.gitattributes

@@ -0,0 +1 @@
+src/metric/client-plugins/all-in-one-full/plugins/*/bin/* filter=lfs diff=lfs merge=lfs -text

build/build_images.sh

@@ -10,20 +10,28 @@ Usage: $0 [OPTIONS]
 Options:
   --intranet        Use intranet mirror for log/bind builds
   --master-offline  Build master offline image (requires src/master/offline_wheels.tar.gz)
+  --metric          Build metric module images (ftp, prometheus, grafana, test nodes)
   --no-cache        Build all images without using Docker layer cache
+  --only LIST       Comma-separated targets to build: core,master,metric,web,alert,sys,all
   -h, --help        Show this help message
 
 Examples:
   $0                             # Build with default sources
   $0 --intranet                  # Build with intranet mirror
   $0 --master-offline            # Additionally build argus-master:offline
-  $0 --intranet --master-offline
+  $0 --metric                    # Additionally build metric module images
+  $0 --intranet --master-offline --metric
 EOF
 }
 
 use_intranet=false
+build_core=true
 build_master=true
 build_master_offline=false
+build_metric=true
+build_web=true
+build_alert=true
+build_sys=true
 no_cache=false
 
 while [[ $# -gt 0 ]]; do
@@ -41,10 +49,35 @@ while [[ $# -gt 0 ]]; do
       build_master_offline=true
       shift
       ;;
+    --metric)
+      build_metric=true
+      shift
+      ;;
     --no-cache)
       no_cache=true
       shift
       ;;
+    --only)
+      if [[ -z ${2:-} ]]; then
+        echo "--only requires a target list" >&2; exit 1
+      fi
+      sel="$2"; shift 2
+      # reset all, then enable selected
+      build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false; build_sys=false
+      IFS=',' read -ra parts <<< "$sel"
+      for p in "${parts[@]}"; do
+        case "$p" in
+          core) build_core=true ;;
+          master) build_master=true ;;
+          metric) build_metric=true ;;
+          web) build_web=true ;;
+          alert) build_alert=true ;;
+          sys) build_sys=true ;;
+          all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true; build_sys=true ;;
+          *) echo "Unknown --only target: $p" >&2; exit 1 ;;
+        esac
+      done
+      ;;
     -h|--help)
       show_help
       exit 0
@@ -115,14 +148,22 @@ build_image() {
   local image_name=$1
   local dockerfile_path=$2
   local tag=$3
+  local context="."
   shift 3
+
+  if [[ $# -gt 0 ]]; then
+    context=$1
+    shift
+  fi
+
   local extra_args=("$@")
 
   echo "🔄 Building $image_name image..."
   echo "   Dockerfile: $dockerfile_path"
   echo "   Tag: $tag"
+  echo "   Context: $context"
 
-  if docker build "${build_args[@]}" "${extra_args[@]}" -f "$dockerfile_path" -t "$tag" .; then
+  if docker build "${build_args[@]}" "${extra_args[@]}" -f "$dockerfile_path" -t "$tag" "$context"; then
     echo "✅ $image_name image built successfully"
     return 0
   else
@@ -131,29 +172,59 @@ build_image() {
   fi
 }
 
+pull_base_image() {
+  local image_ref=$1
+  local attempts=${2:-3}
+  local delay=${3:-5}
+
+  # If the image already exists locally, skip pulling.
+  if docker image inspect "$image_ref" >/dev/null 2>&1; then
+    echo "   Local image present; skip pull: $image_ref"
+    return 0
+  fi
+
+  for ((i=1; i<=attempts; i++)); do
+    echo "   Pulling base image ($i/$attempts): $image_ref"
+    if docker pull "$image_ref" >/dev/null; then
+      echo "   Base image ready: $image_ref"
+      return 0
+    fi
+    echo "   Pull failed: $image_ref"
+    if (( i < attempts )); then
+      echo "   Retrying in ${delay}s..."
+      sleep "$delay"
+    fi
+  done
+
+  echo "❌ Unable to pull base image after ${attempts} attempts: $image_ref"
+  return 1
+}
+
 images_built=()
 build_failed=false
 
-if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:latest"; then
-  images_built+=("argus-elasticsearch:latest")
-else
-  build_failed=true
-fi
+if [[ "$build_core" == true ]]; then
+  if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:latest"; then
+    images_built+=("argus-elasticsearch:latest")
+  else
+    build_failed=true
+  fi
 
-echo ""
+  echo ""
 
-if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:latest"; then
-  images_built+=("argus-kibana:latest")
-else
-  build_failed=true
-fi
+  if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:latest"; then
+    images_built+=("argus-kibana:latest")
+  else
+    build_failed=true
+  fi
 
-echo ""
+  echo ""
 
-if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:latest"; then
-  images_built+=("argus-bind9:latest")
-else
-  build_failed=true
+  if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:latest"; then
+    images_built+=("argus-bind9:latest")
+  else
+    build_failed=true
+  fi
 fi
 
 echo ""
@@ -184,6 +255,127 @@ if [[ "$build_master" == true ]]; then
   popd >/dev/null
 fi
 
+if [[ "$build_metric" == true ]]; then
+  echo ""
+  echo "Building Metric module images..."
+
+  metric_base_images=(
+    "ubuntu:22.04"
+    "ubuntu/prometheus:3-24.04_stable"
+    "grafana/grafana:11.1.0"
+  )
+
+  for base_image in "${metric_base_images[@]}"; do
+    if ! pull_base_image "$base_image"; then
+      build_failed=true
+    fi
+  done
+
+  metric_builds=(
+    "Metric FTP|src/metric/ftp/build/Dockerfile|argus-metric-ftp:latest|src/metric/ftp/build"
+    "Metric Prometheus|src/metric/prometheus/build/Dockerfile|argus-metric-prometheus:latest|src/metric/prometheus/build"
+    "Metric Grafana|src/metric/grafana/build/Dockerfile|argus-metric-grafana:latest|src/metric/grafana/build"
+  )
+
+  for build_spec in "${metric_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
+fi
+
+# =======================================
+# Sys (system tests) node images
+# =======================================
+
+if [[ "$build_sys" == true ]]; then
+  echo ""
+  echo "Building Sys node images..."
+
+  sys_base_images=(
+    "ubuntu:22.04"
+    "nvidia/cuda:12.2.2-runtime-ubuntu22.04"
+  )
+
+  for base_image in "${sys_base_images[@]}"; do
+    if ! pull_base_image "$base_image"; then
+      build_failed=true
+    fi
+  done
+
+  sys_builds=(
+    "Sys Node|src/sys/build/node/Dockerfile|argus-sys-node:latest|."
+    "Sys Metric Test Node|src/sys/build/test-node/Dockerfile|argus-sys-metric-test-node:latest|."
+    "Sys Metric Test GPU Node|src/sys/build/test-gpu-node/Dockerfile|argus-sys-metric-test-gpu-node:latest|."
+  )
+
+  for build_spec in "${sys_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
+fi
+
+# =======================================
+# Web & Alert module images
+# =======================================
+
+if [[ "$build_web" == true || "$build_alert" == true ]]; then
+  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
+
+  if [[ "$build_web" == true ]]; then
+    web_builds=(
+      "Web Frontend|src/web/build_tools/frontend/Dockerfile|argus-web-frontend:latest|."
+      "Web Proxy|src/web/build_tools/proxy/Dockerfile|argus-web-proxy:latest|."
+    )
+    for build_spec in "${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
+  fi
+
+  if [[ "$build_alert" == true ]]; then
+    alert_builds=(
+      "Alertmanager|src/alert/alertmanager/build/Dockerfile|argus-alertmanager:latest|."
+    )
+    for build_spec in "${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
+  fi
+fi
+
 echo "======================================="
 echo "📦 Build Summary"
 echo "======================================="
@@ -210,7 +402,6 @@ if [[ "$build_master_offline" == true ]]; then
   echo ""
   echo "🧳 Master offline wheels 已解压到 $master_offline_dir"
 fi
-
 echo ""
 echo "🚀 Next steps:"
 echo "   ./build/save_images.sh --compress          # 导出镜像"

build/save_images.sh

@@ -68,6 +68,12 @@ declare -A images=(
     ["argus-kibana:latest"]="argus-kibana-latest.tar"
     ["argus-bind9:latest"]="argus-bind9-latest.tar"
     ["argus-master:offline"]="argus-master-offline.tar"
+    ["argus-metric-ftp:latest"]="argus-metric-ftp-latest.tar"
+    ["argus-metric-prometheus:latest"]="argus-metric-prometheus-latest.tar"
+    ["argus-metric-grafana:latest"]="argus-metric-grafana-latest.tar"
+    ["argus-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
@@ -220,4 +226,4 @@ fi
 
 echo ""
 echo "✅ Image export completed successfully!"
-echo ""
+echo ""

src/agent/scripts/build_binary.sh

@@ -12,6 +12,8 @@ VENV_DIR="$BUILD_ROOT/venv"
 
 AGENT_BUILD_IMAGE="${AGENT_BUILD_IMAGE:-python:3.11-slim-bullseye}"
 AGENT_BUILD_USE_DOCKER="${AGENT_BUILD_USE_DOCKER:-1}"
+# 默认在容器内忽略代理以避免公司内网代理在 Docker 网络不可达导致 pip 失败（可用 0 关闭）
+AGENT_BUILD_IGNORE_PROXY="${AGENT_BUILD_IGNORE_PROXY:-1}"
 USED_DOCKER=0
 
 run_host_build() {
@@ -71,6 +73,7 @@ run_docker_build() {
   pass_env_if_set http_proxy
   pass_env_if_set https_proxy
   pass_env_if_set no_proxy
+  pass_env_if_set AGENT_BUILD_IGNORE_PROXY
 
 build_script=$(cat <<'INNER'
 set -euo pipefail
@@ -82,6 +85,10 @@ rm -rf build dist
 mkdir -p build/pyinstaller dist
 python3 -m venv --copies build/venv
 source build/venv/bin/activate
+# 若指定忽略代理，则清空常见代理与 pip 镜像环境变量，避免容器内代理不可达
+if [ "${AGENT_BUILD_IGNORE_PROXY:-1}" = "1" ]; then
+  unset http_proxy https_proxy HTTP_PROXY HTTPS_PROXY PIP_INDEX_URL PIP_EXTRA_INDEX_URL PIP_TRUSTED_HOST
+fi
 pip install --upgrade pip
 pip install .
 pip install pyinstaller==6.6.0

src/alert/alertmanager/build/Dockerfile

@@ -9,21 +9,21 @@ RUN apt-get update && \
     apt-get install -y wget supervisor net-tools inetutils-ping vim ca-certificates passwd && \
     apt-get clean && rm -rf /var/lib/apt/lists/*
 
-# 设置 Alertmanager 版本
+# 设置 Alertmanager 版本（与本地离线包保持一致）
 ARG ALERTMANAGER_VERSION=0.28.1
 
-# 下载并解压 Alertmanager 二进制
-RUN wget https://github.com/prometheus/alertmanager/releases/download/v${ALERTMANAGER_VERSION}/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
-    tar xvf alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
-    mv alertmanager-${ALERTMANAGER_VERSION}.linux-amd64 /usr/local/alertmanager && \
-    rm alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz
+# 使用仓库内预置的离线包构建（无需联网）
+COPY src/alert/alertmanager/build/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz /tmp/
+RUN tar xvf /tmp/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz -C /tmp && \
+    mv /tmp/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64 /usr/local/alertmanager && \
+    rm -f /tmp/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz
 
 ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
 
-ARG ARGUS_UID=2133
-ARG ARGUS_GID=2015
-ENV ARGUS_UID=${ARGUS_UID}
-ENV ARGUS_GID=${ARGUS_GID}
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID}
+ENV ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
 
 RUN mkdir -p /usr/share/alertmanager && \
     mkdir -p ${ALERTMANAGER_BASE_PATH} && \
@@ -33,16 +33,24 @@ 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 ${ARGUS_GID} alertmanager
+RUN set -eux; \
+    # 确保目标 GID 存在；若已被占用，直接使用该 GID（组名不限）\
+    if ! getent group "${ARGUS_BUILD_GID}" >/dev/null; then \
+        groupadd -g "${ARGUS_BUILD_GID}" alertmanager || true; \
+    fi; \
+    # 确保存在 alertmanager 用户；若 UID 已被占用，跳过并继续使用现有 UID 的用户
+    if ! id alertmanager >/dev/null 2>&1; then \
+        if getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
+            # UID 已占用，则创建同名用户但不指定 UID（避免冲突），仅保证 user 存在
+            useradd -M -s /usr/sbin/nologin -g "${ARGUS_BUILD_GID}" alertmanager || true; \
+        else \
+            useradd -M -s /usr/sbin/nologin -u "${ARGUS_BUILD_UID}" -g "${ARGUS_BUILD_GID}" alertmanager || true; \
+        fi; \
+    else \
+        usermod -g "${ARGUS_BUILD_GID}" alertmanager || true; \
+    fi
 
-# 创建 alertmanager 用户并指定组
-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 ${ALERTMANAGER_BASE_PATH} && \
-    chown -R alertmanager:alertmanager /private/argus/etc && \
-    chown -R alertmanager:alertmanager /usr/local/bin
+RUN chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" /usr/share/alertmanager /alertmanager ${ALERTMANAGER_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 \
@@ -86,4 +94,3 @@ 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

@@ -5,9 +5,9 @@ docker pull ubuntu:24.04
 source src/alert/tests/.env
 
 docker build \
-  --build-arg ARGUS_UID=${ARGUS_UID} \
-  --build-arg ARGUS_GID=${ARGUS_GID} \
+  --build-arg ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+  --build-arg ARGUS_BUILD_GID=${ARGUS_BUILD_GID} \
   -f src/alert/alertmanager/build/Dockerfile \
   -t argus-alertmanager:latest .
 
-docker save -o argus-alertmanager-latest.tar argus-alertmanager:latest
+docker save -o argus-alertmanager-latest.tar argus-alertmanager:latest

src/alert/alertmanager/build/fetch-dist.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 下载 Alertmanager 离线安装包到本目录，用于 Docker 构建时 COPY
+# 用法：
+#   ./fetch-dist.sh [version]
+# 示例：
+#   ./fetch-dist.sh 0.28.1
+
+VER="${1:-0.28.1}"
+OUT="alertmanager-${VER}.linux-amd64.tar.gz"
+URL="https://github.com/prometheus/alertmanager/releases/download/v${VER}/${OUT}"
+
+if [[ -f "$OUT" ]]; then
+  echo "[INFO] $OUT already exists, skip download"
+  exit 0
+fi
+
+echo "[INFO] Downloading $URL"
+curl -fL --retry 3 --connect-timeout 10 -o "$OUT" "$URL"
+echo "[OK] Saved to $(pwd)/$OUT"
+

src/alert/alertmanager/build/start-am-supervised.sh

@@ -7,10 +7,8 @@ ALERTMANAGER_BASE_PATH=${ALERTMANAGER_BASE_PATH:-/private/argus/alert/alertmanag
 
 echo "[INFO] Alertmanager base path: ${ALERTMANAGER_BASE_PATH}"
 
-# 生成配置文件
-echo "[INFO] Generating Alertmanager configuration file..."
-sed "s|\${ALERTMANAGER_BASE_PATH}|${ALERTMANAGER_BASE_PATH}|g" \
-    /etc/alertmanager/alertmanager.yml > ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
+# 使用容器内的 /etc/alertmanager/alertmanager.yml 作为配置文件，避免写入挂载卷导致的权限问题
+echo "[INFO] Using /etc/alertmanager/alertmanager.yml as configuration"
 
 
 # 记录容器 IP 地址

src/alert/alertmanager/build/supervisord.conf

@@ -6,7 +6,7 @@ user=root
 
 [program:alertmanager]
 command=/usr/local/bin/start-am-supervised.sh
-user=alertmanager
+user=ubuntu
 stdout_logfile=/var/log/supervisor/alertmanager.log
 stderr_logfile=/var/log/supervisor/alertmanager_error.log
 autorestart=true

src/alert/tests/.env

@@ -1,5 +1,5 @@
 DATA_ROOT=/home/argus/tmp/private/argus
-ARGUS_UID=1048
-ARGUS_GID=1048
+ARGUS_BUILD_UID=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_GID: ${ARGUS_GID:-2015}
+        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
+        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_GID=${ARGUS_GID:-2015}
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - 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/log/fluent-bit/build/start-fluent-bit.sh

@@ -1,47 +1,96 @@
 #!/bin/bash
 set -euo pipefail
 
-echo "[INFO] Starting Fluent Bit setup in Ubuntu container..."
+echo "[INFO] Starting Fluent Bit setup in Ubuntu container (offline-first)..."
 
-# 安装必要的工具
-echo "[INFO] Installing required packages..."
 export DEBIAN_FRONTEND=noninteractive
-apt-get update -qq
-apt-get install -y -qq curl
 
-# 解压bundle到/tmp
-echo "[INFO] Extracting fluent-bit bundle..."
-cp -r /private/etc /tmp
-cp -r /private/packages /tmp
-cd /tmp
+# Stage bundle to /tmp (read-only mount under /private)
+echo "[INFO] Staging fluent-bit bundle..."
+rm -rf /tmp/flb && mkdir -p /tmp/flb
+cp -r /private/etc /tmp/flb/
+mkdir -p /tmp/flb/packages
+cp -r /private/packages/* /tmp/flb/packages/ 2>/dev/null || true
 
-# 安装 Fluent Bit 从 deb 包
-echo "[INFO] Installing Fluent Bit from deb package..."
-dpkg -i /tmp/packages/fluent-bit_3.1.9_amd64.deb || true
-apt-get install -f -y -qq  # 解决依赖问题
+# Helper: check and install a local deb if not already satisfied
+ensure_lib() {
+  local soname="$1"; shift
+  local pattern="$1"; shift
+  if ldconfig -p 2>/dev/null | grep -q "$soname"; then
+    echo "[OK] $soname already present"
+    return 0
+  fi
+  local deb="$(ls /tmp/flb/packages/$pattern 2>/dev/null | head -n1 || true)"
+  if [[ -n "$deb" ]]; then
+    echo "[INFO] Installing local dependency: $(basename "$deb")"
+    dpkg -i "$deb" >/dev/null 2>&1 || true
+  else
+    echo "[WARN] Local deb for $soname not found (pattern=$pattern)"
+  fi
+  if ! ldconfig -p 2>/dev/null | grep -q "$soname"; then
+    echo "[WARN] $soname still missing after local install; attempting apt fallback"
+    apt-get update -qq || true
+    case "$soname" in
+      libpq.so.5) apt-get install -y -qq libpq5 || true ;;
+      libyaml-0.so.2) apt-get install -y -qq libyaml-0-2 || true ;;
+    esac
+  fi
+  ldconfig 2>/dev/null || true
+}
+
+# Offline-first: satisfy runtime deps from local debs, fallback to apt only if necessary
+ensure_lib "libpq.so.5" "libpq5_*_amd64.deb"
+ensure_lib "libyaml-0.so.2" "libyaml-0-2_*_amd64.deb"
+ensure_lib "libsasl2.so.2" "libsasl2-2_*_amd64.deb"
+ensure_lib "libldap-2.5.so.0" "libldap-2.5-0_*_amd64.deb"
+
+# Install fluent-bit main package from local bundle
+FLB_DEB="$(ls /tmp/flb/packages/fluent-bit_*_amd64.deb 2>/dev/null | head -n1 || true)"
+if [[ -z "$FLB_DEB" ]]; then
+  echo "[ERROR] fluent-bit deb not found under /private/packages" >&2
+  exit 1
+fi
+echo "[INFO] Installing Fluent Bit: $(basename "$FLB_DEB")"
+dpkg -i "$FLB_DEB" >/dev/null 2>&1 || true
+
+# If dpkg reported unresolved dependencies, try apt -f only as last resort
+if ! command -v /opt/fluent-bit/bin/fluent-bit >/dev/null 2>&1; then
+  echo "[WARN] fluent-bit binary missing after dpkg; attempting apt --fix-broken"
+  apt-get install -f -y -qq || true
+fi
+
+# Ensure runtime library dependencies are satisfied (libsasl2, libldap are required via libpq/curl)
+MISSING=$(ldd /opt/fluent-bit/bin/fluent-bit 2>/dev/null | awk '/not found/{print $1}' | xargs -r echo || true)
+if [[ -n "$MISSING" ]]; then
+  echo "[WARN] missing shared libs: $MISSING"
+  apt-get update -qq || true
+  apt-get install -y -qq libsasl2-2 libldap-2.5-0 || true
+  apt-get install -f -y -qq || true
+fi
 
-# 验证 Fluent Bit 可以运行
 echo "[INFO] Fluent Bit version:"
-/opt/fluent-bit/bin/fluent-bit --version
+/opt/fluent-bit/bin/fluent-bit --version || { echo "[ERROR] fluent-bit not installed or libraries missing" >&2; exit 1; }
 
-# 创建配置目录
+# Place configuration
 mkdir -p /etc/fluent-bit
-cp -r /tmp/etc/* /etc/fluent-bit/
+cp -r /tmp/flb/etc/* /etc/fluent-bit/
 
-# 创建日志和缓冲区目录
+# Create logs/buffers dirs
 mkdir -p /logs/train /logs/infer /buffers
 chmod 755 /logs/train /logs/infer /buffers
 
-# 等待 Elasticsearch 就绪
-echo "[INFO] Waiting for Elasticsearch to be ready..."
-while ! curl -fs http://${ES_HOST}:${ES_PORT}/_cluster/health >/dev/null 2>&1; do
-    echo "  Waiting for ES at ${ES_HOST}:${ES_PORT}..."
-    sleep 5
+# Wait for Elasticsearch via bash /dev/tcp to avoid curl dependency
+echo "[INFO] Waiting for Elasticsearch to be ready (tcp ${ES_HOST}:${ES_PORT})..."
+for i in $(seq 1 120); do
+  if exec 3<>/dev/tcp/${ES_HOST}/${ES_PORT}; then
+    exec 3<&- 3>&-
+    echo "[INFO] Elasticsearch is ready"
+    break
+  fi
+  [[ $i -eq 120 ]] && { echo "[ERROR] ES not reachable" >&2; exit 1; }
+  sleep 1
 done
-echo "[INFO] Elasticsearch is ready"
 
-# 启动 Fluent Bit
 echo "[INFO] Starting Fluent Bit with configuration from /etc/fluent-bit/"
 echo "[INFO] Command: /opt/fluent-bit/bin/fluent-bit --config=/etc/fluent-bit/fluent-bit.conf"
-exec /opt/fluent-bit/bin/fluent-bit \
-    --config=/etc/fluent-bit/fluent-bit.conf
+exec /opt/fluent-bit/bin/fluent-bit --config=/etc/fluent-bit/fluent-bit.conf

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

@@ -32,3 +32,42 @@ fi
 
 echo "[OK] 初始化完成: private/argus/log/{elasticsearch,kibana}"
 echo "[INFO] Fluent-bit files should be in fluent-bit/ directory"
+
+# 准备 Fluent Bit 离线依赖（从 metric all-in-one-full 复制 deb 到 ../fluent-bit/build/packages）
+FLB_BUILD_PACKAGES_DIR="$root/../fluent-bit/build/packages"
+mkdir -p "$FLB_BUILD_PACKAGES_DIR"
+for deb in \
+  "$project_root/src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/bin/libyaml-0-2_"*_amd64.deb \
+  "$project_root/src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/bin/libpq5_"*_amd64.deb ; do
+  if ls $deb >/dev/null 2>&1; then
+    for f in $deb; do
+      base="$(basename "$f")"
+      if [[ ! -f "$FLB_BUILD_PACKAGES_DIR/$base" ]]; then
+        cp "$f" "$FLB_BUILD_PACKAGES_DIR/"
+        echo "  [+] copied $base"
+      fi
+    done
+  fi
+done
+
+# 额外：从 all-in-one-full 的 ubuntu22/curl.tar.gz 解包必要依赖（libsasl2/ldap），便于离线安装
+CURLOPT_TAR="$project_root/src/metric/client-plugins/all-in-one-full/deps/ubuntu22/curl.tar.gz"
+if [[ -f "$CURLOPT_TAR" ]]; then
+  tmpdir=$(mktemp -d)
+  if tar -xzf "$CURLOPT_TAR" -C "$tmpdir" 2>/dev/null; then
+    for p in \
+      libsasl2-2_*_amd64.deb \
+      libsasl2-modules-db_*_amd64.deb \
+      libldap-2.5-0_*_amd64.deb \
+      libidn2-0_*_amd64.deb \
+      libbrotli1_*_amd64.deb \
+      libssl3_*_amd64.deb ; do
+      src=$(ls "$tmpdir"/curl/$p 2>/dev/null | head -n1 || true)
+      if [[ -n "$src" ]]; then
+        base="$(basename "$src")"
+        [[ -f "$FLB_BUILD_PACKAGES_DIR/$base" ]] || cp "$src" "$FLB_BUILD_PACKAGES_DIR/" && echo "  [+] staged $base"
+      fi
+    done
+  fi
+  rm -rf "$tmpdir"
+fi

src/metric/.gitignore

@@ -4,4 +4,4 @@
 /client-plugins/demo-all-in-one/publish/
 /client-plugins/demo-all-in-one/checklist
 /client-plugins/demo-all-in-one/VERSION
-/client-plugins/all-in-one-full/
+/client-plugins/all-in-one-full/artifact/

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
-log_info "设置文件所有者为: $OWNER"
-sudo chown "$OWNER" "$PUBLISH_DIR/$TAR_NAME"
+if [[ "$NEED_CHOWN" == true ]]; then
+    log_info "设置文件所有者为: $OWNER"
+    chown "$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
-sudo chown "$OWNER" "$PUBLISH_DIR/LATEST_VERSION"
+echo "$VERSION" > "$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" "$PUBLISH_DIR/"
-    sudo chown "$OWNER" "$PUBLISH_DIR/dns.conf"
+    cp "config/dns.conf" "$PUBLISH_DIR/"
+    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/"
-    sudo chown "$OWNER" "$PUBLISH_DIR/setup.sh"
+    cp "scripts/setup.sh" "$PUBLISH_DIR/"
+    if [[ "$NEED_CHOWN" == true ]]; then
+        chown "$OWNER" "$PUBLISH_DIR/setup.sh"
+    fi
 fi
 
 # 显示发布结果

src/metric/client-plugins/all-in-one-full/README.md

@@ -0,0 +1,59 @@
+# 客户侧组件安装包构建、发布流程
+
+## 第一步：配置版本和组件
+
+首先搞定配置文件：
+
+1. 把 `.checklist.example` 重命名成 `checklist`
+2. 把 `.VERSION.example` 重命名成 `VERSION`
+
+### checklist 文件格式
+```
+# 组件名称 目录路径 版本号 [依赖组件] [安装顺序]
+dcgm-exporter-installer /path/to/dcgm-exporter-installer 1.1.0
+node-exporter-installer /path/to/node-exporter-installer 1.1.0
+```
+
+### VERSION 文件
+设置需要发布的版本号，比如 `1.29.0`
+
+> 建议用 `version-manager.sh` 来管理版本
+
+## 第二步：构建安装包
+
+直接跑脚本：
+```bash
+./package_artifact.sh
+```
+
+构建完的东西会放在 `artifact/` 目录下，按版本分文件夹。
+
+如果版本已经存在了，想要覆盖重新构建：
+```bash
+./package_artifact.sh --force
+```
+
+构建完可以手工测试安装包。
+
+## 第三步：发布安装包
+
+用这个脚本发布：
+```bash
+./publish_artifact.sh
+```
+
+发布后的内容在 `publish/` 目录里，包含：
+- 压缩版本的安装包
+- 一键安装的bash脚本
+
+## 第四步：部署到FTP服务器
+
+把发布的内容上传到FTP服务器，客户端就可以通过一键命令安装：
+
+```bash
+curl -fsSL http://your-ftp-server/install.sh | sh -
+
+curl -fsSL "ftp://ftpuser:{PASSWD}!@10.211.55.4/share/setup.sh" | sudo bash -s -- --server 10.211.55.4 --user ftpuser --password {PASSWD}
+```
+
+这样客户就能直接从FTP服务器下载并安装组件了。

src/metric/client-plugins/all-in-one-full/config/.VERSION.example

@@ -0,0 +1 @@
+1.29.0

src/metric/client-plugins/all-in-one-full/config/.checklist.example

@@ -0,0 +1,3 @@
+# 组件名称 目录路径 版本号 [依赖组件] [安装顺序]
+dcgm-exporter-installer /Users/sundapeng/Project/nlp/aiops/client-plugins/dcgm-exporter-installer 1.1.0
+node-exporter-installer /Users/sundapeng/Project/nlp/aiops/client-plugins/node-exporter-installer 1.1.0

src/metric/client-plugins/all-in-one-full/config/VERSION

@@ -0,0 +1 @@
+1.35.0

src/metric/client-plugins/all-in-one-full/config/checklist

@@ -0,0 +1,5 @@
+# 组件名称 目录路径 版本号 [依赖组件] [安装顺序]
+argus-agent plugins/argus-agent 1.0.0
+node-exporter plugins/node-exporter 1.0.0
+dcgm-exporter plugins/dcgm-exporter 1.0.0
+fluent-bit plugins/fluent-bit 1.0.0

src/metric/client-plugins/all-in-one-full/config/config.env

@@ -0,0 +1,14 @@
+# Elasticsearch
+ES_HOST=es.log.argus.com
+ES_PORT=9200
+
+# Argus-Agent
+# 连接master服务
+MASTER_ENDPOINT=master.argus.com:3000
+# 上报状态间隔描述
+REPORT_INTERVAL_SECONDS=5
+
+# FTP
+FTP_SERVER=172.31.0.40
+FTP_USER=ftpuser
+FTP_PASSWORD=ZGClab1234!

src/metric/client-plugins/all-in-one-full/config/config.env.example

@@ -0,0 +1,8 @@
+# Argus Metric 配置文件示例
+# 复制此文件为 config.env 并根据需要修改配置
+
+# 连接master服务
+MASTER_ENDPOINT=master.argus.com:3000
+
+# 上报状态间隔描述（秒）
+REPORT_INTERVAL_SECONDS=60

src/metric/client-plugins/all-in-one-full/config/dns.conf

@@ -0,0 +1 @@
+172.31.0.2

src/metric/client-plugins/all-in-one-full/plugins/argus-agent/README.md

@@ -0,0 +1,94 @@
+# Argus Agent 插件
+
+这是 Argus Agent 的安装和管理插件，提供了完整的安装、卸载、健康检查功能。
+
+## 文件结构
+
+```
+argus-agent/
+├── bin/
+│   └── argus-agent          # Argus Agent 二进制文件
+├── config/                  # 配置文件目录
+├── install.sh              # 安装脚本
+├── uninstall.sh            # 卸载脚本
+├── check_health.sh         # 健康检查脚本
+├── package.sh              # 打包脚本
+└── README.md               # 说明文档
+```
+
+## 使用方法
+
+### 安装
+
+```bash
+sudo ./install.sh
+```
+
+安装脚本会：
+- 检查系统要求
+- 停止可能运行的服务
+- 安装二进制文件到 `/usr/local/bin/argus-agent`
+- 创建 `argus-agent` 用户
+- 创建配置和数据目录
+- 启动服务并记录 PID
+
+### 卸载
+
+```bash
+sudo ./uninstall.sh
+```
+
+卸载脚本会：
+- 停止所有 argus-agent 进程
+- 删除二进制文件
+- 删除配置和数据目录
+- 清理日志文件
+- 更新安装记录
+
+### 健康检查
+
+```bash
+./check_health.sh
+```
+
+健康检查脚本会：
+- 检查安装记录中的 PID
+- 验证进程是否正在运行
+- 输出 JSON 格式的健康状态
+
+### 打包
+
+```bash
+./package.sh
+```
+
+打包脚本会：
+- 检查所有必要文件
+- 创建时间戳命名的压缩包
+- 输出安装包信息
+
+## 安装后的文件位置
+
+- 二进制文件: `/usr/local/bin/argus-agent`
+- 配置目录: `/etc/argus-agent/`
+- 数据目录: `/var/lib/argus-agent/`
+- 日志文件: `/var/log/argus-agent.log`
+- PID 文件: `/var/run/argus-agent.pid`
+- 安装记录: `/opt/argus-metric/current/.install_record`
+
+## 健康检查输出格式
+
+```json
+{
+  "name": "argus-agent",
+  "status": "health|unhealth",
+  "reason": "状态说明"
+}
+```
+
+## 注意事项
+
+1. 安装和卸载脚本需要 root 权限
+2. 健康检查脚本使用安装记录中的 PID 来验证进程状态
+3. 如果 jq 命令不可用，健康检查会使用简单的文本解析
+4. 卸载时会保留 `argus-agent` 用户，避免影响其他服务

src/metric/client-plugins/all-in-one-full/plugins/argus-agent/check_health.sh

@@ -0,0 +1,69 @@
+#!/bin/bash
+
+# Argus Agent 健康检查脚本
+# 输出 JSON 格式结果
+
+set -e
+
+# 检查 Argus Agent 健康状态
+check_health() {
+    local name="argus-agent"
+    local status="unhealth"
+    local reason=""
+    local install_record="/opt/argus-metric/current/.install_record"
+    
+    # 首先尝试通过安装记录文件检查进程
+    if [[ -f "$install_record" ]]; then
+        # 尝试使用jq解析JSON格式的安装记录文件
+        local pid=""
+        if command -v jq &> /dev/null; then
+            pid=$(jq -r '.components."argus-agent".pid // empty' "$install_record" 2>/dev/null || echo "")
+        else
+            # 如果没有jq，使用简单的文本解析方法
+            pid=$(grep -A 10 '"argus-agent"' "$install_record" | grep '"pid"' | cut -d'"' -f4 | head -1)
+        fi
+        
+        if [[ -n "$pid" && "$pid" =~ ^[0-9]+$ ]]; then
+            if kill -0 "$pid" 2>/dev/null; then
+                # 进程存在且运行正常
+                status="health"
+                reason="进程运行正常 (PID: $pid)"
+                echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+                exit 0
+            else
+                reason="安装记录中的 PID $pid 进程不存在"
+                echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+                exit 1
+            fi
+        else
+            reason="安装记录文件中未找到有效的 argus-agent PID"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    else
+        # 如果安装记录文件不存在，尝试查找 argus-agent 进程
+        local pids=$(pgrep -f "argus-agent" 2>/dev/null || true)
+        if [[ -n "$pids" ]]; then
+            # 取第一个找到的 PID
+            local pid=$(echo "$pids" | head -1)
+            status="health"
+            reason="发现 argus-agent 进程运行 (PID: $pid)，但未找到安装记录"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 0
+        else
+            reason="未找到 argus-agent 进程，且安装记录文件不存在"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    fi
+}
+
+# 主函数
+main() {
+    check_health
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/argus-agent/install.sh

@@ -0,0 +1,289 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "Argus Agent 安装脚本"
+    echo
+    echo "用法: $0 [选项]"
+    echo
+    echo "选项:"
+    echo "  --help     显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0          # 安装 Argus Agent"
+    echo
+}
+
+# 解析命令行参数
+INSTALL_DIR=""
+for arg in "$@"; do
+    case $arg in
+        --help|-h)
+            show_help
+            exit 0
+            ;;
+        *)
+            # 如果参数不是以--开头，则认为是安装目录
+            if [[ ! "$arg" =~ ^-- ]]; then
+                INSTALL_DIR="$arg"
+            else
+                log_error "未知参数: $arg"
+                show_help
+                exit 1
+            fi
+            ;;
+    esac
+done
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    source /etc/os-release
+    log_info "检测到操作系统: $NAME $VERSION"
+    
+    # 检查是否为 Linux 系统
+    if [[ "$ID" != "ubuntu" && "$ID" != "debian" && "$ID" != "centos" && "$ID" != "rhel" && "$ID" != "fedora" ]]; then
+        log_warning "此脚本主要针对常见 Linux 发行版，其他系统可能需要调整"
+    fi
+    
+    # 检查系统架构
+    local arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    if [[ "$arch" != "x86_64" && "$arch" != "amd64" ]]; then
+        log_warning "当前架构为 $arch，argus-agent 主要支持 x86_64/amd64"
+    fi
+}
+
+# 停止可能运行的服务
+stop_existing_service() {
+    log_info "检查并停止可能运行的服务..."
+    local pid_file="/var/run/argus-agent.pid"
+
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if ps -p "$pid" -o comm= | grep -q "^argus-agent$"; then
+            kill "$pid" 2>/dev/null || true
+            sleep 2
+            kill -9 "$pid" 2>/dev/null || true
+            log_success "服务已停止"
+        fi
+        rm -f "$pid_file"
+    fi
+
+    local pids=$(pgrep -x argus-agent 2>/dev/null || true)
+    if [[ -n "$pids" ]]; then
+        for pid in $pids; do kill -9 "$pid" 2>/dev/null || true; done
+    fi
+
+    # 检查僵尸进程
+    local zombies=$(ps -eo pid,stat,comm | grep '[a]rgus-agent' | awk '$2 ~ /Z/ {print $1}')
+    if [[ -n "$zombies" ]]; then
+        for pid in $zombies; do
+            local ppid=$(ps -o ppid= -p $pid)
+            log_warning "检测到僵尸 argus-agent (PID=$pid, PPID=$ppid)，尝试清理"
+            [[ "$ppid" -ne 1 ]] && kill -9 "$ppid" 2>/dev/null || true
+        done
+    fi
+}
+
+
+# 安装 Argus Agent 二进制文件
+install_argus_agent() {
+    log_info "安装 Argus Agent..."
+    local binary_file="bin/argus-agent"
+    local install_dir="/usr/local/bin"
+    local target_file="$install_dir/argus-agent"
+
+    [[ ! -f "$binary_file" ]] && log_error "找不到 Argus Agent 二进制文件: $binary_file" && exit 1
+
+    stop_existing_service
+
+    local timeout=10
+    while [[ $timeout -gt 0 ]]; do
+        remaining_pids=$(pgrep -x argus-agent | grep -vw $$ || true)
+        [[ -z "$remaining_pids" ]] && break
+        if ps -eo pid,stat,comm | grep -E 'argus-agent' | grep -q 'Z'; then
+            log_warning "检测到僵尸 argus-agent，跳过等待"
+            break
+        fi
+        log_warning "等待 argus-agent 完全退出... ($timeout)"
+        sleep 1
+        ((timeout--))
+    done
+
+    cp "$binary_file" "${target_file}.new"
+    chmod +x "${target_file}.new"
+    mv -f "${target_file}.new" "$target_file"
+    log_success "Argus Agent 二进制文件安装完成"
+}
+
+
+# 创建用户和组
+create_user() {
+    log_info "创建 argus-agent 用户..."
+    
+    # 检查用户是否已存在
+    if id "argus-agent" &>/dev/null; then
+        log_info "用户 argus-agent 已存在"
+    else
+        useradd --no-create-home --shell /bin/false argus-agent
+        log_success "用户 argus-agent 创建完成"
+    fi
+}
+
+# 安装配置文件
+install_config() {
+    log_info "安装配置文件..."
+    
+    local config_dir="/etc/argus-agent"
+    
+    # 创建配置目录
+    mkdir -p "$config_dir"
+    
+    # 创建健康检查目录
+    mkdir -p "/var/lib/argus-agent/health"
+    chown argus-agent:argus-agent "/var/lib/argus-agent/health"
+}
+
+# 启动 Argus Agent 服务
+start_argus_agent() {
+    log_info "启动 Argus Agent 服务..."
+    local binary_path="/usr/local/bin/argus-agent"
+    local log_file="/var/log/argus-agent.log"
+    local pid_file="/var/run/argus-agent.pid"
+
+    [[ -f "$pid_file" ]] && rm -f "$pid_file"
+
+    log_info "正在启动 Argus Agent..."
+    setsid "$binary_path" > "$log_file" 2>&1 < /dev/null &
+    local pid=$!
+    echo "$pid" > "$pid_file"
+    sleep 2
+
+    if kill -0 "$pid" 2>/dev/null; then
+        log_success "Argus Agent 服务启动成功 (PID: $pid)"
+    else
+        log_error "Argus Agent 启动失败"
+        [[ -f "$log_file" ]] && tail -n 10 "$log_file"
+        rm -f "$pid_file"
+    fi
+}
+
+
+# 更新安装记录
+update_install_record() {
+    local pid="$1"
+    # 使用传入的安装目录参数，如果没有则使用默认值
+    local install_base_dir="${2:-/opt/argus-metric/current}"
+    local install_record="$install_base_dir/.install_record"
+    
+    # 如果安装记录文件不存在，说明是首次安装，由主安装脚本统一创建
+    if [[ ! -f "$install_record" ]]; then
+        log_info "安装记录文件不存在，将由主安装脚本创建"
+        return 0
+    fi
+    
+    # 如果文件存在，说明是重启场景，只更新 PID 字段
+    if command -v jq &> /dev/null; then
+        # 读取当前 PID
+        local current_pid=$(jq -r '.components."argus-agent".pid // ""' "$install_record" 2>/dev/null)
+        
+        if [[ -z "$current_pid" ]]; then
+            log_warning "无法读取当前 PID，跳过更新"
+            return 1
+        fi
+        
+        # 使用 jq 只更新 pid 字段，保持字符串类型，保留其他字段
+        jq --arg new_pid "$pid" '.components."argus-agent".pid = $new_pid' "$install_record" > "$install_record.tmp" && mv "$install_record.tmp" "$install_record"
+        log_info "PID 已更新: $current_pid -> $pid"
+    else
+        log_warning "jq 命令不可用，无法更新安装记录文件"
+    fi
+}
+
+# 显示安装信息
+show_install_info() {
+    log_success "Argus Agent 安装完成！"
+    echo
+    echo "安装信息:"
+    echo "  二进制文件: /usr/local/bin/argus-agent"
+    echo "  运行用户: argus-agent"
+    echo "  配置目录: /etc/argus-agent/"
+    echo "  健康检查目录: /var/lib/argus-agent/health"
+    echo
+    echo "使用方法:"
+    echo "  手动启动: /usr/local/bin/argus-agent"
+    echo "  后台启动: nohup /usr/local/bin/argus-agent &"
+    echo
+    echo "健康检查:"
+    echo "  ./check_health.sh"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus Agent 安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    check_system
+    
+    log_info "开始安装 Argus Agent..."
+    
+    install_argus_agent
+    create_user
+    install_config
+    start_argus_agent
+    
+    show_install_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/argus-agent/package.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+# 获取当前目录
+CURRENT_DIR=$(pwd)
+PACKAGE_NAME="argus-agent-$(date +%Y%m%d-%H%M%S)"
+PACKAGE_FILE="${PACKAGE_NAME}.tar.gz"
+
+log_info "开始打包 Argus Agent 安装包..."
+
+# 检查必要文件
+log_info "检查必要文件..."
+
+required_files=(
+    "install.sh"
+    "uninstall.sh"
+    "bin/argus-agent"
+    "check_health.sh"
+)
+
+missing_files=()
+for file in "${required_files[@]}"; do
+    if [[ ! -f "$file" ]]; then
+        missing_files+=("$file")
+    fi
+done
+
+if [[ ${#missing_files[@]} -gt 0 ]]; then
+    echo "缺少以下文件:"
+    for file in "${missing_files[@]}"; do
+        echo "  - $file"
+    done
+    exit 1
+fi
+
+log_success "所有必要文件检查完成"
+
+# 创建临时目录
+TEMP_DIR=$(mktemp -d)
+log_info "创建临时目录: $TEMP_DIR"
+
+# 复制文件到临时目录
+cp -r . "$TEMP_DIR/$PACKAGE_NAME"
+
+# 进入临时目录
+cd "$TEMP_DIR"
+
+# 创建压缩包
+log_info "创建压缩包: $PACKAGE_FILE"
+tar -czf "$PACKAGE_FILE" "$PACKAGE_NAME"
+
+# 移动压缩包到原目录
+mv "$PACKAGE_FILE" "$CURRENT_DIR/"
+
+# 清理临时目录
+rm -rf "$TEMP_DIR"
+
+# 返回原目录
+cd "$CURRENT_DIR"
+
+# 显示结果
+log_success "打包完成！"
+echo
+echo "安装包文件: $PACKAGE_FILE"
+echo "文件大小: $(du -h "$PACKAGE_FILE" | cut -f1)"
+echo
+echo "使用方法:"
+echo "1. 将 $PACKAGE_FILE 传输到目标服务器"
+echo "2. 解压: tar -xzf $PACKAGE_FILE"
+echo "3. 进入目录: cd $PACKAGE_NAME"
+echo "4. 运行安装: sudo ./install.sh"
+echo
+echo "注意: 请确保所有必要文件都存在"

src/metric/client-plugins/all-in-one-full/plugins/argus-agent/uninstall.sh

@@ -0,0 +1,255 @@
+#!/bin/bash
+
+# Argus Agent 卸载脚本
+# 版本: 1.0
+# 作者: AIOps Team
+# 日期: $(date +%Y-%m-%d)
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 停止运行中的进程
+stop_processes() {
+    log_info "停止 Argus Agent 进程..."
+    
+    local pid_file="/var/run/argus-agent.pid"
+    local stopped=false
+    
+    # 首先尝试通过 PID 文件停止服务
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "通过 PID 文件停止服务 (PID: $pid)..."
+            kill "$pid"
+            sleep 3
+            
+            # 检查进程是否已停止
+            if kill -0 "$pid" 2>/dev/null; then
+                log_warning "进程未响应，强制终止..."
+                kill -9 "$pid" 2>/dev/null || true
+            fi
+            log_success "Argus Agent 进程已停止"
+            stopped=true
+        else
+            log_warning "PID 文件存在但进程已不存在，清理 PID 文件"
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 查找并杀死所有 argus-agent 进程
+    local pids=$(pgrep -f "argus-agent" 2>/dev/null || true)
+    if [[ -n "$pids" ]]; then
+        log_info "发现 argus-agent 进程，正在停止..."
+        for pid in $pids; do
+            log_info "停止进程 PID: $pid"
+            kill "$pid" 2>/dev/null || true
+        done
+        sleep 2
+        
+        # 检查是否还有进程在运行，如果有则强制终止
+        local remaining_pids=$(pgrep -f "argus-agent" 2>/dev/null || true)
+        if [[ -n "$remaining_pids" ]]; then
+            log_warning "进程未响应，强制终止..."
+            for pid in $remaining_pids; do
+                log_info "强制终止进程 PID: $pid"
+                kill -9 "$pid" 2>/dev/null || true
+            done
+            sleep 1
+        fi
+        
+        # 最终检查
+        if pgrep -f "argus-agent" > /dev/null; then
+            log_error "无法停止所有 argus-agent 进程"
+        else
+            log_success "所有 Argus Agent 进程已停止"
+            stopped=true
+        fi
+    else
+        log_info "Argus Agent 进程未运行"
+    fi
+    
+    # 清理 PID 文件
+    rm -f "$pid_file"
+    
+    if [[ "$stopped" == "false" ]]; then
+        log_warning "未发现需要停止的 Argus Agent 进程"
+    fi
+}
+
+# 删除二进制文件
+remove_binary() {
+    log_info "删除 Argus Agent 二进制文件..."
+    
+    local binary_files=(
+        "/usr/local/bin/argus-agent"
+    )
+    
+    local deleted=false
+    for binary_file in "${binary_files[@]}"; do
+        if [[ -f "$binary_file" ]]; then
+            rm -f "$binary_file"
+            log_success "二进制文件已删除: $binary_file"
+            deleted=true
+        fi
+    done
+    
+    if [[ "$deleted" == "false" ]]; then
+        log_info "二进制文件不存在"
+    fi
+}
+
+# 删除配置文件
+remove_config() {
+    log_info "删除配置文件..."
+    
+    local config_dir="/etc/argus-agent"
+    
+    if [[ -d "$config_dir" ]]; then
+        rm -rf "$config_dir"
+        log_success "配置目录已删除"
+    else
+        log_info "配置目录不存在"
+    fi
+}
+
+# 删除数据目录
+remove_data_dir() {
+    log_info "删除数据目录..."
+    
+    local data_dir="/var/lib/argus-agent"
+    
+    if [[ -d "$data_dir" ]]; then
+        rm -rf "$data_dir"
+        log_success "数据目录已删除"
+    else
+        log_info "数据目录不存在"
+    fi
+}
+
+# 检查用户状态（可选）
+check_user_status() {
+    log_info "检查 argus-agent 用户状态..."
+    
+    if id "argus-agent" &>/dev/null; then
+        log_info "检测到 argus-agent 用户存在"
+        log_warning "argus-agent 是系统用户，可能被其他服务使用"
+        log_info "为了系统稳定性，将保留 argus-agent 用户"
+        log_info "如需手动删除，请运行: sudo userdel argus-agent"
+    else
+        log_info "argus-agent 用户不存在"
+    fi
+}
+
+# 清理日志文件
+cleanup_logs() {
+    log_info "清理日志文件..."
+    
+    # 删除安装脚本创建的日志文件
+    rm -f /var/log/argus-agent.log
+    
+    log_success "日志文件已清理"
+}
+
+# 清理安装记录
+cleanup_install_record() {
+    log_info "清理安装记录..."
+    
+    local install_record="/opt/argus-metric/current/.install_record"
+    
+    if [[ -f "$install_record" ]]; then
+        if command -v jq &> /dev/null; then
+            # 使用 jq 删除 argus-agent 记录
+            jq 'del(.components."argus-agent")' "$install_record" > "$install_record.tmp" && mv "$install_record.tmp" "$install_record"
+            log_success "安装记录已更新"
+        else
+            log_warning "jq 命令不可用，无法清理安装记录"
+        fi
+    else
+        log_info "安装记录文件不存在"
+    fi
+}
+
+# 显示卸载信息
+show_uninstall_info() {
+    log_success "Argus Agent 卸载完成！"
+    echo
+    echo "已删除的内容:"
+    echo "  - 二进制文件: /usr/local/bin/argus-agent"
+    echo "  - 配置目录: /etc/argus-agent"
+    echo "  - 数据目录: /var/lib/argus-agent"
+    echo "  - 相关日志文件"
+    echo
+    echo "注意:"
+    echo "  - argus-agent 用户已保留（系统用户，可能被其他服务使用）"
+    echo "  - 如需完全清理，请手动检查并删除相关文件"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus Agent 卸载脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    
+    log_warning "此操作将完全卸载 Argus Agent"
+    read -p "确认继续？(y/N): " confirm
+    
+    if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+        log_info "取消卸载操作"
+        exit 0
+    fi
+    
+    log_info "开始卸载 Argus Agent..."
+    
+    stop_processes
+    remove_binary
+    remove_config
+    remove_data_dir
+    cleanup_logs
+    cleanup_install_record
+    
+    # 检查用户状态
+    check_user_status
+    
+    show_uninstall_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/check_health.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+
+# DCGM Exporter 健康检查脚本
+# 输出 JSON 格式结果
+
+set -e
+
+# 检查 DCGM Exporter 健康状态
+check_health() {
+    local url="http://localhost:9400"
+    local metrics_url="$url/metrics"
+    local name="dcgm-exporter"
+    local status="unhealth"
+    local reason=""
+    
+    # 检查 curl 是否可用
+    if ! command -v curl &> /dev/null; then
+        reason="curl 命令不可用，无法进行健康检查"
+        echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+        exit 1
+    fi
+    
+    # 测试根路径连接
+    local http_code=$(curl -s -o /dev/null -w "%{http_code}" "$url" 2>/dev/null || echo "000")
+    
+    if [[ "$http_code" == "200" ]]; then
+        # 测试 metrics 端点
+        local metrics_code=$(curl -s -o /dev/null -w "%{http_code}" "$metrics_url" 2>/dev/null || echo "000")
+        
+        if [[ "$metrics_code" == "200" ]]; then
+            status="health"
+            reason="success"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 0
+        else
+            reason="Metrics 端点异常 (HTTP $metrics_code)"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    else
+        reason="HTTP 服务异常 (HTTP $http_code)，请检查 DCGM Exporter 是否正在运行在端口 9400"
+        echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    check_health
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/config/default-counters.csv

@@ -0,0 +1,77 @@
+# Format
+# If line starts with a '#' it is considered a comment
+# DCGM FIELD, Prometheus metric type, help message
+
+# Clocks
+DCGM_FI_DEV_SM_CLOCK,  gauge, SM clock frequency (in MHz).
+DCGM_FI_DEV_MEM_CLOCK, gauge, Memory clock frequency (in MHz).
+# DCGM_EXP_CLOCK_EVENTS_COUNT, gauge, Count of clock events within the user-specified time window (see clock-events-count-window-size param).
+
+# Temperature
+DCGM_FI_DEV_MEMORY_TEMP, gauge, Memory temperature (in C).
+DCGM_FI_DEV_GPU_TEMP,    gauge, GPU temperature (in C).
+
+# Power
+DCGM_FI_DEV_POWER_USAGE,              gauge, Power draw (in W).
+DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION, counter, Total energy consumption since boot (in mJ).
+
+# PCIE
+DCGM_FI_PROF_PCIE_TX_BYTES,  counter, Total number of bytes transmitted through PCIe TX via NVML.
+DCGM_FI_PROF_PCIE_RX_BYTES,  counter, Total number of bytes received through PCIe RX via NVML.
+DCGM_FI_DEV_PCIE_REPLAY_COUNTER, counter, Total number of PCIe retries.
+
+# Utilization (the sample period varies depending on the product)
+DCGM_FI_DEV_GPU_UTIL,      gauge, GPU utilization (in %).
+DCGM_FI_DEV_MEM_COPY_UTIL, gauge, Memory utilization (in %).
+DCGM_FI_DEV_ENC_UTIL,      gauge, Encoder utilization (in %).
+DCGM_FI_DEV_DEC_UTIL ,     gauge, Decoder utilization (in %).
+
+# Errors and violations
+DCGM_FI_DEV_XID_ERRORS,              gauge,   Value of the last XID error encountered.
+# DCGM_FI_DEV_POWER_VIOLATION,       counter, Throttling duration due to power constraints (in us).
+# DCGM_FI_DEV_THERMAL_VIOLATION,     counter, Throttling duration due to thermal constraints (in us).
+# DCGM_FI_DEV_SYNC_BOOST_VIOLATION,  counter, Throttling duration due to sync-boost constraints (in us).
+# DCGM_FI_DEV_BOARD_LIMIT_VIOLATION, counter, Throttling duration due to board limit constraints (in us).
+# DCGM_FI_DEV_LOW_UTIL_VIOLATION,    counter, Throttling duration due to low utilization (in us).
+# DCGM_FI_DEV_RELIABILITY_VIOLATION, counter, Throttling duration due to reliability constraints (in us).
+# DCGM_EXP_XID_ERRORS_COUNT,         gauge,   Count of XID Errors within user-specified time window (see xid-count-window-size param).
+# Memory usage
+DCGM_FI_DEV_FB_FREE, gauge, Frame buffer memory free (in MB).
+DCGM_FI_DEV_FB_USED, gauge, Frame buffer memory used (in MB).
+
+# ECC
+# DCGM_FI_DEV_ECC_SBE_VOL_TOTAL, counter, Total number of single-bit volatile ECC errors.
+# DCGM_FI_DEV_ECC_DBE_VOL_TOTAL, counter, Total number of double-bit volatile ECC errors.
+# DCGM_FI_DEV_ECC_SBE_AGG_TOTAL, counter, Total number of single-bit persistent ECC errors.
+# DCGM_FI_DEV_ECC_DBE_AGG_TOTAL, counter, Total number of double-bit persistent ECC errors.
+
+# Retired pages
+# DCGM_FI_DEV_RETIRED_SBE,     counter, Total number of retired pages due to single-bit errors.
+# DCGM_FI_DEV_RETIRED_DBE,     counter, Total number of retired pages due to double-bit errors.
+# DCGM_FI_DEV_RETIRED_PENDING, counter, Total number of pages pending retirement.
+
+# NVLink
+# DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL, counter, Total number of NVLink flow-control CRC errors.
+# DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL, counter, Total number of NVLink data CRC errors.
+# DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL,   counter, Total number of NVLink retries.
+# DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL, counter, Total number of NVLink recovery errors.
+DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL,            counter, Total number of NVLink bandwidth counters for all lanes
+
+# VGPU License status
+DCGM_FI_DEV_VGPU_LICENSE_STATUS, gauge, vGPU License status
+
+# Remapped rows
+DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for uncorrectable errors
+DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS,   counter, Number of remapped rows for correctable errors
+DCGM_FI_DEV_ROW_REMAP_FAILURE,           gauge,   Whether remapping of rows has failed
+
+# Static configuration information. These appear as labels on the other metrics
+DCGM_FI_DRIVER_VERSION,        label, Driver Version
+# DCGM_FI_NVML_VERSION,          label, NVML Version
+# DCGM_FI_DEV_BRAND,             label, Device Brand
+# DCGM_FI_DEV_SERIAL,            label, Device Serial Number
+# DCGM_FI_DEV_OEM_INFOROM_VER,   label, OEM inforom version
+# DCGM_FI_DEV_ECC_INFOROM_VER,   label, ECC inforom version
+# DCGM_FI_DEV_POWER_INFOROM_VER, label, Power management object inforom version
+# DCGM_FI_DEV_INFOROM_IMAGE_VER, label, Inforom image version
+# DCGM_FI_DEV_VBIOS_VERSION,     label, VBIOS version of the device

src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/install.sh

@@ -0,0 +1,365 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 更新安装记录
+update_install_record() {
+    local pid="$1"
+    # 使用传入的安装目录参数，如果没有则使用默认值
+    local install_base_dir="${2:-/opt/argus-metric/current}"
+    local install_record="$install_base_dir/.install_record"
+    
+    # 如果安装记录文件不存在，说明是首次安装，由主安装脚本统一创建
+    if [[ ! -f "$install_record" ]]; then
+        log_info "安装记录文件不存在，将由主安装脚本创建"
+        return 0
+    fi
+    
+    # 如果文件存在，说明是重启场景，只更新 PID 字段
+    if command -v jq &> /dev/null; then
+        # 读取当前 PID
+        local current_pid=$(jq -r '.components."dcgm-exporter".pid // ""' "$install_record" 2>/dev/null)
+        
+        if [[ -z "$current_pid" ]]; then
+            log_warning "无法读取当前 PID，跳过更新"
+            return 1
+        fi
+        
+        # 使用 jq 只更新 pid 字段，保持字符串类型，保留其他字段
+        jq --arg new_pid "$pid" '.components."dcgm-exporter".pid = $new_pid' "$install_record" > "$install_record.tmp" && mv "$install_record.tmp" "$install_record"
+        log_info "PID 已更新: $current_pid -> $pid"
+    else
+        log_warning "jq 命令不可用，无法更新安装记录文件"
+    fi
+}
+
+# 显示帮助信息
+show_help() {
+    echo "DCGM Exporter 安装脚本"
+    echo
+    echo "用法: $0 [选项]"
+    echo
+    echo "选项:"
+    echo "  --help     显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0          # 安装 DCGM Exporter"
+    echo
+}
+
+# 解析命令行参数
+INSTALL_DIR=""
+for arg in "$@"; do
+    case $arg in
+        --help|-h)
+            show_help
+            exit 0
+            ;;
+        *)
+            # 如果参数不是以--开头，则认为是安装目录
+            if [[ ! "$arg" =~ ^-- ]]; then
+                INSTALL_DIR="$arg"
+            else
+                log_error "未知参数: $arg"
+                show_help
+                exit 1
+            fi
+            ;;
+    esac
+done
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    source /etc/os-release
+    log_info "检测到操作系统: $NAME $VERSION"
+    
+    # 检查是否为 Ubuntu/Debian
+    if [[ "$ID" != "ubuntu" && "$ID" != "debian" ]]; then
+        log_warning "此脚本主要针对 Ubuntu/Debian 系统，其他系统可能需要调整"
+    fi
+    
+    # 检查 NVIDIA GPU
+    if ! command -v nvidia-smi &> /dev/null; then
+        log_warning "未检测到 nvidia-smi，请确保已安装 NVIDIA 驱动"
+    else
+        log_success "检测到 NVIDIA GPU"
+        nvidia-smi --query-gpu=name --format=csv,noheader,nounits | head -1
+    fi
+}
+
+# 安装 DCGM 依赖
+install_dcgm_dependency() {
+    log_info "安装 DCGM 依赖..."
+    
+    local deb_file="bin/datacenter-gpu-manager_3.3.9_amd64.deb"
+    
+    if [[ ! -f "$deb_file" ]]; then
+        log_error "找不到 DCGM 依赖文件: $deb_file"
+        exit 1
+    fi
+    
+    # 安装 deb 包
+    dpkg -i "$deb_file" || {
+        log_warning "dpkg 安装失败，尝试使用 apt 修复依赖..."
+        apt-get update
+        apt-get install -f -y
+        dpkg -i "$deb_file"
+    }
+    
+    log_success "DCGM 依赖安装完成"
+}
+
+# 检查 DCGM 服务状态
+check_dcgm_service() {
+    log_info "检查 DCGM 服务状态..."
+    
+    # 检查 DCGM 服务是否在运行
+    if systemctl is-active --quiet dcgm 2>/dev/null; then
+        log_success "DCGM 服务已在运行"
+    elif pgrep -f nv-hostengine > /dev/null; then
+        log_success "nv-hostengine 进程已在运行"
+    else
+        log_warning "DCGM 服务未运行，需要手动启动"
+        log_info "启动 DCGM 服务的方法:"
+        log_info "  1. 使用 systemd: sudo systemctl start dcgm"
+        log_info "  2. 手动启动: nohup nv-hostengine > /var/log/nv-hostengine.log 2>&1 &"
+    fi
+    
+    # 测试 DCGM 连接
+    if systemctl is-active --quiet dcgm 2>/dev/null || pgrep -f nv-hostengine > /dev/null; then
+        log_info "测试 DCGM 连接..."
+        if dcgmi discovery -l > /dev/null 2>&1; then
+            log_success "DCGM 连接测试成功"
+        else
+            log_warning "DCGM 连接测试失败，请检查服务状态"
+        fi
+    fi
+}
+
+# 停止可能运行的服务
+stop_existing_service() {
+    log_info "检查并停止可能运行的服务..."
+    
+    local pid_file="/var/run/dcgm-exporter.pid"
+    
+    # 检查并停止通过 PID 文件管理的服务
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "发现正在运行的 DCGM Exporter 服务 (PID: $pid)，正在停止..."
+            kill "$pid" > /dev/null 2>&1 || true
+            sleep 2
+            if kill -0 "$pid" 2>/dev/null; then
+                log_warning "进程未响应，强制终止..."
+                kill -9 "$pid" > /dev/null 2>&1 || true
+            fi
+            rm -f "$pid_file"
+            log_success "服务已停止"
+        else
+            log_warning "发现过期的 PID 文件，正在清理..."
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 查找并停止所有 dcgm-exporter 进程（排除脚本自身）
+    local exporter_bin="/usr/local/bin/dcgm-exporter"
+    local pids=$(pgrep -f "$exporter_bin")
+
+    if [[ -n "$pids" ]]; then
+        log_info "发现其他 dcgm-exporter 进程，正在停止..."
+        for pid in $pids; do
+            if [[ "$pid" != "$$" ]]; then
+                kill "$pid" > /dev/null 2>&1 || true
+                sleep 1
+                if kill -0 "$pid" 2>/dev/null; then
+                    log_warning "进程 $pid 未响应，强制终止..."
+                    kill -9 "$pid" > /dev/null 2>&1 || true
+                fi
+            fi
+        done
+        log_success "所有 dcgm-exporter 进程已停止"
+    fi
+}
+
+# 安装 DCGM Exporter 二进制文件
+install_dcgm_exporter() {
+    log_info "安装 DCGM Exporter..."
+    
+    local binary_file="bin/dcgm-exporter"
+    local install_dir="/usr/local/bin"
+    
+    if [[ ! -f "$binary_file" ]]; then
+        log_error "找不到 DCGM Exporter 二进制文件: $binary_file"
+        exit 1
+    fi
+    
+    # 停止可能运行的服务
+    stop_existing_service
+    
+    # 复制二进制文件
+    cp "$binary_file" "$install_dir/"
+    chmod +x "$install_dir/dcgm-exporter"
+    
+    log_success "DCGM Exporter 二进制文件安装完成"
+}
+
+# 安装配置文件
+install_config() {
+    log_info "安装配置文件..."
+    
+    local config_dir="/etc/dcgm-exporter"
+    local config_file="config/default-counters.csv"
+    
+    # 创建配置目录
+    mkdir -p "$config_dir"
+    
+    if [[ -f "$config_file" ]]; then
+        cp "$config_file" "$config_dir/"
+        log_success "配置文件安装完成"
+    else
+        log_warning "未找到配置文件，使用默认配置"
+    fi
+}
+
+# 启动 DCGM Exporter 服务
+start_dcgm_exporter() {
+    log_info "启动 DCGM Exporter 服务..."
+    
+    local binary_path="/usr/local/bin/dcgm-exporter"
+    local log_file="/var/log/dcgm-exporter.log"
+    local pid_file="/var/run/dcgm-exporter.pid"
+    
+    # 检查服务是否已经在运行
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "DCGM Exporter 服务已在运行 (PID: $pid)"
+            return 0
+        else
+            log_warning "发现过期的 PID 文件，正在清理..."
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 检查端口是否被占用
+    if netstat -tuln 2>/dev/null | grep -q ":9400 "; then
+        log_warning "端口 9400 已被占用，请检查是否有其他服务在运行"
+        return 1
+    fi
+    
+    # 启动服务
+    log_info "正在启动 DCGM Exporter..."
+    nohup "$binary_path" --address=:9400 > "$log_file" 2>&1 &
+    local pid=$!
+    
+    # 保存 PID
+    echo "$pid" > "$pid_file"
+    
+    # 等待服务启动
+    sleep 2
+    
+    # 检查服务是否成功启动
+    if kill -0 "$pid" 2>/dev/null; then
+        log_success "DCGM Exporter 服务启动成功 (PID: $pid)"
+        log_info "日志文件: $log_file"
+        log_info "PID 文件: $pid_file"
+        
+        # 更新安装记录
+        update_install_record "$pid" "$INSTALL_DIR"
+    else
+        log_error "DCGM Exporter 服务启动失败"
+        rm -f "$pid_file"
+        return 1
+    fi
+}
+
+
+
+# 显示安装信息
+show_install_info() {
+    log_success "DCGM Exporter 安装完成！"
+    echo
+    echo "安装信息:"
+    echo "  二进制文件: /usr/local/bin/dcgm-exporter"
+    echo "  配置文件: /etc/dcgm-exporter/default-counters.csv"
+    echo "  默认端口: 9400"
+    echo
+    echo "使用方法:"
+    echo "  1. 启动 DCGM 服务:"
+    echo "     sudo systemctl start dcgm"
+    echo "     或: nohup nv-hostengine > /var/log/nv-hostengine.log 2>&1 &"
+    echo "  2. 启动 DCGM Exporter:"
+    echo "     /usr/local/bin/dcgm-exporter --address=:9400"
+    echo "     或: nohup /usr/local/bin/dcgm-exporter --address=:9400 &"
+    echo
+    echo "测试连接:"
+    echo "  curl http://localhost:9400/metrics"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    DCGM Exporter 安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    check_system
+    
+    log_info "开始安装 DCGM Exporter..."
+    
+    install_dcgm_dependency
+    check_dcgm_service
+    install_dcgm_exporter
+    install_config
+    start_dcgm_exporter
+    
+    show_install_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/package.sh

@@ -0,0 +1,88 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+# 获取当前目录
+CURRENT_DIR=$(pwd)
+PACKAGE_NAME="dcgm-exporter-$(date +%Y%m%d-%H%M%S)"
+PACKAGE_FILE="${PACKAGE_NAME}.tar.gz"
+
+log_info "开始打包 DCGM Exporter 安装包..."
+
+# 检查必要文件
+log_info "检查必要文件..."
+
+required_files=(
+    "install.sh"
+    "uninstall.sh"
+    "bin/dcgm-exporter"
+    "bin/datacenter-gpu-manager_3.3.9_amd64.deb"
+    "check_health.sh"
+)
+
+missing_files=()
+for file in "${required_files[@]}"; do
+    if [[ ! -f "$file" ]]; then
+        missing_files+=("$file")
+    fi
+done
+
+if [[ ${#missing_files[@]} -gt 0 ]]; then
+    echo "缺少以下文件:"
+    for file in "${missing_files[@]}"; do
+        echo "  - $file"
+    done
+    exit 1
+fi
+
+log_success "所有必要文件检查完成"
+
+# 创建临时目录
+TEMP_DIR=$(mktemp -d)
+log_info "创建临时目录: $TEMP_DIR"
+
+# 复制文件到临时目录
+cp -r . "$TEMP_DIR/$PACKAGE_NAME"
+
+# 进入临时目录
+cd "$TEMP_DIR"
+
+# 创建压缩包
+log_info "创建压缩包: $PACKAGE_FILE"
+tar -czf "$PACKAGE_FILE" "$PACKAGE_NAME"
+
+# 移动压缩包到原目录
+mv "$PACKAGE_FILE" "$CURRENT_DIR/"
+
+# 清理临时目录
+rm -rf "$TEMP_DIR"
+
+# 返回原目录
+cd "$CURRENT_DIR"
+
+# 显示结果
+log_success "打包完成！"
+echo
+echo "安装包文件: $PACKAGE_FILE"
+echo "文件大小: $(du -h "$PACKAGE_FILE" | cut -f1)"
+echo
+echo "使用方法:"
+echo "1. 将 $PACKAGE_FILE 传输到目标服务器"
+echo "2. 解压: tar -xzf $PACKAGE_FILE"
+echo "3. 进入目录: cd $PACKAGE_NAME"
+echo "4. 运行安装: sudo ./install.sh"
+echo
+echo "注意: 请确保 config/default-counters.csv 文件存在"

src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/uninstall.sh

@@ -0,0 +1,216 @@
+#!/bin/bash
+
+# DCGM Exporter 卸载脚本
+# 版本: 1.0
+# 作者: AIOps Team
+# 日期: $(date +%Y-%m-%d)
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 停止运行中的进程
+stop_processes() {
+    log_info "停止 DCGM Exporter 进程..."
+    
+    local pid_file="/var/run/dcgm-exporter.pid"
+    local stopped=false
+    
+    # 首先尝试通过 PID 文件停止服务
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "通过 PID 文件停止服务 (PID: $pid)..."
+            kill "$pid"
+            sleep 3
+            
+            # 检查进程是否已停止
+            if kill -0 "$pid" 2>/dev/null; then
+                log_warning "进程未响应，强制终止..."
+                kill -9 "$pid" 2>/dev/null || true
+            fi
+            log_success "DCGM Exporter 进程已停止"
+            stopped=true
+        else
+            log_warning "PID 文件存在但进程已不存在，清理 PID 文件"
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 查找并杀死所有 dcgm-exporter 进程
+    local pids=$(pgrep -f "dcgm-exporter" 2>/dev/null || true)
+    if [[ -n "$pids" ]]; then
+        log_info "发现 dcgm-exporter 进程，正在停止..."
+        for pid in $pids; do
+            log_info "停止进程 PID: $pid"
+            kill "$pid" 2>/dev/null || true
+        done
+        sleep 2
+        
+        # 检查是否还有进程在运行，如果有则强制终止
+        local remaining_pids=$(pgrep -f "dcgm-exporter" 2>/dev/null || true)
+        if [[ -n "$remaining_pids" ]]; then
+            log_warning "进程未响应，强制终止..."
+            for pid in $remaining_pids; do
+                log_info "强制终止进程 PID: $pid"
+                kill -9 "$pid" 2>/dev/null || true
+            done
+            sleep 1
+        fi
+        
+        # 最终检查
+        if pgrep -f "dcgm-exporter" > /dev/null; then
+            log_error "无法停止所有 dcgm-exporter 进程"
+        else
+            log_success "所有 DCGM Exporter 进程已停止"
+            stopped=true
+        fi
+    else
+        log_info "DCGM Exporter 进程未运行"
+    fi
+    
+    # 清理 PID 文件
+    rm -f "$pid_file"
+    
+    if [[ "$stopped" == "false" ]]; then
+        log_warning "未发现需要停止的 DCGM Exporter 进程"
+    fi
+}
+
+# 删除二进制文件
+remove_binary() {
+    log_info "删除 DCGM Exporter 二进制文件..."
+    
+    local binary_file="/usr/local/bin/dcgm-exporter"
+    
+    if [[ -f "$binary_file" ]]; then
+        rm -f "$binary_file"
+        log_success "二进制文件已删除"
+    else
+        log_info "二进制文件不存在"
+    fi
+}
+
+# 删除配置文件
+remove_config() {
+    log_info "删除配置文件..."
+    
+    local config_dir="/etc/dcgm-exporter"
+    
+    if [[ -d "$config_dir" ]]; then
+        rm -rf "$config_dir"
+        log_success "配置目录已删除"
+    else
+        log_info "配置目录不存在"
+    fi
+}
+
+# 卸载 DCGM 依赖（可选）
+remove_dcgm_dependency() {
+    log_info "检查 DCGM 依赖状态..."
+    
+    # 检查是否安装了 DCGM 包
+    if dpkg -l | grep -q datacenter-gpu-manager; then
+        log_info "检测到 DCGM 依赖包已安装"
+        log_warning "DCGM 是系统级依赖，可能被其他应用程序使用"
+        log_info "为了系统稳定性，将保留 DCGM 依赖包"
+        log_info "如需手动卸载，请运行: sudo apt-get remove --purge datacenter-gpu-manager"
+    else
+        log_info "DCGM 依赖包未安装"
+    fi
+}
+
+# 清理日志文件
+cleanup_logs() {
+    log_info "清理日志文件..."
+    
+    # 清理 journal 日志
+    journalctl --vacuum-time=1s --quiet || true
+    
+    # 删除可能的日志文件
+    rm -f /var/log/nv-hostengine.log
+    rm -f /var/log/dcgm-exporter.log
+    
+    log_success "日志文件已清理"
+}
+
+# 显示卸载信息
+show_uninstall_info() {
+    log_success "DCGM Exporter 卸载完成！"
+    echo
+    echo "已删除的内容:"
+    echo "  - 二进制文件: /usr/local/bin/dcgm-exporter"
+    echo "  - 配置目录: /etc/dcgm-exporter"
+    echo "  - 相关日志文件"
+    echo
+    echo "注意:"
+    echo "  - DCGM 依赖包可能仍然存在"
+    echo "  - 如需完全清理，请手动检查并删除相关文件"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    DCGM Exporter 卸载脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    
+    log_warning "此操作将完全卸载 DCGM Exporter"
+    read -p "确认继续？(y/N): " confirm
+    
+    if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+        log_info "取消卸载操作"
+        exit 0
+    fi
+    
+    log_info "开始卸载 DCGM Exporter..."
+    
+    stop_processes
+    remove_binary
+    remove_config
+    cleanup_logs
+    
+    # 询问是否卸载 DCGM 依赖
+    remove_dcgm_dependency
+    
+    show_uninstall_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/README.md

@@ -0,0 +1,181 @@
+# Fluent Bit 安装包
+
+这是一个 Fluent Bit 的自动化安装包，提供了完整的安装、卸载和健康检查功能。
+
+## 目录结构
+
+```
+fluent-bit-installer/
+├── install.sh                    # 安装脚本
+├── uninstall.sh                  # 卸载脚本
+├── package.sh                    # 打包脚本
+├── check_health.sh               # 健康检查脚本
+├── bin/
+│   └── fluent-bit_3.1.9_amd64.deb  # Fluent Bit 安装包
+└── config/
+    ├── fluent-bit.conf           # 主配置文件
+    ├── inject_labels.lua         # Lua 脚本
+    ├── parsers.conf              # 解析器配置
+    ├── inputs.d/                 # 输入配置目录
+    │   ├── 10-train.conf
+    │   └── 20-infer.conf
+    └── outputs.d/                # 输出配置目录
+        └── 10-es.conf
+```
+
+## 功能特性
+
+- **自动化安装**: 一键安装 Fluent Bit 及其依赖
+- **配置管理**: 自动部署预配置的配置文件
+- **服务管理**: 自动启动和停止 Fluent Bit 服务
+- **健康检查**: 提供 JSON 格式的健康状态检查
+- **完整卸载**: 彻底清理所有相关文件和配置
+- **用户管理**: 自动创建专用的 fluent-bit 用户
+
+## 使用方法
+
+### 1. 打包安装包
+
+```bash
+./package.sh
+```
+
+这将创建一个带时间戳的压缩包，例如：`fluent-bit-installer-20250924-160954.tar.gz`
+
+### 2. 安装 Fluent Bit
+
+```bash
+# 解压安装包
+tar -xzf fluent-bit-installer-*.tar.gz
+cd fluent-bit-installer-*
+
+# 运行安装脚本（需要 root 权限）
+sudo ./install.sh
+```
+
+### 3. 健康检查
+
+```bash
+./check_health.sh
+```
+
+输出示例：
+```json
+{"name": "fluent-bit", "status": "health", "reason": "success"}
+```
+
+### 4. 卸载 Fluent Bit
+
+```bash
+sudo ./uninstall.sh
+```
+
+## 安装后的文件位置
+
+- **二进制文件**: `/opt/fluent-bit/bin/fluent-bit`
+- **配置文件**: `/etc/fluent-bit/`
+- **日志文件**: `/var/log/fluent-bit/`
+- **缓冲区目录**: `/var/lib/fluent-bit/buffers/`
+- **运行用户**: `fluent-bit`
+- **HTTP 端口**: `2020`
+
+## 配置说明
+
+### 主配置文件
+
+主配置文件位于 `/etc/fluent-bit/fluent-bit.conf`，包含以下主要部分：
+
+- **SERVICE**: 服务配置，包括 HTTP 服务器设置
+- **INPUT**: 输入配置，通过 `inputs.d/` 目录管理
+- **FILTER**: 过滤器配置，包括解析器和标签注入
+- **OUTPUT**: 输出配置，通过 `outputs.d/` 目录管理
+
+### 输入配置
+
+- `10-train.conf`: 训练日志输入配置
+- `20-infer.conf`: 推理日志输入配置
+
+### 输出配置
+
+- `10-es.conf`: Elasticsearch 输出配置
+
+## 服务管理
+
+### 手动启动
+
+```bash
+/opt/fluent-bit/bin/fluent-bit --config=/etc/fluent-bit/fluent-bit.conf
+```
+
+### 后台启动
+
+```bash
+nohup /opt/fluent-bit/bin/fluent-bit --config=/etc/fluent-bit/fluent-bit.conf &
+```
+
+### 检查服务状态
+
+```bash
+# 检查进程
+ps aux | grep fluent-bit
+
+# 检查端口
+netstat -tuln | grep 2020
+
+# 检查日志
+tail -f /var/log/fluent-bit/fluent-bit.log
+```
+
+## API 接口
+
+Fluent Bit 提供 HTTP API 用于监控和管理：
+
+- **根路径**: `http://localhost:2020`
+- **状态接口**: `http://localhost:2020/api/v1/status`
+- **指标接口**: `http://localhost:2020/api/v1/metrics`
+
+## 故障排除
+
+### 常见问题
+
+1. **端口被占用**
+   - 检查端口 2020 是否被其他服务占用
+   - 修改配置文件中的端口设置
+
+2. **权限问题**
+   - 确保 fluent-bit 用户有足够的权限访问日志文件
+   - 检查目录权限设置
+
+3. **配置文件错误**
+   - 检查配置文件语法
+   - 查看日志文件中的错误信息
+
+### 日志查看
+
+```bash
+# 查看服务日志
+tail -f /var/log/fluent-bit/fluent-bit.log
+
+# 查看系统日志
+journalctl -u fluent-bit -f
+```
+
+## 系统要求
+
+- **操作系统**: Ubuntu/Debian/CentOS/RHEL/Fedora
+- **架构**: x86_64/amd64
+- **权限**: root 权限（用于安装和卸载）
+- **依赖**: curl（用于健康检查）
+
+## 版本信息
+
+- **Fluent Bit 版本**: 3.1.9
+- **安装包版本**: 1.0
+- **支持架构**: amd64
+
+## 注意事项
+
+1. 安装前请确保系统已更新
+2. 卸载时会保留 fluent-bit 用户（系统用户，可能被其他服务使用）
+3. 配置文件包含环境变量，请根据实际环境调整
+4. 建议在生产环境使用前进行充分测试

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/check_health.sh

@@ -0,0 +1,69 @@
+#!/bin/bash
+
+# Fluent Bit 健康检查脚本
+# 输出 JSON 格式结果
+
+set -e
+
+# 检查 Fluent Bit 健康状态
+check_health() {
+    local name="fluent-bit"
+    local status="unhealth"
+    local reason=""
+    local install_record="/opt/argus-metric/current/.install_record"
+    
+    # 首先尝试通过安装记录文件检查进程
+    if [[ -f "$install_record" ]]; then
+        # 尝试使用jq解析JSON格式的安装记录文件
+        local pid=""
+        if command -v jq &> /dev/null; then
+            pid=$(jq -r '.components."fluent-bit".pid // empty' "$install_record" 2>/dev/null || echo "")
+        else
+            # 如果没有jq，使用简单的文本解析方法
+            pid=$(grep -A 10 '"fluent-bit"' "$install_record" | grep '"pid"' | cut -d'"' -f4 | head -1)
+        fi
+        
+        if [[ -n "$pid" && "$pid" =~ ^[0-9]+$ ]]; then
+            if kill -0 "$pid" 2>/dev/null; then
+                # 进程存在且运行正常
+                status="health"
+                reason="进程运行正常 (PID: $pid)"
+                echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+                exit 0
+            else
+                reason="安装记录中的 PID $pid 进程不存在"
+                echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+                exit 1
+            fi
+        else
+            reason="安装记录文件中未找到有效的 fluent-bit PID"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    else
+        # 如果安装记录文件不存在，尝试查找 fluent-bit 进程
+        local pids=$(pgrep -f "fluent-bit" 2>/dev/null || true)
+        if [[ -n "$pids" ]]; then
+            # 取第一个找到的 PID
+            local pid=$(echo "$pids" | head -1)
+            status="health"
+            reason="发现 fluent-bit 进程运行 (PID: $pid)，但未找到安装记录"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 0
+        else
+            reason="未找到 fluent-bit 进程，且安装记录文件不存在"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    fi
+}
+
+# 主函数
+main() {
+    check_health
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/config/fluent-bit.conf

@@ -0,0 +1,37 @@
+[SERVICE]
+    Daemon       Off
+    Parsers_File parsers.conf
+    HTTP_Server  On
+    HTTP_Listen  0.0.0.0
+    HTTP_Port    2020
+    storage.path /buffers
+    storage.sync normal
+    storage.checksum on
+    storage.backlog.mem_limit 128M
+    # 备注：该镜像默认未开启 Hot Reload，修改配置后请重启容器。
+
+@INCLUDE inputs.d/*.conf
+
+[FILTER]
+    Name   parser
+    Match  app.*
+    Key_Name log
+    Parser timestamp_parser
+    Reserve_Data On
+    Preserve_Key On
+    Unescape_Key On
+
+[FILTER]
+    Name   record_modifier
+    Match  *
+    Record cluster  ${CLUSTER}
+    Record rack     ${RACK}
+    Record host     ${HOSTNAME}
+
+[FILTER]
+    Name   lua
+    Match  app.*
+    script inject_labels.lua
+    call   add_labels
+
+@INCLUDE outputs.d/*.conf

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/config/inject_labels.lua

@@ -0,0 +1,15 @@
+function add_labels(tag, ts, record)
+  record["job_id"] = os.getenv("FB_JOB_ID") or record["job_id"] or "unknown"
+  record["user"]   = os.getenv("FB_USER")   or record["user"]   or "unknown"
+  record["model"]  = os.getenv("FB_MODEL")  or record["model"]  or "unknown"
+  record["gpu_id"] = os.getenv("FB_GPU_ID") or record["gpu_id"] or "na"
+  local p = record["log_path"] or ""
+  if string.find(p, "/logs/infer/") then
+    record["role"] = "infer"
+  elseif string.find(p, "/logs/train/") then
+    record["role"] = "train"
+  else
+    record["role"] = record["role"] or "app"
+  end
+  return 1, ts, record
+end

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/config/inputs.d/10-train.conf

@@ -0,0 +1,10 @@
+[INPUT]
+    Name              tail
+    Path              /logs/train/*.log
+    Tag               app.train
+    Path_Key          log_path
+    Refresh_Interval  5
+    DB                /buffers/train.db
+    Skip_Long_Lines   On
+    storage.type      filesystem
+    multiline.parser  python,go,java

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/config/inputs.d/20-infer.conf

@@ -0,0 +1,10 @@
+[INPUT]
+    Name              tail
+    Path              /logs/infer/*.log
+    Tag               app.infer
+    Path_Key          log_path
+    Refresh_Interval  5
+    DB                /buffers/infer.db
+    Skip_Long_Lines   On
+    storage.type      filesystem
+    multiline.parser  python,go,java

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/config/outputs.d/10-es.conf

@@ -0,0 +1,24 @@
+# 重要：使用 Logstash_Format + Logstash_Prefix，生成 train-*/infer-* 索引
+[OUTPUT]
+    Name                es
+    Match               app.train
+    Host                ${ES_HOST:-localhost}
+    Port                ${ES_PORT:-9200}
+    Logstash_Format     On
+    Logstash_Prefix     train
+    Replace_Dots        On
+    Generate_ID         On
+    Retry_Limit         False
+    Suppress_Type_Name  On
+
+[OUTPUT]
+    Name                es
+    Match               app.infer
+    Host                ${ES_HOST:-localhost}
+    Port                ${ES_PORT:-9200}
+    Logstash_Format     On
+    Logstash_Prefix     infer
+    Replace_Dots        On
+    Generate_ID         On
+    Retry_Limit         False
+    Suppress_Type_Name  On

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/config/parsers.conf

@@ -0,0 +1,27 @@
+[MULTILINE_PARSER]
+    Name   python
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^\d{4}-\d{2}-\d{2}[\sT]/"  "cont"
+    Rule   "cont"         "/^\s+|^Traceback|^\tat\s+/" "cont"
+
+[MULTILINE_PARSER]
+    Name   go
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^[0-9]{4}\/[0-9]{2}\/[0-9]{2}/" "cont"
+    Rule   "cont"         "/^\s+|^\t/" "cont"
+
+[MULTILINE_PARSER]
+    Name   java
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}/" "cont"
+    Rule   "cont"         "/^\s+at\s+|^\t.../" "cont"
+
+[PARSER]
+    Name   timestamp_parser
+    Format regex
+    Regex  ^(?<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})\s+(?<level>\w+)\s+(?<message>.*)$
+    Time_Key    timestamp
+    Time_Format %Y-%m-%d %H:%M:%S

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/install.sh

@@ -0,0 +1,291 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+log_info "Starting Fluent Bit installation..."
+
+# 解析命令行参数
+INSTALL_DIR="${1:-/opt/argus-metric/current}"
+
+# 更新安装记录
+update_install_record() {
+    local pid="$1"
+    # 使用传入的安装目录参数，如果没有则使用默认值
+    local install_base_dir="${2:-/opt/argus-metric/current}"
+    local install_record="$install_base_dir/.install_record"
+    
+    # 如果安装记录文件不存在，说明是首次安装，由主安装脚本统一创建
+    if [[ ! -f "$install_record" ]]; then
+        log_info "安装记录文件不存在，将由主安装脚本创建"
+        return 0
+    fi
+    
+    # 如果文件存在，说明是重启场景，只更新 PID 字段
+    if command -v jq &> /dev/null; then
+        # 读取当前 PID
+        local current_pid=$(jq -r '.components."fluent-bit".pid // ""' "$install_record" 2>/dev/null)
+        
+        if [[ -z "$current_pid" ]]; then
+            log_warning "无法读取当前 PID，跳过更新"
+            return 1
+        fi
+        
+        # 使用 jq 只更新 pid 字段，保持字符串类型，保留其他字段
+        jq --arg new_pid "$pid" '.components."fluent-bit".pid = $new_pid' "$install_record" > "$install_record.tmp" && mv "$install_record.tmp" "$install_record"
+        log_info "PID updated: $current_pid -> $pid"
+    else
+        log_warning "jq 命令不可用，无法更新安装记录文件"
+    fi
+}
+
+# 检查是否为 root 用户
+if [[ $EUID -ne 0 ]]; then
+    log_error "This script requires root privileges"
+    log_info "Please use: sudo $0"
+    exit 1
+fi
+
+# 停止可能运行的服务
+log_info "Stopping existing fluent-bit processes..."
+
+# 只匹配进程名为 fluent-bit 的进程
+pids=$(pgrep -x fluent-bit 2>/dev/null || true)
+
+if [[ -n "$pids" ]]; then
+    for pid in $pids; do
+        log_info "Stopping process PID: $pid"
+        kill "$pid" 2>/dev/null || true
+    done
+    sleep 2
+
+    # 检查是否还有残留进程
+    remaining_pids=$(pgrep -x fluent-bit 2>/dev/null || true)
+    if [[ -n "$remaining_pids" ]]; then
+        log_warning "Force killing unresponsive processes..."
+        for pid in $remaining_pids; do
+            kill -9 "$pid" 2>/dev/null || true
+        done
+    fi
+fi
+
+# 安装 Fluent Bit 依赖库 libpq5（离线模式）
+log_info "Checking Fluent Bit dependency: libpq5 ..."
+if ! ldconfig -p | grep -q libpq.so.5; then
+    if ls bin/libpq5_*.deb >/dev/null 2>&1; then
+        log_info "Installing local dependency package: libpq5"
+        DEBIAN_FRONTEND=noninteractive dpkg -i bin/libpq5_*.deb >/dev/null 2>&1 || {
+            log_error "Failed to install libpq5 from bin/, please check package validity"
+            exit 1
+        }
+    else
+        log_error "Missing dependency: libpq5 (libpq.so.5). Please put bin/libpq5_*.deb in the bin/ directory."
+        exit 1
+    fi
+else
+    log_info "libpq.so.5 already present on system"
+fi
+
+# 安装 Fluent Bit 依赖库 libyaml-0-2（离线模式）
+log_info "Checking Fluent Bit dependency: libyaml-0.so.2 ..."
+if ! ldconfig -p | grep -q libyaml-0.so.2; then
+    if ls bin/libyaml-0-2_*.deb >/dev/null 2>&1; then
+        log_info "Installing local dependency package: libyaml-0-2"
+        DEBIAN_FRONTEND=noninteractive dpkg -i bin/libyaml-0-2_*.deb >/dev/null 2>&1 || {
+            log_error "Failed to install libyaml-0-2 from bin/, please check package validity"
+            exit 1
+        }
+    else
+        log_error "Missing dependency: libyaml-0-2 (libyaml-0.so.2). Please put bin/libyaml-0-2_*.deb in the bin/ directory."
+        exit 1
+    fi
+else
+    log_info "libyaml-0.so.2 already present on system"
+fi
+
+# 清理可能存在的旧 fluent-bit 安装（避免配置文件冲突）
+log_info "Cleaning up old fluent-bit installation if exists..."
+if dpkg -l | grep -q "^ii.*fluent-bit"; then
+    log_info "Found existing fluent-bit package, removing..."
+    dpkg --purge fluent-bit 2>/dev/null || true
+    apt-get remove --purge -y fluent-bit 2>/dev/null || true
+fi
+
+# 确保清理残留的配置文件
+if [[ -d "/etc/fluent-bit" ]]; then
+    log_info "Removing old fluent-bit configuration directory..."
+    rm -rf /etc/fluent-bit
+fi
+
+# 安装 Fluent Bit 主包
+log_info "Installing Fluent Bit from deb package..."
+deb_file="bin/fluent-bit_3.1.9_amd64.deb"
+if [[ ! -f "$deb_file" ]]; then
+    log_error "Fluent Bit package not found: $deb_file"
+    exit 1
+fi
+
+DEBIAN_FRONTEND=noninteractive dpkg -i "$deb_file" >/dev/null 2>&1 || true
+
+# 验证 Fluent Bit 可以运行
+fb_version=$(/opt/fluent-bit/bin/fluent-bit --version 2>&1 | head -1)
+log_info "Fluent Bit version: $fb_version"
+
+# 创建 fluent-bit 用户
+log_info "Creating fluent-bit user..."
+if ! id "fluent-bit" &>/dev/null; then
+    useradd --no-create-home --shell /bin/false fluent-bit
+fi
+
+# 创建配置目录
+log_info "Installing configuration files..."
+mkdir -p /etc/fluent-bit
+if [[ -d "config" ]]; then
+    cp -r config/* /etc/fluent-bit/
+    chown -R fluent-bit:fluent-bit /etc/fluent-bit
+fi
+
+# 创建日志和缓冲区目录
+log_info "Creating log and buffer directories..."
+mkdir -p /logs/train /logs/infer /buffers
+chmod 755 /logs/train /logs/infer
+chmod 770 /buffers
+chown -R fluent-bit:fluent-bit /logs /buffers
+
+# 启动 Fluent Bit
+log_info "Starting Fluent Bit with configuration from /etc/fluent-bit/"
+config_path="/etc/fluent-bit/fluent-bit.conf"
+
+if [[ ! -f "$config_path" ]]; then
+    log_error "Configuration file not found: $config_path"
+    exit 1
+fi
+
+# 设置环境变量
+log_info "Setting environment variables..."
+
+# 获取非 127.0.0.1 的 IP 地址作为 HOSTNAME
+if [[ -z "${HOSTNAME:-}" ]]; then
+    # 获取 177.x.x.x 段的 IP 地址
+    HOSTNAME=$(ip route get 8.8.8.8 2>/dev/null | grep -oP 'src \K\S+' | grep '^177\.' | head -1)
+    
+    # 如果没有找到 177.x.x.x 段的 IP，则获取第一个非 127.0.0.1 的 IP
+    if [[ -z "$HOSTNAME" ]]; then
+        HOSTNAME=$(ip route get 8.8.8.8 2>/dev/null | grep -oP 'src \K\S+' | grep -v '^127\.' | head -1)
+    fi
+    
+    # 如果还是没有找到，使用 hostname 命令
+    if [[ -z "$HOSTNAME" ]]; then
+        HOSTNAME=$(hostname)
+    fi
+fi
+export HOSTNAME
+
+export CLUSTER="${CLUSTER:-local}"
+export RACK="${RACK:-dev}"
+export ES_HOST="${ES_HOST:-localhost}"
+export ES_PORT="${ES_PORT:-9200}"
+
+log_info "Environment variables:"
+log_info "  CLUSTER=$CLUSTER"
+log_info "  RACK=$RACK"
+log_info "  HOSTNAME=$HOSTNAME"
+log_info "  ES_HOST=$ES_HOST"
+log_info "  ES_PORT=$ES_PORT"
+
+# 检查 fluent-bit 二进制文件
+log_info "[DEBUG] Checking fluent-bit binary..."
+if [[ ! -f "/opt/fluent-bit/bin/fluent-bit" ]]; then
+    log_error "fluent-bit binary not found at /opt/fluent-bit/bin/fluent-bit"
+    exit 1
+fi
+log_info "[DEBUG] fluent-bit binary exists and is executable: $(ls -lh /opt/fluent-bit/bin/fluent-bit)"
+
+# 检查配置文件
+log_info "[DEBUG] Checking configuration file: $config_path"
+if [[ ! -f "$config_path" ]]; then
+    log_error "Configuration file not found: $config_path"
+    exit 1
+fi
+log_info "[DEBUG] Configuration file exists: $(ls -lh $config_path)"
+
+# 显示完整的启动命令
+log_info "[DEBUG] Full command to execute:"
+log_info "[DEBUG]   su -s /bin/bash fluent-bit -c 'env CLUSTER=\"$CLUSTER\" RACK=\"$RACK\" HOSTNAME=\"$HOSTNAME\" ES_HOST=\"$ES_HOST\" ES_PORT=\"$ES_PORT\" /opt/fluent-bit/bin/fluent-bit --config=\"$config_path\"'"
+
+# 清空或创建日志文件
+log_info "[DEBUG] Preparing log file: /var/log/fluent-bit.log"
+: > /var/log/fluent-bit.log
+chmod 666 /var/log/fluent-bit.log
+
+log_info "Command: /opt/fluent-bit/bin/fluent-bit --config=$config_path"
+log_info "[DEBUG] Starting fluent-bit process as fluent-bit user (using su)..."
+nohup su -s /bin/bash fluent-bit -c "env CLUSTER='$CLUSTER' RACK='$RACK' HOSTNAME='$HOSTNAME' ES_HOST='$ES_HOST' ES_PORT='$ES_PORT' /opt/fluent-bit/bin/fluent-bit --config='$config_path' >> /var/log/fluent-bit.log 2>&1" &
+
+bg_pid=$!
+log_info "[DEBUG] Background process started with PID: $bg_pid"
+
+# 等待服务启动
+log_info "[DEBUG] Waiting 3 seconds for service to start..."
+sleep 3
+
+# 查找实际的 fluent-bit 进程 PID
+log_info "[DEBUG] Searching for fluent-bit process..."
+log_info "[DEBUG] Running: pgrep -u fluent-bit -x fluent-bit"
+actual_pid=$(pgrep -u fluent-bit -x fluent-bit | head -1)
+
+# 显示所有 fluent-bit 相关进程
+log_info "[DEBUG] All fluent-bit related processes:"
+ps aux | grep fluent-bit | grep -v grep || log_warning "No fluent-bit processes found in ps output"
+
+if [[ -n "$actual_pid" ]]; then
+    log_success "Fluent Bit started successfully (PID: $actual_pid)"
+    log_info "[DEBUG] Process details: $(ps -p $actual_pid -o pid,user,cmd --no-headers)"
+    
+    # 更新安装记录
+    update_install_record "$actual_pid" "$INSTALL_DIR"
+else
+    log_error "Fluent Bit failed to start - no fluent-bit process found"
+    log_info "[DEBUG] Checking if background process $bg_pid still exists..."
+    if ps -p $bg_pid > /dev/null 2>&1; then
+        log_warning "Background shell process $bg_pid still exists"
+    else
+        log_warning "Background shell process $bg_pid has exited"
+    fi
+    
+    log_info "[DEBUG] Last 20 lines of /var/log/fluent-bit.log:"
+    if [[ -f "/var/log/fluent-bit.log" ]]; then
+        tail -20 /var/log/fluent-bit.log | while IFS= read -r line; do
+            log_info "[LOG] $line"
+        done
+    else
+        log_error "Log file /var/log/fluent-bit.log does not exist"
+    fi
+    
+    exit 1
+fi
+
+log_success "Fluent Bit installation completed!"

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/package.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+# 获取当前目录
+CURRENT_DIR=$(pwd)
+PACKAGE_NAME="fluent-bit-$(date +%Y%m%d-%H%M%S)"
+PACKAGE_FILE="${PACKAGE_NAME}.tar.gz"
+
+log_info "开始打包 Fluent Bit 安装包..."
+
+# 检查必要文件
+log_info "检查必要文件..."
+
+required_files=(
+    "install.sh"
+    "uninstall.sh"
+    "bin/fluent-bit_3.1.9_amd64.deb"
+    "check_health.sh"
+)
+
+missing_files=()
+for file in "${required_files[@]}"; do
+    if [[ ! -f "$file" ]]; then
+        missing_files+=("$file")
+    fi
+done
+
+if [[ ${#missing_files[@]} -gt 0 ]]; then
+    echo "缺少以下文件:"
+    for file in "${missing_files[@]}"; do
+        echo "  - $file"
+    done
+    exit 1
+fi
+
+log_success "所有必要文件检查完成"
+
+# 创建临时目录
+TEMP_DIR=$(mktemp -d)
+log_info "创建临时目录: $TEMP_DIR"
+
+# 复制文件到临时目录
+cp -r . "$TEMP_DIR/$PACKAGE_NAME"
+
+# 进入临时目录
+cd "$TEMP_DIR"
+
+# 创建压缩包
+log_info "创建压缩包: $PACKAGE_FILE"
+tar -czf "$PACKAGE_FILE" "$PACKAGE_NAME"
+
+# 移动压缩包到原目录
+mv "$PACKAGE_FILE" "$CURRENT_DIR/"
+
+# 清理临时目录
+rm -rf "$TEMP_DIR"
+
+# 返回原目录
+cd "$CURRENT_DIR"
+
+# 显示结果
+log_success "打包完成！"
+echo
+echo "安装包文件: $PACKAGE_FILE"
+echo "文件大小: $(du -h "$PACKAGE_FILE" | cut -f1)"
+echo
+echo "使用方法:"
+echo "1. 将 $PACKAGE_FILE 传输到目标服务器"
+echo "2. 解压: tar -xzf $PACKAGE_FILE"
+echo "3. 进入目录: cd $PACKAGE_NAME"
+echo "4. 运行安装: sudo ./install.sh"
+echo
+echo "注意: 请确保所有必要文件都存在"

src/metric/client-plugins/all-in-one-full/plugins/fluent-bit/uninstall.sh

@@ -0,0 +1,169 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting Fluent Bit uninstallation..."
+
+# 检查是否为 root 用户
+if [[ $EUID -ne 0 ]]; then
+    echo "[ERROR] This script requires root privileges"
+    echo "[INFO] Please use: sudo $0"
+    exit 1
+fi
+
+echo "[WARNING] This operation will completely uninstall Fluent Bit"
+read -p "Confirm to continue? (y/N): " confirm
+
+if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+    echo "[INFO] Uninstallation cancelled"
+    exit 0
+fi
+
+# 停止运行中的进程
+echo "[INFO] Stopping Fluent Bit processes..."
+install_record="/opt/argus-metric/current/.install_record"
+stopped=false
+
+# 首先尝试通过安装记录文件停止服务
+if [[ -f "$install_record" ]]; then
+    # 尝试使用jq解析JSON格式的安装记录文件
+    pid=""
+    if command -v jq &> /dev/null; then
+        pid=$(jq -r '.components."fluent-bit".pid // empty' "$install_record" 2>/dev/null || echo "")
+    else
+        # 如果没有jq，使用简单的文本解析方法
+        pid=$(grep -A 10 '"fluent-bit"' "$install_record" | grep '"pid"' | cut -d'"' -f4 | head -1)
+    fi
+    
+    if [[ -n "$pid" && "$pid" =~ ^[0-9]+$ ]]; then
+        if kill -0 "$pid" 2>/dev/null; then
+            echo "[INFO] Stopping service via installation record (PID: $pid)..."
+            kill "$pid"
+            sleep 3
+            
+            # 检查进程是否已停止
+            if kill -0 "$pid" 2>/dev/null; then
+                echo "[WARNING] Process unresponsive, force killing..."
+                kill -9 "$pid" 2>/dev/null || true
+            fi
+            echo "[SUCCESS] Fluent Bit process stopped"
+            stopped=true
+        else
+            echo "[WARNING] PID in installation record no longer exists"
+        fi
+    fi
+fi
+
+# 查找并杀死所有 fluent-bit 进程
+pids=$(pgrep -f "fluent-bit" 2>/dev/null || true)
+if [[ -n "$pids" ]]; then
+    echo "[INFO] Found fluent-bit processes, stopping..."
+    for pid in $pids; do
+        echo "[INFO] Stopping process PID: $pid"
+        kill "$pid" 2>/dev/null || true
+    done
+    sleep 2
+    
+    # 检查是否还有进程在运行，如果有则强制终止
+    remaining_pids=$(pgrep -f "fluent-bit" 2>/dev/null || true)
+    if [[ -n "$remaining_pids" ]]; then
+        echo "[WARNING] Processes unresponsive, force killing..."
+        for pid in $remaining_pids; do
+            echo "[INFO] Force killing process PID: $pid"
+            kill -9 "$pid" 2>/dev/null || true
+        done
+        sleep 1
+    fi
+    
+    # 最终检查
+    if pgrep -f "fluent-bit" > /dev/null; then
+        echo "[ERROR] Unable to stop all fluent-bit processes"
+    else
+        echo "[SUCCESS] All Fluent Bit processes stopped"
+        stopped=true
+    fi
+else
+    echo "[INFO] No Fluent Bit processes running"
+fi
+
+if [[ "$stopped" == "false" ]]; then
+    echo "[WARNING] No Fluent Bit processes found to stop"
+fi
+
+# 卸载 Fluent Bit 包
+echo "[INFO] Uninstalling Fluent Bit package..."
+if dpkg -l | grep -q "fluent-bit"; then
+    echo "[INFO] Found fluent-bit package installed via dpkg, uninstalling..."
+    dpkg --remove --force-remove-reinstreq fluent-bit || true
+    echo "[SUCCESS] Fluent Bit package uninstalled"
+else
+    echo "[INFO] No fluent-bit package found via package manager"
+fi
+
+# 删除二进制文件
+echo "[INFO] Removing Fluent Bit binary files..."
+binary_dir="/opt/fluent-bit"
+if [[ -d "$binary_dir" ]]; then
+    rm -rf "$binary_dir"
+    echo "[SUCCESS] Binary directory removed: $binary_dir"
+else
+    echo "[INFO] Binary directory does not exist"
+fi
+
+# 删除配置文件
+echo "[INFO] Removing configuration files..."
+config_dir="/etc/fluent-bit"
+if [[ -d "$config_dir" ]]; then
+    rm -rf "$config_dir"
+    echo "[SUCCESS] Configuration directory removed"
+else
+    echo "[INFO] Configuration directory does not exist"
+fi
+
+# 删除数据目录
+echo "[INFO] Removing data directories..."
+data_dirs=("/logs" "/buffers")
+deleted=false
+for data_dir in "${data_dirs[@]}"; do
+    if [[ -d "$data_dir" ]]; then
+        rm -rf "$data_dir"
+        echo "[SUCCESS] Data directory removed: $data_dir"
+        deleted=true
+    fi
+done
+
+if [[ "$deleted" == "false" ]]; then
+    echo "[INFO] No data directories found"
+fi
+
+# 清理安装记录
+echo "[INFO] Cleaning up installation record..."
+if [[ -f "$install_record" ]]; then
+    # 从安装记录中移除 fluent-bit 条目
+    sed -i '/^fluent-bit:/d' "$install_record"
+    echo "[SUCCESS] Installation record cleaned"
+else
+    echo "[INFO] Installation record file does not exist"
+fi
+
+# 检查用户状态
+echo "[INFO] Checking fluent-bit user status..."
+if id "fluent-bit" &>/dev/null; then
+    echo "[INFO] fluent-bit user exists"
+    echo "[WARNING] fluent-bit is a system user, may be used by other services"
+    echo "[INFO] fluent-bit user will be preserved for system stability"
+    echo "[INFO] To manually remove, run: sudo userdel fluent-bit"
+else
+    echo "[INFO] fluent-bit user does not exist"
+fi
+
+echo "[SUCCESS] Fluent Bit uninstallation completed!"
+echo
+echo "Removed content:"
+echo "  - Binary directory: /opt/fluent-bit"
+echo "  - Configuration directory: /etc/fluent-bit"
+echo "  - Application log directory: /logs"
+echo "  - Buffer directory: /buffers"
+echo
+echo "Note:"
+echo "  - fluent-bit user preserved (system user, may be used by other services)"
+echo "  - For complete cleanup, manually check and remove related files"

src/metric/client-plugins/all-in-one-full/plugins/node-exporter/check_health.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+
+# Node Exporter 健康检查脚本
+# 输出 JSON 格式结果
+
+set -e
+
+# 检查 Node Exporter 健康状态
+check_health() {
+    local url="http://localhost:9100"
+    local metrics_url="$url/metrics"
+    local name="node-exporter"
+    local status="unhealth"
+    local reason=""
+    
+    # 检查 curl 是否可用
+    if ! command -v curl &> /dev/null; then
+        reason="curl 命令不可用，无法进行健康检查"
+        echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+        exit 1
+    fi
+    
+    # 测试根路径连接
+    local http_code=$(curl -s -o /dev/null -w "%{http_code}" "$url" 2>/dev/null || echo "000")
+    
+    if [[ "$http_code" == "200" ]]; then
+        # 测试 metrics 端点
+        local metrics_code=$(curl -s -o /dev/null -w "%{http_code}" "$metrics_url" 2>/dev/null || echo "000")
+        
+        if [[ "$metrics_code" == "200" ]]; then
+            status="health"
+            reason="success"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 0
+        else
+            reason="Metrics 端点异常 (HTTP $metrics_code)"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    else
+        reason="HTTP 服务异常 (HTTP $http_code)，请检查 Node Exporter 是否正在运行在端口 9100"
+        echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    check_health
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/plugins/node-exporter/install.sh

@@ -0,0 +1,343 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 更新安装记录
+update_install_record() {
+    local pid="$1"
+    # 使用传入的安装目录参数，如果没有则使用默认值
+    local install_base_dir="${2:-/opt/argus-metric/current}"
+    local install_record="$install_base_dir/.install_record"
+    
+    # 如果安装记录文件不存在，说明是首次安装，由主安装脚本统一创建
+    if [[ ! -f "$install_record" ]]; then
+        log_info "安装记录文件不存在，将由主安装脚本创建"
+        return 0
+    fi
+    
+    # 如果文件存在，说明是重启场景，只更新 PID 字段
+    if command -v jq &> /dev/null; then
+        # 读取当前 PID
+        local current_pid=$(jq -r '.components."node-exporter".pid // ""' "$install_record" 2>/dev/null)
+        
+        if [[ -z "$current_pid" ]]; then
+            log_warning "无法读取当前 PID，跳过更新"
+            return 1
+        fi
+        
+        # 使用 jq 只更新 pid 字段，保持字符串类型，保留其他字段
+        jq --arg new_pid "$pid" '.components."node-exporter".pid = $new_pid' "$install_record" > "$install_record.tmp" && mv "$install_record.tmp" "$install_record"
+        log_info "PID 已更新: $current_pid -> $pid"
+    else
+        log_warning "jq 命令不可用，无法更新安装记录文件"
+    fi
+}
+
+# 显示帮助信息
+show_help() {
+    echo "Node Exporter 安装脚本"
+    echo
+    echo "用法: $0 [选项]"
+    echo
+    echo "选项:"
+    echo "  --help     显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0          # 安装 Node Exporter"
+    echo
+}
+
+# 解析命令行参数
+INSTALL_DIR=""
+for arg in "$@"; do
+    case $arg in
+        --help|-h)
+            show_help
+            exit 0
+            ;;
+        *)
+            # 如果参数不是以--开头，则认为是安装目录
+            if [[ ! "$arg" =~ ^-- ]]; then
+                INSTALL_DIR="$arg"
+            else
+                log_error "未知参数: $arg"
+                show_help
+                exit 1
+            fi
+            ;;
+    esac
+done
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    source /etc/os-release
+    log_info "检测到操作系统: $NAME $VERSION"
+    
+    # 检查是否为 Linux 系统
+    if [[ "$ID" != "ubuntu" && "$ID" != "debian" && "$ID" != "centos" && "$ID" != "rhel" && "$ID" != "fedora" ]]; then
+        log_warning "此脚本主要针对常见 Linux 发行版，其他系统可能需要调整"
+    fi
+    
+    # 检查系统架构
+    local arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    if [[ "$arch" != "x86_64" && "$arch" != "amd64" ]]; then
+        log_warning "当前架构为 $arch，node_exporter 主要支持 x86_64/amd64"
+    fi
+}
+
+stop_existing_service() {
+    log_info "检查并停止可能运行的 Node Exporter 服务..."
+
+    # 当前脚本 PID，防止误杀
+    SELF_PID=$$
+
+    # 1. 停止 systemd 服务（如果存在）
+    if systemctl list-units --full -all | grep -q "node_exporter.service"; then
+        log_info "检测到 systemd 服务 node_exporter，正在停止..."
+        systemctl stop node_exporter || true
+        systemctl disable node_exporter || true
+    fi
+
+    # 2. 清理可能存在的 PID 文件
+    for pid_file in /var/run/node-exporter.pid /var/run/node_exporter.pid /tmp/node_exporter.pid; do
+        if [[ -f "$pid_file" ]]; then
+            local pid=$(cat "$pid_file")
+            if kill -0 "$pid" 2>/dev/null; then
+                log_info "发现 Node Exporter (PID: $pid)，正在停止..."
+                kill "$pid"
+                sleep 2
+                kill -0 "$pid" 2>/dev/null && kill -9 "$pid"
+            fi
+            rm -f "$pid_file"
+        fi
+    done
+
+    # 3. 用 pgrep 查找进程，排除当前脚本
+    local pids=$(pgrep -f "node_exporter|node-exporter|/usr/local/bin/node-exporter" | grep -vw "$SELF_PID" || true)
+    if [[ -n "$pids" ]]; then
+        log_info "发现 Node Exporter 进程 (PID: $pids)，正在停止..."
+        for pid in $pids; do
+            if kill -0 "$pid" 2>/dev/null; then
+                kill "$pid" 2>/dev/null || true
+                sleep 1
+                kill -0 "$pid" 2>/dev/null && kill -9 "$pid" 2>/dev/null || true
+            fi
+        done
+    fi
+
+    # 4. 兜底：检查是否有进程占用 9100 端口
+    local listen_pids=$(lsof -ti:9100 2>/dev/null || true)
+    if [[ -n "$listen_pids" ]]; then
+        log_warning "发现占用 9100 端口的进程 (PID: $listen_pids)，强制终止..."
+        for pid in $listen_pids; do
+            kill -9 "$pid" 2>/dev/null || true
+        done
+        sleep 1
+    fi
+
+    # 5. 最终验证
+    if netstat -tuln 2>/dev/null | grep -q ":9100 "; then
+        log_error "端口 9100 仍被占用，请手动检查"
+        return 1
+    else
+        log_success "旧的 Node Exporter 已完全停止"
+    fi
+}
+
+
+# 安装 Node Exporter 二进制文件
+install_node_exporter() {
+    log_info "安装 Node Exporter..."
+    
+    local binary_file="bin/node_exporter"
+    local install_dir="/usr/local/bin"
+    
+    if [[ ! -f "$binary_file" ]]; then
+        log_error "找不到 Node Exporter 二进制文件: $binary_file"
+        exit 1
+    fi
+    
+    # 停止可能运行的服务
+    stop_existing_service
+    
+    # 复制二进制文件并重命名为统一格式
+    cp "$binary_file" "$install_dir/node-exporter"
+    chmod +x "$install_dir/node-exporter"
+    
+    log_success "Node Exporter 二进制文件安装完成"
+}
+
+# 创建用户和组
+create_user() {
+    log_info "创建 node_exporter 用户..."
+    
+    # 检查用户是否已存在
+    if id "node_exporter" &>/dev/null; then
+        log_info "用户 node_exporter 已存在"
+    else
+        useradd --no-create-home --shell /bin/false node_exporter
+        log_success "用户 node_exporter 创建完成"
+    fi
+}
+
+# 安装配置文件
+install_config() {
+    log_info "安装配置文件..."
+    
+    local config_dir="/etc/node_exporter"
+    
+    # 创建配置目录
+    mkdir -p "$config_dir"
+    
+    # 创建文本文件收集器目录
+    mkdir -p "/var/lib/node_exporter/textfile_collector"
+    chown node_exporter:node_exporter "/var/lib/node_exporter/textfile_collector"
+}
+
+# 启动 Node Exporter 服务
+start_node_exporter() {
+    log_info "启动 Node Exporter 服务..."
+    
+    local binary_path="/usr/local/bin/node-exporter"
+    local log_file="/var/log/node-exporter.log"
+    local pid_file="/var/run/node-exporter.pid"
+    
+    # 检查服务是否已经在运行
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "Node Exporter 服务已在运行 (PID: $pid)"
+            return 0
+        else
+            log_warning "发现过期的 PID 文件，正在清理..."
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 检查端口是否被占用
+    if netstat -tuln 2>/dev/null | grep -q ":9100 "; then
+        log_warning "端口 9100 已被占用，请检查是否有其他服务在运行"
+        return 1
+    fi
+    
+    # 启动服务
+    log_info "正在启动 Node Exporter..."
+    nohup "$binary_path" --web.listen-address=:9100 > "$log_file" 2>&1 &
+    local pid=$!
+    
+    # 保存 PID
+    echo "$pid" > "$pid_file"
+    
+    # 等待服务启动
+    sleep 2
+    
+    # 检查服务是否成功启动
+    if kill -0 "$pid" 2>/dev/null; then
+        log_success "Node Exporter 服务启动成功 (PID: $pid)"
+        log_info "日志文件: $log_file"
+        log_info "PID 文件: $pid_file"
+        
+        # 更新安装记录
+        update_install_record "$pid" "$INSTALL_DIR"
+    else
+        log_error "Node Exporter 服务启动失败"
+        rm -f "$pid_file"
+        return 1
+    fi
+}
+
+
+
+# 显示安装信息
+show_install_info() {
+    log_success "Node Exporter 安装完成！"
+    echo
+    echo "安装信息:"
+    echo "  二进制文件: /usr/local/bin/node-exporter"
+    echo "  运行用户: node_exporter"
+    echo "  配置目录: /etc/node_exporter/"
+    echo "  默认端口: 9100"
+    echo
+    echo "使用方法:"
+    echo "  手动启动: /usr/local/bin/node-exporter --web.listen-address=:9100"
+    echo "  后台启动: nohup /usr/local/bin/node-exporter --web.listen-address=:9100 &"
+    echo
+    echo "测试连接:"
+    echo "  curl http://localhost:9100/metrics"
+    echo "  curl http://localhost:9100"
+    echo
+    echo "Prometheus 配置示例:"
+    echo "  - job_name: 'node_exporter'"
+    echo "    static_configs:"
+    echo "      - targets: ['localhost:9100']"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Node Exporter 安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    check_system
+    
+    log_info "开始安装 Node Exporter..."
+    
+    install_node_exporter
+    create_user
+    install_config
+    start_node_exporter
+    
+    show_install_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi
+

src/metric/client-plugins/all-in-one-full/plugins/node-exporter/package.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+# 获取当前目录
+CURRENT_DIR=$(pwd)
+PACKAGE_NAME="node-exporter-$(date +%Y%m%d-%H%M%S)"
+PACKAGE_FILE="${PACKAGE_NAME}.tar.gz"
+
+log_info "开始打包 Node Exporter 安装包..."
+
+# 检查必要文件
+log_info "检查必要文件..."
+
+required_files=(
+    "install.sh"
+    "uninstall.sh"
+    "bin/node_exporter"
+    "check_health.sh"
+)
+
+missing_files=()
+for file in "${required_files[@]}"; do
+    if [[ ! -f "$file" ]]; then
+        missing_files+=("$file")
+    fi
+done
+
+if [[ ${#missing_files[@]} -gt 0 ]]; then
+    echo "缺少以下文件:"
+    for file in "${missing_files[@]}"; do
+        echo "  - $file"
+    done
+    exit 1
+fi
+
+log_success "所有必要文件检查完成"
+
+# 创建临时目录
+TEMP_DIR=$(mktemp -d)
+log_info "创建临时目录: $TEMP_DIR"
+
+# 复制文件到临时目录
+cp -r . "$TEMP_DIR/$PACKAGE_NAME"
+
+# 进入临时目录
+cd "$TEMP_DIR"
+
+# 创建压缩包
+log_info "创建压缩包: $PACKAGE_FILE"
+tar -czf "$PACKAGE_FILE" "$PACKAGE_NAME"
+
+# 移动压缩包到原目录
+mv "$PACKAGE_FILE" "$CURRENT_DIR/"
+
+# 清理临时目录
+rm -rf "$TEMP_DIR"
+
+# 返回原目录
+cd "$CURRENT_DIR"
+
+# 显示结果
+log_success "打包完成！"
+echo
+echo "安装包文件: $PACKAGE_FILE"
+echo "文件大小: $(du -h "$PACKAGE_FILE" | cut -f1)"
+echo
+echo "使用方法:"
+echo "1. 将 $PACKAGE_FILE 传输到目标服务器"
+echo "2. 解压: tar -xzf $PACKAGE_FILE"
+echo "3. 进入目录: cd $PACKAGE_NAME"
+echo "4. 运行安装: sudo ./install.sh"
+echo
+echo "注意: 请确保所有必要文件都存在"

src/metric/client-plugins/all-in-one-full/plugins/node-exporter/uninstall.sh

@@ -0,0 +1,239 @@
+#!/bin/bash
+
+# Node Exporter 卸载脚本
+# 版本: 1.0
+# 作者: AIOps Team
+# 日期: $(date +%Y-%m-%d)
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 停止运行中的进程
+stop_processes() {
+    log_info "停止 Node Exporter 进程..."
+    
+    local pid_file="/var/run/node-exporter.pid"
+    local stopped=false
+    
+    # 首先尝试通过 PID 文件停止服务
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "通过 PID 文件停止服务 (PID: $pid)..."
+            kill "$pid"
+            sleep 3
+            
+            # 检查进程是否已停止
+            if kill -0 "$pid" 2>/dev/null; then
+                log_warning "进程未响应，强制终止..."
+                kill -9 "$pid" 2>/dev/null || true
+            fi
+            log_success "Node Exporter 进程已停止"
+            stopped=true
+        else
+            log_warning "PID 文件存在但进程已不存在，清理 PID 文件"
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 查找并杀死所有 node_exporter 和 node-exporter 进程
+    local pids=$(pgrep -f "node_exporter\|node-exporter" 2>/dev/null || true)
+    if [[ -n "$pids" ]]; then
+        log_info "发现 node_exporter 或 node-exporter 进程，正在停止..."
+        for pid in $pids; do
+            log_info "停止进程 PID: $pid"
+            kill "$pid" 2>/dev/null || true
+        done
+        sleep 2
+        
+        # 检查是否还有进程在运行，如果有则强制终止
+        local remaining_pids=$(pgrep -f "node_exporter\|node-exporter" 2>/dev/null || true)
+        if [[ -n "$remaining_pids" ]]; then
+            log_warning "进程未响应，强制终止..."
+            for pid in $remaining_pids; do
+                log_info "强制终止进程 PID: $pid"
+                kill -9 "$pid" 2>/dev/null || true
+            done
+            sleep 1
+        fi
+        
+        # 最终检查
+        if pgrep -f "node_exporter\|node-exporter" > /dev/null; then
+            log_error "无法停止所有 node_exporter 进程"
+        else
+            log_success "所有 Node Exporter 进程已停止"
+            stopped=true
+        fi
+    else
+        log_info "Node Exporter 进程未运行"
+    fi
+    
+    # 清理 PID 文件
+    rm -f "$pid_file"
+    
+    if [[ "$stopped" == "false" ]]; then
+        log_warning "未发现需要停止的 Node Exporter 进程"
+    fi
+}
+
+# 删除二进制文件
+remove_binary() {
+    log_info "删除 Node Exporter 二进制文件..."
+    
+    local binary_files=(
+        "/usr/local/bin/node-exporter"
+        "/usr/local/bin/node_exporter"
+    )
+    
+    local deleted=false
+    for binary_file in "${binary_files[@]}"; do
+        if [[ -f "$binary_file" ]]; then
+            rm -f "$binary_file"
+            log_success "二进制文件已删除: $binary_file"
+            deleted=true
+        fi
+    done
+    
+    if [[ "$deleted" == "false" ]]; then
+        log_info "二进制文件不存在"
+    fi
+}
+
+# 删除配置文件
+remove_config() {
+    log_info "删除配置文件..."
+    
+    local config_dir="/etc/node_exporter"
+    
+    if [[ -d "$config_dir" ]]; then
+        rm -rf "$config_dir"
+        log_success "配置目录已删除"
+    else
+        log_info "配置目录不存在"
+    fi
+}
+
+# 删除数据目录
+remove_data_dir() {
+    log_info "删除数据目录..."
+    
+    local data_dir="/var/lib/node_exporter"
+    
+    if [[ -d "$data_dir" ]]; then
+        rm -rf "$data_dir"
+        log_success "数据目录已删除"
+    else
+        log_info "数据目录不存在"
+    fi
+}
+
+# 检查用户状态（可选）
+check_user_status() {
+    log_info "检查 node_exporter 用户状态..."
+    
+    if id "node_exporter" &>/dev/null; then
+        log_info "检测到 node_exporter 用户存在"
+        log_warning "node_exporter 是系统用户，可能被其他服务使用"
+        log_info "为了系统稳定性，将保留 node_exporter 用户"
+        log_info "如需手动删除，请运行: sudo userdel node_exporter"
+    else
+        log_info "node_exporter 用户不存在"
+    fi
+}
+
+# 清理日志文件
+cleanup_logs() {
+    log_info "清理日志文件..."
+    
+    # 清理 journal 日志
+    journalctl --vacuum-time=1s --quiet || true
+    
+    # 删除安装脚本创建的日志文件
+    rm -f /var/log/node-exporter.log
+    
+    log_success "日志文件已清理"
+}
+
+# 显示卸载信息
+show_uninstall_info() {
+    log_success "Node Exporter 卸载完成！"
+    echo
+    echo "已删除的内容:"
+    echo "  - 二进制文件: /usr/local/bin/node-exporter"
+    echo "  - 配置目录: /etc/node_exporter"
+    echo "  - 数据目录: /var/lib/node_exporter"
+    echo "  - 相关日志文件"
+    echo
+    echo "注意:"
+    echo "  - node_exporter 用户已保留（系统用户，可能被其他服务使用）"
+    echo "  - 如需完全清理，请手动检查并删除相关文件"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Node Exporter 卸载脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    
+    log_warning "此操作将完全卸载 Node Exporter"
+    read -p "确认继续？(y/N): " confirm
+    
+    if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+        log_info "取消卸载操作"
+        exit 0
+    fi
+    
+    log_info "开始卸载 Node Exporter..."
+    
+    stop_processes
+    remove_binary
+    remove_config
+    remove_data_dir
+    cleanup_logs
+    
+    # 检查用户状态
+    check_user_status
+    
+    show_uninstall_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/check_health.sh

@@ -0,0 +1,286 @@
+#!/bin/bash
+
+# 整体健康检查脚本，调用各个组件的健康检查并将结果写入 .health_log 文件
+
+set -e
+
+# PID 文件检测，防止重复执行
+PIDFILE="/var/run/check_health.pid"
+if [ -f "$PIDFILE" ] && kill -0 $(cat "$PIDFILE") 2>/dev/null; then
+    echo "健康检查脚本已在运行中，跳过本次执行" >&2
+    exit 0
+fi
+echo $$ > "$PIDFILE"
+trap "rm -f $PIDFILE" EXIT
+
+# 获取脚本所在目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+HEALTH_LOG_FILE="$SCRIPT_DIR/.health_log"
+INSTALL_RECORD_FILE="$SCRIPT_DIR/.install_record"
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数 - 输出到 stderr 避免影响 JSON 结果
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1" >&2
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1" >&2
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1" >&2
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1" >&2
+}
+
+# 检查单个组件健康状态
+check_component() {
+    local component_name="$1"
+    local check_script_path="$2"
+
+    log_info "检查 $component_name 健康状态..."
+
+    if [[ ! -f "$check_script_path" ]]; then
+        log_error "健康检查脚本不存在: $check_script_path"
+        echo "{\"name\": \"$component_name\", \"status\": \"unhealth\", \"reason\": \"健康检查脚本不存在: $check_script_path\"}"
+        return 1
+    fi
+
+    if [[ ! -x "$check_script_path" ]]; then
+        log_error "健康检查脚本无执行权限: $check_script_path"
+        echo "{\"name\": \"$component_name\", \"status\": \"unhealth\", \"reason\": \"健康检查脚本无执行权限: $check_script_path\"}"
+        return 1
+    fi
+
+    # 执行健康检查脚本，只捕获 stdout，stderr 输出到终端
+    local result
+    if result=$("$check_script_path" 2>/dev/null); then
+        log_success "$component_name 健康检查通过"
+        echo "$result"
+        return 0
+    else
+        log_warning "$component_name 健康检查失败"
+        echo "$result"
+        return 1
+    fi
+}
+
+# 生成时间戳
+get_timestamp() {
+    date '+%Y-%m-%d %H:%M:%S'
+}
+
+# 生成UTC时间戳
+get_utc_timestamp() {
+    date -u '+%Y-%m-%dT%H:%M:%SZ'
+}
+
+# 获取主机名
+get_hostname() {
+    echo "${HOSTNAME:-$(hostname)}"
+}
+
+# 创建健康状态目录
+create_health_dir() {
+    local hostname=$(get_hostname)
+    local health_dir="/private/argus/agent/$hostname/health"
+    
+    if [[ ! -d "$health_dir" ]]; then
+        log_info "创建健康状态目录: $health_dir"
+        mkdir -p "$health_dir"
+    fi
+    
+    echo "$health_dir"
+}
+
+# 写入单个模块的健康状态JSON文件
+write_component_health_json() {
+    local component_name="$1"
+    local status="$2"
+    local error_msg="$3"
+    local health_dir="$4"
+    
+    # 生成模块名前缀-xxx.json格式的文件名
+    local module_prefix="metric"
+    local filename="${module_prefix}-${component_name}.json"
+    local filepath="$health_dir/$filename"
+    
+    # 生成UTC时间戳
+    local timestamp=$(get_utc_timestamp)
+    
+    # 构建JSON内容
+    local json_content=$(cat << EOF
+{
+    "status": "$status",
+    "error": "$error_msg",
+    "timestamp": "$timestamp"
+}
+EOF
+)
+    
+    # 写入文件
+    echo "$json_content" > "$filepath"
+    log_info "已写入模块健康状态文件: $filepath"
+}
+
+# 从安装记录文件中读取组件安装目录
+read_install_record() {
+    local install_record_file="$1"
+
+    if [[ ! -f "$install_record_file" ]]; then
+        log_error "安装记录文件不存在: $install_record_file"
+        return 1
+    fi
+
+    # 检查是否有 jq 命令来解析 JSON
+    if command -v jq &> /dev/null; then
+        # 使用 jq 解析 JSON
+        local components_json
+        if components_json=$(jq -r '.components | to_entries[] | "\(.key):\(.value.install_dir)"' "$install_record_file" 2>/dev/null); then
+            echo "$components_json"
+            return 0
+        else
+            log_error "无法解析安装记录文件 JSON 格式: $install_record_file"
+            return 1
+        fi
+    else
+        # 如果没有 jq，尝试简单的文本解析
+        log_warning "jq 命令不可用，尝试简单文本解析"
+
+        # 查找所有 install_dir 行
+        local components=()
+        while IFS= read -r line; do
+            if [[ "$line" =~ \"install_dir\":[[:space:]]*\"([^\"]+)\" ]]; then
+                local install_dir="${BASH_REMATCH[1]}"
+                # 从路径中提取组件名称
+                local component_name=$(basename "$install_dir")
+                components+=("$component_name:$install_dir")
+            fi
+        done < "$install_record_file"
+
+        if [[ ${#components[@]} -gt 0 ]]; then
+            printf '%s\n' "${components[@]}"
+            return 0
+        else
+            log_error "无法从安装记录文件中提取组件信息"
+            return 1
+        fi
+    fi
+}
+
+# 主函数
+main() {
+    echo "==========================================" >&2
+    echo "    整体健康检查脚本" >&2
+    echo "==========================================" >&2
+    echo >&2
+
+    # 记录健康检查开始时间
+    local start_time=$(get_timestamp)
+    log_info "健康检查开始时间: $start_time"
+
+    # 创建健康状态目录
+    local health_dir
+    health_dir=$(create_health_dir)
+
+    # 从安装记录文件中读取组件信息
+    log_info "从安装记录文件读取组件信息: $INSTALL_RECORD_FILE"
+    local components_info
+    if ! components_info=$(read_install_record "$INSTALL_RECORD_FILE"); then
+        log_error "无法读取安装记录文件，健康检查终止"
+        exit 1
+    fi
+
+    # 存储所有检查结果
+    local all_results=()
+    local overall_status="health"
+
+    # 逐个检查组件
+    while IFS= read -r component_info; do
+        if [[ -n "$component_info" ]]; then
+            IFS=':' read -r component_name install_dir <<< "$component_info"
+            local check_script_path="$install_dir/check_health.sh"
+
+            local result
+            local component_status="healthy"
+            local error_msg=""
+            
+            if result=$(check_component "$component_name" "$check_script_path"); then
+                all_results+=("$result")
+            else
+                all_results+=("$result")
+                overall_status="unhealth"
+                component_status="unhealthy"
+                # 从结果中提取错误信息
+                if command -v jq &> /dev/null; then
+                    error_msg=$(echo "$result" | jq -r '.reason // ""' 2>/dev/null || echo "")
+                else
+                    # 简单的文本解析提取错误信息
+                    if [[ "$result" =~ \"reason\":[[:space:]]*\"([^\"]+)\" ]]; then
+                        error_msg="${BASH_REMATCH[1]}"
+                    fi
+                fi
+            fi
+            
+            # 写入单个模块的健康状态JSON文件
+            write_component_health_json "$component_name" "$component_status" "$error_msg" "$health_dir"
+        fi
+    done <<< "$components_info"
+
+    # 记录健康检查结束时间
+    local end_time=$(get_timestamp)
+    log_info "健康检查结束时间: $end_time"
+
+    # 构建完整的健康检查结果 JSON
+    local health_check_result=$(cat << EOF
+{
+  "start_time": "$start_time",
+  "end_time": "$end_time",
+  "overall_status": "$overall_status",
+  "components": [
+$(printf '%s,\n' "${all_results[@]}" | sed '$s/,$//')
+  ]
+}
+EOF
+)
+
+    # 写入健康日志文件
+    log_info "将健康检查结果写入日志文件: $HEALTH_LOG_FILE"
+    echo "$health_check_result" >> "$HEALTH_LOG_FILE"
+
+    # 输出 JSON 结果到 stdout
+    echo "$health_check_result"
+
+    # 显示总结到 stderr
+    echo >&2
+    echo "==========================================" >&2
+    echo "    健康检查总结" >&2
+    echo "==========================================" >&2
+    echo "开始时间: $start_time" >&2
+    echo "结束时间: $end_time" >&2
+    echo "整体状态: $overall_status" >&2
+    echo "日志文件: $HEALTH_LOG_FILE" >&2
+    echo >&2
+
+    if [[ "$overall_status" == "health" ]]; then
+        log_success "所有组件健康检查通过！"
+        exit 0
+    else
+        log_error "部分组件健康检查失败，请查看上述详细信息"
+        exit 1
+    fi
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/check_version.sh

@@ -0,0 +1,240 @@
+#!/bin/bash
+
+# 版本校验脚本
+# 比较本地 LATEST_VERSION 与 FTP 的 VERSION 版本，如果不一致则更新对应版本
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数 - 输出到 stderr 避免影响函数返回值
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1" >&2
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1" >&2
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1" >&2
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1" >&2
+}
+
+# 获取脚本所在目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# 动态获取当前版本目录
+get_current_version_dir() {
+    # 查找 /opt/argus-metric/versions/ 下的最新版本目录
+    local versions_dir="/opt/argus-metric/versions"
+    if [[ -d "$versions_dir" ]]; then
+        # 按版本号排序，获取最新的版本目录
+        local latest_version_dir=$(ls -1 "$versions_dir" 2>/dev/null | sort -V | tail -1)
+        if [[ -n "$latest_version_dir" ]]; then
+            echo "$versions_dir/$latest_version_dir"
+        else
+            echo "/opt/argus-metric"
+        fi
+    else
+        echo "/opt/argus-metric"
+    fi
+}
+
+# 获取当前版本目录
+CURRENT_VERSION_DIR=$(get_current_version_dir)
+# LATEST_VERSION 文件在根目录
+LOCAL_VERSION_FILE="/opt/argus-metric/LATEST_VERSION"
+REMOTE_VERSION_URL=""
+LOG_FILE="$CURRENT_VERSION_DIR/.version_check.log"
+
+# 从环境变量或配置文件获取 FTP 服务器信息
+get_ftp_config() {
+    # 优先从环境变量获取配置
+    log_info "获取 FTP 配置信息..."
+    
+    # 如果环境变量中没有设置，则尝试从配置文件读取
+    if [[ -z "$FTP_SERVER" || -z "$FTP_USER" || -z "$FTP_PASSWORD" ]]; then
+        local config_file="$SCRIPT_DIR/../config/config.env"
+        if [[ -f "$config_file" ]]; then
+            log_info "从配置文件读取 FTP 配置: $config_file"
+            source "$config_file"
+        fi
+    else
+        log_info "使用环境变量中的 FTP 配置"
+    fi
+    
+    # 设置默认值（如果环境变量和配置文件都没有设置）
+    FTP_SERVER="${FTP_SERVER:-localhost}"
+    FTP_USER="${FTP_USER:-ftpuser}"
+    FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+    
+    # 构建远程版本文件 URL
+    REMOTE_VERSION_URL="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/LATEST_VERSION"
+    
+    log_info "FTP 配置来源: ${FTP_CONFIG_SOURCE:-环境变量/配置文件}"
+}
+
+# 获取远程版本号
+get_remote_version() {
+    log_info "从 FTP 服务器获取远程版本号..."
+    log_info "远程地址: $REMOTE_VERSION_URL"
+    
+    # 先测试 FTP 连接
+    log_info "测试 FTP 连接..."
+    if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null 2>&1; then
+        log_success "FTP 服务器连接成功"
+    else
+        log_error "无法连接到 FTP 服务器: $FTP_SERVER"
+        return 1
+    fi
+    
+    # 测试 LATEST_VERSION 文件是否存在
+    log_info "检查远程 LATEST_VERSION 文件是否存在..."
+    if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/LATEST_VERSION" >/dev/null 2>&1; then
+        log_success "远程 LATEST_VERSION 文件存在"
+    else
+        log_error "远程 LATEST_VERSION 文件不存在或无法访问"
+        return 1
+    fi
+    
+    # 获取远程版本号
+    local remote_version
+    if remote_version=$(curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfL "ftp://${FTP_SERVER}/LATEST_VERSION" 2>/dev/null | tr -d '[:space:]'); then
+        if [[ -n "$remote_version" ]]; then
+            log_success "获取到远程版本号: $remote_version"
+            echo "$remote_version"
+        else
+            log_error "远程版本号为空"
+            return 1
+        fi
+    else
+        log_error "获取远程版本号失败"
+        return 1
+    fi
+}
+
+# 获取本地版本号
+get_local_version() {
+    if [[ -f "$LOCAL_VERSION_FILE" ]]; then
+        local local_version=$(cat "$LOCAL_VERSION_FILE" 2>/dev/null | tr -d '[:space:]')
+        if [[ -n "$local_version" ]]; then
+            log_info "本地版本号: $local_version"
+            echo "$local_version"
+        else
+            log_warning "本地版本文件为空"
+            echo ""
+        fi
+    else
+        log_warning "本地版本文件不存在: $LOCAL_VERSION_FILE"
+        echo ""
+    fi
+}
+
+# 更新到新版本
+update_to_version() {
+    local new_version="$1"
+    local temp_dir="/tmp/argus-update-$$"
+    local setup_script="$temp_dir/setup.sh"
+    
+    log_info "开始更新到版本: $new_version"
+    
+    # 创建临时目录
+    mkdir -p "$temp_dir"
+    
+    # 下载最新的 setup.sh
+    log_info "从 FTP 服务器下载最新的安装脚本..."
+    local setup_url="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/setup.sh"
+    
+    if curl -fsS "$setup_url" -o "$setup_script"; then
+        log_success "安装脚本下载完成"
+    else
+        log_error "下载安装脚本失败: $setup_url"
+        rm -rf "$temp_dir"
+        return 1
+    fi
+    
+    # 添加执行权限
+    chmod +x "$setup_script"
+    
+    # 执行安装脚本
+    log_info "执行安装脚本进行版本更新..."
+    if "$setup_script" --server "$FTP_SERVER" --user "$FTP_USER" --password "$FTP_PASSWORD" --version "$new_version"; then
+        log_success "版本更新完成: $new_version"
+        rm -rf "$temp_dir"
+        return 0
+    else
+        log_error "版本更新失败: $new_version"
+        rm -rf "$temp_dir"
+        return 1
+    fi
+}
+
+# 记录检查日志
+log_check() {
+    local message="$1"
+    local timestamp=$(date '+%Y-%m-%d %H:%M:%S')
+    echo "[$timestamp] $message" >> "$LOG_FILE"
+}
+
+# 主函数
+main() {
+    log_info "开始版本校验检查..."
+    log_check "版本校验检查开始"
+    
+    # 确保系统目录存在
+    mkdir -p "/opt/argus-metric"
+    mkdir -p "$CURRENT_VERSION_DIR"
+    
+    log_info "当前版本目录: $CURRENT_VERSION_DIR"
+    
+    # 获取 FTP 配置
+    get_ftp_config
+    
+    # 获取本地版本号
+    local local_version
+    local_version=$(get_local_version)
+    
+    # 获取远程版本号
+    local remote_version
+    if ! remote_version=$(get_remote_version); then
+        log_error "无法获取远程版本号，跳过本次检查"
+        log_check "版本校验失败：无法获取远程版本号"
+        exit 1
+    fi
+    
+    # 比较版本号
+    if [[ "$local_version" == "$remote_version" ]]; then
+        log_info "版本一致，无需更新 (本地: $local_version, 远程: $remote_version)"
+        log_check "版本校验完成：版本一致 ($local_version)"
+    else
+        log_info "检测到版本不一致 (本地: $local_version, 远程: $remote_version)"
+        log_check "检测到版本不一致：本地($local_version) -> 远程($remote_version)"
+        
+        # 更新到新版本
+        if update_to_version "$remote_version"; then
+            log_success "版本更新成功: $local_version -> $remote_version"
+            log_check "版本更新成功：$local_version -> $remote_version"
+        else
+            log_error "版本更新失败"
+            log_check "版本更新失败：$local_version -> $remote_version"
+            exit 1
+        fi
+    fi
+    
+    log_success "版本校验检查完成"
+    log_check "版本校验检查完成"
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/install_artifact.sh

@@ -0,0 +1,991 @@
+#!/bin/bash
+
+set -e
+
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+log_info() {
+    local message="[INFO] $1"
+    echo -e "${BLUE}${message}${NC}"
+    echo "$(date '+%Y-%m-%d %H:%M:%S') $message" >> "$LOG_FILE"
+}
+
+log_success() {
+    local message="[SUCCESS] $1"
+    echo -e "${GREEN}${message}${NC}"
+    echo "$(date '+%Y-%m-%d %H:%M:%S') $message" >> "$LOG_FILE"
+}
+
+log_warning() {
+    local message="[WARNING] $1"
+    echo -e "${YELLOW}${message}${NC}"
+    echo "$(date '+%Y-%m-%d %H:%M:%S') $message" >> "$LOG_FILE"
+}
+
+log_error() {
+    local message="[ERROR] $1"
+    echo -e "${RED}${message}${NC}"
+    echo "$(date '+%Y-%m-%d %H:%M:%S') $message" >> "$LOG_FILE"
+}
+
+# 配置变量
+INSTALL_DIR="${1:-$(pwd)}"  # 使用第一个参数作为安装目录，如果没有参数则使用当前目录
+TEMP_DIR="/tmp/metrics-install-$$"
+VERSION_FILE="version.json"
+LOG_FILE="${INSTALL_DIR}/.install.log"  # 安装日志文件
+
+
+# 加载配置文件
+load_config() {
+    local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+    local config_file="$script_dir/config.env"
+    
+    if [[ -f "$config_file" ]]; then
+        log_info "加载配置文件: $config_file"
+        # 导出配置文件中的环境变量
+        set -a  # 自动导出所有变量
+        source "$config_file"
+        set +a  # 关闭自动导出
+        log_success "配置文件加载完成"
+    else
+        log_warning "配置文件不存在: $config_file，使用默认配置"
+    fi
+}
+
+# 复制配置文件到安装目录
+copy_config_files() {
+    log_info "复制配置文件到安装目录..."
+    
+    local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+    local source_config="$script_dir/../config/config.env"
+    local target_config="$INSTALL_DIR/config.env"
+    
+    if [[ -f "$source_config" ]]; then
+        # 检查源文件和目标文件是否是同一个文件
+        if [[ "$source_config" == "$target_config" ]]; then
+            log_info "配置文件已在目标位置，跳过复制"
+            log_success "配置文件已存在: $target_config"
+        else
+            if cp "$source_config" "$target_config"; then
+                log_success "配置文件复制完成: $target_config"
+            else
+                log_error "配置文件复制失败"
+                return 1
+            fi
+        fi
+    else
+        log_warning "源配置文件不存在: $source_config"
+    fi
+    
+    # 复制版本校验脚本
+    log_info "复制版本校验脚本到安装目录..."
+    local target_check_version="$INSTALL_DIR/check_version.sh"
+    
+    # 检查目标文件是否已存在（从 artifact 包中解压出来的）
+    if [[ -f "$target_check_version" ]]; then
+        log_info "版本校验脚本已存在，设置执行权限..."
+        chmod +x "$target_check_version"
+        log_success "版本校验脚本权限设置完成: $target_check_version"
+    else
+        log_warning "版本校验脚本不存在: $target_check_version"
+        log_info "请确保 check_version.sh 已包含在 artifact 包中"
+    fi
+}
+
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0 [安装目录]"
+        log_info "如果不指定安装目录，将使用当前目录: $(pwd)"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    source /etc/os-release
+    log_info "检测到操作系统: $NAME $VERSION"
+    
+    # 检查系统架构
+    arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    # 检查磁盘空间
+    available_space=$(df / | awk 'NR==2 {print $4}')
+    if [[ $available_space -lt 10485760 ]]; then  # 10GB in KB
+        log_warning "可用磁盘空间不足 10GB，当前可用: $(($available_space / 1024 / 1024))GB"
+    fi
+    
+    # 检查内存
+    total_mem=$(free -m | awk 'NR==2{print $2}')
+    if [[ $total_mem -lt 4096 ]]; then  # 4GB
+        log_warning "系统内存不足 4GB，当前: ${total_mem}MB"
+    fi
+}
+
+# 查找版本文件
+find_version_file() {
+    log_info "查找版本信息文件..."
+    
+    # 在当前目录查找
+    if [[ -f "$VERSION_FILE" ]]; then
+        VERSION_FILE_PATH="$(pwd)/$VERSION_FILE"
+        log_success "找到版本文件: $VERSION_FILE"
+        return 0
+    fi
+    
+    # 在 artifact 目录查找
+    for version_dir in artifact/*/; do
+        if [[ -f "${version_dir}${VERSION_FILE}" ]]; then
+            VERSION_FILE_PATH="$(cd "$(dirname "${version_dir}${VERSION_FILE}")" && pwd)/$(basename "${version_dir}${VERSION_FILE}")"
+            log_success "找到版本文件: $VERSION_FILE_PATH"
+            return 0
+        fi
+    done
+    
+    log_error "未找到版本信息文件 $VERSION_FILE"
+    exit 1
+}
+
+# 解析版本信息
+parse_version_info() {
+    log_info "解析版本信息..."
+    
+    if [[ ! -f "$VERSION_FILE_PATH" ]]; then
+        log_error "版本文件不存在: $VERSION_FILE_PATH"
+        exit 1
+    fi
+    
+    # 使用 jq 解析 JSON（如果可用）
+    if command -v jq &> /dev/null; then
+        # 验证JSON文件格式
+        if ! jq empty "$VERSION_FILE_PATH" 2>/dev/null; then
+            log_error "JSON文件格式错误，请检查 $VERSION_FILE_PATH"
+            exit 1
+        fi
+        
+        VERSION=$(jq -r '.version' "$VERSION_FILE_PATH")
+        BUILD_TIME=$(jq -r '.build_time' "$VERSION_FILE_PATH")
+        
+        # 解析 artifact_list
+        if jq -e '.artifact_list' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.artifact_list | to_entries[] | "\(.key):\(.value)"' "$VERSION_FILE_PATH" > "$TEMP_DIR/components.txt"
+        else
+            log_error "version.json 中缺少 artifact_list 字段"
+            exit 1
+        fi
+        
+        # 解析 checksums
+        if jq -e '.checksums' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.checksums | to_entries[] | "\(.key):\(.value)"' "$VERSION_FILE_PATH" > "$TEMP_DIR/checksums.txt"
+        else
+            log_error "version.json 中缺少 checksums 字段"
+            exit 1
+        fi
+        
+        # 解析 install_order（现在包含完整的文件名）
+        if jq -e '.install_order' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.install_order[]' "$VERSION_FILE_PATH" > "$TEMP_DIR/install_order.txt"
+        else
+            log_error "version.json 中缺少 install_order 字段"
+            exit 1
+        fi
+        
+    else
+        log_warning "jq 未安装，使用简单的 JSON 解析"
+        # 简单的 JSON 解析
+        VERSION=$(grep '"version"' "$VERSION_FILE_PATH" | sed 's/.*"version": *"\([^"]*\)".*/\1/')
+        BUILD_TIME=$(grep '"build_time"' "$VERSION_FILE_PATH" | sed 's/.*"build_time": *"\([^"]*\)".*/\1/')
+        
+        # 解析 artifact_list（跳过字段名本身）
+        grep -A 100 '"artifact_list"' "$VERSION_FILE_PATH" | grep -v '"artifact_list"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)":\s*"[^"]*".*/\1/')
+            version=$(echo "$line" | sed 's/.*"[^"]*":\s*"\([^"]*\)".*/\1/')
+            echo "$component:$version" >> "$TEMP_DIR/components.txt"
+        done
+        
+        # 解析 checksums（跳过字段名本身）
+        grep -A 100 '"checksums"' "$VERSION_FILE_PATH" | grep -v '"checksums"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)":\s*"[^"]*".*/\1/')
+            checksum=$(echo "$line" | sed 's/.*"[^"]*":\s*"\([^"]*\)".*/\1/')
+            echo "$component:$checksum" >> "$TEMP_DIR/checksums.txt"
+        done
+        
+        # 解析 install_order（跳过字段名本身，只取数组元素）
+        grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -v '"install_order"' | grep -E '^\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)".*/\1/')
+            echo "$component" >> "$TEMP_DIR/install_order.txt"
+        done
+        
+        # 验证解析结果
+        if [[ ! -f "$TEMP_DIR/components.txt" || ! -s "$TEMP_DIR/components.txt" ]]; then
+            log_error "无法解析 artifact_list，请检查 version.json 格式"
+            exit 1
+        fi
+        
+        if [[ ! -f "$TEMP_DIR/checksums.txt" || ! -s "$TEMP_DIR/checksums.txt" ]]; then
+            log_error "无法解析 checksums，请检查 version.json 格式"
+            exit 1
+        fi
+        
+        if [[ ! -f "$TEMP_DIR/install_order.txt" || ! -s "$TEMP_DIR/install_order.txt" ]]; then
+            log_error "无法解析 install_order，请检查 version.json 格式"
+            exit 1
+        fi
+    fi
+    
+    log_success "版本信息解析完成"
+    log_info "  版本: $VERSION"
+    log_info "  构建时间: $BUILD_TIME"
+    
+    component_count=0
+    if [[ -f "$TEMP_DIR/components.txt" ]]; then
+        component_count=$(wc -l < "$TEMP_DIR/components.txt")
+        log_info "  组件数量: $component_count"
+        log_info "  组件列表:"
+        while IFS= read -r line; do
+            component=$(echo "$line" | cut -d':' -f1)
+            version=$(echo "$line" | cut -d':' -f2)
+            log_info "    - $component v$version"
+        done < "$TEMP_DIR/components.txt"
+    else
+        log_error "components.txt 文件不存在"
+        exit 1
+    fi
+}
+
+# 验证文件完整性
+verify_checksums() {
+    log_info "验证文件完整性..."
+    
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    log_info "Artifact 目录: $artifact_dir"
+    failed_verification=0
+    
+    if [[ -f "$TEMP_DIR/checksums.txt" ]]; then
+        while IFS= read -r line; do
+            component=$(echo "$line" | cut -d':' -f1)
+            expected_checksum=$(echo "$line" | cut -d':' -f2-)
+            
+            # 查找匹配的 tar 文件
+            actual_file=""
+            for file in "$artifact_dir/${component}-"*.tar.gz; do
+                if [[ -f "$file" ]]; then
+                    actual_file="$file"
+                    break
+                fi
+            done
+            
+            if [[ -z "$actual_file" ]]; then
+                log_error "找不到组件文件: $component"
+                failed_verification=1
+                continue
+            fi
+            
+            # 计算实际校验和
+            actual_checksum="sha256:$(sha256sum "$actual_file" | cut -d' ' -f1)"
+            
+            if [[ "$actual_checksum" == "$expected_checksum" ]]; then
+                log_success "  $component: 校验通过"
+            else
+                log_error "  $component: 校验失败"
+                log_error "    期望: $expected_checksum"
+                log_error "    实际: $actual_checksum"
+                failed_verification=1
+            fi
+        done < "$TEMP_DIR/checksums.txt"
+    fi
+    
+    if [[ $failed_verification -eq 1 ]]; then
+        log_error "文件完整性验证失败"
+        exit 1
+    fi
+    
+    log_success "所有文件校验通过"
+}
+
+# 创建安装目录
+create_install_dirs() {
+    log_info "创建安装目录..."
+    
+    mkdir -p "$INSTALL_DIR"
+    mkdir -p "$TEMP_DIR"
+    
+    log_success "安装目录创建完成: $INSTALL_DIR"
+}
+
+# 获取系统版本
+get_system_version() {
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        return 1
+    fi
+    
+    source /etc/os-release
+    
+    # 提取主版本号
+    case "$VERSION_ID" in
+        "20.04")
+            echo "ubuntu20"
+            ;;
+        "22.04")
+            echo "ubuntu22"
+            ;;
+        *)
+            log_warning "未识别的Ubuntu版本: $VERSION_ID，尝试使用ubuntu22"
+            echo "ubuntu22"
+            ;;
+    esac
+}
+
+# 安装系统依赖包
+install_system_deps() {
+    log_info "开始安装系统依赖包（离线模式）..."
+
+    local artifact_dir
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    local deps_dir="$artifact_dir/deps"
+    local system_version
+    system_version=$(get_system_version)
+    local version_deps_dir="$deps_dir/$system_version"
+
+    if [[ ! -d "$version_deps_dir" ]]; then
+        log_warning "未找到 $system_version 版本的依赖目录: $version_deps_dir，跳过安装"
+        return 0
+    fi
+
+    log_info "找到系统版本依赖目录: $version_deps_dir"
+
+    local deps_temp_dir="/tmp/argus_deps"
+    mkdir -p "$deps_temp_dir"
+    rm -rf "$deps_temp_dir"/*
+
+    local FAILED_DEPS=()
+    local CORE_DEPS=(jq cron curl)  # 核心依赖列表
+
+    # 遍历每个 tar.gz
+    for tar_file in "$version_deps_dir"/*.tar.gz; do
+        [[ -f "$tar_file" ]] || continue
+
+        local tar_basename
+        tar_basename=$(basename "$tar_file")
+        log_info "处理依赖包: $tar_basename"
+
+        local extract_dir="$deps_temp_dir/${tar_basename%.tar.gz}"
+        mkdir -p "$extract_dir"
+
+        if tar -xzf "$tar_file" -C "$extract_dir"; then
+            log_success "  $tar_basename 解压完成"
+        else
+            log_error "  $tar_basename 解压失败"
+            FAILED_DEPS+=("$tar_basename")
+            continue
+        fi
+
+        # 递归查找所有 deb 文件，一次性安装
+        mapfile -t deb_files < <(find "$extract_dir" -type f -name "*.deb")
+        if [[ ${#deb_files[@]} -eq 0 ]]; then
+            log_warning "  没有找到 deb 包，跳过"
+            continue
+        fi
+
+        log_info "  安装 ${#deb_files[@]} 个 deb 包..."
+        if dpkg -i "${deb_files[@]}" &>/tmp/dpkg_install.log; then
+            log_success "  所有 deb 包安装成功"
+        else
+            dpkg --configure -a || true
+            if dpkg -l | grep -q '^ii'; then
+                log_success "  dpkg --configure 修复后安装成功"
+            else
+                log_error "  部分 deb 包安装失败，请手动安装"
+                for deb in "${deb_files[@]}"; do
+                    pkg_name=$(dpkg-deb -f "$deb" Package 2>/dev/null || true)
+                    FAILED_DEPS+=("${pkg_name:-$deb}")
+                done
+            fi
+        fi
+    done
+
+    # 启动 cron 服务或其它必要服务
+    start_cron_service
+
+    # 检查核心依赖是否都已安装
+    local missing_core=()
+    for dep in "${CORE_DEPS[@]}"; do
+        if ! dpkg -s "$dep" &>/dev/null; then
+            missing_core+=("$dep")
+        fi
+    done
+
+    if [[ ${#missing_core[@]} -gt 0 ]]; then
+        log_error "核心依赖安装失败，请手动安装以下组件:"
+        for d in "${missing_core[@]}"; do
+            echo "  - $d"
+        done
+        exit 1
+    fi
+
+    # 最终处理其他安装失败的包
+    if [[ ${#FAILED_DEPS[@]} -gt 0 ]]; then
+        log_error "以下系统依赖安装失败，请手动安装后重试："
+        for f in "${FAILED_DEPS[@]}"; do
+            echo "  - $f"
+        done
+        exit 1
+    fi
+
+    log_success "系统依赖安装完成，全部就绪"
+}
+
+# 启动 cron 服务
+start_cron_service() {
+    log_info "检查并启动 cron 服务..."
+    
+    # 检查 cron 是否已经在运行
+    if pgrep -x "cron" > /dev/null; then
+        log_success "cron 服务已在运行"
+        return 0
+    fi
+    
+    # 检查 /usr/sbin/cron 是否存在
+    if [[ ! -f "/usr/sbin/cron" ]]; then
+        log_warning "cron 可执行文件不存在，跳过启动"
+        return 1
+    fi
+    
+    # 启动 cron 服务
+    log_info "启动 cron 服务..."
+    if /usr/sbin/cron start 2>/dev/null || /usr/sbin/cron 2>/dev/null; then
+        log_success "cron 服务启动成功"
+        
+        sleep 2
+        
+        if pgrep -x "cron" > /dev/null; then
+            log_success "cron 服务运行正常"
+        else
+            log_warning "cron 服务可能未正常启动"
+        fi
+    else
+        log_error "cron 服务启动失败"
+        return 1
+    fi
+}
+
+# 安装组件
+install_components() {
+    log_info "开始安装组件..."
+    
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    log_info "Artifact 目录: $artifact_dir"
+    install_count=0
+    total_count=0
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        total_count=$(wc -l < "$TEMP_DIR/install_order.txt")
+    fi
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        while IFS= read -r filename; do
+            install_count=$((install_count + 1))
+            
+            # 从文件名中提取组件名（去掉时间戳后缀）
+            component=$(echo "$filename" | sed 's/-[0-9]\{8\}-[0-9]\{6\}\.tar\.gz$//')
+            
+            log_info "[$install_count/$total_count] 安装 $component..."
+            log_info "  文件名: $filename"
+            
+            # 直接使用完整的文件名
+            tar_file="$artifact_dir/$filename"
+            
+            if [[ ! -f "$tar_file" ]]; then
+                log_error "找不到组件文件: $filename"
+                log_info "  期望路径: $tar_file"
+                log_info "  当前目录: $(pwd)"
+                log_info "  目录内容:"
+                ls -la "$artifact_dir" | while read line; do
+                    log_info "    $line"
+                done
+                exit 1
+            fi
+            
+            log_info "  找到文件: $tar_file"
+            
+            # 解压到临时目录
+            component_temp_dir="$TEMP_DIR/$component"
+            mkdir -p "$component_temp_dir"
+            
+            if tar -xzf "$tar_file" -C "$component_temp_dir" 2>/dev/null; then
+                log_success "  $component 解压完成"
+            else
+                log_error "  $component 解压失败"
+                exit 1
+            fi
+            
+            # 查找解压后的目录
+            extracted_dir=""
+            for dir in "$component_temp_dir"/*; do
+                if [[ -d "$dir" ]]; then
+                    extracted_dir="$dir"
+                    break
+                fi
+            done
+            
+            if [[ -z "$extracted_dir" ]]; then
+                log_error "  $component 解压后未找到目录"
+                exit 1
+            fi
+            
+            # 执行安装脚本
+            if [[ -f "$extracted_dir/install.sh" ]]; then
+                log_info "  执行 $component 安装脚本..."
+                if (cd "$extracted_dir" && ./install.sh "$INSTALL_DIR"); then
+                    log_success "  $component 安装完成"
+                else
+                    log_error "  $component 安装失败"
+                    exit 1
+                fi
+            else
+                log_error "  $component 缺少 install.sh 文件"
+                exit 1
+            fi
+            
+            # 将解压后的目录移动到安装目录，保留组件目录
+            component_install_dir="$INSTALL_DIR/$component"
+            # 简化安装逻辑：直接删除旧目录，不进行备份
+            if [[ -d "$component_install_dir" ]]; then
+                log_info "  组件目录已存在，删除旧版本: $component_install_dir"
+                rm -rf "$component_install_dir"
+                # log_info "  组件目录已存在，备份后更新: $component_install_dir"
+                # mv "$component_install_dir" "${component_install_dir}.backup.$(date +%Y%m%d_%H%M%S)"
+            fi
+            mv "$extracted_dir" "$component_install_dir"
+            log_success "  组件目录已保存: $component_install_dir"
+            
+            # 清理临时文件
+            rm -rf "$component_temp_dir"
+        done < "$TEMP_DIR/install_order.txt"
+    fi
+    
+    log_success "所有组件安装完成"
+}
+
+# 创建安装记录
+create_install_record() {
+    log_info "创建安装记录..."
+    
+    # 等待一段时间确保所有进程都已启动
+    log_info "等待进程启动..."
+    sleep 3
+    
+    local install_time=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+    local install_record_file="$INSTALL_DIR/.install_record"
+    
+    # 创建 JSON 格式的安装记录
+    cat > "$install_record_file" << EOF
+{
+  "version": "$VERSION",
+  "build_time": "$BUILD_TIME",
+  "install_time": "$install_time",
+  "install_dir": "$INSTALL_DIR",
+  "install_pid": $$,
+  "components": {
+EOF
+
+    # 添加组件信息
+    local first_component=true
+    if [[ -f "$TEMP_DIR/components.txt" ]]; then
+        while IFS= read -r line; do
+            component=$(echo "$line" | cut -d':' -f1)
+            version=$(echo "$line" | cut -d':' -f2)
+            
+            # 获取组件的进程信息
+            local component_pid=""
+            
+            # 根据组件名查找进程，使用多种方法确保能找到PID
+            case "$component" in
+                "node-exporter")
+                    # 尝试多种方式查找node_exporter进程
+                    component_pid=$(pgrep -f "node_exporter" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(pgrep -f "node-exporter" | head -1)
+                    fi
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "node_exporter" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+                "dcgm-exporter")
+                    # 查找dcgm-exporter进程
+                    component_pid=$(pgrep -f "dcgm-exporter" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(pgrep -f "dcgm_exporter" | head -1)
+                    fi
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "dcgm-exporter" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+                "fluent-bit")
+                    # 查找fluent-bit进程
+                    component_pid=$(pgrep -f "fluent-bit" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(pgrep -f "fluent_bit" | head -1)
+                    fi
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "fluent-bit" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+                "argus-agent")
+                    # 查找argus-agent进程
+                    component_pid=$(pgrep -f "argus-agent" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "argus-agent" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+            esac
+            
+            # 记录找到的PID信息
+            if [[ -n "$component_pid" ]]; then
+                log_info "  找到 $component 进程 PID: $component_pid"
+            else
+                log_warning "  未找到 $component 进程"
+            fi
+            
+            # 添加逗号分隔符
+            if [[ "$first_component" == "true" ]]; then
+                first_component=false
+            else
+                echo "," >> "$install_record_file"
+            fi
+            
+            # 添加组件信息
+            cat >> "$install_record_file" << EOF
+    "$component": {
+      "version": "$version",
+      "pid": "$component_pid",
+      "install_dir": "$INSTALL_DIR/$component"
+    }
+EOF
+        done < "$TEMP_DIR/components.txt"
+    fi
+    
+    # 结束 JSON
+    cat >> "$install_record_file" << EOF
+  }
+}
+EOF
+
+    log_success "安装记录已创建: $install_record_file"
+}
+
+# 检查cron任务是否已存在
+check_cron_task_exists() {
+    local task_pattern="$1"
+    local temp_cron="$2"
+    
+    if grep -q "$task_pattern" "$temp_cron"; then
+        return 0  # 任务已存在
+    else
+        return 1  # 任务不存在
+    fi
+}
+
+# 设置健康检查定时任务
+setup_health_check_cron() {
+    log_info "设置健康检查定时任务..."
+    
+    # 直接使用当前安装目录，不依赖current软链接
+    # INSTALL_DIR 是 /opt/argus-metric/versions/1.34.0
+    local check_health_script="$INSTALL_DIR/check_health.sh"
+    
+    # 检查健康检查脚本是否存在
+    if [[ ! -f "$check_health_script" ]]; then
+        log_error "健康检查脚本不存在: $check_health_script"
+        return 1
+    fi
+    
+    # 确保脚本有执行权限
+    chmod +x "$check_health_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    
+    # 获取当前用户的crontab（如果存在）
+    crontab -l 2>/dev/null > "$temp_cron" || touch "$temp_cron"
+    
+    # 检查并删除旧的健康检查任务
+    if check_cron_task_exists "check_health.sh" "$temp_cron"; then
+        log_info "发现旧的健康检查定时任务，正在更新..."
+        # 删除所有包含check_health.sh的行
+        grep -v "check_health.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的健康检查定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每5分钟执行一次）
+    echo "# Argus-Metrics 健康检查定时任务" >> "$temp_cron"
+    echo "*/5 * * * * $check_health_script >> $INSTALL_DIR/.health_cron.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "健康检查定时任务设置成功"
+        log_info "  执行频率: 每5分钟"
+        log_info "  日志文件: $INSTALL_DIR/.health_cron.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "健康检查定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "健康检查通过crontab自动执行"
+}
+
+# 设置 DNS 同步定时任务
+setup_dns_sync_cron() {
+    log_info "设置 DNS 同步定时任务..."
+    
+    # 使用当前版本目录中的 DNS 同步脚本
+    local sync_dns_script="$INSTALL_DIR/sync_dns.sh"
+    
+    # 检查 DNS 同步脚本是否存在
+    if [[ ! -f "$sync_dns_script" ]]; then
+        log_warning "DNS 同步脚本不存在: $sync_dns_script"
+        log_warning "跳过 DNS 同步定时任务设置"
+        return 0
+    fi
+    
+    # 确保脚本有执行权限
+    chmod +x "$sync_dns_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    
+    # 获取当前用户的crontab（如果存在）
+    crontab -l 2>/dev/null > "$temp_cron" || touch "$temp_cron"
+    
+    # 检查并删除旧的 DNS 同步任务
+    if check_cron_task_exists "sync_dns.sh" "$temp_cron"; then
+        log_info "发现旧的 DNS 同步定时任务，正在更新..."
+        # 删除所有包含sync_dns.sh的行
+        grep -v "sync_dns.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的 DNS 同步定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每1分钟执行一次）
+    # 直接使用版本目录中的 DNS 同步脚本
+    echo "# Argus-Metrics DNS 同步定时任务" >> "$temp_cron"
+    echo "* * * * * $sync_dns_script >> $INSTALL_DIR/.dns_sync.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "DNS 同步定时任务设置成功"
+        log_info "  执行频率: 每1分钟"
+        log_info "  日志文件: $INSTALL_DIR/.dns_sync.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "DNS 同步定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "DNS 同步通过crontab自动执行"
+}
+
+# 设置版本校验定时任务
+setup_version_check_cron() {
+    log_info "设置版本校验定时任务..."
+    
+    # 使用当前版本目录中的版本校验脚本
+    local check_version_script="$INSTALL_DIR/check_version.sh"
+    
+    # 检查脚本是否存在
+    if [[ ! -f "$check_version_script" ]]; then
+        log_warning "版本校验脚本不存在: $check_version_script"
+        log_info "跳过版本校验定时任务设置"
+        return 0
+    fi
+    
+    # 确保脚本可执行
+    chmod +x "$check_version_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    crontab -l > "$temp_cron" 2>/dev/null || touch "$temp_cron"
+    
+    # 检查是否已存在版本校验定时任务
+    if check_cron_task_exists "check_version.sh" "$temp_cron"; then
+        log_info "发现旧的版本校验定时任务，正在更新..."
+        # 删除所有包含check_version.sh的行
+        grep -v "check_version.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的版本校验定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每30分钟执行一次）
+    echo "# Argus-Metrics 版本校验定时任务" >> "$temp_cron"
+    echo "*/1 * * * * $check_version_script >> $INSTALL_DIR/.version_check.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "版本校验定时任务设置成功"
+        log_info "  执行频率: 每1分钟"
+        log_info "  日志文件: $INSTALL_DIR/.version_check.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "版本校验定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "版本校验通过crontab自动执行"
+}
+
+# 设置自动重启定时任务
+setup_restart_cron() {
+    log_info "设置自动重启定时任务..."
+    
+    # 使用当前版本目录中的重启脚本
+    local restart_script="$INSTALL_DIR/restart_unhealthy.sh"
+    
+    # 检查脚本是否存在
+    if [[ ! -f "$restart_script" ]]; then
+        log_warning "重启脚本不存在: $restart_script"
+        log_info "跳过自动重启定时任务设置"
+        return 0
+    fi
+    
+    # 确保脚本可执行
+    chmod +x "$restart_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    crontab -l > "$temp_cron" 2>/dev/null || touch "$temp_cron"
+    
+    # 检查是否已存在自动重启定时任务
+    if check_cron_task_exists "restart_unhealthy.sh" "$temp_cron"; then
+        log_info "发现旧的自动重启定时任务，正在更新..."
+        # 删除所有包含restart_unhealthy.sh的行
+        grep -v "restart_unhealthy.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的自动重启定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每2分钟执行一次）
+    echo "# Argus-Metrics 自动重启定时任务" >> "$temp_cron"
+    echo "*/2 * * * * $restart_script >> $INSTALL_DIR/.restart.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "自动重启定时任务设置成功"
+        log_info "  执行频率: 每2分钟"
+        log_info "  日志文件: $INSTALL_DIR/.restart.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "自动重启定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "自动重启检查通过crontab自动执行"
+}
+
+# 显示安装信息
+show_install_info() {
+    log_success "Argus-Metrics All-in-One 安装完成！"
+    echo
+    log_info "安装日志已保存到: $LOG_FILE"
+    log_info "如需查看详细日志，请执行: cat $LOG_FILE"
+    echo
+}
+
+cleanup() {
+    if [[ -d "$TEMP_DIR" ]]; then
+        rm -rf "$TEMP_DIR"
+    fi
+}
+
+trap cleanup EXIT
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus-Metrics All-in-One 安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    # 初始化日志文件
+    mkdir -p "$INSTALL_DIR"
+    echo "==========================================" > "$LOG_FILE"
+    echo "    Argus-Metrics All-in-One 安装日志" >> "$LOG_FILE"
+    echo "    开始时间: $(date '+%Y-%m-%d %H:%M:%S')" >> "$LOG_FILE"
+    echo "==========================================" >> "$LOG_FILE"
+    
+    # 加载配置文件
+    load_config
+    
+    log_info "安装目录: $INSTALL_DIR"
+    log_info "日志文件: $LOG_FILE"
+    echo
+    
+    check_root
+    check_system
+    find_version_file
+    create_install_dirs
+    install_system_deps     
+    parse_version_info    
+    verify_checksums
+    install_components
+    copy_config_files
+    create_install_record
+    setup_health_check_cron
+    setup_dns_sync_cron
+    setup_version_check_cron
+    setup_restart_cron
+    
+    # 注释掉立即执行健康检查，避免与cron任务重复执行
+    # log_info "立即执行一次健康检查..."
+    # local check_health_script="$INSTALL_DIR/check_health.sh"
+    # if [[ -f "$check_health_script" ]]; then
+    #     if "$check_health_script" >> "$INSTALL_DIR/.health_check.log" 2>&1; then
+    #         log_success "健康检查执行完成"
+    #     else
+    #         log_warning "健康检查执行失败，请检查日志: $INSTALL_DIR/.health_check.log"
+    #     fi
+    # else
+    #     log_warning "健康检查脚本不存在: $check_health_script"
+    # fi
+    
+    show_install_info
+}
+
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/package_artifact.sh

@@ -0,0 +1,474 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "AIOps All-in-One 打包脚本"
+    echo
+    echo "用法: $0 [选项]"
+    echo
+    echo "选项:"
+    echo "  --force     强制重新打包，即使版本已存在"
+    echo "  --help     显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0              # 正常打包，跳过已存在的版本"
+    echo "  $0 --force      # 强制重新打包"
+    echo
+}
+
+# 解析命令行参数
+FORCE_PACKAGE=false
+if [[ "$1" == "--force" ]]; then
+    FORCE_PACKAGE=true
+    log_info "强制重新打包模式"
+elif [[ "$1" == "--help" || "$1" == "-h" ]]; then
+    show_help
+    exit 0
+fi
+
+# 获取当前目录和版本
+CURRENT_DIR=$(pwd)
+VERSION=$(cat config/VERSION 2>/dev/null || echo "1.0.0")
+ARTIFACT_DIR="artifact/$VERSION"
+
+log_info "开始打包 AIOps All-in-One 安装包 v$VERSION"
+
+# 检查必要文件
+log_info "检查必要文件..."
+if [[ ! -f "config/VERSION" ]]; then
+    log_error "VERSION 文件不存在"
+    exit 1
+fi
+
+if [[ ! -f "config/checklist" ]]; then
+    log_error "checklist 文件不存在"
+    exit 1
+fi
+
+# 检查是否已存在该版本
+if [[ -d "$ARTIFACT_DIR" && "$FORCE_PACKAGE" == "false" ]]; then
+    log_info "检查版本 $VERSION 是否已存在..."
+    
+    # 检查 version.json 是否存在
+    if [[ -f "$ARTIFACT_DIR/version.json" ]]; then
+        log_info "找到已存在的版本信息文件"
+        
+        # 检查是否所有组件文件都存在
+        missing_files=0
+        existing_components=0
+        
+        # 解析已存在的 version.json 来检查文件
+        if command -v jq &> /dev/null; then
+            # 使用 jq 解析
+            while IFS= read -r component; do
+                existing_components=$((existing_components + 1))
+                # 查找对应的 tar 文件
+                found_file=false
+                for file in "$ARTIFACT_DIR/${component}-"*.tar.gz; do
+                    if [[ -f "$file" ]]; then
+                        found_file=true
+                        break
+                    fi
+                done
+                if [[ "$found_file" == "false" ]]; then
+                    missing_files=$((missing_files + 1))
+                    log_warning "  缺少文件: $component"
+                fi
+            done < <(jq -r '.artifact_list | keys[]' "$ARTIFACT_DIR/version.json" 2>/dev/null)
+        else
+            # 简单的文件检查
+            for file in "$ARTIFACT_DIR"/*.tar.gz; do
+                if [[ -f "$file" ]]; then
+                    existing_components=$((existing_components + 1))
+                fi
+            done
+        fi
+        
+        # 如果所有文件都存在，则跳过打包
+        if [[ $missing_files -eq 0 && $existing_components -gt 0 ]]; then
+            log_success "版本 $VERSION 已完整打包，跳过重复打包"
+            echo
+            echo "现有文件:"
+            ls -la "$ARTIFACT_DIR"
+            echo
+            echo "如需强制重新打包，请删除目录: rm -rf $ARTIFACT_DIR"
+            echo "或使用: ./package.sh --force"
+            exit 0
+        else
+            log_warning "版本 $VERSION 存在但不完整，将重新打包"
+            log_info "  现有组件: $existing_components"
+            log_info "  缺少文件: $missing_files"
+        fi
+    else
+        log_warning "版本目录存在但缺少 version.json，将重新打包"
+    fi
+fi
+
+# 创建 artifact 目录
+mkdir -p "$ARTIFACT_DIR"
+log_info "创建输出目录: $ARTIFACT_DIR"
+
+# 创建临时文件存储数据
+TEMP_DIR=$(mktemp -d)
+COMPONENTS_FILE="$TEMP_DIR/components.txt"
+VERSIONS_FILE="$TEMP_DIR/versions.txt"
+DEPENDENCIES_FILE="$TEMP_DIR/dependencies.txt"
+INSTALL_ORDER_FILE="$TEMP_DIR/install_order.txt"
+CHECKSUMS_FILE="$TEMP_DIR/checksums.txt"
+ARTIFACT_LIST_FILE="$TEMP_DIR/artifact_list.txt"
+
+# 解析 checklist 文件
+log_info "解析组件清单..."
+line_num=0
+component_count=0
+
+while IFS= read -r line; do
+    [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+    
+    line_num=$((line_num + 1))
+    
+    # 解析行: 组件名 目录路径 版本 [依赖组件] [安装顺序]
+    read -r component component_path version dep_component order <<< "$line"
+    
+    if [[ -z "$component" || -z "$component_path" || -z "$version" ]]; then
+        log_warning "跳过无效行 $line_num: $line"
+        continue
+    fi
+    
+    # 存储组件信息
+    echo "$component" >> "$COMPONENTS_FILE"
+    echo "$component:$version" >> "$VERSIONS_FILE"
+    echo "$component:$component_path" >> "$TEMP_DIR/component_paths.txt"
+    
+    if [[ -n "$dep_component" && "$dep_component" != "$component" ]]; then
+        echo "$component:$dep_component" >> "$DEPENDENCIES_FILE"
+    fi
+    
+    if [[ -n "$order" && "$order" =~ ^[0-9]+$ ]]; then
+        echo "$order:$component" >> "$INSTALL_ORDER_FILE"
+    else
+        # 如果没有指定顺序，按解析顺序分配
+        echo "$line_num:$component" >> "$INSTALL_ORDER_FILE"
+    fi
+    
+    component_count=$((component_count + 1))
+    log_info "  - $component v$version"
+done < config/checklist
+
+if [[ $component_count -eq 0 ]]; then
+    log_error "没有找到有效的组件"
+    rm -rf "$TEMP_DIR"
+    exit 1
+fi
+
+log_success "找到 $component_count 个组件"
+
+# 检查组件目录是否存在
+log_info "检查组件目录..."
+missing_components=()
+
+while IFS= read -r component; do
+    # 获取组件路径
+    component_path=$(grep "^$component:" "$TEMP_DIR/component_paths.txt" | cut -d':' -f2-)
+    if [[ -z "$component_path" ]]; then
+        log_error "未找到组件 $component 的路径配置"
+        log_info "请检查 component_paths.txt 文件或添加路径配置"
+        exit 1
+    fi
+    
+    if [[ ! -d "$component_path" ]]; then
+        missing_components+=("$component:$component_path")
+    fi
+done < "$COMPONENTS_FILE"
+
+if [[ ${#missing_components[@]} -gt 0 ]]; then
+    log_error "以下组件目录不存在:"
+    for component_path in "${missing_components[@]}"; do
+        echo "  - $component_path"
+    done
+    rm -rf "$TEMP_DIR"
+    exit 1
+fi
+
+# 打包各个组件
+log_info "开始打包组件..."
+
+while IFS= read -r component; do
+    # 获取组件版本和路径
+    version=$(grep "^$component:" "$VERSIONS_FILE" | cut -d':' -f2)
+    component_path=$(grep "^$component:" "$TEMP_DIR/component_paths.txt" | cut -d':' -f2-)
+    if [[ -z "$component_path" ]]; then
+        log_error "未找到组件 $component 的路径配置"
+        log_info "请检查 component_paths.txt 文件或添加路径配置"
+        exit 1
+    fi
+    
+    log_info "打包 $component v$version..."
+    log_info "  组件路径: $component_path"
+    
+    # 进入组件目录
+    cd "$component_path"
+    
+    # 检查组件是否有 package.sh
+    if [[ ! -f "package.sh" ]]; then
+        log_error "$component 缺少 package.sh 文件"
+        cd "$CURRENT_DIR"
+        rm -rf "$TEMP_DIR"
+        exit 1
+    fi
+    
+    # 执行组件的打包脚本
+    if ./package.sh; then
+        # 查找生成的 tar 包
+        tar_file=$(find . -name "*.tar.gz" -type f | head -1)
+        if [[ -n "$tar_file" ]]; then
+            # 移动到 artifact 目录
+            mv "$tar_file" "$CURRENT_DIR/$ARTIFACT_DIR/"
+            tar_filename=$(basename "$tar_file")
+            
+            # 计算校验和
+            checksum=$(sha256sum "$CURRENT_DIR/$ARTIFACT_DIR/$tar_filename" | cut -d' ' -f1)
+            echo "$component:sha256:$checksum" >> "$CHECKSUMS_FILE"
+            echo "$component:$version" >> "$ARTIFACT_LIST_FILE"
+            
+            # 将完整的文件名存储到安装顺序文件中
+            echo "$tar_filename" >> "$TEMP_DIR/install_order_files.txt"
+            
+            log_success "  $component 打包完成: $tar_filename"
+        else
+            log_error "$component 打包失败，未找到生成的 tar 包"
+            cd "$CURRENT_DIR"
+            rm -rf "$TEMP_DIR"
+            exit 1
+        fi
+    else
+        log_error "$component 打包失败"
+        cd "$CURRENT_DIR"
+        rm -rf "$TEMP_DIR"
+        exit 1
+    fi
+    
+    # 返回主目录
+    cd "$CURRENT_DIR"
+done < "$COMPONENTS_FILE"
+
+# 生成 version.json
+log_info "生成版本信息文件..."
+version_json="$ARTIFACT_DIR/version.json"
+
+# 构建依赖关系 JSON
+deps_json=""
+if [[ -f "$DEPENDENCIES_FILE" ]]; then
+    first=true
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        dep=$(echo "$line" | cut -d':' -f2)
+        if [[ "$first" == "true" ]]; then
+            deps_json="\"$component\":[\"$dep\"]"
+            first=false
+        else
+            deps_json="$deps_json,\"$component\":[\"$dep\"]"
+        fi
+    done < "$DEPENDENCIES_FILE"
+fi
+
+# 构建安装顺序数组
+order_array=""
+if [[ -f "$TEMP_DIR/install_order_files.txt" ]]; then
+    first=true
+    while IFS= read -r filename; do
+        if [[ "$first" == "true" ]]; then
+            order_array="\"$filename\""
+            first=false
+        else
+            order_array="$order_array,\"$filename\""
+        fi
+    done < "$TEMP_DIR/install_order_files.txt"
+fi
+
+# 构建 artifact_list JSON
+artifact_json=""
+if [[ -f "$ARTIFACT_LIST_FILE" ]]; then
+    first=true
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        version=$(echo "$line" | cut -d':' -f2)
+        if [[ "$first" == "true" ]]; then
+            artifact_json="\"$component\":\"$version\""
+            first=false
+        else
+            artifact_json="$artifact_json,\"$component\":\"$version\""
+        fi
+    done < "$ARTIFACT_LIST_FILE"
+fi
+
+# 构建 checksums JSON
+checksums_json=""
+if [[ -f "$CHECKSUMS_FILE" ]]; then
+    first=true
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        checksum=$(echo "$line" | cut -d':' -f2-)
+        if [[ "$first" == "true" ]]; then
+            checksums_json="\"$component\":\"$checksum\""
+            first=false
+        else
+            checksums_json="$checksums_json,\"$component\":\"$checksum\""
+        fi
+    done < "$CHECKSUMS_FILE"
+fi
+
+# 生成完整的 version.json
+cat > "$version_json" << EOF
+{
+  "version": "$VERSION",
+  "build_time": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
+  "artifact_list": {
+    $artifact_json
+  },
+  "checksums": {
+    $checksums_json
+  },
+  "dependencies": {
+    $deps_json
+  },
+  "install_order": [
+    $order_array
+  ]
+}
+EOF
+
+log_success "版本信息文件生成完成: $version_json"
+
+# 复制`安装`脚本到 artifact 目录
+log_info "复制安装脚本..."
+if [[ -f "scripts/install_artifact.sh" ]]; then
+    cp "scripts/install_artifact.sh" "$ARTIFACT_DIR/install.sh"
+    chmod +x "$ARTIFACT_DIR/install.sh"
+    log_success "安装脚本复制完成: $ARTIFACT_DIR/install.sh"
+else
+    log_warning "scripts/install_artifact.sh 文件不存在"
+fi
+
+# 复制`卸载`脚本到 artifact 目录
+log_info "复制卸载脚本..."
+if [[ -f "scripts/uninstall_artifact.sh" ]]; then
+    cp "scripts/uninstall_artifact.sh" "$ARTIFACT_DIR/uninstall.sh"
+    chmod +x "$ARTIFACT_DIR/uninstall.sh"
+    log_success "卸载脚本复制完成: $ARTIFACT_DIR/uninstall.sh"
+else
+    log_warning "scripts/uninstall_artifact.sh 文件不存在"
+fi
+
+# 复制`健康检查`脚本到 artifact 目录
+log_info "复制健康检查脚本..."
+if [[ -f "scripts/check_health.sh" ]]; then
+    cp "scripts/check_health.sh" "$ARTIFACT_DIR/check_health.sh"
+    chmod +x "$ARTIFACT_DIR/check_health.sh"
+    log_success "健康检查脚本复制完成: $ARTIFACT_DIR/check_health.sh"
+else
+    log_warning "scripts/check_health.sh 文件不存在"
+fi
+
+# 复制`DNS 同步`脚本到 artifact 目录
+log_info "复制 DNS 同步脚本..."
+if [[ -f "scripts/sync_dns.sh" ]]; then
+    cp "scripts/sync_dns.sh" "$ARTIFACT_DIR/sync_dns.sh"
+    chmod +x "$ARTIFACT_DIR/sync_dns.sh"
+    log_success "DNS 同步脚本复制完成: $ARTIFACT_DIR/sync_dns.sh"
+else
+    log_warning "scripts/sync_dns.sh 文件不存在"
+fi
+
+# 复制`版本校验`脚本到 artifact 目录
+log_info "复制版本校验脚本..."
+if [[ -f "scripts/check_version.sh" ]]; then
+    cp "scripts/check_version.sh" "$ARTIFACT_DIR/check_version.sh"
+    chmod +x "$ARTIFACT_DIR/check_version.sh"
+    log_success "版本校验脚本复制完成: $ARTIFACT_DIR/check_version.sh"
+else
+    log_warning "scripts/check_version.sh 文件不存在"
+fi
+
+# 复制`自动重启`脚本到 artifact 目录
+log_info "复制自动重启脚本..."
+if [[ -f "scripts/restart_unhealthy.sh" ]]; then
+    cp "scripts/restart_unhealthy.sh" "$ARTIFACT_DIR/restart_unhealthy.sh"
+    chmod +x "$ARTIFACT_DIR/restart_unhealthy.sh"
+    log_success "自动重启脚本复制完成: $ARTIFACT_DIR/restart_unhealthy.sh"
+else
+    log_warning "scripts/restart_unhealthy.sh 文件不存在"
+fi
+
+# 复制配置文件到 artifact 目录
+log_info "复制配置文件..."
+if [[ -f "config/config.env" ]]; then
+    cp "config/config.env" "$ARTIFACT_DIR/"
+    log_success "配置文件复制完成: $ARTIFACT_DIR/config.env"
+else
+    log_warning "config 目录不存在，跳过配置文件复制"
+fi
+
+# DNS 配置文件不需要复制到版本目录，直接从 FTP 服务器根目录获取
+
+# 复制 deps 目录到 artifact 目录
+log_info "复制系统依赖包..."
+if [[ -d "deps" ]]; then
+    cp -r "deps" "$ARTIFACT_DIR/"
+    log_success "系统依赖包复制完成: $ARTIFACT_DIR/deps"
+    
+    # 显示deps目录内容
+    log_info "  依赖包列表:"
+    find "$ARTIFACT_DIR/deps" -name "*.tar.gz" -exec basename {} \; | while read dep_file; do
+        log_info "    - $dep_file"
+    done
+else
+    log_warning "deps 目录不存在，跳过依赖包复制"
+fi
+
+# 显示打包结果
+log_success "打包完成！"
+echo
+echo "版本: $VERSION"
+echo "输出目录: $ARTIFACT_DIR"
+echo "包含组件:"
+if [[ -f "$ARTIFACT_LIST_FILE" ]]; then
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        version=$(echo "$line" | cut -d':' -f2)
+        echo "  - $component v$version"
+    done < "$ARTIFACT_LIST_FILE"
+fi
+echo
+echo "文件列表:"
+ls -la "$ARTIFACT_DIR"
+echo
+
+# 清理临时文件
+rm -rf "$TEMP_DIR"

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

@@ -0,0 +1,293 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+RED='\033[0;31m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "Argus-Metric Artifact 发布脚本"
+    echo
+    echo "用法: $0 <版本号> [选项]"
+    echo
+    echo "参数:"
+    echo "  <版本号>              要发布的版本号，对应 artifact 目录中的版本"
+    echo
+    echo "选项:"
+    echo "  --output-dir <路径>   指定输出目录 (默认: /private/argus/ftp/share/)"
+    echo "  --owner <uid:gid>     指定文件所有者 (默认: 2133:2015)"
+    echo "  -h, --help           显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0 1.20.0                                    # 使用默认配置发布"
+    echo "  $0 1.20.0 --output-dir /tmp/publish          # 指定输出目录"
+    echo "  $0 1.20.0 --owner 1000:1000                  # 指定文件所有者"
+    echo "  $0 1.20.0 --output-dir /srv/ftp --owner root:root  # 同时指定两者"
+    echo
+}
+
+# 默认配置
+DEFAULT_PUBLISH_DIR="/private/argus/ftp/share/"
+DEFAULT_OWNER="2133:2015"
+
+# 解析参数
+VERSION=""
+PUBLISH_DIR="$DEFAULT_PUBLISH_DIR"
+OWNER="$DEFAULT_OWNER"
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        --output-dir)
+            PUBLISH_DIR="$2"
+            shift 2
+            ;;
+        --owner)
+            OWNER="$2"
+            shift 2
+            ;;
+        *)
+            if [[ -z "$VERSION" ]]; then
+                VERSION="$1"
+                shift
+            else
+                log_error "未知参数: $1"
+                show_help
+                exit 1
+            fi
+            ;;
+    esac
+done
+
+# 检查版本号是否提供
+if [[ -z "$VERSION" ]]; then
+    log_error "请提供版本号参数"
+    show_help
+    exit 1
+fi
+
+ARTIFACT_DIR="artifact/$VERSION"
+
+# 检查版本目录是否存在
+if [[ ! -d "$ARTIFACT_DIR" ]]; then
+    log_error "版本目录不存在: $ARTIFACT_DIR"
+    exit 1
+fi
+
+log_info "开始发布版本: $VERSION"
+log_info "输出目录: $PUBLISH_DIR"
+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: $PUBLISH_DIR"
+mkdir -p "$PUBLISH_DIR"
+
+# 解析并校验所有者（仅在需要时 chown）
+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-$$"
+mkdir -p "$TEMP_PACKAGE_DIR"
+
+# 复制所有 tar.gz 文件到临时目录
+log_info "准备 artifact 文件..."
+tar_files=$(find "$ARTIFACT_DIR" -name "*.tar.gz" -type f)
+
+if [[ -z "$tar_files" ]]; then
+    log_error "在 $ARTIFACT_DIR 中未找到 tar.gz 文件"
+    exit 1
+fi
+
+for file in $tar_files; do
+    filename=$(basename "$file")
+    log_info "  准备: $filename"
+    cp "$file" "$TEMP_PACKAGE_DIR/"
+done
+
+# 复制版本信息文件
+if [[ -f "$ARTIFACT_DIR/version.json" ]]; then
+    log_info "复制版本信息文件..."
+    cp "$ARTIFACT_DIR/version.json" "$TEMP_PACKAGE_DIR/"
+fi
+
+# 复制健康检查脚本
+if [[ -f "$ARTIFACT_DIR/check_health.sh" ]]; then
+    log_info "复制健康检查脚本..."
+    cp "$ARTIFACT_DIR/check_health.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/check_health.sh" ]]; then
+    log_info "复制健康检查脚本 (从当前目录)..."
+    cp "scripts/check_health.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 check_health.sh 文件"
+fi
+
+# 复制 DNS 同步脚本
+if [[ -f "$ARTIFACT_DIR/sync_dns.sh" ]]; then
+    log_info "复制 DNS 同步脚本..."
+    cp "$ARTIFACT_DIR/sync_dns.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/sync_dns.sh" ]]; then
+    log_info "复制 DNS 同步脚本 (从当前目录)..."
+    cp "scripts/sync_dns.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 sync_dns.sh 文件"
+fi
+
+# 复制版本校验脚本
+if [[ -f "$ARTIFACT_DIR/check_version.sh" ]]; then
+    log_info "复制版本校验脚本..."
+    cp "$ARTIFACT_DIR/check_version.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/check_version.sh" ]]; then
+    log_info "复制版本校验脚本 (从当前目录)..."
+    cp "scripts/check_version.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 check_version.sh 文件"
+fi
+
+# 复制重启失败脚本
+if [[ -f "$ARTIFACT_DIR/restart_unhealthy.sh" ]]; then
+    log_info "复制重启失败脚本..."
+    cp "$ARTIFACT_DIR/restart_unhealthy.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/restart_unhealthy.sh" ]]; then
+    log_info "复制重启失败脚本 (从当前目录)..."
+    cp "scripts/restart_unhealthy.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 restart_unhealthy.sh 文件"
+fi
+
+# 复制安装脚本并重命名为 install.sh
+if [[ -f "scripts/install_artifact.sh" ]]; then
+    log_info "复制安装脚本..."
+    cp "scripts/install_artifact.sh" "$TEMP_PACKAGE_DIR/install.sh"
+fi
+
+if [[ -f "scripts/uninstall_artifact.sh" ]]; then
+    log_info "复制卸载脚本..."
+    cp "scripts/uninstall_artifact.sh" "$TEMP_PACKAGE_DIR/uninstall.sh"
+fi
+
+# 复制配置文件
+if [[ -f "$ARTIFACT_DIR/config.env" ]]; then
+    log_info "复制配置文件..."
+    cp "$ARTIFACT_DIR/config.env" "$TEMP_PACKAGE_DIR/"
+    log_success "配置文件复制完成"
+else
+    log_warning "未找到 config.env 文件"
+fi
+
+# DNS 配置文件将在后面直接复制到发布目录根目录，不包含在 tar.gz 中
+
+# 复制 deps 目录
+if [[ -d "$ARTIFACT_DIR/deps" ]]; then
+    log_info "复制系统依赖包..."
+    cp -r "$ARTIFACT_DIR/deps" "$TEMP_PACKAGE_DIR/"
+    log_success "系统依赖包复制完成"
+fi
+
+# 创建tar包，使用新的命名规范
+TAR_NAME="argus-metric_$(echo $VERSION | tr '.' '_').tar.gz"
+log_info "创建发布包: $TAR_NAME"
+cd "$TEMP_PACKAGE_DIR"
+tar -czf "$PUBLISH_DIR/$TAR_NAME" .
+cd - > /dev/null
+
+# 设置文件所有者
+log_info "设置文件所有者为: $OWNER"
+if [[ "$NEED_CHOWN" == true ]]; then
+    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 "$VERSION" > "$PUBLISH_DIR/LATEST_VERSION"
+if [[ "$NEED_CHOWN" == true ]]; then
+    chown "$OWNER" "$PUBLISH_DIR/LATEST_VERSION"
+fi
+
+# 复制 DNS 配置文件到发布目录根目录（直接从 config 目录复制）
+if [[ -f "config/dns.conf" ]]; then
+    log_info "复制 DNS 配置文件到发布目录根目录..."
+    cp "config/dns.conf" "$PUBLISH_DIR/"
+    if [[ "$NEED_CHOWN" == true ]]; then
+        chown "$OWNER" "$PUBLISH_DIR/dns.conf"
+    fi
+    log_success "DNS 配置文件复制完成: $PUBLISH_DIR/dns.conf"
+else
+    log_warning "未找到 config/dns.conf 文件，跳过 DNS 配置文件复制"
+fi
+
+# 复制 setup.sh 到发布目录
+if [[ -f "scripts/setup.sh" ]]; then
+    log_info "复制 setup.sh 到发布目录..."
+    cp "scripts/setup.sh" "$PUBLISH_DIR/"
+    if [[ "$NEED_CHOWN" == true ]]; then
+        chown "$OWNER" "$PUBLISH_DIR/setup.sh"
+    fi
+fi
+
+# 显示发布结果
+log_success "版本 $VERSION 发布完成！"
+echo
+echo "发布目录: $PUBLISH_DIR"
+echo "发布包: $PUBLISH_DIR/$TAR_NAME"
+echo "包大小: $(du -h "$PUBLISH_DIR/$TAR_NAME" | cut -f1)"
+echo "最新版本: $(cat "$PUBLISH_DIR/LATEST_VERSION")"
+echo
+echo "发布目录中的文件:"
+ls -la "$PUBLISH_DIR" | while read line; do
+    echo "  $line"
+done
+echo
+echo "使用方法:"
+echo "  1. 确保 /srv/ftp/share 目录可通过 FTP 访问"
+echo "  2. 用户首先下载安装脚本:"
+echo "     curl -u ftpuser:admin1234 ftp://10.211.55.4/setup.sh -o setup.sh"
+echo "  3. 然后执行安装 (自动获取最新版本):"
+echo "     sudo sh setup.sh"
+echo "  4. 或者指定版本安装:"
+echo "     sudo sh setup.sh --version $VERSION"
+echo "  5. 或者指定不同的FTP服务器:"
+echo "     sudo sh setup.sh --server 192.168.1.100 --user myuser --password mypass"

src/metric/client-plugins/all-in-one-full/scripts/restart_unhealthy.sh

@@ -0,0 +1,337 @@
+#!/bin/bash
+
+# 此脚本会检查各组件的健康状态，并重启不健康的组件
+
+# PID 文件检测，防止重复执行
+PIDFILE="/var/run/restart_unhealthy.pid"
+if [ -f "$PIDFILE" ] && kill -0 $(cat "$PIDFILE") 2>/dev/null; then
+    echo "自动重启脚本已在运行中，跳过本次执行" >&2
+    exit 0
+fi
+echo $$ > "$PIDFILE"
+trap "rm -f $PIDFILE" EXIT
+
+# 获取脚本所在目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+INSTALL_RECORD_FILE="$SCRIPT_DIR/.install_record"
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+# 加载配置文件
+load_config() {
+    local config_file="$SCRIPT_DIR/config.env"
+    
+    if [[ -f "$config_file" ]]; then
+        log_info "加载配置文件: $config_file"
+        set -a
+        source "$config_file"
+        set +a
+        log_success "配置文件加载完成"
+    else
+        log_warning "配置文件不存在: $config_file，使用默认配置"
+    fi
+}
+
+# 检查单个组件健康状态
+check_component_health() {
+    local component_name="$1"
+    local check_script_path="$2"
+
+    if [[ ! -f "$check_script_path" ]]; then
+        log_error "$component_name: 健康检查脚本不存在: $check_script_path"
+        return 1
+    fi
+
+    if [[ ! -x "$check_script_path" ]]; then
+        chmod +x "$check_script_path" 2>/dev/null || true
+    fi
+
+    # 执行健康检查，捕获退出码
+    if "$check_script_path" > /dev/null 2>&1; then
+        return 0
+    else
+        return 1
+    fi
+}
+
+# 重启单个组件
+restart_component() {
+    local component_name="$1"
+    local install_dir="$2"
+
+    log_warning "正在重启组件: $component_name"
+    
+    # 先执行卸载脚本
+    local uninstall_script="$install_dir/uninstall.sh"
+    if [[ -f "$uninstall_script" ]]; then
+        log_info "$component_name: 执行卸载脚本..."
+        chmod +x "$uninstall_script" 2>/dev/null || true
+        # 使用 yes 命令自动回答所有确认提示
+        yes 2>/dev/null | (cd "$install_dir" && "$uninstall_script") || true
+        log_info "$component_name: 卸载完成"
+    fi
+    
+    # 执行安装脚本
+    local install_script="$install_dir/install.sh"
+    if [[ ! -f "$install_script" ]]; then
+        log_error "$component_name: 安装脚本不存在: $install_script"
+        return 1
+    fi
+    
+    chmod +x "$install_script" 2>/dev/null || true
+    log_info "$component_name: 执行安装脚本..."
+    
+    # 使用 yes 命令自动回答所有确认提示，传递 SCRIPT_DIR 作为参数
+    yes 2>/dev/null | (cd "$install_dir" && "$install_script" "$SCRIPT_DIR") || true
+    
+    log_info "$component_name: 安装脚本执行完成"
+    return 0
+}
+
+# 查找组件进程 PID
+find_component_pid() {
+    local component_name="$1"
+    local component_pid=""
+    
+    case "$component_name" in
+        "node-exporter")
+            component_pid=$(pgrep -f "node_exporter" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(pgrep -f "node-exporter" | head -1)
+            fi
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "node_exporter" | awk '{print $2}' | head -1)
+            fi
+            ;;
+        "dcgm-exporter")
+            component_pid=$(pgrep -f "dcgm-exporter" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(pgrep -f "dcgm_exporter" | head -1)
+            fi
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "dcgm-exporter" | awk '{print $2}' | head -1)
+            fi
+            ;;
+        "fluent-bit")
+            component_pid=$(pgrep -f "fluent-bit" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(pgrep -f "fluent_bit" | head -1)
+            fi
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "fluent-bit" | awk '{print $2}' | head -1)
+            fi
+            ;;
+        "argus-agent")
+            component_pid=$(pgrep -f "argus-agent" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "argus-agent" | awk '{print $2}' | head -1)
+            fi
+            ;;
+    esac
+    
+    echo "$component_pid"
+}
+
+# 更新安装记录文件中的 PID
+update_install_record_pid() {
+    local component_name="$1"
+    local new_pid="$2"
+    
+    if [[ ! -f "$INSTALL_RECORD_FILE" ]]; then
+        log_error "安装记录文件不存在: $INSTALL_RECORD_FILE"
+        return 1
+    fi
+    
+    # 读取当前 PID
+    local current_pid=""
+    if command -v jq &> /dev/null; then
+        current_pid=$(jq -r --arg comp "$component_name" '.components[$comp].pid // ""' "$INSTALL_RECORD_FILE" 2>/dev/null)
+    fi
+    
+    if [[ -z "$current_pid" ]]; then
+        log_warning "$component_name: 无法读取当前 PID，跳过更新"
+        return 1
+    fi
+    
+    # 使用 sed 精确替换 PID，保持原有格式不变
+    # 只替换指定组件块中的 pid 字段
+    local temp_file="${INSTALL_RECORD_FILE}.tmp"
+    local in_component=0
+    local updated=0
+    
+    while IFS= read -r line; do
+        if [[ "$line" =~ \"$component_name\":[[:space:]]*\{ ]]; then
+            in_component=1
+            echo "$line"
+        elif [[ $in_component -eq 1 && "$line" =~ \"pid\":[[:space:]]*\"$current_pid\" ]]; then
+            echo "$line" | sed "s/\"pid\": \"$current_pid\"/\"pid\": \"$new_pid\"/"
+            updated=1
+            in_component=0
+        else
+            echo "$line"
+            if [[ "$line" =~ ^[[:space:]]*\}[[:space:]]*$ ]]; then
+                in_component=0
+            fi
+        fi
+    done < "$INSTALL_RECORD_FILE" > "$temp_file"
+    
+    # 验证替换是否成功
+    if [[ $updated -eq 1 ]]; then
+        mv "$temp_file" "$INSTALL_RECORD_FILE"
+        log_success "$component_name: PID 已更新为 $new_pid（原值: $current_pid）"
+        return 0
+    else
+        log_error "$component_name: PID 替换失败"
+        rm -f "$temp_file"
+        return 1
+    fi
+}
+
+# 从安装记录文件中读取组件信息
+read_install_record() {
+    local install_record_file="$1"
+
+    if [[ ! -f "$install_record_file" ]]; then
+        log_error "安装记录文件不存在: $install_record_file"
+        return 1
+    fi
+
+    # 检查是否有 jq 命令来解析 JSON
+    if command -v jq &> /dev/null; then
+        # 使用 jq 解析 JSON
+        local components_json
+        if components_json=$(jq -r '.components | to_entries[] | "\(.key):\(.value.install_dir)"' "$install_record_file" 2>/dev/null); then
+            echo "$components_json"
+            return 0
+        else
+            log_error "无法解析安装记录文件 JSON 格式: $install_record_file"
+            return 1
+        fi
+    else
+        # 如果没有 jq，尝试简单的文本解析
+        log_warning "jq 命令不可用，尝试简单文本解析"
+
+        # 查找所有 install_dir 行
+        local components=()
+        while IFS= read -r line; do
+            if [[ "$line" =~ \"install_dir\":[[:space:]]*\"([^\"]+)\" ]]; then
+                local install_dir="${BASH_REMATCH[1]}"
+                # 从路径中提取组件名称
+                local component_name=$(basename "$install_dir")
+                components+=("$component_name:$install_dir")
+            fi
+        done < "$install_record_file"
+
+        if [[ ${#components[@]} -gt 0 ]]; then
+            printf '%s\n' "${components[@]}"
+            return 0
+        else
+            log_error "无法从安装记录文件中提取组件信息"
+            return 1
+        fi
+    fi
+}
+
+# 主函数
+main() {
+    log_info "=========================================="
+    log_info "    组件自动重启检查"
+    log_info "=========================================="
+
+    # 检查是否是root用户
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        exit 1
+    fi
+
+    # 加载配置文件
+    load_config
+
+    # 从安装记录文件中读取组件信息
+    log_info "从安装记录文件读取组件信息: $INSTALL_RECORD_FILE"
+    local components_info
+    if ! components_info=$(read_install_record "$INSTALL_RECORD_FILE"); then
+        log_error "无法读取安装记录文件，自动重启检查终止"
+        exit 1
+    fi
+
+    local restart_count=0
+    local check_count=0
+
+    # 逐个检查组件
+    while IFS= read -r component_info; do
+        if [[ -n "$component_info" ]]; then
+            IFS=':' read -r component_name install_dir <<< "$component_info"
+            check_count=$((check_count + 1))
+            
+            local check_script_path="$install_dir/check_health.sh"
+
+            log_info "检查组件: $component_name"
+            
+            # 检查健康状态
+            if check_component_health "$component_name" "$check_script_path"; then
+                log_success "$component_name: 运行正常"
+            else
+                log_warning "$component_name: 健康检查失败，尝试重启"
+                restart_count=$((restart_count + 1))
+                
+                # 执行重启
+                restart_component "$component_name" "$install_dir"
+                
+                # 等待服务启动
+                log_info "$component_name: 等待进程启动..."
+                sleep 10
+                
+                # 查找新的进程 PID
+                local new_pid=$(find_component_pid "$component_name")
+                if [[ -n "$new_pid" ]]; then
+                    log_info "$component_name: 找到新进程 PID: $new_pid"
+                    update_install_record_pid "$component_name" "$new_pid"
+                else
+                    log_warning "$component_name: 未找到新进程 PID"
+                fi
+                
+                # 再次检查健康状态
+                if check_component_health "$component_name" "$check_script_path"; then
+                    log_success "$component_name: 重启成功"
+                else
+                    log_warning "$component_name: 重启后仍不健康，可能需要手动检查"
+                fi
+            fi
+        fi
+    done <<< "$components_info"
+
+    log_info "=========================================="
+    log_info "检查完成: 共检查 $check_count 个组件，尝试重启 $restart_count 个"
+    log_info "=========================================="
+
+    exit 0
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi
+

src/metric/client-plugins/all-in-one-full/scripts/setup.sh

@@ -0,0 +1,931 @@
+#!/bin/bash
+
+set -e
+
+# 加载配置文件（仅在解压后的目录中可用）
+load_config() {
+    # setup.sh 脚本不需要配置文件，FTP参数通过命令行参数或环境变量提供
+    log_info "setup.sh 脚本使用命令行参数或环境变量获取FTP配置"
+}
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+FTP_SERVER="${FTP_SERVER}"
+FTP_USER="${FTP_USER}"
+FTP_PASS="${FTP_PASS}"
+FTP_PORT="${FTP_PORT:-21}"
+BASE_URL=""                                  # FTP基础URL (将在check_ftp_params中设置)
+LATEST_VERSION_URL=""                        # 版本文件URL (将在check_ftp_params中设置)
+TEMP_DIR="/tmp/argus-metric-install-$$"
+
+# 安装目录配置
+DEFAULT_INSTALL_DIR="/opt/argus-metric"      # 默认安装目录
+INSTALL_DIR="${INSTALL_DIR:-$DEFAULT_INSTALL_DIR}"  # 可通过环境变量覆盖
+VERSIONS_DIR="$INSTALL_DIR/versions"         # 版本目录
+BACKUPS_DIR="$INSTALL_DIR/backups"           # 备份目录
+CURRENT_LINK="$INSTALL_DIR/current"          # 当前版本软链接
+LATEST_VERSION_FILE="$INSTALL_DIR/LATEST_VERSION"  # 当前版本记录文件
+
+# 检查必需的FTP参数
+check_ftp_params() {
+    local missing_params=()
+    
+    if [[ -z "$FTP_SERVER" ]]; then
+        missing_params+=("FTP_SERVER")
+    fi
+    
+    if [[ -z "$FTP_USER" ]]; then
+        missing_params+=("FTP_USER")
+    fi
+    
+    if [[ -z "$FTP_PASS" ]]; then
+        missing_params+=("FTP_PASS")
+    fi
+    
+    if [[ ${#missing_params[@]} -gt 0 ]]; then
+        log_error "缺少必需的FTP参数: ${missing_params[*]}"
+        log_error "请通过以下方式之一设置FTP参数:"
+        log_error "  1. 命令行参数: --server <地址> --user <用户名> --password <密码>"
+        log_error "  2. 环境变量: FTP_SERVER=<地址> FTP_USER=<用户名> FTP_PASS=<密码>"
+        log_error ""
+        log_error "示例:"
+        log_error "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234"
+        log_error "  FTP_SERVER=10.211.55.4 FTP_USER=ftpuser FTP_PASS=admin1234 sudo sh setup.sh"
+        exit 1
+    fi
+    
+    # 设置BASE_URL和LATEST_VERSION_URL
+    BASE_URL="ftp://${FTP_SERVER}:${FTP_PORT}"
+    LATEST_VERSION_URL="$BASE_URL/LATEST_VERSION"
+    
+    log_info "FTP配置:"
+    log_info "  服务器: $FTP_SERVER:$FTP_PORT"
+    log_info "  用户: $FTP_USER"
+}
+
+# 获取最新版本号的函数
+get_latest_version() {
+    log_info "获取最新版本信息..." >&2
+    log_info "尝试从URL获取: $LATEST_VERSION_URL" >&2
+    
+    # 先测试FTP连接
+    log_info "测试FTP连接..." >&2
+    if ! curl -u "${FTP_USER}:${FTP_PASS}" -sfI "$LATEST_VERSION_URL" >/dev/null 2>&1; then
+        log_error "无法连接到FTP服务器或文件不存在" >&2
+        log_error "URL: $LATEST_VERSION_URL" >&2
+        log_error "请检查:" >&2
+        log_error "  1. FTP服务器是否运行: $FTP_SERVER:$FTP_PORT" >&2
+        log_error "  2. 用户名密码是否正确: $FTP_USER" >&2
+        log_error "  3. LATEST_VERSION文件是否存在" >&2
+        log_error "手动测试命令: curl -u ${FTP_USER}:${FTP_PASS} ftp://${FTP_SERVER}/LATEST_VERSION" >&2
+        exit 1
+    fi
+    
+    # 获取文件内容
+    if ! LATEST_VERSION=$(curl -u "${FTP_USER}:${FTP_PASS}" -sfL "$LATEST_VERSION_URL" 2>/dev/null | tr -d '[:space:]'); then
+        log_error "下载LATEST_VERSION文件失败" >&2
+        exit 1
+    fi
+    
+    log_info "原始获取内容: '$LATEST_VERSION'" >&2
+    
+    if [[ -z "$LATEST_VERSION" ]]; then
+        log_error "获取到的版本信息为空" >&2
+        log_error "可能的原因:" >&2
+        log_error "  1. LATEST_VERSION文件为空" >&2
+        log_error "  2. 文件内容格式不正确" >&2
+        log_error "  3. 网络传输问题" >&2
+        log_error "请检查FTP服务器上的 /srv/ftp/share/LATEST_VERSION 文件" >&2
+        exit 1
+    fi
+    
+    log_info "检测到最新版本: $LATEST_VERSION" >&2
+    echo "$LATEST_VERSION"
+}
+
+# 解析参数
+ARGUS_VERSION=""  # 使用不同的变量名避免与系统VERSION冲突
+ACTION="install"
+FORCE_INSTALL=false
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --version)
+            ARGUS_VERSION="$2"
+            shift 2
+            ;;
+        --server)
+            FTP_SERVER="$2"
+            shift 2
+            ;;
+        --user)
+            FTP_USER="$2"
+            shift 2
+            ;;
+        --password)
+            FTP_PASS="$2"
+            shift 2
+            ;;
+        --port)
+            FTP_PORT="$2"
+            shift 2
+            ;;
+        --uninstall)
+            ACTION="uninstall"
+            shift
+            ;;
+        --install-dir)
+            INSTALL_DIR="$2"
+            shift 2
+            ;;
+        # 简化安装逻辑：不再支持回滚和备份列表功能
+        # --rollback)
+        #     ACTION="rollback"
+        #     shift
+        #     ;;
+        # --backup-list)
+        #     ACTION="backup-list"
+        #     shift
+        #     ;;
+        --status)
+            ACTION="status"
+            shift
+            ;;
+        --force)
+            FORCE_INSTALL=true
+            shift
+            ;;
+        --help)
+            echo "Argus Metric FTP在线安装脚本"
+            echo
+            echo "用法: curl -u <用户名>:<密码> ftp://<服务器>/setup.sh -o setup.sh && sh setup.sh [选项]"
+            echo
+            echo "必需参数 (必须通过命令行参数或环境变量设置):"
+            echo "  --server SERVER       FTP服务器地址 (必须)"
+            echo "  --user USER           FTP用户名 (必须)"
+            echo "  --password PASS       FTP密码 (必须)"
+            echo
+            echo "可选参数:"
+            echo "  --version VERSION     指定版本 (默认: 自动获取最新版本)"
+            echo "  --port PORT           FTP端口 (默认: 21)"
+            echo "  --install-dir DIR     安装目录 (默认: /opt/argus-metric)"
+            echo "  --force               强制重新安装 (即使相同版本)"
+            echo "  --uninstall           卸载 (自动确认)"
+            # echo "  --rollback            回滚到上一个备份版本"
+            # echo "  --backup-list         列出所有备份版本"
+            echo "  --status              显示当前安装状态"
+            echo "  --help                显示帮助"
+            echo
+            echo "环境变量:"
+            echo "  FTP_SERVER            FTP服务器地址 (必须)"
+            echo "  FTP_USER              FTP用户名 (必须)"
+            echo "  FTP_PASS              FTP密码 (必须)"
+            echo "  FTP_PORT              FTP端口 (默认: 21)"
+            echo
+            echo "示例:"
+            echo "  # 方式1: 使用命令行参数"
+            echo "  curl -u ftpuser:admin1234 ftp://10.211.55.4/setup.sh -o setup.sh"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234"
+            echo "  "
+            echo "  # 方式2: 使用环境变量"
+            echo "  FTP_SERVER=10.211.55.4 FTP_USER=ftpuser FTP_PASS=admin1234 sudo sh setup.sh"
+            echo "  "
+            echo "  # 指定版本安装"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234 --version 1.30.0"
+            echo "  "
+            echo "  # 强制重新安装"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234 --force"
+            echo "  "
+            echo "  # 卸载"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234 --uninstall"
+            exit 0
+            ;;
+        *)
+            log_error "未知参数: $1"
+            echo "使用 --help 查看帮助信息"
+            exit 1
+            ;;
+    esac
+done
+
+# 清理函数
+cleanup() {
+    if [[ -d "$TEMP_DIR" ]]; then
+        rm -rf "$TEMP_DIR"
+    fi
+}
+
+trap cleanup EXIT
+
+# 创建安装目录结构
+create_install_directories() {
+    log_info "创建安装目录结构..."
+    
+    # 创建主要目录
+    mkdir -p "$VERSIONS_DIR"
+    mkdir -p "$BACKUPS_DIR"
+    
+    log_success "安装目录结构创建完成: $INSTALL_DIR"
+}
+
+# 获取当前安装的版本
+get_current_version() {
+    # 优先从LATEST_VERSION文件读取
+    if [[ -f "$LATEST_VERSION_FILE" ]]; then
+        local version_from_file=$(cat "$LATEST_VERSION_FILE" 2>/dev/null | tr -d '[:space:]')
+        if [[ -n "$version_from_file" ]]; then
+            # 确保版本号格式一致（不带v前缀）
+            echo "$version_from_file"
+            return 0
+        fi
+    fi
+    
+    # 如果文件不存在或为空，从软链接读取
+    if [[ -L "$CURRENT_LINK" ]]; then
+        local current_path=$(readlink "$CURRENT_LINK")
+        # 从版本目录名中提取版本号（现在不带v前缀）
+        basename "$current_path"
+    else
+        echo ""
+    fi
+}
+
+# 检查是否已安装
+check_installed() {
+    if [[ -L "$CURRENT_LINK" ]] && [[ -d "$CURRENT_LINK" ]]; then
+        local current_version=$(get_current_version)
+        if [[ -n "$current_version" ]]; then
+            log_info "检测到已安装版本: v$current_version"
+            return 0
+        fi
+    fi
+    return 1
+}
+
+# 更新LATEST_VERSION文件
+update_latest_version_file() {
+    local version="$1"
+    log_info "更新LATEST_VERSION文件: $version"
+    
+    if echo "$version" > "$LATEST_VERSION_FILE"; then
+        log_success "LATEST_VERSION文件已更新"
+    else
+        log_error "更新LATEST_VERSION文件失败"
+        return 1
+    fi
+}
+
+# 初始化 DNS 配置文件到系统目录
+init_dns_config_to_system() {
+    log_info "初始化 DNS 配置文件到系统目录..."
+    
+    # 系统 DNS 配置文件
+    local system_dns_conf="$INSTALL_DIR/dns.conf"
+    
+    # 如果系统目录中还没有 dns.conf，创建一个空的占位文件
+    if [[ ! -f "$system_dns_conf" ]]; then
+        touch "$system_dns_conf"
+        chmod 644 "$system_dns_conf"
+        log_success "DNS 配置文件占位文件已创建: $system_dns_conf"
+        log_info "DNS 同步脚本将从 FTP 服务器下载实际的 DNS 配置"
+    else
+        log_info "DNS 配置文件已存在: $system_dns_conf"
+    fi
+}
+
+# 备份当前版本
+backup_current_version() {
+    local current_version=$(get_current_version)
+    if [[ -z "$current_version" ]]; then
+        log_info "没有当前版本需要备份"
+        return 0
+    fi
+    
+    # 确保备份目录存在
+    mkdir -p "$BACKUPS_DIR"
+    
+    local backup_name="$current_version"
+    local backup_path="$BACKUPS_DIR/$backup_name"
+    
+    log_info "备份当前版本 $current_version 到: $backup_path"
+    
+    # 如果备份已存在，先删除
+    if [[ -d "$backup_path" ]]; then
+        log_info "备份版本已存在，覆盖: $backup_path"
+        rm -rf "$backup_path"
+    fi
+    
+    # 复制当前版本目录（跟随软链接复制实际内容）
+    if cp -rL "$CURRENT_LINK" "$backup_path"; then
+        log_success "版本备份完成: $backup_name"
+
+    else
+        log_error "版本备份失败"
+        exit 1
+    fi
+}
+
+# 回滚到备份版本
+rollback_to_backup() {
+    local backup_name="$1"
+    
+    # 确保备份目录存在
+    mkdir -p "$BACKUPS_DIR"
+    
+    local backup_path="$BACKUPS_DIR/$backup_name"
+    
+    if [[ ! -d "$backup_path" ]]; then
+        log_error "备份不存在: $backup_path"
+        return 1
+    fi
+    
+    log_info "回滚到备份版本: $backup_name"
+    
+    # 停止当前服务
+    stop_services
+    
+    # 检查是否存在对应的版本目录
+    local version_dir="$VERSIONS_DIR/$backup_name"
+    
+    if [[ ! -d "$version_dir" ]]; then
+        log_info "版本目录不存在，从备份恢复版本目录: $version_dir"
+        # 从备份目录恢复到版本目录
+        mkdir -p "$VERSIONS_DIR"
+        cp -r "$backup_path" "$version_dir"
+    fi
+    
+    # 恢复软链接指向版本目录
+    if ln -sfn "$version_dir" "$CURRENT_LINK"; then
+        log_success "版本回滚完成: $backup_name"
+        
+        # 更新LATEST_VERSION文件
+        update_latest_version_file "$backup_name"
+        
+        return 0
+    else
+        log_error "版本回滚失败"
+        return 1
+    fi
+}
+
+# 停止服务
+stop_services() {
+    log_info "停止当前服务..."
+    
+    # 检查服务是否正在运行
+    if ! check_services_running; then
+        log_info "服务未运行，无需停止"
+        return 0
+    fi
+    
+    # 尝试使用卸载脚本停止服务
+    if [[ -f "$CURRENT_LINK/uninstall.sh" ]]; then
+        cd "$CURRENT_LINK"
+        chmod +x uninstall.sh
+        
+        # 自动确认停止服务（避免交互式确认）
+        echo "y" | ./uninstall.sh >/dev/null 2>&1
+        local stop_exit_code=$?
+        
+        if [[ $stop_exit_code -eq 0 ]]; then
+            log_success "服务停止完成"
+        else
+            log_warning "停止服务时出现警告，尝试手动停止"
+            manual_stop_services
+        fi
+    else
+        log_warning "未找到卸载脚本，尝试手动停止服务"
+        manual_stop_services
+    fi
+}
+
+# 手动停止服务
+manual_stop_services() {
+    log_info "手动停止服务..."
+    
+    # 停止 node_exporter
+    if pgrep -f "node_exporter" >/dev/null 2>&1; then
+        pkill -f "node_exporter" && log_info "node_exporter 已停止"
+    fi
+    
+    # 停止 dcgm_exporter
+    if pgrep -f "dcgm_exporter" >/dev/null 2>&1; then
+        pkill -f "dcgm_exporter" && log_info "dcgm_exporter 已停止"
+    fi
+    
+    # 等待进程完全停止
+    sleep 2
+    
+    # 检查是否还有残留进程
+    if pgrep -f "node_exporter\|dcgm_exporter" >/dev/null 2>&1; then
+        log_warning "仍有服务进程运行，尝试强制停止"
+        pkill -9 -f "node_exporter\|dcgm_exporter" 2>/dev/null || true
+    fi
+    
+    log_success "手动停止服务完成"
+}
+
+# 启动服务
+start_services() {
+    log_info "启动服务..."
+    
+    # 检查服务是否已经在运行
+    if check_services_running; then
+        log_info "服务已在运行，跳过启动"
+        return 0
+    fi
+    
+    # 由于 install_artifact.sh 已经安装了所有组件并设置了健康检查定时任务
+    # 这里只需要简单验证服务状态即可
+    log_info "组件已安装完成，健康检查定时任务已设置"
+    log_info "服务将在健康检查时自动启动（每5分钟检查一次）"
+    
+    # 等待一下让服务有时间启动
+    sleep 3
+    
+    # 验证服务状态
+    if check_services_running; then
+        log_success "服务启动成功"
+    else
+        log_info "服务可能正在启动中，健康检查机制将自动监控"
+    fi
+    
+    return 0
+}
+
+# 检查服务是否正在运行
+check_services_running() {
+    # 检查常见的服务端口是否在监听
+    local ports=(9100 9400)  # node-exporter 和 dcgm-exporter 的默认端口
+    
+    for port in "${ports[@]}"; do
+        if netstat -tlnp 2>/dev/null | grep -q ":$port "; then
+            log_info "检测到服务正在端口 $port 上运行"
+            return 0
+        fi
+    done
+    
+    # 检查相关进程
+    if pgrep -f "node_exporter\|dcgm_exporter" >/dev/null 2>&1; then
+        log_info "检测到相关服务进程正在运行"
+        return 0
+    fi
+    
+    return 1
+}
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo sh setup.sh"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    # 读取系统信息，使用子shell避免污染当前环境变量
+    local OS_INFO=$(source /etc/os-release && echo "$NAME $VERSION_ID")
+    log_info "检测到操作系统: $OS_INFO"
+    
+    # 检查系统架构
+    arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    # 检查磁盘空间
+    available_space=$(df / | awk 'NR==2 {print $4}')
+    if [[ $available_space -lt 1024 ]]; then
+        log_warning "可用磁盘空间不足 1GB，当前可用: $(($available_space / 1024 / 1024))GB"
+    fi
+}
+
+# 下载并安装
+install_argus_metric() {
+    # 如果没有指定版本，获取最新版本
+    if [[ -z "$ARGUS_VERSION" ]]; then
+        ARGUS_VERSION=$(get_latest_version)
+    fi
+    
+    log_info "开始安装 Argus Metric v$ARGUS_VERSION..."
+    log_info "安装目录: $INSTALL_DIR"
+    
+    # 创建安装目录结构（必须先创建，以便备份时目录存在）
+    create_install_directories
+    
+    # 检查是否已安装
+    local is_upgrade=false
+    if check_installed; then
+        local current_version=$(get_current_version)
+        if [[ "$current_version" == "$ARGUS_VERSION" ]]; then
+            if [[ "$FORCE_INSTALL" == true ]]; then
+                log_info "检测到相同版本 v$ARGUS_VERSION，但使用了 --force 参数，将强制重新安装"
+                is_upgrade=true
+                # 简化安装逻辑：不再备份当前版本
+                # backup_current_version
+            else
+                log_info "版本 v$ARGUS_VERSION 已安装，无需重复安装"
+                log_info "如需强制重新安装，请使用 --force 参数"
+                return 0
+            fi
+        else
+            log_info "检测到版本升级: v$current_version -> v$ARGUS_VERSION"
+            is_upgrade=true
+            
+            # 简化安装逻辑：不再备份当前版本
+            # backup_current_version
+        fi
+    fi
+    
+    # 创建临时目录
+    mkdir -p "$TEMP_DIR"
+    cd "$TEMP_DIR"
+    
+    # 下载发布包，使用新的命名规范
+    TAR_NAME="argus-metric_$(echo $ARGUS_VERSION | tr '.' '_').tar.gz"
+    log_info "下载发布包: $TAR_NAME"
+    log_info "从FTP服务器下载: $FTP_SERVER:$FTP_PORT, 用户: $FTP_USER"
+    
+    # 构造curl命令并显示（隐藏密码）
+    CURL_CMD="curl -u \"${FTP_USER}:***\" -sfL \"$BASE_URL/$TAR_NAME\" -o \"$TAR_NAME\""
+    log_info "执行命令: $CURL_CMD"
+    
+    if ! curl -u "${FTP_USER}:${FTP_PASS}" -sfL "$BASE_URL/$TAR_NAME" -o "$TAR_NAME"; then
+        log_error "下载发布包失败: $BASE_URL/$TAR_NAME"
+        log_error "完整命令: curl -u \"${FTP_USER}:${FTP_PASS}\" -sfL \"$BASE_URL/$TAR_NAME\" -o \"$TAR_NAME\""
+        log_error "请检查FTP服务器连接、用户名密码是否正确"
+        exit 1
+    fi
+    
+    # 解压发布包到当前目录
+    log_info "解压发布包..."
+    if ! tar -xzf "$TAR_NAME"; then
+        log_error "解压发布包失败"
+        exit 1
+    fi
+    
+    # 显示解压后的文件结构
+    log_info "解压后的文件结构:"
+    ls -la "$TEMP_DIR"
+    
+    # 准备版本目录
+    local version_dir="$VERSIONS_DIR/$ARGUS_VERSION"
+    log_info "安装到版本目录: $version_dir"
+    
+    # 如果升级，先停止服务
+    if [[ "$is_upgrade" == true ]]; then
+        stop_services
+    fi
+    
+    # 创建版本目录
+    if [[ -d "$version_dir" ]]; then
+        log_info "版本目录已存在，备份后更新"
+        rm -rf "$version_dir"
+    fi
+    
+    # 创建新的版本目录
+    mkdir -p "$version_dir"
+    
+    # 移动解压的文件到版本目录
+    log_info "移动文件到版本目录: $TEMP_DIR/* -> $version_dir/"
+    
+    # 检查源目录是否有内容
+    if [[ ! "$(ls -A "$TEMP_DIR" 2>/dev/null)" ]]; then
+        log_error "临时目录为空，无法移动文件"
+        exit 1
+    fi
+    
+    # 检查目标目录是否存在
+    if [[ ! -d "$version_dir" ]]; then
+        log_error "目标版本目录不存在: $version_dir"
+        exit 1
+    fi
+    
+    # 执行文件移动
+    if mv "$TEMP_DIR"/* "$version_dir" 2>/dev/null; then
+        log_success "文件移动到版本目录完成"
+    else
+        log_error "移动文件到版本目录失败"
+        log_error "源目录内容:"
+        ls -la "$TEMP_DIR" || true
+        log_error "目标目录状态:"
+        ls -la "$version_dir" || true
+        log_error "权限检查:"
+        ls -ld "$TEMP_DIR" "$version_dir" || true
+        exit 1
+    fi
+    
+    # 执行安装脚本
+    log_info "执行安装脚本..."
+    cd "$version_dir"
+    if [[ -f "install.sh" ]]; then
+        chmod +x install.sh
+        # 传递安装根目录给安装脚本，让install_artifact.sh安装到正确的版本目录
+        if ./install.sh "$version_dir"; then
+            log_success "安装脚本执行完成"
+        else
+            log_error "安装脚本执行失败"
+            # 简化安装逻辑：不再自动回滚
+            # if [[ "$is_upgrade" == true ]]; then
+            #     log_warning "升级失败，尝试回滚到之前版本..."
+            #     # 确保备份目录存在
+            #     mkdir -p "$BACKUPS_DIR"
+            #     local latest_backup=$(ls -1t "$BACKUPS_DIR" 2>/dev/null | head -n 1)
+            #     if [[ -n "$latest_backup" ]]; then
+            #         rollback_to_backup "$latest_backup"
+            #         return 1
+            #     fi
+            # fi
+            exit 1
+        fi
+    else
+        log_error "未找到安装脚本 install.sh"
+        exit 1
+    fi
+    
+    # 更新软链接指向新版本
+    log_info "更新当前版本链接..."
+    
+    # 如果 current 已经存在且是目录，先删除它
+    if [[ -d "$CURRENT_LINK" ]] && [[ ! -L "$CURRENT_LINK" ]]; then
+        log_warning "发现 current 是目录而不是符号链接，正在删除..."
+        rm -rf "$CURRENT_LINK"
+    fi
+    
+    if ln -sfn "$version_dir" "$CURRENT_LINK"; then
+        log_success "版本链接更新完成: $CURRENT_LINK -> $version_dir"
+    else
+        log_error "版本链接更新失败"
+        exit 1
+    fi
+    
+    # 更新LATEST_VERSION文件
+    update_latest_version_file "$ARGUS_VERSION"
+    
+    # 初始化 DNS 配置文件到系统目录
+    init_dns_config_to_system
+    
+    # 启动服务
+    # start_services
+    
+    log_success "Argus Metric v$ARGUS_VERSION 安装完成！"
+    
+    # 显示安装信息
+    echo
+    log_info "安装信息:"
+    log_info "  版本: $ARGUS_VERSION"
+    log_info "  安装目录: $INSTALL_DIR"
+    log_info "  版本目录: $version_dir"
+    log_info "  当前链接: $CURRENT_LINK"
+    if [[ "$is_upgrade" == true ]]; then
+        log_info "  升级类型: 版本升级"
+    else
+        log_info "  安装类型: 全新安装"
+    fi
+}
+
+# 卸载
+uninstall_argus_metric() {
+    log_info "开始卸载 Argus Metric..."
+    log_info "安装目录: $INSTALL_DIR"
+    
+    # 检查是否已安装
+    if ! check_installed; then
+        log_info "未检测到已安装的 Argus Metric"
+        return 0
+    fi
+    
+    local current_version=$(get_current_version)
+    log_info "检测到当前版本: v$current_version"
+    
+    # 停止服务
+    stop_services
+    
+    # 执行卸载脚本
+    log_info "执行卸载脚本..."
+    if [[ -f "$CURRENT_LINK/uninstall.sh" ]]; then
+        cd "$CURRENT_LINK"
+        chmod +x uninstall.sh
+        
+        # 自动确认卸载（因为用户已经明确使用了 --uninstall 参数）
+        log_info "自动确认卸载操作..."
+        echo "y" | ./uninstall.sh
+        local uninstall_exit_code=$?
+        
+        if [[ $uninstall_exit_code -eq 0 ]]; then
+            log_success "卸载脚本执行完成"
+        else
+            log_error "卸载脚本执行失败 (退出码: $uninstall_exit_code)"
+            exit 1
+        fi
+    else
+        log_warning "未找到卸载脚本，执行基本清理"
+    fi
+    
+    # 清理安装目录
+    log_info "清理安装目录..."
+    if [[ -d "$INSTALL_DIR" ]]; then
+        # 询问是否完全删除安装目录
+        log_warning "这将删除整个安装目录: $INSTALL_DIR"
+        log_warning "包括所有版本、备份和配置文件"
+        
+        # 在自动化环境中，直接删除
+        if rm -rf "$INSTALL_DIR"; then
+            log_success "安装目录已完全清理: $INSTALL_DIR"
+        else
+            log_error "清理安装目录失败"
+            exit 1
+        fi
+    else
+        log_info "安装目录不存在，无需清理"
+    fi
+    
+    log_success "Argus Metric 卸载完成！"
+}
+
+# 显示状态
+show_status() {
+    echo "=========================================="
+    echo "    Argus Metric 安装状态"
+    echo "=========================================="
+    echo
+    
+    if check_installed; then
+        local current_version=$(get_current_version)
+        log_info "当前版本: $current_version"
+        log_info "安装目录: $INSTALL_DIR"
+        log_info "当前链接: $CURRENT_LINK"
+        log_info "版本目录: $VERSIONS_DIR/$current_version"
+        log_info "版本文件: $LATEST_VERSION_FILE"
+        
+        # 显示LATEST_VERSION文件内容
+        if [[ -f "$LATEST_VERSION_FILE" ]]; then
+            local file_version=$(cat "$LATEST_VERSION_FILE" 2>/dev/null | tr -d '[:space:]')
+            log_info "版本文件内容: $file_version"
+        fi
+        
+        echo
+        log_info "目录结构:"
+        if [[ -d "$INSTALL_DIR" ]]; then
+            tree -L 2 "$INSTALL_DIR" 2>/dev/null || ls -la "$INSTALL_DIR"
+        fi
+        
+        echo
+        log_info "可用版本:"
+        if [[ -d "$VERSIONS_DIR" ]]; then
+            ls -1 "$VERSIONS_DIR" 2>/dev/null | sed 's/^/  - /'
+        else
+            echo "  无"
+        fi
+        
+        # 简化安装逻辑：不再显示备份版本信息
+        # echo
+        # log_info "备份版本:"
+        # if [[ -d "$BACKUPS_DIR" ]] && [[ $(ls -1 "$BACKUPS_DIR" 2>/dev/null | wc -l) -gt 0 ]]; then
+        #     ls -1t "$BACKUPS_DIR" 2>/dev/null | sed 's/^/  - /'
+        # else
+        #     echo "  无"
+        # fi
+    else
+        log_warning "Argus Metric 未安装"
+        log_info "安装目录: $INSTALL_DIR"
+    fi
+}
+
+# 列出备份
+list_backups() {
+    echo "=========================================="
+    echo "    Argus Metric 备份列表"
+    echo "=========================================="
+    echo
+    
+    if [[ -d "$BACKUPS_DIR" ]] && [[ $(ls -1 "$BACKUPS_DIR" 2>/dev/null | wc -l) -gt 0 ]]; then
+        log_info "可用备份版本:"
+        ls -1t "$BACKUPS_DIR" 2>/dev/null | while read backup; do
+            local backup_time=$(stat -c %y "$BACKUPS_DIR/$backup" 2>/dev/null | cut -d' ' -f1-2)
+            echo "  - $backup (创建时间: $backup_time)"
+        done
+    else
+        log_warning "没有可用的备份版本"
+    fi
+}
+
+# 回滚功能
+rollback_version() {
+    log_info "开始回滚操作..."
+    
+    if ! check_installed; then
+        log_error "没有检测到已安装的版本，无法回滚"
+        exit 1
+    fi
+    
+    # 确保备份目录存在
+    mkdir -p "$BACKUPS_DIR"
+    
+    # 获取最新的备份
+    local latest_backup=$(ls -1t "$BACKUPS_DIR" 2>/dev/null | head -n 1)
+    if [[ -z "$latest_backup" ]]; then
+        log_error "没有找到可用的备份版本"
+        exit 1
+    fi
+    
+    log_info "将回滚到备份版本: $latest_backup"
+    
+    if rollback_to_backup "$latest_backup"; then
+        log_success "回滚完成！"
+        
+        # 显示当前状态
+        echo
+        show_status
+    else
+        log_error "回滚失败"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus Metric 在线安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    # 加载配置文件
+    load_config
+    
+    # 对于状态操作，不需要FTP参数和root权限
+    # 简化安装逻辑：不再支持备份列表操作
+    if [[ "$ACTION" == "status" ]]; then
+        show_status
+        return 0
+    fi
+    # if [[ "$ACTION" == "status" || "$ACTION" == "backup-list" ]]; then
+    #     if [[ "$ACTION" == "status" ]]; then
+    #         show_status
+    #     elif [[ "$ACTION" == "backup-list" ]]; then
+    #         list_backups
+    #     fi
+    #     return 0
+    # fi
+    
+    check_root
+    
+    # 更新目录配置变量（在设置INSTALL_DIR后）
+    VERSIONS_DIR="$INSTALL_DIR/versions"
+    BACKUPS_DIR="$INSTALL_DIR/backups"
+    CURRENT_LINK="$INSTALL_DIR/current"
+    LATEST_VERSION_FILE="$INSTALL_DIR/LATEST_VERSION"
+    
+    # 简化安装逻辑：不再支持回滚操作
+    # if [[ "$ACTION" == "rollback" ]]; then
+    #     rollback_version
+    #     return 0
+    # fi
+    
+    check_ftp_params
+    check_system
+    
+    if [[ "$ACTION" == "uninstall" ]]; then
+        uninstall_argus_metric
+    else
+        install_argus_metric
+    fi
+    
+    echo
+    log_info "操作完成！"
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/sync_dns.sh

