/dev/null 2>&1 || true
+  sysctl -w fs.inotify.max_user_watches=524288 >/dev/null 2>&1 || true
+  bash -lc 'ulimit -n 65536 || true; exec /private/start-fluent-bit.sh' &
 else
   log "missing /private/start-fluent-bit.sh; fluent-bit will not start"
 fi
@@ -54,4 +56,3 @@ fi
 # Start agent in foreground as runtime user
 log "starting argus-agent"
 exec su -s /bin/bash -c /usr/local/bin/argus-agent "$RUNTIME_USER"
-

src/web/build_tools/frontend/Dockerfile

@@ -24,24 +24,37 @@ RUN apt-get update && \
     apt-get clean && rm -rf /var/lib/apt/lists/*
 
 ENV FRONTEND_BASE_PATH=/private/argus/web/frontend
-ARG ARGUS_UID=2133
+ARG ARGUS_BUILD_UID=2133
-ARG ARGUS_GID=2015
+ARG ARGUS_BUILD_GID=2015
-ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID}
-ENV ARGUS_GID=${ARGUS_GID}
+ENV ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
 
 RUN mkdir -p ${FRONTEND_BASE_PATH} && \
     mkdir -p /private/argus/etc
 
 # 创建 web 用户（可自定义 UID/GID）
 # 创建 web 用户组
-RUN groupadd -g ${ARGUS_GID} web
+RUN set -eux; \
-
+    # 确保目标 GID 存在（组名可不固定）\
-# 创建 web 用户并指定组
+    if ! getent group "${ARGUS_BUILD_GID}" >/dev/null; then \
-RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} web
+        groupadd -g "${ARGUS_BUILD_GID}" web || true; \
-
+    fi; \
-RUN chown -R web:web ${FRONTEND_BASE_PATH} && \
+    # 若存在 web 用户则尽量对齐 UID/GID；否则仅在 UID 未被占用时创建
-    chown -R web:web /private/argus/etc && \
+    if id web >/dev/null 2>&1; then \
-    chown -R web:web /usr/local/bin
+        current_uid="$(id -u web)"; \
+        if [ "$current_uid" != "${ARGUS_BUILD_UID}" ] && ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
+            usermod -u "${ARGUS_BUILD_UID}" web; \
+        fi; \
+        usermod -g "${ARGUS_BUILD_GID}" web || true; \
+    else \
+        if ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
+            useradd -M -s /usr/sbin/nologin -u "${ARGUS_BUILD_UID}" -g "${ARGUS_BUILD_GID}" web; \
+        else \
+            echo "UID ${ARGUS_BUILD_UID} already exists; skip creating user 'web'"; \
+        fi; \
+    fi; \
+    # 用数值 UID:GID 赋权，避免依赖用户名/组名
+    chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" ${FRONTEND_BASE_PATH} /private/argus/etc /usr/local/bin || true
 
 # 配置内网 apt 源 (如果指定了内网选项)
 RUN if [ "$USE_INTRANET" = "true" ]; then \

src/web/build_tools/frontend/build.sh

@@ -4,7 +4,7 @@ docker pull ubuntu:24.04
 source src/web/tests/.env
 
 docker build \
-  --build-arg ARGUS_UID=${ARGUS_UID} \
+  --build-arg ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
-  --build-arg ARGUS_GID=${ARGUS_GID} \
+  --build-arg ARGUS_BUILD_GID=${ARGUS_BUILD_GID} \
   -f src/web/build_tools/frontend/Dockerfile -t argus-web-frontend:latest .
 docker save -o argus-web-frontend-latest.tar argus-web-frontend:latest

src/web/build_tools/frontend/start-web-supervised.sh

@@ -8,8 +8,8 @@ DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
 DOMAIN=web.argus.com
 WEB_DOMAIN_FILE="${DNS_DIR}/${DOMAIN}"
 RUNTIME_USER="${ARGUS_RUNTIME_USER:-argus}"
-RUNTIME_UID="${ARGUS_UID:-2133}"
+RUNTIME_UID="${ARGUS_BUILD_UID:-2133}"
-RUNTIME_GID="${ARGUS_GID:-2015}"
+RUNTIME_GID="${ARGUS_BUILD_GID:-2015}"
 
 mkdir -p "$DNS_DIR"
 chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true

src/web/build_tools/proxy/Dockerfile

@@ -8,24 +8,34 @@ RUN apt-get update && \
     apt-get clean && rm -rf /var/lib/apt/lists/*
 