@@ -0,0 +1,143 @@
+#!/bin/bash
+set -e
+
+# 颜色
+RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; BLUE='\033[0;34m'; NC='\033[0m'
+
+# 日志函数
+log_info() { echo -e "${BLUE}[INFO]${NC} $1" >&2; }
+log_success() { echo -e "${GREEN}[SUCCESS]${NC} $1" >&2; }
+log_warning() { echo -e "${YELLOW}[WARNING]${NC} $1" >&2; }
+log_error() { echo -e "${RED}[ERROR]${NC} $1" >&2; }
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+LOCAL_DNS_CONF="/opt/argus-metric/dns.conf"
+RESOLV_CONF="/etc/resolv.conf"
+ALT_RESOLV_CONF="/run/resolv.conf"
+LOG_FILE="/opt/argus-metric/.dns_sync.log"
+REMOTE_DNS_CONF_URL=""
+
+# 获取 FTP 配置
+get_ftp_config() {
+    log_info "获取 FTP 配置信息..."
+    if [[ -z "$FTP_SERVER" || -z "$FTP_USER" || -z "$FTP_PASSWORD" ]]; then
+        [[ -f "$SCRIPT_DIR/config.env" ]] && source "$SCRIPT_DIR/config.env"
+    fi
+    FTP_SERVER="${FTP_SERVER:-localhost}"
+    FTP_USER="${FTP_USER:-ftpuser}"
+    FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+    REMOTE_DNS_CONF_URL="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/dns.conf"
+}
+
+# 下载远程 dns.conf
+download_remote_dns_conf() {
+    local tmp="/tmp/dns.remote.$$"
+    log_info "测试 FTP 连接..."
+    if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null; then
+        log_error "无法连接到 FTP 服务器: $FTP_SERVER"; return 1
+    fi
+    if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sf "ftp://${FTP_SERVER}/dns.conf" -o "$tmp" 2>/dev/null; then
+        log_error "下载 dns.conf 失败"; rm -f "$tmp"; return 1
+    fi
+    echo "$tmp"
+}
+
+# 文件比较
+compare_files() { diff -q "$1" "$2" >/dev/null 2>&1; }
+
+# 从 dns.conf 提取有效 IP
+get_dns_ips() {
+    grep -Eo '^[0-9]{1,3}(\.[0-9]{1,3}){3}$' "$1" | sort -u
+}
+
+# 安全更新 resolv.conf（保留符号链接）
+update_resolv_conf() {
+    local dns_conf="$1"
+    local dns_ips
+    mapfile -t dns_ips < <(get_dns_ips "$dns_conf")
+    [[ ${#dns_ips[@]} -eq 0 ]] && { log_warning "未检测到有效 DNS"; return; }
+
+    local target_file="$RESOLV_CONF"
+    if [[ ! -w "$RESOLV_CONF" ]]; then
+        log_warning "/etc/resolv.conf 不可写，使用兜底路径 $ALT_RESOLV_CONF"
+        target_file="$ALT_RESOLV_CONF"
+    fi
+
+    local temp="/tmp/resolv.new.$$"
+    cp "$target_file" "${target_file}.backup.$(date +%Y%m%d_%H%M%S)" 2>/dev/null || true
+    log_info "更新 DNS 配置文件: $target_file"
+
+    # 写入新的 nameserver 行
+    for ip in "${dns_ips[@]}"; do
+        echo "nameserver $ip"
+    done >"$temp"
+
+    # 追加原内容（去掉重复 nameserver）
+    grep -v '^nameserver' "$target_file" >>"$temp" 2>/dev/null || true
+    awk '!a[$0]++' "$temp" >"${temp}.uniq"
+
+    # ⚙️ 使用 cat 原地覆盖，避免 mv 引发 “设备忙”
+    if cat "${temp}.uniq" >"$target_file" 2>/dev/null; then
+        chmod 644 "$target_file"
+        log_success "DNS 更新完成: ${dns_ips[*]}"
+    else
+        log_error "无法写入 $target_file，可能被系统锁定"
+    fi
+
+    rm -f "$temp" "${temp}.uniq"
+}
+
+# 检查 resolv.conf 是否包含 dns.conf 内容
+ensure_dns_in_resolv() {
+    local dns_conf="$1"
+    local dns_ips
+    mapfile -t dns_ips < <(get_dns_ips "$dns_conf")
+    [[ ${#dns_ips[@]} -eq 0 ]] && return
+
+    for ip in "${dns_ips[@]}"; do
+        if ! grep -q "nameserver $ip" "$RESOLV_CONF" 2>/dev/null; then
+            log_warning "检测到 /etc/resolv.conf 缺少 $ip，执行兜底修复"
+            update_resolv_conf "$dns_conf"
+            return
+        fi
+    done
+    log_info "/etc/resolv.conf 已包含所有 DNS"
+}
+
+log_sync() { echo "[$(date '+%F %T')] $1" >>"$LOG_FILE"; }
+
+main() {
+    log_info "开始 DNS 同步检查..."
+    mkdir -p /opt/argus-metric
+
+    get_ftp_config
+    local remote_file
+    if ! remote_file=$(download_remote_dns_conf); then
+        log_error "下载失败"; log_sync "同步失败"; exit 1
+    fi
+
+    if [[ ! -f "$LOCAL_DNS_CONF" ]]; then
+        log_info "本地 dns.conf 不存在，初始化..."
+        cp "$remote_file" "$LOCAL_DNS_CONF"
+        update_resolv_conf "$LOCAL_DNS_CONF"
+        log_sync "首次同步完成"
+    else
+        if compare_files "$LOCAL_DNS_CONF" "$remote_file"; then
+            log_info "dns.conf 无变化"
+            ensure_dns_in_resolv "$LOCAL_DNS_CONF"
+            log_sync "dns.conf 无变化，执行兜底检查"
+        else
+            log_info "检测到 DNS 配置更新"
+            cp "$remote_file" "$LOCAL_DNS_CONF"
+            update_resolv_conf "$LOCAL_DNS_CONF"
+            log_sync "DNS 配置同步完成"
+        fi
+    fi
+
+    rm -f "$remote_file"
+    log_success "DNS 同步流程完成"
+}
+
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/uninstall_artifact.sh

@@ -0,0 +1,274 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 配置变量
+INSTALL_DIR="/opt/argus-metric"
+TEMP_DIR="/tmp/argus-metric-uninstall-$$"
+VERSION_FILE="version.json"
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 查找版本文件
+find_version_file() {
+    log_info "查找版本信息文件..."
+    
+    # 在当前目录查找
+    if [[ -f "$VERSION_FILE" ]]; then
+        VERSION_FILE_PATH="$VERSION_FILE"
+        log_success "找到版本文件: $VERSION_FILE"
+        return 0
+    fi
+    
+    # 在 artifact 目录查找
+    for version_dir in artifact/*/; do
+        if [[ -f "${version_dir}${VERSION_FILE}" ]]; then
+            VERSION_FILE_PATH="${version_dir}${VERSION_FILE}"
+            log_success "找到版本文件: $VERSION_FILE_PATH"
+            return 0
+        fi
+    done
+    
+    log_error "未找到版本信息文件 $VERSION_FILE"
+    log_info "请确保在正确的目录下运行此脚本"
+    exit 1
+}
+
+# 解析版本信息
+parse_version_info() {
+    log_info "解析版本信息..."
+    
+    if [[ ! -f "$VERSION_FILE_PATH" ]]; then
+        log_error "版本文件不存在: $VERSION_FILE_PATH"
+        exit 1
+    fi
+    
+    # 使用 jq 解析 JSON（如果可用）
+    if command -v jq &> /dev/null; then
+        VERSION=$(jq -r '.version' "$VERSION_FILE_PATH")
+        BUILD_TIME=$(jq -r '.build_time' "$VERSION_FILE_PATH")
+        
+        # 解析 install_order（现在包含完整的文件名）
+        if jq -e '.install_order' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.install_order[]' "$VERSION_FILE_PATH" > "$TEMP_DIR/install_order.txt"
+        else
+            log_error "version.json 中缺少 install_order 字段"
+            exit 1
+        fi
+    else
+        log_warning "jq 未安装，使用简单的 JSON 解析"
+        VERSION=$(grep '"version"' "$VERSION_FILE_PATH" | sed 's/.*"version": *"\([^"]*\)".*/\1/')
+        BUILD_TIME=$(grep '"build_time"' "$VERSION_FILE_PATH" | sed 's/.*"build_time": *"\([^"]*\)".*/\1/')
+        
+        # 解析 install_order
+        grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -E '^\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)".*/\1/')
+            echo "$component" >> "$TEMP_DIR/install_order.txt"
+        done
+    fi
+    
+    log_success "版本信息解析完成"
+    log_info "  版本: $VERSION"
+    log_info "  构建时间: $BUILD_TIME"
+}
+
+# 创建临时目录
+create_temp_dirs() {
+    log_info "创建临时目录..."
+    mkdir -p "$TEMP_DIR"
+    log_success "临时目录创建完成: $TEMP_DIR"
+}
+
+# 卸载组件
+uninstall_components() {
+    log_info "开始卸载组件..."
+    
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    uninstall_count=0
+    total_count=0
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        total_count=$(wc -l < "$TEMP_DIR/install_order.txt")
+    fi
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        while IFS= read -r filename; do
+            uninstall_count=$((uninstall_count + 1))
+            
+            # 从文件名中提取组件名（去掉时间戳后缀）
+            component=$(echo "$filename" | sed 's/-[0-9]\{8\}-[0-9]\{6\}\.tar\.gz$//')
+            
+            log_info "[$uninstall_count/$total_count] 卸载 $component..."
+            
+            # 直接使用完整的文件名
+            tar_file="$artifact_dir/$filename"
+            
+            if [[ ! -f "$tar_file" ]]; then
+                log_error "找不到组件文件: $filename"
+                exit 1
+            fi
+            
+            # 解压到临时目录
+            component_temp_dir="$TEMP_DIR/$component"
+            mkdir -p "$component_temp_dir"
+            
+            if tar -xzf "$tar_file" -C "$component_temp_dir"; then
+                log_success "  $component 解压完成"
+            else
+                log_error "  $component 解压失败"
+                exit 1
+            fi
+            
+            # 查找解压后的目录
+            extracted_dir=""
+            for dir in "$component_temp_dir"/*; do
+                if [[ -d "$dir" ]]; then
+                    extracted_dir="$dir"
+                    break
+                fi
+            done
+            
+            if [[ -z "$extracted_dir" ]]; then
+                log_error "  $component 解压后未找到目录"
+                exit 1
+            fi
+            
+            # 执行卸载脚本
+            if [[ -f "$extracted_dir/uninstall.sh" ]]; then
+                log_info "  执行 $component 卸载脚本..."
+                # 所有组件都只需要一个确认
+                if (cd "$extracted_dir" && echo "y" | ./uninstall.sh); then
+                    log_success "  $component 卸载完成"
+                else
+                    log_error "  $component 卸载失败"
+                    exit 1
+                fi
+            else
+                log_warning "  $component 缺少 uninstall.sh 文件，跳过卸载"
+            fi
+            
+            # 清理临时文件
+            rm -rf "$component_temp_dir"
+        done < "$TEMP_DIR/install_order.txt"
+    fi
+    
+    log_success "所有组件卸载完成"
+}
+
+# 清理全局文件
+cleanup_global_files() {
+    log_info "清理全局文件..."
+    
+    # 清理安装目录
+    if [[ -d "$INSTALL_DIR" ]]; then
+        rm -rf "$INSTALL_DIR"
+        log_success "安装目录已清理: $INSTALL_DIR"
+    else
+        log_info "安装目录不存在: $INSTALL_DIR"
+    fi
+    
+    # 清理可能的全局配置文件
+    local global_configs=(
+        "/etc/argus-metric"
+        "/var/log/argus-metric"
+    )
+    
+    for config in "${global_configs[@]}"; do
+        if [[ -d "$config" ]]; then
+            rm -rf "$config"
+            log_success "全局配置已清理: $config"
+        fi
+    done
+}
+
+# 显示卸载信息
+show_uninstall_info() {
+    log_success "Argus-Metrics All-in-One 卸载完成！"
+    echo
+    echo "卸载信息:"
+    echo "  版本: $VERSION"
+    echo "  构建时间: $BUILD_TIME"
+    echo
+    echo "清理内容:"
+    echo "  - 二进制文件"
+    echo "  - 配置文件"
+    echo "  - 数据目录"
+    echo "  - 进程和服务"
+    echo "  - 全局安装目录"
+    echo
+    echo "注意:"
+    echo "  - 系统依赖包可能仍然存在"
+    echo "  - 如需完全清理，请手动检查并删除相关文件"
+    echo
+}
+
+# 清理函数
+cleanup() {
+    if [[ -d "$TEMP_DIR" ]]; then
+        rm -rf "$TEMP_DIR"
+    fi
+}
+
+# 设置清理陷阱
+trap cleanup EXIT
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus-Metrics All-in-One 卸载脚本"
+    echo "=========================================="
+    echo
+    
+    check_root
+    find_version_file
+    create_temp_dirs
+    parse_version_info
+    
+    log_warning "此操作将完全卸载 Argus-Metrics All-in-One"
+    read -p "确认继续？(y/N): " confirm
+    
+    if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+        log_info "取消卸载操作"
+        exit 0
+    fi
+    
+    uninstall_components
+    cleanup_global_files
+    show_uninstall_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-full/scripts/version-manager.sh

@@ -0,0 +1,350 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "AIOps 版本管理工具"
+    echo
+    echo "用法: $0 <command> [options]"
+    echo
+    echo "命令:"
+    echo "  bump <type>     - 升级版本号 (major|minor|patch)"
+    echo "  set <version>   - 设置指定版本号"
+    echo "  show            - 显示当前版本信息"
+    echo "  list            - 列出所有版本"
+    echo "  clean           - 清理旧版本"
+    echo "  validate        - 验证版本配置"
+    echo
+    echo "示例:"
+    echo "  $0 bump minor    # 升级次版本号 1.0.0 -> 1.1.0"
+    echo "  $0 set 2.0.0     # 设置版本为 2.0.0"
+    echo "  $0 show          # 显示当前版本"
+    echo "  $0 list          # 列出所有版本"
+}
+
+# 获取当前版本
+get_current_version() {
+    if [[ -f "config/VERSION" ]]; then
+        cat config/VERSION
+    else
+        echo "0.0.0"
+    fi
+}
+
+# 设置版本号
+set_version() {
+    local new_version="$1"
+    
+    # 验证版本号格式
+    if [[ ! "$new_version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+        log_error "无效的版本号格式: $new_version"
+        log_info "版本号格式应为: major.minor.patch (如: 1.2.3)"
+        exit 1
+    fi
+    
+    echo "$new_version" > config/VERSION
+    log_success "版本号已设置为: $new_version"
+}
+
+# 升级版本号
+bump_version() {
+    local bump_type="$1"
+    local current_version=$(get_current_version)
+    
+    # 解析当前版本号
+    IFS='.' read -r major minor patch <<< "$current_version"
+    
+    case "$bump_type" in
+        "major")
+            major=$((major + 1))
+            minor=0
+            patch=0
+            ;;
+        "minor")
+            minor=$((minor + 1))
+            patch=0
+            ;;
+        "patch")
+            patch=$((patch + 1))
+            ;;
+        *)
+            log_error "无效的升级类型: $bump_type"
+            log_info "支持的类型: major, minor, patch"
+            exit 1
+            ;;
+    esac
+    
+    local new_version="$major.$minor.$patch"
+    set_version "$new_version"
+    log_success "版本号已从 $current_version 升级到 $new_version"
+}
+
+# 显示当前版本信息
+show_version() {
+    local current_version=$(get_current_version)
+    log_info "当前版本: $current_version"
+    
+    if [[ -f "config/checklist" ]]; then
+        echo
+        echo "组件清单:"
+        while IFS= read -r line; do
+            [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+            read -r component version dep order <<< "$line"
+            if [[ -n "$component" && -n "$version" ]]; then
+                echo "  - $component v$version"
+            fi
+        done < config/checklist
+    fi
+    
+    # 检查是否有对应的 artifact
+    local artifact_dir="artifact/$current_version"
+    if [[ -d "$artifact_dir" ]]; then
+        echo
+        echo "已构建的组件:"
+        for file in "$artifact_dir"/*.tar.gz; do
+            if [[ -f "$file" ]]; then
+                local filename=$(basename "$file")
+                local size=$(du -h "$file" | cut -f1)
+                echo "  - $filename ($size)"
+            fi
+        done
+        
+        if [[ -f "$artifact_dir/version.json" ]]; then
+            echo
+            echo "版本信息文件: $artifact_dir/version.json"
+        fi
+    else
+        echo
+        log_warning "未找到对应的构建目录: $artifact_dir"
+        log_info "运行 ./package.sh 进行构建"
+    fi
+}
+
+# 列出所有版本
+list_versions() {
+    log_info "所有版本列表:"
+    echo
+    
+    if [[ ! -d "artifact" ]]; then
+        log_warning "artifact 目录不存在"
+        return
+    fi
+    
+    for version_dir in artifact/*/; do
+        if [[ -d "$version_dir" ]]; then
+            local version=$(basename "$version_dir")
+            local current_version=$(get_current_version)
+            
+            if [[ "$version" == "$current_version" ]]; then
+                echo "  * $version (当前版本)"
+            else
+                echo "    $version"
+            fi
+            
+            # 显示该版本的组件
+            local component_count=0
+            for file in "$version_dir"/*.tar.gz; do
+                if [[ -f "$file" ]]; then
+                    component_count=$((component_count + 1))
+                fi
+            done
+            
+            if [[ $component_count -gt 0 ]]; then
+                echo "      包含 $component_count 个组件"
+            fi
+        fi
+    done
+}
+
+# 清理旧版本
+clean_versions() {
+    local current_version=$(get_current_version)
+    local keep_versions=5  # 保留最近5个版本
+    
+    log_info "清理旧版本 (保留最近 $keep_versions 个版本)..."
+    
+    if [[ ! -d "artifact" ]]; then
+        log_warning "artifact 目录不存在"
+        return
+    fi
+    
+    # 获取所有版本目录，按修改时间排序
+    local versions=()
+    while IFS= read -r -d '' version_dir; do
+        versions+=("$(basename "$version_dir")")
+    done < <(find artifact -maxdepth 1 -type d -name "[0-9]*" -print0 | sort -z)
+    
+    local total_versions=${#versions[@]}
+    local versions_to_remove=$((total_versions - keep_versions))
+    
+    if [[ $versions_to_remove -le 0 ]]; then
+        log_info "无需清理，当前只有 $total_versions 个版本"
+        return
+    fi
+    
+    log_info "将删除 $versions_to_remove 个旧版本..."
+    
+    for ((i=0; i<versions_to_remove; i++)); do
+        local version="${versions[i]}"
+        if [[ "$version" != "$current_version" ]]; then
+            log_info "删除版本: $version"
+            rm -rf "artifact/$version"
+        fi
+    done
+    
+    log_success "旧版本清理完成"
+}
+
+# 验证版本配置
+validate_version() {
+    log_info "验证版本配置..."
+    
+    local errors=0
+    
+    # 检查 VERSION 文件
+    if [[ ! -f "config/VERSION" ]]; then
+        log_error "VERSION 文件不存在"
+        errors=$((errors + 1))
+    else
+        local version=$(get_current_version)
+        if [[ ! "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            log_error "VERSION 文件格式无效: $version"
+            errors=$((errors + 1))
+        else
+            log_success "VERSION 文件格式正确: $version"
+        fi
+    fi
+    
+    # 检查 checklist 文件
+    if [[ ! -f "config/checklist" ]]; then
+        log_error "checklist 文件不存在"
+        errors=$((errors + 1))
+    else
+        local component_count=0
+        while IFS= read -r line; do
+            [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+            read -r component version dep order <<< "$line"
+            if [[ -n "$component" && -n "$version" ]]; then
+                component_count=$((component_count + 1))
+                
+                # 检查组件目录是否存在
+                if [[ ! -d "plugins/$component" ]]; then
+                    log_error "组件目录不存在: plugins/$component"
+                    errors=$((errors + 1))
+                fi
+            fi
+        done < config/checklist
+        
+        if [[ $component_count -gt 0 ]]; then
+            log_success "checklist 包含 $component_count 个组件"
+        else
+            log_error "checklist 中没有有效组件"
+            errors=$((errors + 1))
+        fi
+    fi
+    
+    # 检查 package.sh 文件
+    if [[ ! -f "scripts/package_artifact.sh" ]]; then
+        log_error "package_artifact.sh 文件不存在"
+        errors=$((errors + 1))
+    else
+        if [[ -x "scripts/package_artifact.sh" ]]; then
+            log_success "package_artifact.sh 可执行"
+        else
+            log_warning "package_artifact.sh 不可执行，请运行: chmod +x scripts/package_artifact.sh"
+        fi
+    fi
+    
+    # 检查 install.sh 文件
+    if [[ ! -f "scripts/install_artifact.sh" ]]; then
+        log_error "install_artifact.sh 文件不存在"
+        errors=$((errors + 1))
+    else
+        if [[ -x "scripts/install_artifact.sh" ]]; then
+            log_success "install_artifact.sh 可执行"
+        else
+            log_warning "install_artifact.sh 不可执行，请运行: chmod +x scripts/install_artifact.sh"
+        fi
+    fi
+    
+    if [[ $errors -eq 0 ]]; then
+        log_success "版本配置验证通过"
+    else
+        log_error "发现 $errors 个配置问题"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    case "${1:-}" in
+        "bump")
+            if [[ -z "${2:-}" ]]; then
+                log_error "请指定升级类型: major, minor, patch"
+                exit 1
+            fi
+            bump_version "$2"
+            ;;
+        "set")
+            if [[ -z "${2:-}" ]]; then
+                log_error "请指定版本号"
+                exit 1
+            fi
+            set_version "$2"
+            ;;
+        "show")
+            show_version
+            ;;
+        "list")
+            list_versions
+            ;;
+        "clean")
+            clean_versions
+            ;;
+        "validate")
+            validate_version
+            ;;
+        "help"|"-h"|"--help")
+            show_help
+            ;;
+        "")
+            show_help
+            ;;
+        *)
+            log_error "未知命令: $1"
+            echo
+            show_help
+            exit 1
+            ;;
+    esac
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/grafana/build/Dockerfile

@@ -2,6 +2,18 @@ FROM grafana/grafana:11.1.0
 
 USER root
 
+# 构建参数：是否使用内网镜像
+ARG USE_INTRANET=false
+
+# 根据是否为内网构建切换 apk 源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apk repositories..." && \
+        sed -i 's#https\?://[^/]\+#http://10.68.64.1#g' /etc/apk/repositories; \
+    else \
+        echo "Configuring public apk repositories..." && \
+        sed -i 's#https\?://[^/]\+#https://mirrors.aliyun.com#g' /etc/apk/repositories; \
+    fi
+
 # 安装必要的工具
 RUN apk add --no-cache \
         supervisor \
@@ -10,6 +22,11 @@ RUN apk add --no-cache \
         vim \
         bash
 
+# 部署镜像时恢复到部署侧使用的内网镜像源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        sed -i 's#https\?://[^/]\+#https://10.92.132.52/mirrors#g' /etc/apk/repositories; \
+    fi
+
 # supervisor 日志目录
 RUN mkdir -p /var/log/supervisor
 
@@ -48,6 +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/dashboards/default_dashboard_by_hostname.json

@@ -581,6 +581,372 @@
       ],
       "title": "Node Process Count",
       "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "GPU Utilization (%)",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "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": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 80
+              },
+              {
+                "color": "red",
+                "value": 95
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "id": 301,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_GPU_UTIL{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 利用率 (单卡)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Memory Used (%)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "orange",
+                "value": 80
+              },
+              {
+                "color": "red",
+                "value": 95
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "id": 403,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "round(DCGM_FI_DEV_FB_USED{hostname=~\"$hostname\"} / (DCGM_FI_DEV_FB_USED{hostname=~\"$hostname\"} + DCGM_FI_DEV_FB_FREE{hostname=~\"$hostname\"}) * 100)",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 显存使用率 (单卡)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Temperature (℃)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "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": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 75
+              },
+              {
+                "color": "red",
+                "value": 85
+              }
+            ]
+          },
+          "unit": "celsius"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "id": 501,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_GPU_TEMP{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 温度（单卡）",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Power (W)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "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": [],
+          "max": 300,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 200
+              },
+              {
+                "color": "red",
+                "value": 300
+              }
+            ]
+          },
+          "unit": "watt"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 32
+      },
+      "id": 502,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_POWER_USAGE{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 功率 (单卡)",
+      "type": "timeseries"
     }
   ],
   "refresh": "15s",
@@ -589,11 +955,6 @@
   "templating": {
     "list": [
       {
-        "current": {
-          "selected": true,
-          "text": "node-exporter-A1",
-          "value": "node-exporter-A1"
-        },
         "datasource": {
           "type": "prometheus"
         },
@@ -623,7 +984,7 @@
   },
   "timepicker": {},
   "timezone": "",
-  "title": "Node and GPU Metrics",
-  "uid": "node_gpu_metrics",
+  "title": "Node and GPU Metrics (by hostname)",
+  "uid": "node_gpu_metrics_by_hostname",
   "weekStart": ""
-}
+}

src/metric/grafana/build/dashboards/default_dashboard_by_instance.json

@@ -622,7 +622,7 @@
     },
     "timepicker": {},
     "timezone": "",
-    "title": "Node and GPU Metrics",
-    "uid": "node_gpu_metrics",
+    "title": "Node and GPU Metrics (by instance)",
+    "uid": "node_gpu_metrics_by_instance",
     "weekStart": ""
-  }
+  }

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
-    echo "[INFO] Copying datasource configuration to /private/argus/metric/grafana/provisioning/datasources/"
-    cp /tmp/datasources.yml /private/argus/metric/grafana/provisioning/datasources/datasources.yml
-    echo "[INFO] Datasource configuration copied successfully"
-elif [ -d "/private/argus/metric/grafana/provisioning/datasources" ] && [ "$(ls -A /private/argus/metric/grafana/provisioning/datasources)" ]; then
-    echo "[INFO] Found existing datasource provisioning files in /private/argus/metric/grafana/provisioning/datasources"
+DS_OUT="/private/argus/metric/grafana/provisioning/datasources/datasources.yml"
+PROM_DOMAIN="prom.metric.argus.com:9090"
+
+if [ -f "/tmp/datasources.yml" ] && [ ! -f "$DS_OUT" ]; then
+    echo "[INFO] Initializing datasource provisioning file from /tmp"
+    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
-if [ -f "/tmp/default_dashboard.json" ]; then
-    echo "[INFO] Copying default dashboard to /private/argus/metric/grafana/provisioning/dashboards/"
-    cp /tmp/default_dashboard.json /private/argus/metric/grafana/provisioning/dashboards/default_dashboard.json
-    echo "[INFO] Default dashboard copied successfully"
+# 复制默认仪表板到挂载目录（按需，不覆盖已存在文件）
+copy_dashboard_if_missing() {
+    local src="$1"; local dst_name="$2"
+    local dst_dir="/private/argus/metric/grafana/provisioning/dashboards"
+    local dst="$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/metric/prometheus/build/Dockerfile

@@ -11,13 +11,6 @@ RUN if [ "$USE_INTRANET" = "true" ]; then \
         echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
         echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
         echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
-    else \
-        echo "Configuring fast apt sources for external network..." && \
-        find /etc/apt -name "sources.list*" -exec sed -i 's/archive.ubuntu.com/mirrors.aliyun.com/g' {} \; && \
-        find /etc/apt -name "sources.list*" -exec sed -i 's/security.ubuntu.com/mirrors.aliyun.com/g' {} \; && \
-        echo "deb http://mirrors.aliyun.com/ubuntu/ jammy main restricted universe multiverse" > /etc/apt/sources.list && \
-        echo "deb http://mirrors.aliyun.com/ubuntu/ jammy-updates main restricted universe multiverse" >> /etc/apt/sources.list && \
-        echo "deb http://mirrors.aliyun.com/ubuntu/ jammy-security main restricted universe multiverse" >> /etc/apt/sources.list; \
     fi
 
 # 验证源配置并安装常用工具
@@ -61,10 +54,25 @@ RUN mkdir -p ${PROMETHEUS_BASE_PATH}/rules \
     && ln -s ${PROMETHEUS_BASE_PATH} /prometheus
 
 # 修改 Prometheus 用户 UID/GID 并授权
-RUN usermod -u ${ARGUS_BUILD_UID} nobody && \
-    groupmod -g ${ARGUS_BUILD_GID} nogroup && \
-    chown -h nobody:nogroup /prometheus && \
-    chown -R nobody:nogroup ${PROMETHEUS_BASE_PATH} && \
+RUN set -eux; \
+    existing_user=""; \
+    if getent passwd "${ARGUS_BUILD_UID}" >/dev/null 2>&1; then \
+        existing_user="$(getent passwd "${ARGUS_BUILD_UID}" | cut -d: -f1)"; \
+    fi; \
+    if [ -n "$existing_user" ] && [ "$existing_user" != "nobody" ]; then \
+        userdel -r "$existing_user" || true; \
+    fi; \
+    existing_group=""; \
+    if getent group "${ARGUS_BUILD_GID}" >/dev/null 2>&1; then \
+        existing_group="$(getent group "${ARGUS_BUILD_GID}" | cut -d: -f1)"; \
+    fi; \
+    if [ -n "$existing_group" ] && [ "$existing_group" != "nogroup" ]; then \
+        groupdel "$existing_group" || true; \
+    fi; \
+    usermod -u ${ARGUS_BUILD_UID} nobody; \
+    groupmod -g ${ARGUS_BUILD_GID} nogroup; \
+    chown -h nobody:nogroup /prometheus; \
+    chown -R nobody:nogroup ${PROMETHEUS_BASE_PATH}; \
     chown -R nobody:nogroup /etc/prometheus
 
 # supervisor 配置

src/metric/tests/docker-compose.yml

@@ -5,13 +5,6 @@ networks:
 
 services:
   ftp:
-    build:
-      context: ../ftp/build
-      dockerfile: Dockerfile
-      args:
-        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
-        USE_INTRANET: ${USE_INTRANET:-false}
     image: argus-metric-ftp:latest
     container_name: argus-ftp
     restart: unless-stopped
@@ -41,13 +34,6 @@ services:
         max-file: "3"
 
   prometheus:
-    build:
-      context: ../prometheus/build
-      dockerfile: Dockerfile
-      args:
-        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
-        USE_INTRANET: ${USE_INTRANET:-false}
     image: argus-metric-prometheus:latest
     container_name: argus-prometheus
     restart: unless-stopped
@@ -73,12 +59,6 @@ services:
         max-file: "3"
 
   grafana:
-    build:
-      context: ../grafana/build
-      dockerfile: Dockerfile
-      args:
-        ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
-        ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
     image: argus-metric-grafana:latest
     container_name: argus-grafana
     restart: unless-stopped
@@ -109,9 +89,6 @@ services:
         max-file: "3"
 
   test-node:
-    build:
-      context: ./client-test-node/build
-      dockerfile: Dockerfile
     image: argus-metric-test-node:latest
     container_name: argus-metric-test-node
     hostname: test-metric-node-001
@@ -143,9 +120,6 @@ services:
         max-file: "3"
 
   test-gpu-node:
-    build:
-      context: ./client-test-gpu-node/build
-      dockerfile: Dockerfile
     image: argus-metric-test-gpu-node:latest
     container_name: argus-metric-test-gpu-node
     hostname: test-metric-gpu-node-001

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

@@ -3,15 +3,8 @@ set -e
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 
-# 解析参数
-REBUILD_FLAG=""
-if [[ "$1" == "--rebuild" || "$1" == "-r" ]]; then
-    REBUILD_FLAG="--rebuild"
-    echo "[01] 启用强制重新构建模式"
-fi
-
 echo "[01] 启动所有服务..."
-bash "$SCRIPT_DIR/common/start-all.sh" $REBUILD_FLAG
+bash "$SCRIPT_DIR/common/start-all.sh"
 
 echo "[01] 等待服务就绪..."
 sleep 5

src/metric/tests/scripts/04_test_gpu_node_install.sh

@@ -1,6 +1,9 @@
 #!/bin/bash
 set -e
 
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+COMMON_DIR="$SCRIPT_DIR/common"
+
 FTP_SERVER="${FTP_SERVER:-172.30.0.40}"
 FTP_USER="${FTP_USER:-ftpuser}"
 FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
@@ -8,26 +11,37 @@ FTP_PORT="${FTP_PORT:-21}"
 
 FTP_HOST="${FTP_SERVER}"
 
-echo "[03] 进入测试节点执行安装..."
-echo "[03] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
+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 '[03] curl 未安装，正在安装...'
+    echo '[04] curl 未安装，正在安装...'
     apt-get update && apt-get install -y curl
 fi
 
 cd /tmp
-echo '[03] 下载 setup.sh...'
+echo '[04] 下载 setup.sh...'
 curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_HOST}:${FTP_PORT}/setup.sh -o setup.sh
 
-echo '[03] 执行安装...'
+echo '[04] 执行安装...'
 chmod +x setup.sh
 bash setup.sh --server ${FTP_HOST} --user ${FTP_USER} --password '${FTP_PASSWORD}' --port ${FTP_PORT}
 
-echo '[03] 安装完成'
+echo '[04] 安装完成'
 "
 
-echo "[03] 完成"
+echo "[04] 完成"

src/metric/tests/scripts/common/check-gpu.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# GPU环境检测脚本
+# 检测系统是否有NVIDIA GPU硬件
+
+set -e
+
+# 检测函数
+check_gpu_support() {
+    echo "检测GPU环境..."
+    
+    # 方法1: 检测GPU设备文件
+    if ls /dev/nvidia* &>/dev/null; then
+        echo "✓ 检测到NVIDIA GPU设备文件"
+        return 0
+    fi
+    
+    # 方法2: 检测lspci中的NVIDIA设备（Linux）
+    if command -v lspci &> /dev/null; then
+        if lspci | grep -i nvidia &> /dev/null; then
+            echo "✓ 检测到NVIDIA GPU硬件"
+            return 0
+        fi
+    fi
+    
+    # 方法3: 检测nvidia-smi
+    if command -v nvidia-smi &> /dev/null; then
+        if nvidia-smi &> /dev/null; then
+            echo "✓ 检测到NVIDIA GPU硬件"
+            return 0
+        fi
+    fi
+    
+    echo "✗ 未检测到NVIDIA GPU硬件"
+    return 1
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "  GPU环境检测"
+    echo "=========================================="
+    echo ""
+    
+    if check_gpu_support; then
+        echo ""
+        echo "结果: GPU环境可用"
+        exit 0
+    else
+        echo ""
+        echo "结果: GPU环境不可用，将跳过GPU相关服务"
+        exit 1
+    fi
+}
+
+# 如果直接运行此脚本
+if [ "${BASH_SOURCE[0]}" = "${0}" ]; then
+    main "$@"
+fi

src/metric/tests/scripts/common/start-all.sh

@@ -1,7 +1,8 @@
 #!/bin/bash
 
 # 一键启动脚本
-# 用于初始化目录、构建镜像并启动所有服务
+# 用于初始化目录并启动所有服务
+# 镜像构建已移至 build/build_images.sh
 
 set -e
 
@@ -9,12 +10,6 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
 cd "$TEST_DIR"
 
-# 解析参数
-FORCE_REBUILD=false
-if [[ "$1" == "--rebuild" ]]; then
-    FORCE_REBUILD=true
-fi
-
 echo "=========================================="
 echo "  Argus Metrics 一键启动脚本"
 echo "=========================================="
@@ -37,26 +32,6 @@ echo "使用: docker compose"
 echo "Compose 文件: $TEST_DIR/docker-compose.yml"
 echo ""
 
-# 检查必要的构建目录
-echo "检查构建目录..."
-BUILD_DIRS=(
-    "../ftp/build"
-    "../prometheus/build"
-    "../grafana/build"
-    "client-test-node/build"
-    "client-test-gpu-node/build"
-)
-
-for dir in "${BUILD_DIRS[@]}"; do
-    if [ ! -d "$dir" ]; then
-        echo "错误: 构建目录不存在: $dir"
-        echo "完整路径: $(cd "$(dirname "$dir")" 2>/dev/null && pwd)/$(basename "$dir")"
-        exit 1
-    else
-        echo "  ✓ 找到: $dir"
-    fi
-done
-echo ""
 
 # 检查并创建 .env 文件
 if [ ! -f .env ]; then
@@ -84,118 +59,65 @@ echo "1. 初始化目录结构..."
 bash "$SCRIPT_DIR/init-directories.sh"
 
 echo ""
-echo "2. 准备 Docker 镜像..."
-
-# 检查镜像是否存在
-IMAGE_CACHE_DIR="$TEST_DIR/images-cache"
-IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest" "argus-metric-test-node:latest" "argus-metric-test-gpu-node:latest")
-all_images_exist=true
-
-for image in "${IMAGES[@]}"; do
-    if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
-        all_images_exist=false
-        break
-    fi
-done
-
-if $FORCE_REBUILD; then
-    echo "强制重新构建镜像（--rebuild 模式）..."
-    cd "$TEST_DIR"
-    docker compose build --no-cache
-    echo "镜像重新构建完成"
-elif $all_images_exist; then
-    echo "所有镜像已存在，跳过构建"
+echo "2. 检测GPU环境..."
+# 检测GPU环境
+if bash "$SCRIPT_DIR/check-gpu.sh"; then
+    echo "GPU环境可用，将启动GPU节点"
+    GPU_AVAILABLE=true
 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"
-                        ;;
-                    "argus-metric-test-node:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-test-node.tar"
-                        ;;
-                    "argus-metric-test-gpu-node:latest")
-                        cache_file="${IMAGE_CACHE_DIR}/argus-test-gpu-node.tar"
-                        ;;
-                esac
-                
-                if [ -f "$cache_file" ]; then
-                    echo "  从缓存加载: $image"
-                    docker load -i "$cache_file"
-                    loaded_from_cache=true
-                fi
-            fi
-        done
-    fi
-    
-    # 检查加载后是否还有缺失的镜像
-    need_build=false
-    for image in "${IMAGES[@]}"; do
-        if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
-            need_build=true
-            break
-        fi
-    done
-    
-    if $need_build; then
-        echo ""
-        echo "部分镜像缺失，开始构建..."
-        echo "工作目录: $(pwd)"
-        cd "$TEST_DIR"
-        docker compose build --no-cache
-        
-        # 询问是否保存镜像
-        echo ""
-        read -p "是否保存镜像到缓存以便下次快速启动? (Y/n): " -n 1 -r
-        echo
-        if [[ ! $REPLY =~ ^[Nn]$ ]]; then
-            mkdir -p "$IMAGE_CACHE_DIR"
-            echo "保存镜像到缓存..."
-            for image in "${IMAGES[@]}"; do
-                case "$image" in
-                    "argus-metric-ftp:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-ftp.tar" "$image" && echo "  已保存: argus-ftp.tar"
-                        ;;
-                    "argus-metric-prometheus:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-prometheus.tar" "$image" && echo "  已保存: argus-prometheus.tar"
-                        ;;
-                    "argus-metric-grafana:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-grafana.tar" "$image" && echo "  已保存: argus-grafana.tar"
-                        ;;
-                    "argus-metric-test-node:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-test-node.tar" "$image" && echo "  已保存: argus-test-node.tar"
-                        ;;
-                    "argus-metric-test-gpu-node:latest")
-                        docker save -o "${IMAGE_CACHE_DIR}/argus-test-gpu-node.tar" "$image" && echo "  已保存: argus-test-gpu-node.tar"
-                        ;;
-                esac
-            done
-            echo "镜像已保存到: $IMAGE_CACHE_DIR/"
-        fi
-    elif $loaded_from_cache; then
-        echo ""
-        echo "所有镜像已从缓存加载完成！"
-    fi
+    echo "GPU环境不可用，跳过GPU节点"
+    GPU_AVAILABLE=false
 fi
 
 echo ""
-echo "3. 启动基础服务..."
+echo "3. 检查 Docker 镜像..."
+
+# 检查必要的镜像是否存在
+BASE_IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest" "argus-metric-test-node:latest")
+GPU_IMAGES=("argus-metric-test-gpu-node:latest")
+
+# 先检查基础镜像
+missing_images=()
+for image in "${BASE_IMAGES[@]}"; do
+    if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
+        missing_images+=("$image")
+    fi
+done
+
+# 检查GPU镜像（如果GPU环境可用）
+if [ "$GPU_AVAILABLE" = true ]; then
+    for image in "${GPU_IMAGES[@]}"; do
+        if ! docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
+            missing_images+=("$image")
+        fi
+    done
+fi
+
+if [ ${#missing_images[@]} -gt 0 ]; then
+    echo "以下镜像缺失，请先运行 build/build_images.sh 构建镜像："
+    for image in "${missing_images[@]}"; do
+        echo "   • $image"
+    done
+    echo ""
+    echo "构建命令："
+    echo "   ./build/build_images.sh --metric"
+    exit 1
+else
+    echo "所有必要镜像已存在"
+fi
+
+echo ""
+echo "4. 启动基础服务..."
 cd "$TEST_DIR"
-# 启动除GPU节点外的所有服务
-docker compose up -d ftp prometheus grafana test-node test-gpu-node
+
+# 根据GPU环境决定启动的服务
+if [ "$GPU_AVAILABLE" = true ]; then
+    echo "启动所有服务（包括GPU节点）..."
+    docker compose up -d ftp prometheus grafana test-node test-gpu-node
+else
+    echo "启动基础服务（跳过GPU节点）..."
+    docker compose up -d ftp prometheus grafana test-node
+fi
 
 echo ""
 echo "4. 等待服务启动..."

src/sys/build/node/Dockerfile

@@ -0,0 +1,36 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional: switch to intranet apt mirrors during build
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+      echo "Configuring intranet apt sources..." && \
+      cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+      echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+      echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+      echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Install base tools and all libs that Fluent Bit may require at runtime
+# so that start-fluent-bit.sh will NOT fallback to apt during container start.
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      ca-certificates tzdata \
+      procps iproute2 net-tools lsof \
+      libpq5 libyaml-0-2 libsasl2-2 libldap-2.5-0; \
+    rm -rf /var/lib/apt/lists/*
+
+# Keep root; compose provides entrypoint via bind mount
+USER root
+
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/build/test-gpu-node/Dockerfile

@@ -0,0 +1,34 @@
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai \
+    NVIDIA_VISIBLE_DEVICES=all \
+    NVIDIA_DRIVER_CAPABILITIES=compute,utility
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional intranet mirror for build-time apt
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+      echo "Configuring intranet apt sources..." && \
+      cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+      echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+      echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+      echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Pre-install curl and diagnostics to avoid runtime apt installs in GPU test node
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      curl ca-certificates tzdata \
+      procps iproute2 net-tools lsof; \
+    rm -rf /var/lib/apt/lists/*
+
+USER root
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/build/test-node/Dockerfile

@@ -0,0 +1,32 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional intranet mirror for build-time apt
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+      echo "Configuring intranet apt sources..." && \
+      cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+      echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+      echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+      echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Pre-install curl and common diagnostics to avoid runtime apt installs
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      curl ca-certificates tzdata \
+      procps iproute2 net-tools lsof; \
+    rm -rf /var/lib/apt/lists/*
+
+USER root
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/tests/README.md

@@ -32,7 +32,7 @@
 
 - 一键执行
   - `cd src/sys/tests`
-  - `./scripts/00_e2e_test.sh`
+  - `./scripts/00_e2e_test.sh`（CPU-only）或 `./scripts/00_e2e_test.sh --enable-gpu`（启用 GPU 流程）
 
 - 分步执行（推荐用于排查）
   - `./scripts/01_bootstrap.sh` 生成目录/拷贝 `update-dns.sh`/构建 agent 二进制/写 `.env`
@@ -42,7 +42,12 @@
   - `./scripts/05_agent_register.sh` 获取两个节点的 `node_id` 与初始 IP，检查本地 `node.json`
   - `./scripts/06_write_health_and_assert.sh` 写健康文件并断言 `nodes.json` 仅包含 2 个在线节点
   - `./scripts/07_logs_send_and_assert.sh` 向两个节点写日志，断言 ES `train-*`/`infer-*` 计数增长
-  - `./scripts/08_restart_agent_reregister.sh` `node-b` 改为固定 IP `172.29.0.200`，验证保持同一节点 ID 且 IP/时间戳更新
+  - `./scripts/08_restart_agent_reregister.sh` `node-b` 改为固定 IP `172.31.0.200`，验证保持同一节点 ID 且 IP/时间戳更新
+  - `./scripts/10_metric_publish.sh` 发布 metric 客户端包到 FTP
+  - `./scripts/11_metric_node_install.sh` 在 CPU 节点安装并验证端点
+  - `./scripts/12_metric_gpu_install.sh` 在 GPU 节点安装并等待 9100/9400 就绪（仅启用 GPU 时）
+  - `./scripts/13_metric_verify.sh` 对 master/Prometheus/数据面/Grafana 做综合校验（含 GPU 时校验 dcgm 指标）
+  - `./scripts/14_metric_cleanup.sh` 清理 FTP 产物
   - `./scripts/09_down.sh` 回收容器、网络并清理 `private*/`、`tmp/`
 
 - 重置环境
@@ -53,16 +58,17 @@
 ## 二、测试部署架构（docker-compose）
 
 - 网络
-  - 自定义 bridge：`argus-sys-net`，子网 `172.29.0.0/16`
-  - 固定地址：bind=`172.29.0.2`，master=`172.29.0.10`
+  - 自定义 bridge：`argus-sys-net`，子网 `172.31.0.0/16`
+  - 固定地址：bind=`172.31.0.2`，master=`172.31.0.10`
 
-- 服务与端口
+- 服务与端口（宿主机映射端口由 `01_bootstrap.sh` 自动分配并写入 `.env`）
+  - 关键变量：`MASTER_PORT`、`ES_HTTP_PORT`、`KIBANA_PORT`、`NODE_A_PORT`、`NODE_B_PORT`、`PROMETHEUS_PORT`、`GRAFANA_PORT`、`ALERTMANAGER_PORT`、`WEB_PROXY_PORT_8080..8085`、`FTP_PORT`、`FTP_DATA_PORT`、`FTP_PASSIVE_HOST_RANGE`
   - `bind`（`argus-bind9:latest`）：监听 53/tcp+udp；负责同步 `*.argus.com` 记录
-  - `master`（`argus-master:latest`）：对外 `32300→3000`；API `http://localhost:32300`
-  - `es`（`argus-elasticsearch:latest`）：`9200→9200`；单节点，无安全
-  - `kibana`（`argus-kibana:latest`）：`5601→5601`；通过 `ELASTICSEARCH_HOSTS=http://es:9200` 访问 ES
-  - `node-a`（`ubuntu:22.04`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-nbnyx10-cp2f-pod-0`，`2020→2020`
-  - `node-b`（`ubuntu:22.04`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-uuuu10-ep2f-pod-0`，`2021→2020`
+  - `master`（`argus-master:latest`）：对外 `${MASTER_PORT}→3000`；API `http://localhost:${MASTER_PORT}`
+  - `es`（`argus-elasticsearch:latest`）：`${ES_HTTP_PORT}→9200`；单节点，无安全
+  - `kibana`（`argus-kibana:latest`）：`${KIBANA_PORT}→5601`；通过 `ELASTICSEARCH_HOSTS=http://es:9200` 访问 ES
+  - `node-a`（`ubuntu:22.04`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-nbnyx10-cp2f-pod-0`，`${NODE_A_PORT}→2020`
+  - `node-b`（`ubuntu:22.04`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-uuuu10-ep2f-pod-0`，`${NODE_B_PORT}→2020`
 
 - 卷与目录
   - 核心服务（bind/master/es/kibana）共享宿主 `./private` 挂载到容器 `/private`
@@ -72,7 +78,7 @@
   - 节点容器的 Fluent Bit/agent 资产以只读方式挂载到 `/assets`/`/usr/local/bin/argus-agent`
 
 - DNS 配置
-  - 节点容器通过 compose 配置 `dns: [172.29.0.2]` 指向 bind，不挂载 `/etc/resolv.conf`，也不依赖 `update-dns.sh`
+  - 节点容器通过 compose 配置 `dns: [172.31.0.2]` 指向 bind，不挂载 `/etc/resolv.conf`，也不依赖 `update-dns.sh`
   - master/es/kibana 仍共享 `./private`，master 启动会写 `/private/argus/etc/master.argus.com` 供 bind 同步 A 记录
 
 - 节点入口
@@ -106,6 +112,7 @@
   - 判定：
     - `private/argus/etc/master.argus.com` 存在且为 master IP
     - 在 node-a/node-b 内 `getent hosts master.argus.com` 成功解析到 master IP
+    - 在 metric CPU/GPU 节点内可解析 `master.argus.com` 与 `prom.metric.argus.com`
 
 - `05_agent_register.sh`
   - 目的：确认两个节点注册到 master 并持久化 `node.json`
@@ -136,3 +143,16 @@
 ---
 
 如需更严格的断言（例如 Kibana 载入具体插件、ES 文档字段校验），可在 `07_*.sh` 中追加查询与校验逻辑。
+
+---
+
+## 可选：GPU 流程说明
+- 前置条件：宿主安装 NVIDIA 驱动与 `nvidia-container-toolkit`，`nvidia-smi` 在宿主可用。
+- 启用方式：
+  - 一键：`./scripts/00_e2e_test.sh --enable-gpu`
+  - 分步：设置 `ARGUS_SYS_ENABLE_GPU=true` 后执行 `01_bootstrap.sh`、`02_up.sh`；或直接在 `.env` 中将 `ENABLE_GPU=true` 后单独运行 `02_up.sh`。
+- `01_bootstrap.sh` 会写入：
+  - `METRIC_TEST_HOSTNAME_GPU=test-metric-gpu-node-001`
+  - `METRIC_TEST_INSTANCE_GPU=172.31.0.51:9100`
+  - `METRIC_TEST_DCGM_GPU=172.31.0.51:9400`
+- 验证点：`04_verify_dns_routing.sh` 增加对 metric 节点的域名解析；`12_metric_gpu_install.sh` 等待 9100/9400；`13_metric_verify_*` 校验 dcgm 指标与 Grafana 面板。

src/sys/tests/docker-compose.yml

@@ -1,21 +1,18 @@
-version: "3.8"
-
 networks:
-  default:
-    name: argus-sys-net
+  sysnet:
     driver: bridge
     ipam:
       driver: default
       config:
-        - subnet: 172.29.0.0/16
+        - subnet: 172.31.0.0/16
 
 services:
   bind:
     image: ${BIND_IMAGE_TAG:-argus-bind9:latest}
     container_name: argus-bind-sys
     networks:
-      default:
-        ipv4_address: 172.29.0.2
+      sysnet:
+        ipv4_address: 172.31.0.2
     volumes:
       - ./private:/private
     restart: unless-stopped
@@ -32,14 +29,14 @@ services:
       - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
       - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
     ports:
-      - "32300:3000"
+      - "${MASTER_PORT:-32300}:3000"
     volumes:
       - ./private/argus/master:/private/argus/master
       - ./private/argus/metric/prometheus:/private/argus/metric/prometheus
       - ./private/argus/etc:/private/argus/etc
     networks:
-      default:
-        ipv4_address: 172.29.0.10
+      sysnet:
+        ipv4_address: 172.31.0.10
     restart: unless-stopped
 
   es:
@@ -55,8 +52,11 @@ services:
       - ./private/argus/log/elasticsearch:/private/argus/log/elasticsearch
       - ./private/argus/etc:/private/argus/etc
     ports:
-      - "9200:9200"
+      - "${ES_HTTP_PORT:-9200}:9200"
     restart: unless-stopped
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.3
 
   kibana:
     image: argus-kibana:latest
@@ -71,11 +71,14 @@ services:
     depends_on:
       - es
     ports:
-      - "5601:5601"
+      - "${KIBANA_PORT:-5601}:5601"
     restart: unless-stopped
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.4
 
   node-a:
-    image: ubuntu:22.04
+    image: argus-sys-node:latest
     container_name: argus-node-a
     hostname: dev-yyrshare-nbnyx10-cp2f-pod-0
     depends_on:
@@ -101,13 +104,16 @@ services:
     entrypoint:
       - /usr/local/bin/node-entrypoint.sh
     dns:
-      - 172.29.0.2
+      - 172.31.0.2   # internal bind for *.argus.com
+      - 8.8.8.8      # external fallback for apt/external domains
     ports:
-      - "2020:2020"
+      - "${NODE_A_PORT:-2020}:2020"
     restart: unless-stopped
+    networks:
+      - sysnet
 
   node-b:
-    image: ubuntu:22.04
+    image: argus-sys-node:latest
     container_name: argus-node-b
     hostname: dev-yyrshare-uuuu10-ep2f-pod-0
     depends_on:
@@ -133,7 +139,269 @@ services:
     entrypoint:
       - /usr/local/bin/node-entrypoint.sh
     dns:
-      - 172.29.0.2
+      - 172.31.0.2
+      - 8.8.8.8
     ports:
-      - "2021:2020"
+      - "${NODE_B_PORT:-2021}:2020"
     restart: unless-stopped
+    networks:
+      - sysnet
+
+  ftp:
+    image: argus-metric-ftp:latest
+    container_name: argus-ftp
+    restart: unless-stopped
+    environment:
+      - TZ=Asia/Shanghai
+      - FTP_BASE_PATH=/private/argus/ftp
+      - FTP_PASSWORD=${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"
+      - "${FTP_DATA_PORT:-20}:20"
+      - "${FTP_PASSIVE_HOST_RANGE:-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:
+      sysnet:
+        ipv4_address: 172.31.0.40
+    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:
+      - "${PROMETHEUS_PORT:-9090}:9090"
+    volumes:
+      - ./private/argus/metric/prometheus:/private/argus/metric/prometheus
+      - ./private/argus/etc:/private/argus/etc
+      - /etc/localtime:/etc/localtime:ro
+      - /etc/timezone:/etc/timezone:ro
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.41
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  grafana:
+    image: argus-metric-grafana:latest
+    container_name: argus-grafana
+    restart: unless-stopped
+    environment:
+      - TZ=Asia/Shanghai
+      - GRAFANA_BASE_PATH=/private/argus/metric/grafana
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      - GF_SERVER_HTTP_PORT=3000
+      - GF_LOG_LEVEL=warn
+      - GF_LOG_MODE=console
+      - GF_PATHS_PROVISIONING=/private/argus/metric/grafana/provisioning
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Viewer
+    ports:
+      - "${GRAFANA_PORT:-3000}:3000"
+    volumes:
+      - ./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:
+      sysnet:
+        ipv4_address: 172.31.0.42
+    depends_on:
+      - prometheus
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  # --- Added: Web Frontend (no host port; resolved by DNS as web.argus.com) ---
+  web-frontend:
+    image: argus-web-frontend:latest
+    container_name: argus-web-frontend
+    environment:
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      # Frontend runtime-injected external ports (used to render hyperlinks)
+      - EXTERNAL_MASTER_PORT=${WEB_PROXY_PORT_8085:-8085}
+      - EXTERNAL_ALERTMANAGER_PORT=${WEB_PROXY_PORT_8084:-8084}
+      - EXTERNAL_GRAFANA_PORT=${WEB_PROXY_PORT_8081:-8081}
+      - EXTERNAL_PROMETHEUS_PORT=${WEB_PROXY_PORT_8082:-8082}
+      - EXTERNAL_KIBANA_PORT=${WEB_PROXY_PORT_8083:-8083}
+    volumes:
+      - ./private/argus/etc:/private/argus/etc
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.80
+    restart: unless-stopped
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  test-node:
+    image: argus-sys-metric-test-node:latest
+    container_name: argus-metric-test-node
+    hostname: test-metric-node-001
+    restart: unless-stopped
+    privileged: true
+    depends_on:
+      - ftp
+      - prometheus
+    environment:
+      - TZ=Asia/Shanghai
+      - DEBIAN_FRONTEND=noninteractive
+      - FTP_DOMAIN=${FTP_DOMAIN:-ftp.metric.argus.com}
+      - FTP_SERVER=${FTP_SERVER:-172.31.0.40}
+      - FTP_USER=${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
+    entrypoint:
+      - /usr/local/bin/metric-test-node-entrypoint.sh
+    command:
+      - sleep
+      - infinity
+    dns:
+      - 172.31.0.2
+      - 8.8.8.8
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.50
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  test-gpu-node:
+    profiles: ["gpu"]
+    image: argus-sys-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
+      - 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
+    entrypoint:
+      - /usr/local/bin/metric-test-node-entrypoint.sh
+    command:
+      - sleep
+      - infinity
+    dns:
+      - 172.31.0.2
+      - 8.8.8.8
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.51
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  # --- Added: Alertmanager ---
+  alertmanager:
+    image: argus-alertmanager:latest
+    container_name: argus-alertmanager
+    environment:
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    volumes:
+      - ./private/argus/etc:/private/argus/etc
+      - ./private/argus/alert/alertmanager:/private/argus/alert/alertmanager
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.82
+    ports:
+      - "${ALERTMANAGER_PORT:-9093}:9093"
+    restart: unless-stopped
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  # --- Added: Web Proxy (multi-port gateway) ---
+  web-proxy:
+    image: argus-web-proxy:latest
+    container_name: argus-web-proxy
+    depends_on:
+      - bind
+      - master
+      - grafana
+      - prometheus
+      - kibana
+      - alertmanager
+    environment:
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    volumes:
+      - ./private/argus/etc:/private/argus/etc
+    networks:
+      sysnet:
+        ipv4_address: 172.31.0.81
+    ports:
+      - "${WEB_PROXY_PORT_8080:-8080}:8080"
+      - "${WEB_PROXY_PORT_8081:-8081}:8081"
+      - "${WEB_PROXY_PORT_8082:-8082}:8082"
+      - "${WEB_PROXY_PORT_8083:-8083}:8083"
+      - "${WEB_PROXY_PORT_8084:-8084}:8084"
+      - "${WEB_PROXY_PORT_8085:-8085}:8085"
+    restart: unless-stopped
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"

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

@@ -3,6 +3,45 @@ set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
+ENABLE_GPU=false
+CLEANUP=true
+
+usage() {
+  cat <<'EOF'
+Usage: 00_e2e_test.sh [options]
+
+Options:
+  --enable-gpu   启用 GPU 相关拓扑与测试流程
+  --no-clean     跳过清理流程（不执行 14 和 09）
+  -h, --help     显示帮助信息
+EOF
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --enable-gpu)
+      ENABLE_GPU=true
+      shift
+      ;;
+    --no-clean)
+      CLEANUP=false
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage
+      exit 1
+      ;;
+  esac
+done
+
+export ARGUS_SYS_ENABLE_GPU=$ENABLE_GPU
+
+# 基础步骤（不包含清理与下线）
 SCRIPTS=(
   "01_bootstrap.sh"
   "02_up.sh"
@@ -12,9 +51,20 @@ SCRIPTS=(
   "06_write_health_and_assert.sh"
   "07_logs_send_and_assert.sh"
   "08_restart_agent_reregister.sh"
-  "09_down.sh"
+  "10_metric_publish.sh"
+  "11_metric_node_install.sh"
+  "12_metric_gpu_install.sh"
+  "13_metric_verify.sh"
 )
 
+# 如未禁用清理，则追加清理与下线步骤（保持原有顺序）
+if [[ "$CLEANUP" == "true" ]]; then
+  SCRIPTS+=(
+    "14_metric_cleanup.sh"
+    "09_down.sh"
+  )
+fi
+
 for script in "${SCRIPTS[@]}"; do
   echo "[SYS-E2E] Running $script"
   "$SCRIPT_DIR/$script"
@@ -22,5 +72,8 @@ for script in "${SCRIPTS[@]}"; do
   echo
 done
 
-echo "[SYS-E2E] All tests completed"
-
+if [[ "$CLEANUP" == "true" ]]; then
+  echo "[SYS-E2E] All tests completed"
+else
+  echo "[SYS-E2E] All tests completed (cleanup skipped)"
+fi