 ENV FRONTEND_BASE_PATH=/private/argus/web/proxy
-ARG ARGUS_UID=2133
+ARG ARGUS_BUILD_UID=2133
-ARG ARGUS_GID=2015
+ARG ARGUS_BUILD_GID=2015
-ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID}
-ENV ARGUS_GID=${ARGUS_GID}
+ENV ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
 
 RUN mkdir -p ${FRONTEND_BASE_PATH} && \
     mkdir -p /private/argus/etc
 
 # 创建 proxy 用户（可自定义 UID/GID）
 # 创建 proxy 用户组
-RUN groupadd -g ${ARGUS_GID} web_proxy
+RUN set -eux; \
-
+    if ! getent group "${ARGUS_BUILD_GID}" >/dev/null; then \
-# 创建 proxy 用户并指定组
+        groupadd -g "${ARGUS_BUILD_GID}" web_proxy || true; \
-RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} web_proxy
+    fi; \
-
+    if id web_proxy >/dev/null 2>&1; then \
-RUN chown -R web_proxy:web_proxy ${FRONTEND_BASE_PATH} && \
+        current_uid="$(id -u web_proxy)"; \
-    chown -R web_proxy:web_proxy /private/argus/etc && \
+        if [ "$current_uid" != "${ARGUS_BUILD_UID}" ] && ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
-    chown -R web_proxy:web_proxy /usr/local/bin
+            usermod -u "${ARGUS_BUILD_UID}" web_proxy; \
+        fi; \
+        usermod -g "${ARGUS_BUILD_GID}" web_proxy || true; \
+    else \
+        if ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
+            useradd -M -s /usr/sbin/nologin -u "${ARGUS_BUILD_UID}" -g "${ARGUS_BUILD_GID}" web_proxy; \
+        else \
+            echo "UID ${ARGUS_BUILD_UID} already exists; skip creating user 'web_proxy'"; \
+        fi; \
+    fi; \
+    chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" ${FRONTEND_BASE_PATH} /private/argus/etc /usr/local/bin || true
 
 # 配置内网 apt 源 (如果指定了内网选项)
 RUN if [ "$USE_INTRANET" = "true" ]; then \

src/web/build_tools/proxy/build.sh

@@ -3,7 +3,7 @@ docker pull ubuntu:24.04
 source src/web/tests/.env
 
 docker build \
-    --build-arg ARGUS_UID=${ARGUS_UID} \
+    --build-arg ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
-    --build-arg ARGUS_GID=${ARGUS_GID} \
+    --build-arg ARGUS_BUILD_GID=${ARGUS_BUILD_GID} \
     -f src/web/build_tools/proxy/Dockerfile -t argus-web-proxy:latest .
 docker save -o argus-web-proxy-latest.tar argus-web-proxy:latest

src/web/build_tools/proxy/start-proxy-supervised.sh

@@ -9,8 +9,8 @@ DNS_CONF_PRIVATE="/private/argus/etc/dns.conf"
 DNS_CONF_SYSTEM="/etc/resolv.conf"
 DNS_DIR="/private/argus/etc"
 DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
-RUNTIME_UID="${ARGUS_UID:-2133}"
+RUNTIME_UID="${ARGUS_BUILD_UID:-2133}"
-RUNTIME_GID="${ARGUS_GID:-2015}"
+RUNTIME_GID="${ARGUS_BUILD_GID:-2015}"
 
 mkdir -p "$DNS_DIR"
 chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true

src/web/tests/docker-compose.yml

@@ -4,15 +4,15 @@ services:
       context: ../../../
       dockerfile: src/web/build_tools/frontend/Dockerfile
       args:
-        ARGUS_UID: ${ARGUS_UID:-2133}
+        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_GID: ${ARGUS_GID:-2015}
+        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
         USE_INTRANET: ${USE_INTRANET:-false}
     image: argus-web-frontend:latest
     container_name: argus-web-frontend
     environment:
       - ALERTMANAGER_BASE_PATH=/private/argus/web/frontend
-      - ARGUS_UID=${ARGUS_UID:-2133}
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_GID=${ARGUS_GID:-2015}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
     ports:
       - "${ARGUS_WEB_PORT:-8080}:80"
     volumes:
@@ -31,14 +31,14 @@ services:
       context: ../../../
       dockerfile: src/web/build_tools/proxy/Dockerfile
       args:
-        ARGUS_UID: ${ARGUS_UID:-2133}
+        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_GID: ${ARGUS_GID:-2015}
+        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
         USE_INTRANET: ${USE_INTRANET:-false}
     image: argus-web-proxy:latest
     container_name: argus-web-proxy
     environment:
-      - ARGUS_UID=${ARGUS_UID:-2133}
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_GID=${ARGUS_GID:-2015}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
     ports:
       - "8088:80"
     volumes: