[#14] 更新grafana链接

[#25] 反向代理功能实现
[#14] 前端页面优化

.gitattributes

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

build/README.md

@@ -1,150 +0,0 @@
-# ARGUS 统一构建脚本使用说明（build/build_images.sh）
-
-本目录提供单一入口脚本 `build/build_images.sh`，覆盖常见三类场景：
-- 系统集成测试（src/sys/tests）
-- Swarm 系统集成测试（src/sys/swarm_tests）
-- 构建离线安装包（deployment_new：Server/Client‑GPU）
-
-文档还说明 UID/GID 取值规则、镜像 tag 策略、常用参数与重试机制。
-
-## 环境前置
-- Docker Engine ≥ 20.10（建议 ≥ 23.x/24.x）
-- Docker Compose v2（`docker compose` 子命令）
-- 可选：内网构建镜像源（`--intranet`）
-
-## UID/GID 规则（用于容器内用户/卷属主）
-- 非 pkg 构建（core/master/metric/web/alert/sys/gpu_bundle/cpu_bundle）：
-  - 读取 `configs/build_user.local.conf` → `configs/build_user.conf`；
-  - 可被环境变量覆盖：`ARGUS_BUILD_UID`、`ARGUS_BUILD_GID`；
-- pkg 构建（`--only server_pkg`、`--only client_pkg`）：
-  - 读取 `configs/build_user.pkg.conf`（优先）→ `build_user.local.conf` → `build_user.conf`；
-  - 可被环境变量覆盖；
-- CPU bundle 明确走“非 pkg”链（不读取 `build_user.pkg.conf`）。
-- 说明：仅依赖 UID/GID 的 Docker 层会因参数变动而自动重建，不同构建剖面不会“打错包”。
-
-## 镜像 tag 策略
-- 非 pkg 构建：默认输出 `:latest`。
-- `--only server_pkg`：所有镜像直接输出为 `:<VERSION>`（不覆盖 `:latest`）。
-- `--only client_pkg`：GPU bundle 仅输出 `:<VERSION>`（不覆盖 `:latest`）。
-- `--only cpu_bundle`：默认仅输出 `:<VERSION>`；可加 `--tag-latest` 同时打 `:latest` 以兼容 swarm_tests 默认 compose。
-
-## 不加 --only 的默认构建目标
-不指定 `--only` 时，脚本会构建“基础镜像集合”（不含 bundle 与安装包）：
-- core：`argus-elasticsearch:latest`、`argus-kibana:latest`、`argus-bind9:latest`
-- master：`argus-master:latest`（非 offline）
-- metric：`argus-metric-ftp:latest`、`argus-metric-prometheus:latest`、`argus-metric-grafana:latest`
-- web：`argus-web-frontend:latest`、`argus-web-proxy:latest`
-- alert：`argus-alertmanager:latest`
-- sys：`argus-sys-node:latest`、`argus-sys-metric-test-node:latest`、`argus-sys-metric-test-gpu-node:latest`
-
-说明：默认 tag 为 `:latest`；UID/GID 走“非 pkg”链（`build_user.local.conf → build_user.conf`，可被环境变量覆盖）。
-
-## 通用参数
-- `--intranet`：使用内网构建参数（各 Dockerfile 中按需启用）。
-- `--no-cache`：禁用 Docker 层缓存。
-- `--only <list>`：逗号分隔目标，例：`--only core,master,metric,web,alert`。
-- `--version YYMMDD`：bundle/pkg 的日期标签（必填于 cpu_bundle/gpu_bundle/server_pkg/client_pkg）。
-- `--client-semver X.Y.Z`：all‑in‑one‑full 客户端语义化版本（可选）。
-- `--cuda VER`：GPU bundle CUDA 基镜版本（默认 12.2.2）。
-- `--tag-latest`：CPU bundle 构建时同时打 `:latest`。
-
-## 自动重试
-- 构建单镜像失败会自动重试（默认 3 次，间隔 5s）。
-- 最后一次自动使用 `DOCKER_BUILDKIT=0` 再试，缓解 “failed to receive status: context canceled”。
-- 可调：`ARGUS_BUILD_RETRIES`、`ARGUS_BUILD_RETRY_DELAY` 环境变量。
-
----
-
-## 场景一：系统集成测试（src/sys/tests）
-构建用于系统级端到端测试的镜像（默认 `:latest`）。
-
-示例：
-```
-# 构建核心与周边
-./build/build_images.sh --only core,master,metric,web,alert,sys
-```
-产出：
-- 本地镜像：`argus-elasticsearch:latest`、`argus-kibana:latest`、`argus-master:latest`、`argus-metric-ftp:latest`、`argus-metric-prometheus:latest`、`argus-metric-grafana:latest`、`argus-alertmanager:latest`、`argus-web-frontend:latest`、`argus-web-proxy:latest`、`argus-sys-node:latest` 等。
-
-说明：
-- UID/GID 读取 `build_user.local.conf → build_user.conf`（或环境变量覆盖）。
-- sys/tests 的执行见 `src/sys/tests/README.md`。
-
----
-
-## 场景二：Swarm 系统集成测试（src/sys/swarm_tests）
-需要服务端镜像 + CPU 节点 bundle 镜像。
-
-步骤：
-1) 构建服务端镜像（默认 `:latest`）
-```
-./build/build_images.sh --only core,master,metric,web,alert
-```
-2) 构建 CPU bundle（直接 FROM ubuntu:22.04）
-```
-# 仅版本 tag 输出
-./build/build_images.sh --only cpu_bundle --version 20251114
-# 若要兼容 swarm_tests 默认 latest：
-./build/build_images.sh --only cpu_bundle --version 20251114 --tag-latest
-```
-3) 运行 Swarm 测试
-```
-cd src/sys/swarm_tests
-# 如未打 latest，可先指定：
-export NODE_BUNDLE_IMAGE_TAG=argus-sys-metric-test-node-bundle:20251114
-./scripts/01_server_up.sh
-./scripts/02_wait_ready.sh
-./scripts/03_nodes_up.sh
-./scripts/04_metric_verify.sh   # 验证 Prometheus/Grafana/nodes.json 与日志通路
-./scripts/99_down.sh            # 结束
-```
-产出：
-- 本地镜像：`argus-*:latest` 与 `argus-sys-metric-test-node-bundle:20251114`（或 latest）。
-- `swarm_tests/private-*`：运行态持久化文件。
-
-说明：
-- CPU bundle 构建用户走“非 pkg”链（local.conf → conf）。
-- `04_metric_verify.sh` 已内置 Fluent Bit 启动与配置修正逻辑，偶发未就绪可重跑一次即通过。
-
----
-
-## 场景三：构建离线安装包（deployment_new）
-Server 与 Client‑GPU 安装包均采用“版本直出”，只输出 `:<VERSION>` 标签，不改动 `:latest`。
-
-1) Server 包
-```
-./build/build_images.sh --only server_pkg --version 20251114
-```
-产出：
-- 本地镜像：`argus-<模块>:20251114`（不触碰 latest）。
-- 安装包：`deployment_new/artifact/server/20251114/` 与 `server_20251114.tar.gz`
-- 包内包含：逐镜像 tar.gz、compose/.env.example、scripts（config/install/selfcheck/diagnose 等）、docs、manifest/checksums。
-
-2) Client‑GPU 包
-```
-# 同步构建 GPU bundle（仅 :<VERSION>，不触碰 latest），并生成客户端包
-./build/build_images.sh --only client_pkg --version 20251114 \\
-  --client-semver 1.44.0 --cuda 12.2.2
-```
-产出：
-- 本地镜像：`argus-sys-metric-test-node-bundle-gpu:20251114`
-- 安装包：`deployment_new/artifact/client_gpu/20251114/` 与 `client_gpu_20251114.tar.gz`
-- 包内包含：GPU bundle 镜像 tar.gz、busybox.tar、compose/.env.example、scripts（config/install/uninstall）、docs、manifest/checksums。
-
-说明：
-- pkg 构建使用 `configs/build_user.pkg.conf` 的 UID/GID（可被环境覆盖）。
-- 包内 `.env.example` 的 `PKG_VERSION=<VERSION>` 与镜像 tag 严格一致。
-
----
-
-## 常见问题（FAQ）
-- 构建报 `failed to receive status: context canceled`？
-  - 已内置单镜像多次重试，最后一次禁用 BuildKit；建议加 `--intranet` 与 `--no-cache` 重试，或 `docker builder prune -f` 后再试。
-- 先跑非 pkg（latest），再跑 pkg（version）会不会“打错包”？
-  - 不会。涉及 UID/GID 的层因参数变化会重建，其它层按缓存命中复用，最终 pkg 产物的属主与运行账户按 `build_user.pkg.conf` 生效。
-- swarm_tests 默认拉取 `:latest`，我只构建了 `:<VERSION>` 的 CPU bundle 怎么办？
-  - 在运行前 `export NODE_BUNDLE_IMAGE_TAG=argus-sys-metric-test-node-bundle:<VERSION>`，或在构建时加 `--tag-latest`。
-
----
-
-如需进一步自动化（例如生成 BUILD_SUMMARY.txt 汇总镜像 digest 与构建参数），可在 pkg 产出阶段追加，我可以按需补齐。

build/build_images.sh

@@ -10,45 +10,19 @@ 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,gpu_bundle,cpu_bundle,server_pkg,client_pkg,all
-  --version DATE    Date tag used by gpu_bundle/server_pkg/client_pkg (e.g. 20251112)
-  --client-semver X.Y.Z  Override client semver used in all-in-one-full artifact (optional)
-  --cuda VER        CUDA runtime version for NVIDIA base (default: 12.2.2)
-  --tag-latest      Also tag bundle image as :latest (for cpu_bundle only; default off)
   -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 --metric                    # Additionally build metric module images
-  $0 --intranet --master-offline --metric
+  $0 --intranet --master-offline
 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
-build_gpu_bundle=false
-build_cpu_bundle=false
-build_server_pkg=false
-build_client_pkg=false
-need_bind_image=true
-need_metric_ftp=true
-no_cache=false
-
-bundle_date=""
-client_semver=""
-cuda_ver="12.2.2"
-DEFAULT_IMAGE_TAG="latest"
-tag_latest=false
 
 while [[ $# -gt 0 ]]; do
   case $1 in
@@ -65,55 +39,6 @@ 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="$2"; shift 2
-      # reset all, then enable selected
-      build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false; build_sys=false; build_gpu_bundle=false; build_cpu_bundle=false; build_server_pkg=false; build_client_pkg=false
-      IFS=',' read -ra parts <<< "$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 ;;
-          gpu_bundle) build_gpu_bundle=true ;;
-          cpu_bundle) build_cpu_bundle=true ;;
-          server_pkg) build_server_pkg=true; build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true ;;
-          client_pkg) build_client_pkg=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
-      ;;
-    --version)
-      if [[ -z ${2:-} ]]; then echo "--version requires a value like 20251112" >&2; exit 1; fi
-      bundle_date="$2"; shift 2
-      ;;
-    --client-semver)
-      if [[ -z ${2:-} ]]; then echo "--client-semver requires a value like 1.43.0" >&2; exit 1; fi
-      client_semver="$2"; shift 2
-      ;;
-    --cuda)
-      if [[ -z ${2:-} ]]; then echo "--cuda requires a value like 12.2.2" >&2; exit 1; fi
-      cuda_ver="$2"; shift 2
-      ;;
-    --tag-latest)
-      tag_latest=true
-      shift
-      ;;
     -h|--help)
       show_help
       exit 0
@@ -126,11 +51,6 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-if [[ "$build_server_pkg" == true ]]; then
-  need_bind_image=false
-  need_metric_ftp=false
-fi
-
 root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 . "$root/scripts/common/build_user.sh"
 
@@ -142,23 +62,9 @@ fi
 
 cd "$root"
 
-# Set default image tag policy before building
-if [[ "$build_server_pkg" == true ]]; then
-  DEFAULT_IMAGE_TAG="${bundle_date:-latest}"
-fi
-
-# Select build user profile for pkg vs default
-if [[ "$build_server_pkg" == true || "$build_client_pkg" == true ]]; then
-  export ARGUS_BUILD_PROFILE=pkg
-fi
-
 load_build_user
 build_args+=("--build-arg" "ARGUS_BUILD_UID=${ARGUS_BUILD_UID}" "--build-arg" "ARGUS_BUILD_GID=${ARGUS_BUILD_GID}")
 
-if [[ "$no_cache" == true ]]; then
-  build_args+=("--no-cache")
-fi
-
 master_root="$root/src/master"
 master_offline_tar="$master_root/offline_wheels.tar.gz"
 master_offline_dir="$master_root/offline_wheels"
@@ -199,459 +105,45 @@ 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"
 
-  local tries=${ARGUS_BUILD_RETRIES:-3}
-  local delay=${ARGUS_BUILD_RETRY_DELAY:-5}
-  local attempt=1
-  while (( attempt <= tries )); do
-    local prefix=""
-    if (( attempt == tries )); then
-      # final attempt: disable BuildKit to avoid docker/dockerfile front-end pulls
-      prefix="DOCKER_BUILDKIT=0"
-      echo "   Attempt ${attempt}/${tries} (fallback: DOCKER_BUILDKIT=0)"
-    else
-      echo "   Attempt ${attempt}/${tries}"
-    fi
-    if eval $prefix docker build "${build_args[@]}" "${extra_args[@]}" -f "$dockerfile_path" -t "$tag" "$context"; then
-      echo "✅ $image_name image built successfully"
-      return 0
-    fi
-    echo "⚠️  Build failed for $image_name (attempt ${attempt}/${tries})."
-    if (( attempt < tries )); then
-      echo "   Retrying in ${delay}s..."
-      sleep "$delay"
-    fi
-    attempt=$((attempt+1))
-  done
-  echo "❌ Failed to build $image_name image after ${tries} attempts"
-  return 1
-}
-
-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: $image_ref"
+  if docker build "${build_args[@]}" "${extra_args[@]}" -f "$dockerfile_path" -t "$tag" .; then
+    echo "✅ $image_name image built successfully"
     return 0
+  else
+    echo "❌ Failed to build $image_name image"
+    return 1
   fi
-
-  for ((i=1; i<=attempts; i++)); do
-    echo "   Pulling base image ($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
 
-build_gpu_bundle_image() {
-  local date_tag="$1"      # e.g. 20251112
-  local cuda_ver_local="$2" # e.g. 12.2.2
-  local client_ver="$3"     # semver like 1.43.0
+if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:latest"; then
+  images_built+=("argus-elasticsearch:latest")
+else
+  build_failed=true
+fi
 
-  if [[ -z "$date_tag" ]]; then
-    echo "❌ gpu_bundle requires --version YYMMDD (e.g. 20251112)" >&2
-    return 1
-  fi
+echo ""
 
-  # sanitize cuda version (trim trailing dots like '12.2.')
-  while [[ "$cuda_ver_local" == *"." ]]; do cuda_ver_local="${cuda_ver_local%.}"; done
+if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:latest"; then
+  images_built+=("argus-kibana:latest")
+else
+  build_failed=true
+fi
 
-  # Resolve effective CUDA base tag
-  local resolve_cuda_base_tag
-  resolve_cuda_base_tag() {
-    local want="$1" # can be 12, 12.2 or 12.2.2
-    local major minor patch
-    if [[ "$want" =~ ^([0-9]+)\.([0-9]+)\.([0-9]+)$ ]]; then
-      major="${BASH_REMATCH[1]}"; minor="${BASH_REMATCH[2]}"; patch="${BASH_REMATCH[3]}"
-      echo "nvidia/cuda:${major}.${minor}.${patch}-runtime-ubuntu22.04"; return 0
-    elif [[ "$want" =~ ^([0-9]+)\.([0-9]+)$ ]]; then
-      major="${BASH_REMATCH[1]}"; minor="${BASH_REMATCH[2]}"
-      # try to find best local patch for major.minor
-      local best
-      best=$(docker images --format '{{.Repository}}:{{.Tag}}' nvidia/cuda 2>/dev/null | \
-             grep -E "^nvidia/cuda:${major}\.${minor}\\.[0-9]+-runtime-ubuntu22\.04$" | \
-             sed -E 's#^nvidia/cuda:([0-9]+\.[0-9]+\.)([0-9]+)-runtime-ubuntu22\.04$#\1\2#g' | \
-             sort -V | tail -n1 || true)
-      if [[ -n "$best" ]]; then
-        echo "nvidia/cuda:${best}-runtime-ubuntu22.04"; return 0
-      fi
-      # fallback patch if none local
-      echo "nvidia/cuda:${major}.${minor}.2-runtime-ubuntu22.04"; return 0
-    elif [[ "$want" =~ ^([0-9]+)$ ]]; then
-      major="${BASH_REMATCH[1]}"
-      # try to find best local for this major
-      local best
-      best=$(docker images --format '{{.Repository}}:{{.Tag}}' nvidia/cuda 2>/dev/null | \
-             grep -E "^nvidia/cuda:${major}\\.[0-9]+\\.[0-9]+-runtime-ubuntu22\.04$" | \
-             sed -E 's#^nvidia/cuda:([0-9]+\.[0-9]+\.[0-9]+)-runtime-ubuntu22\.04$#\1#g' | \
-             sort -V | tail -n1 || true)
-      if [[ -n "$best" ]]; then
-        echo "nvidia/cuda:${best}-runtime-ubuntu22.04"; return 0
-      fi
-      echo "nvidia/cuda:${major}.2.2-runtime-ubuntu22.04"; return 0
-    else
-      # invalid format, fallback to default
-      echo "nvidia/cuda:12.2.2-runtime-ubuntu22.04"; return 0
-    fi
-  }
+echo ""
 
-  local base_image
-  base_image=$(resolve_cuda_base_tag "$cuda_ver_local")
-
-  echo
-  echo "🔧 Preparing one-click GPU bundle build"
-  echo "   CUDA runtime base: ${base_image}"
-  echo "   Bundle tag       : ${date_tag}"
-
-  # 1) Ensure NVIDIA base image (skip pull if local)
-  if ! pull_base_image "$base_image"; then
-    # try once more with default if resolution failed
-    if ! pull_base_image "nvidia/cuda:12.2.2-runtime-ubuntu22.04"; then
-      return 1
-    else
-      base_image="nvidia/cuda:12.2.2-runtime-ubuntu22.04"
-    fi
-  fi
-
-  # 2) Build latest argus-agent from source
-  echo "\n🛠  Building argus-agent from src/agent"
-  pushd "$root/src/agent" >/dev/null
-  if ! bash scripts/build_binary.sh; then
-    echo "❌ argus-agent build failed" >&2
-    popd >/dev/null
-    return 1
-  fi
-  if [[ ! -f "dist/argus-agent" ]]; then
-    echo "❌ argus-agent binary missing after build" >&2
-    popd >/dev/null
-    return 1
-  fi
-  popd >/dev/null
-
-  # 3) Inject agent into all-in-one-full plugin and package artifact
-  local aio_root="$root/src/metric/client-plugins/all-in-one-full"
-  local agent_bin_src="$root/src/agent/dist/argus-agent"
-  local agent_bin_dst="$aio_root/plugins/argus-agent/bin/argus-agent"
-  echo "\n📦 Updating all-in-one-full agent binary → $agent_bin_dst"
-  cp -f "$agent_bin_src" "$agent_bin_dst"
-  chmod +x "$agent_bin_dst" || true
-
-  pushd "$aio_root" >/dev/null
-  local prev_version
-  prev_version="$(cat config/VERSION 2>/dev/null || echo "1.0.0")"
-  local use_version="$prev_version"
-  if [[ -n "$client_semver" ]]; then
-    echo "${client_semver}" > config/VERSION
-    use_version="$client_semver"
-  fi
-  echo "   Packaging all-in-one-full artifact version: $use_version"
-  if ! bash scripts/package_artifact.sh --force; then
-    echo "❌ package_artifact.sh failed" >&2
-    # restore VERSION if changed
-    if [[ -n "$client_semver" ]]; then echo "$prev_version" > config/VERSION; fi
-    popd >/dev/null
-    return 1
-  fi
-
-  local artifact_dir="$aio_root/artifact/$use_version"
-  local artifact_tar
-  artifact_tar="$(ls -1 "$artifact_dir"/argus-metric_*.tar.gz 2>/dev/null | head -n1 || true)"
-  if [[ -z "$artifact_tar" ]]; then
-    echo "   No argus-metric_*.tar.gz found; invoking publish_artifact.sh to assemble..."
-    local owner="$(id -u):$(id -g)"
-    if ! bash scripts/publish_artifact.sh "$use_version" --output-dir "$artifact_dir" --owner "$owner"; then
-      echo "❌ publish_artifact.sh failed" >&2
-      if [[ -n "$client_semver" ]]; then echo "$prev_version" > config/VERSION; fi
-      popd >/dev/null
-      return 1
-    fi
-    artifact_tar="$(ls -1 "$artifact_dir"/argus-metric_*.tar.gz 2>/dev/null | head -n1 || true)"
-  fi
-  if [[ -z "$artifact_tar" ]]; then
-    echo "❌ artifact tar not found under $artifact_dir" >&2
-    if [[ -n "$client_semver" ]]; then echo "$prev_version" > config/VERSION; fi
-    popd >/dev/null
-    return 1
-  fi
-  # restore VERSION if changed (keep filesystem clean)
-  if [[ -n "$client_semver" ]]; then echo "$prev_version" > config/VERSION; fi
-  popd >/dev/null
-
-  # 4) Stage docker build context
-  local bundle_ctx="$root/src/bundle/gpu-node-bundle/.build-$date_tag"
-  echo "\n🧰 Staging docker build context: $bundle_ctx"
-  rm -rf "$bundle_ctx"
-  mkdir -p "$bundle_ctx/bundle" "$bundle_ctx/private"
-  cp "$root/src/bundle/gpu-node-bundle/Dockerfile" "$bundle_ctx/"
-  cp "$root/src/bundle/gpu-node-bundle/node-bootstrap.sh" "$bundle_ctx/"
-  cp "$root/src/bundle/gpu-node-bundle/health-watcher.sh" "$bundle_ctx/"
-  # bundle tar
-  cp "$artifact_tar" "$bundle_ctx/bundle/"
-  # offline fluent-bit assets (optional but useful)
-  if [[ -d "$root/src/log/fluent-bit/build/etc" ]]; then
-    cp -r "$root/src/log/fluent-bit/build/etc" "$bundle_ctx/private/"
-  fi
-  if [[ -d "$root/src/log/fluent-bit/build/packages" ]]; then
-    cp -r "$root/src/log/fluent-bit/build/packages" "$bundle_ctx/private/"
-  fi
-  if [[ -f "$root/src/log/fluent-bit/build/start-fluent-bit.sh" ]]; then
-    cp "$root/src/log/fluent-bit/build/start-fluent-bit.sh" "$bundle_ctx/private/"
-  fi
-
-  # 5) Build the final bundle image (directly from NVIDIA base)
-  local image_tag="argus-sys-metric-test-node-bundle-gpu:${date_tag}"
-  echo "\n🔄 Building GPU Bundle image"
-  if build_image "GPU Bundle" "$bundle_ctx/Dockerfile" "$image_tag" "$bundle_ctx" \
-      --build-arg CUDA_VER="$(echo "$base_image" | sed -E 's#^nvidia/cuda:([0-9]+\.[0-9]+\.[0-9]+)-runtime-ubuntu22\.04$#\1#')" \
-      --build-arg CLIENT_VER="$use_version" \
-      --build-arg BUNDLE_DATE="$date_tag"; then
-    images_built+=("$image_tag")
-    # In non-pkg mode, also tag latest for convenience
-    if [[ "${ARGUS_PKG_BUILD:-0}" != "1" ]]; then
-      docker tag "$image_tag" argus-sys-metric-test-node-bundle-gpu:latest >/dev/null 2>&1 || true
-    fi
-    return 0
-  else
-    return 1
-  fi
-}
-
-# Tag helper: ensure :<date_tag> exists for a list of repos
-ensure_version_tags() {
-  local date_tag="$1"; shift
-  local repos=("$@")
-  for repo in "${repos[@]}"; do
-    if docker image inspect "$repo:$date_tag" >/dev/null 2>&1; then
-      :
-    elif docker image inspect "$repo:latest" >/dev/null 2>&1; then
-      docker tag "$repo:latest" "$repo:$date_tag" || true
-    else
-      echo "❌ missing image for tagging: $repo (need :latest or :$date_tag)" >&2
-      return 1
-    fi
-  done
-  return 0
-}
-
-# Build server package after images are built
-build_server_pkg_bundle() {
-  local date_tag="$1"
-  if [[ -z "$date_tag" ]]; then
-    echo "❌ server_pkg requires --version YYMMDD" >&2
-    return 1
-  fi
-  local repos=(
-    argus-master argus-elasticsearch argus-kibana \
-    argus-metric-prometheus argus-metric-grafana \
-    argus-alertmanager argus-web-frontend argus-web-proxy
-  )
-  echo "\n🔖 Verifying server images with :$date_tag and collecting digests (Bind/FTP excluded; relying on Docker DNS aliases)"
-  for repo in "${repos[@]}"; do
-    if ! docker image inspect "$repo:$date_tag" >/dev/null 2>&1; then
-      echo "❌ required image missing: $repo:$date_tag (build phase should have produced it)" >&2
-      return 1
-    fi
-  done
-  # Optional: show digests
-  for repo in "${repos[@]}"; do
-    local digest
-    digest=$(docker images --digests --format '{{.Repository}}:{{.Tag}} {{.Digest}}' | awk -v r="$repo:$date_tag" '$1==r{print $2}' | head -n1)
-    printf '   • %s@%s\n' "$repo:$date_tag" "${digest:-<none>}"
-  done
-  echo "\n📦 Building server package via deployment_new/build/make_server_package.sh --version $date_tag"
-  if ! "$root/deployment_new/build/make_server_package.sh" --version "$date_tag"; then
-    echo "❌ make_server_package.sh failed" >&2
-    return 1
-  fi
-  return 0
-}
-
-# Build client package: ensure gpu bundle image exists, then package client_gpu
-build_client_pkg_bundle() {
-  local date_tag="$1"
-  local semver="$2"
-  local cuda="$3"
-  if [[ -z "$date_tag" ]]; then
-    echo "❌ client_pkg requires --version YYMMDD" >&2
-    return 1
-  fi
-  local bundle_tag="argus-sys-metric-test-node-bundle-gpu:${date_tag}"
-  if ! docker image inspect "$bundle_tag" >/dev/null 2>&1; then
-    echo "\n🧩 GPU bundle image $bundle_tag missing; building it first..."
-    ARGUS_PKG_BUILD=1
-    export ARGUS_PKG_BUILD
-    if ! build_gpu_bundle_image "$date_tag" "$cuda" "$semver"; then
-      return 1
-    fi
-  else
-    echo "\n✅ Using existing GPU bundle image: $bundle_tag"
-  fi
-  echo "\n📦 Building client GPU package via deployment_new/build/make_client_gpu_package.sh --version $date_tag --image $bundle_tag"
-  if ! "$root/deployment_new/build/make_client_gpu_package.sh" --version "$date_tag" --image "$bundle_tag"; then
-    echo "❌ make_client_gpu_package.sh failed" >&2
-    return 1
-  fi
-  return 0
-}
-
-# Build CPU bundle image directly FROM ubuntu:22.04 (no intermediate base)
-build_cpu_bundle_image() {
-  local date_tag="$1"         # e.g. 20251113
-  local client_ver_in="$2"    # semver like 1.43.0 (optional)
-  local want_tag_latest="$3"   # true/false
-
-  if [[ -z "$date_tag" ]]; then
-    echo "❌ cpu_bundle requires --version YYMMDD" >&2
-    return 1
-  fi
-
-  echo "\n🔧 Preparing one-click CPU bundle build"
-  echo "   Base: ubuntu:22.04"
-  echo "   Bundle tag: ${date_tag}"
-
-  # 1) Build latest argus-agent from source
-  echo "\n🛠  Building argus-agent from src/agent"
-  pushd "$root/src/agent" >/dev/null
-  if ! bash scripts/build_binary.sh; then
-    echo "❌ argus-agent build failed" >&2
-    popd >/dev/null
-    return 1
-  fi
-  if [[ ! -f "dist/argus-agent" ]]; then
-    echo "❌ argus-agent binary missing after build" >&2
-    popd >/dev/null
-    return 1
-  fi
-  popd >/dev/null
-
-  # 2) Inject agent into all-in-one-full plugin and package artifact
-  local aio_root="$root/src/metric/client-plugins/all-in-one-full"
-  local agent_bin_src="$root/src/agent/dist/argus-agent"
-  local agent_bin_dst="$aio_root/plugins/argus-agent/bin/argus-agent"
-  echo "\n📦 Updating all-in-one-full agent binary → $agent_bin_dst"
-  cp -f "$agent_bin_src" "$agent_bin_dst"
-  chmod +x "$agent_bin_dst" || true
-
-  pushd "$aio_root" >/dev/null
-  local prev_version use_version
-  prev_version="$(cat config/VERSION 2>/dev/null || echo "1.0.0")"
-  use_version="$prev_version"
-  if [[ -n "$client_ver_in" ]]; then
-    echo "$client_ver_in" > config/VERSION
-    use_version="$client_ver_in"
-  fi
-  echo "   Packaging all-in-one-full artifact: version=$use_version"
-  if ! bash scripts/package_artifact.sh --force; then
-    echo "❌ package_artifact.sh failed" >&2
-    [[ -n "$client_ver_in" ]] && echo "$prev_version" > config/VERSION
-    popd >/dev/null
-    return 1
-  fi
-  local artifact_dir="$aio_root/artifact/$use_version"
-  local artifact_tar
-  artifact_tar="$(ls -1 "$artifact_dir"/argus-metric_*.tar.gz 2>/dev/null | head -n1 || true)"
-  if [[ -z "$artifact_tar" ]]; then
-    echo "   No argus-metric_*.tar.gz found; invoking publish_artifact.sh ..."
-    local owner="$(id -u):$(id -g)"
-    if ! bash scripts/publish_artifact.sh "$use_version" --output-dir "$artifact_dir" --owner "$owner"; then
-      echo "❌ publish_artifact.sh failed" >&2
-      [[ -n "$client_ver_in" ]] && echo "$prev_version" > config/VERSION
-      popd >/dev/null
-      return 1
-    fi
-    artifact_tar="$(ls -1 "$artifact_dir"/argus-metric_*.tar.gz 2>/dev/null | head -n1 || true)"
-  fi
-  [[ -n "$client_ver_in" ]] && echo "$prev_version" > config/VERSION
-  popd >/dev/null
-
-  # 3) Stage docker build context
-  local bundle_ctx="$root/src/bundle/cpu-node-bundle/.build-$date_tag"
-  echo "\n🧰 Staging docker build context: $bundle_ctx"
-  rm -rf "$bundle_ctx"
-  mkdir -p "$bundle_ctx/bundle" "$bundle_ctx/private"
-  cp "$root/src/bundle/cpu-node-bundle/Dockerfile" "$bundle_ctx/"
-  cp "$root/src/bundle/cpu-node-bundle/node-bootstrap.sh" "$bundle_ctx/"
-  cp "$root/src/bundle/cpu-node-bundle/health-watcher.sh" "$bundle_ctx/"
-  # bundle tar
-  cp "$artifact_tar" "$bundle_ctx/bundle/"
-  # offline fluent-bit assets
-  if [[ -d "$root/src/log/fluent-bit/build/etc" ]]; then
-    cp -r "$root/src/log/fluent-bit/build/etc" "$bundle_ctx/private/"
-  fi
-  if [[ -d "$root/src/log/fluent-bit/build/packages" ]]; then
-    cp -r "$root/src/log/fluent-bit/build/packages" "$bundle_ctx/private/"
-  fi
-  if [[ -f "$root/src/log/fluent-bit/build/start-fluent-bit.sh" ]]; then
-    cp "$root/src/log/fluent-bit/build/start-fluent-bit.sh" "$bundle_ctx/private/"
-  fi
-
-  # 4) Build final bundle image
-  local image_tag="argus-sys-metric-test-node-bundle:${date_tag}"
-  echo "\n🔄 Building CPU Bundle image"
-  if build_image "CPU Bundle" "$bundle_ctx/Dockerfile" "$image_tag" "$bundle_ctx"; then
-    images_built+=("$image_tag")
-    if [[ "$want_tag_latest" == "true" ]]; then
-      docker tag "$image_tag" argus-sys-metric-test-node-bundle:latest >/dev/null 2>&1 || true
-    fi
-    return 0
-  else
-    return 1
-  fi
-}
-
-if [[ "$build_core" == true ]]; then
-  if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:${DEFAULT_IMAGE_TAG}"; then
-    images_built+=("argus-elasticsearch:${DEFAULT_IMAGE_TAG}")
-  else
-    build_failed=true
-  fi
-
-  echo ""
-
-  if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:${DEFAULT_IMAGE_TAG}"; then
-    images_built+=("argus-kibana:${DEFAULT_IMAGE_TAG}")
-  else
-    build_failed=true
-  fi
-
-  echo ""
-
-  if [[ "$need_bind_image" == true ]]; then
-    if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:${DEFAULT_IMAGE_TAG}"; then
-      images_built+=("argus-bind9:${DEFAULT_IMAGE_TAG}")
-    else
-      build_failed=true
-    fi
-  fi
+if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:latest"; then
+  images_built+=("argus-bind9:latest")
+else
+  build_failed=true
 fi
 
 echo ""
@@ -660,21 +152,18 @@ if [[ "$build_master" == true ]]; then
   echo ""
   echo "🔄 Building Master image..."
   pushd "$master_root" >/dev/null
-  master_args=("--tag" "argus-master:${DEFAULT_IMAGE_TAG}")
+  master_args=("--tag" "argus-master:latest")
   if [[ "$use_intranet" == true ]]; then
     master_args+=("--intranet")
   fi
   if [[ "$build_master_offline" == true ]]; then
     master_args+=("--offline")
   fi
-  if [[ "$no_cache" == true ]]; then
-    master_args+=("--no-cache")
-  fi
   if ./scripts/build_images.sh "${master_args[@]}"; then
     if [[ "$build_master_offline" == true ]]; then
       images_built+=("argus-master:offline")
     else
-      images_built+=("argus-master:${DEFAULT_IMAGE_TAG}")
+      images_built+=("argus-master:latest")
     fi
   else
     build_failed=true
@@ -682,176 +171,6 @@ if [[ "$build_master" == true ]]; then
   popd >/dev/null
 fi
 
-if [[ "$build_metric" == true ]]; then
-  echo ""
-  echo "Building Metric module images..."
-
-  metric_base_images=(
-    "ubuntu/prometheus:3-24.04_stable"
-    "grafana/grafana:11.1.0"
-  )
-
-  if [[ "$need_metric_ftp" == true ]]; then
-    metric_base_images+=("ubuntu:22.04")
-  fi
-
-  for base_image in "${metric_base_images[@]}"; do
-    if ! pull_base_image "$base_image"; then
-      build_failed=true
-    fi
-  done
-
-  metric_builds=()
-  if [[ "$need_metric_ftp" == true ]]; then
-    metric_builds+=("Metric FTP|src/metric/ftp/build/Dockerfile|argus-metric-ftp:${DEFAULT_IMAGE_TAG}|src/metric/ftp/build")
-  fi
-  metric_builds+=(
-    "Metric Prometheus|src/metric/prometheus/build/Dockerfile|argus-metric-prometheus:${DEFAULT_IMAGE_TAG}|src/metric/prometheus/build"
-    "Metric Grafana|src/metric/grafana/build/Dockerfile|argus-metric-grafana:${DEFAULT_IMAGE_TAG}|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:${DEFAULT_IMAGE_TAG}|."
-      "Web Proxy|src/web/build_tools/proxy/Dockerfile|argus-web-proxy:${DEFAULT_IMAGE_TAG}|."
-    )
-    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:${DEFAULT_IMAGE_TAG}|."
-    )
-    for build_spec in "${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
-
-# =======================================
-# One-click GPU bundle (direct NVIDIA base)
-# =======================================
-
-if [[ "$build_gpu_bundle" == true ]]; then
-  echo ""
-  echo "Building one-click GPU bundle image..."
-  if ! build_gpu_bundle_image "$bundle_date" "$cuda_ver" "$client_semver"; then
-    build_failed=true
-  fi
-fi
-
-# =======================================
-# One-click CPU bundle (from ubuntu:22.04)
-# =======================================
-if [[ "$build_cpu_bundle" == true ]]; then
-  echo ""
-  echo "Building one-click CPU bundle image..."
-  if ! build_cpu_bundle_image "${bundle_date}" "${client_semver}" "${tag_latest}"; then
-    build_failed=true
-  fi
-fi
-
-# =======================================
-# One-click Server/Client packaging
-# =======================================
-
-if [[ "$build_server_pkg" == true ]]; then
-  echo ""
-  echo "🧳 Building one-click Server package..."
-  if ! build_server_pkg_bundle "${bundle_date}"; then
-    build_failed=true
-  fi
-fi
-
-if [[ "$build_client_pkg" == true ]]; then
-  echo ""
-  echo "🧳 Building one-click Client-GPU package..."
-  if ! build_client_pkg_bundle "${bundle_date}" "${client_semver}" "${cuda_ver}"; then
-    build_failed=true
-  fi
-fi
-
 echo "======================================="
 echo "📦 Build Summary"
 echo "======================================="
@@ -878,6 +197,7 @@ 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

@@ -68,12 +68,6 @@ 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
@@ -226,4 +220,4 @@ fi
 
 echo ""
 echo "✅ Image export completed successfully!"
-echo ""
+echo ""

configs/build_user.pkg.conf

@@ -1,6 +0,0 @@
-# Default build-time UID/GID for Argus images
-# Override by creating configs/build_user.local.conf with the same format.
-# Syntax: KEY=VALUE, supports UID/GID only. Whitespace and lines starting with # are ignored.
-
-UID=2133
-GID=2015

deployment_new/.gitignore

@@ -1 +0,0 @@
-artifact/

deployment_new/README.md

@@ -1,14 +0,0 @@
-# deployment_new
-
-本目录用于新的部署打包与交付实现（不影响既有 `deployment/`）。
-
-里程碑 M1（当前实现）
-- `build/make_server_package.sh`：生成 Server 包（逐服务镜像 tar.gz、compose、.env.example、docs、private 骨架、manifest/checksums、打包 tar.gz）。
-- `build/make_client_gpu_package.sh`：生成 Client‑GPU 包（GPU bundle 镜像 tar.gz、busybox.tar、compose、.env.example、docs、private 骨架、manifest/checksums、打包 tar.gz）。
-
-模板
-- `templates/server/compose/docker-compose.yml`：部署专用，镜像默认使用 `:${PKG_VERSION}` 版本 tag，可通过 `.env` 覆盖。
-- `templates/client_gpu/compose/docker-compose.yml`：GPU 节点专用，使用 `:${PKG_VERSION}` 版本 tag。
-
-注意：M1 仅产出安装包，不包含安装脚本落地；安装/运维脚本将在 M2 落地并纳入包内。
-

deployment_new/build/common.sh

@@ -1,33 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-log() { echo -e "\033[0;34m[INFO]\033[0m $*"; }
-warn() { echo -e "\033[1;33m[WARN]\033[0m $*"; }
-err()  { echo -e "\033[0;31m[ERR ]\033[0m $*" >&2; }
-
-require_cmd() {
-  local miss=0
-  for c in "$@"; do
-    if ! command -v "$c" >/dev/null 2>&1; then err "missing command: $c"; miss=1; fi
-  done
-  [[ $miss -eq 0 ]]
-}
-
-today_version() { date +%Y%m%d; }
-
-checksum_dir() {
-  local dir="$1"; local out="$2"; : > "$out";
-  (cd "$dir" && find . -type f -print0 | sort -z | xargs -0 sha256sum) >> "$out"
-}
-
-make_dir() { mkdir -p "$1"; }
-
-copy_tree() {
-  local src="$1" dst="$2"; rsync -a --delete "$src/" "$dst/" 2>/dev/null || cp -r "$src/." "$dst/";
-}
-
-gen_manifest() {
-  local root="$1"; local out="$2"; : > "$out";
-  (cd "$root" && find . -maxdepth 4 -type f -printf "%p\n" | sort) >> "$out"
-}
-

deployment_new/build/make_client_gpu_package.sh

@@ -1,131 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Make client GPU package (versioned gpu bundle image, compose, env, docs, busybox)
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-TEMPL_DIR="$ROOT_DIR/deployment_new/templates/client_gpu"
-ART_ROOT="$ROOT_DIR/deployment_new/artifact/client_gpu"
-
-# Use deployment_new local common helpers
-COMMON_SH="$ROOT_DIR/deployment_new/build/common.sh"
-. "$COMMON_SH"
-
-usage(){ cat <<EOF
-Build Client-GPU Package (deployment_new)
-
-Usage: $(basename "$0") --version YYYYMMDD [--image IMAGE[:TAG]]
-
-Defaults:
-  image = argus-sys-metric-test-node-bundle-gpu:latest
-
-Outputs: deployment_new/artifact/client_gpu/<YYYYMMDD>/ and client_gpu_YYYYMMDD.tar.gz
-EOF
-}
-
-VERSION=""
-IMAGE="argus-sys-metric-test-node-bundle-gpu:latest"
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --version) VERSION="$2"; shift 2;;
-    --image) IMAGE="$2"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) err "unknown arg: $1"; usage; exit 1;;
-  esac
-done
-if [[ -z "$VERSION" ]]; then VERSION="$(today_version)"; fi
-
-require_cmd docker tar gzip
-
-STAGE="$(mktemp -d)"; trap 'rm -rf "$STAGE"' EXIT
-PKG_DIR="$ART_ROOT/$VERSION"
-mkdir -p "$PKG_DIR" "$STAGE/images" "$STAGE/compose" "$STAGE/docs" "$STAGE/scripts" "$STAGE/private/argus"
-
-# 1) Save GPU bundle image with version tag
-if ! docker image inspect "$IMAGE" >/dev/null 2>&1; then
-  err "missing image: $IMAGE"; exit 1; fi
-
-REPO="${IMAGE%%:*}"; TAG_VER="$REPO:$VERSION"
-docker tag "$IMAGE" "$TAG_VER"
-out_tar="$STAGE/images/${REPO//\//-}-$VERSION.tar"
-docker save -o "$out_tar" "$TAG_VER"
-gzip -f "$out_tar"
-
-# 2) Busybox tar for connectivity/overlay warmup (prefer local template; fallback to docker save)
-BB_SRC="$TEMPL_DIR/images/busybox.tar"
-if [[ -f "$BB_SRC" ]]; then
-  cp "$BB_SRC" "$STAGE/images/busybox.tar"
-else
-  if docker image inspect busybox:latest >/dev/null 2>&1 || docker pull busybox:latest >/dev/null 2>&1; then
-    docker save -o "$STAGE/images/busybox.tar" busybox:latest
-    log "Included busybox from local docker daemon"
-  else
-    warn "busybox image not found and cannot pull; skipping busybox.tar"
-  fi
-fi
-
-# 3) Compose + env template and docs/scripts from templates
-cp "$TEMPL_DIR/compose/docker-compose.yml" "$STAGE/compose/docker-compose.yml"
-ENV_EX="$STAGE/compose/.env.example"
-cat >"$ENV_EX" <<EOF
-# Generated by make_client_gpu_package.sh
-PKG_VERSION=$VERSION
-
-NODE_GPU_BUNDLE_IMAGE_TAG=${REPO}:${VERSION}
-
-# Compose project name (isolation from server stack)
-COMPOSE_PROJECT_NAME=argus-client
-
-# Required (no defaults). Must be filled before install.
-AGENT_ENV=
-AGENT_USER=
-AGENT_INSTANCE=
-GPU_NODE_HOSTNAME=
-
-# Overlay network (should match server包 overlay)
-ARGUS_OVERLAY_NET=argus-sys-net
-
-# From cluster-info.env (server package output)
-SWARM_MANAGER_ADDR=
-SWARM_JOIN_TOKEN_WORKER=
-SWARM_JOIN_TOKEN_MANAGER=
-EOF
-
-# 4) Docs from deployment_new templates
-CLIENT_DOC_SRC="$TEMPL_DIR/docs"
-if [[ -d "$CLIENT_DOC_SRC" ]]; then
-  rsync -a "$CLIENT_DOC_SRC/" "$STAGE/docs/" >/dev/null 2>&1 || cp -r "$CLIENT_DOC_SRC/." "$STAGE/docs/"
-fi
-
-# Placeholder scripts (will be implemented in M2)
-cat >"$STAGE/scripts/README.md" <<'EOF'
-# Client-GPU Scripts (Placeholder)
-
-本目录将在 M2 引入：
-- config.sh / install.sh
-
-当前为占位，便于包结构审阅。
-EOF
-
-# 5) Scripts (from deployment_new templates) and Private skeleton
-SCRIPTS_SRC="$TEMPL_DIR/scripts"
-if [[ -d "$SCRIPTS_SRC" ]]; then
-  rsync -a "$SCRIPTS_SRC/" "$STAGE/scripts/" >/dev/null 2>&1 || cp -r "$SCRIPTS_SRC/." "$STAGE/scripts/"
-  find "$STAGE/scripts" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
-fi
-mkdir -p "$STAGE/private/argus/agent"
-
-# 6) Manifest & checksums
-gen_manifest "$STAGE" "$STAGE/manifest.txt"
-checksum_dir "$STAGE" "$STAGE/checksums.txt"
-
-# 7) Move to artifact dir and pack
-mkdir -p "$PKG_DIR"
-rsync -a "$STAGE/" "$PKG_DIR/" >/dev/null 2>&1 || cp -r "$STAGE/." "$PKG_DIR/"
-
-OUT_TAR_DIR="$(dirname "$PKG_DIR")"
-OUT_TAR="$OUT_TAR_DIR/client_gpu_${VERSION}.tar.gz"
-log "Creating tarball: $OUT_TAR"
-(cd "$PKG_DIR/.." && tar -czf "$OUT_TAR" "$(basename "$PKG_DIR")")
-log "Client-GPU package ready: $PKG_DIR"
-echo "$OUT_TAR"

deployment_new/build/make_server_package.sh

@@ -1,160 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Make server deployment package (versioned, per-image tars, full compose, docs, skeleton)
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-TEMPL_DIR="$ROOT_DIR/deployment_new/templates/server"
-ART_ROOT="$ROOT_DIR/deployment_new/artifact/server"
-
-# Use deployment_new local common helpers
-COMMON_SH="$ROOT_DIR/deployment_new/build/common.sh"
-. "$COMMON_SH"
-
-usage(){ cat <<EOF
-Build Server Deployment Package (deployment_new)
-
-Usage: $(basename "$0") --version YYYYMMDD
-
-Outputs: deployment_new/artifact/server/<YYYYMMDD>/ and server_YYYYMMDD.tar.gz
-EOF
-}
-
-VERSION=""
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --version) VERSION="$2"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) err "unknown arg: $1"; usage; exit 1;;
-  esac
-done
-if [[ -z "$VERSION" ]]; then VERSION="$(today_version)"; fi
-
-require_cmd docker tar gzip awk sed
-
-IMAGES=(
-  argus-master
-  argus-elasticsearch
-  argus-kibana
-  argus-metric-prometheus
-  argus-metric-grafana
-  argus-alertmanager
-  argus-web-frontend
-  argus-web-proxy
-)
-
-STAGE="$(mktemp -d)"; trap 'rm -rf "$STAGE"' EXIT
-PKG_DIR="$ART_ROOT/$VERSION"
-mkdir -p "$PKG_DIR" "$STAGE/images" "$STAGE/compose" "$STAGE/docs" "$STAGE/scripts" "$STAGE/private/argus"
-
-# 1) Save per-image tars with version tag
-log "Tagging and saving images (version=$VERSION)"
-for repo in "${IMAGES[@]}"; do
-  if ! docker image inspect "$repo:latest" >/dev/null 2>&1 && ! docker image inspect "$repo:$VERSION" >/dev/null 2>&1; then
-    err "missing image: $repo (need :latest or :$VERSION)"; exit 1; fi
-  if docker image inspect "$repo:$VERSION" >/dev/null 2>&1; then
-    tag="$repo:$VERSION"
-  else
-    docker tag "$repo:latest" "$repo:$VERSION"
-    tag="$repo:$VERSION"
-  fi
-  out_tar="$STAGE/images/${repo//\//-}-$VERSION.tar"
-  docker save -o "$out_tar" "$tag"
-  gzip -f "$out_tar"
-done
-
-# 2) Compose + env template
-cp "$TEMPL_DIR/compose/docker-compose.yml" "$STAGE/compose/docker-compose.yml"
-ENV_EX="$STAGE/compose/.env.example"
-cat >"$ENV_EX" <<EOF
-# Generated by make_server_package.sh
-PKG_VERSION=$VERSION
-
-# Image tags (can be overridden). Default to versioned tags
-MASTER_IMAGE_TAG=argus-master:
-ES_IMAGE_TAG=argus-elasticsearch:
-KIBANA_IMAGE_TAG=argus-kibana:
-PROM_IMAGE_TAG=argus-metric-prometheus:
-GRAFANA_IMAGE_TAG=argus-metric-grafana:
-ALERT_IMAGE_TAG=argus-alertmanager:
-FRONT_IMAGE_TAG=argus-web-frontend:
-WEB_PROXY_IMAGE_TAG=argus-web-proxy:
-EOF
-sed -i "s#:\$#:${VERSION}#g" "$ENV_EX"
-
-# Ports and defaults (based on swarm_tests .env.example)
-cat >>"$ENV_EX" <<'EOF'
-
-# Host ports for server compose
-MASTER_PORT=32300
-ES_HTTP_PORT=9200
-KIBANA_PORT=5601
-PROMETHEUS_PORT=9090
-GRAFANA_PORT=3000
-ALERTMANAGER_PORT=9093
-WEB_PROXY_PORT_8080=8080
-WEB_PROXY_PORT_8081=8081
-WEB_PROXY_PORT_8082=8082
-WEB_PROXY_PORT_8083=8083
-WEB_PROXY_PORT_8084=8084
-WEB_PROXY_PORT_8085=8085
-
-# Overlay network name
-ARGUS_OVERLAY_NET=argus-sys-net
-
-# UID/GID for volume ownership
-ARGUS_BUILD_UID=2133
-ARGUS_BUILD_GID=2015
-
-# Compose project name (isolation from other stacks on same host)
-COMPOSE_PROJECT_NAME=argus-server
-EOF
-
-# 3) Docs (from deployment_new templates)
-DOCS_SRC="$TEMPL_DIR/docs"
-if [[ -d "$DOCS_SRC" ]]; then
-  rsync -a "$DOCS_SRC/" "$STAGE/docs/" >/dev/null 2>&1 || cp -r "$DOCS_SRC/." "$STAGE/docs/"
-fi
-
-# 6) Scripts (from deployment_new templates)
-SCRIPTS_SRC="$TEMPL_DIR/scripts"
-if [[ -d "$SCRIPTS_SRC" ]]; then
-  rsync -a "$SCRIPTS_SRC/" "$STAGE/scripts/" >/dev/null 2>&1 || cp -r "$SCRIPTS_SRC/." "$STAGE/scripts/"
-  find "$STAGE/scripts" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
-fi
-
-# 4) Private skeleton (minimum)
-mkdir -p \
-  "$STAGE/private/argus/etc" \
-  "$STAGE/private/argus/master" \
-  "$STAGE/private/argus/metric/prometheus" \
-  "$STAGE/private/argus/metric/prometheus/data" \
-  "$STAGE/private/argus/metric/prometheus/rules" \
-  "$STAGE/private/argus/metric/prometheus/targets" \
-  "$STAGE/private/argus/metric/grafana" \
-  "$STAGE/private/argus/metric/grafana/data" \
-  "$STAGE/private/argus/metric/grafana/logs" \
-  "$STAGE/private/argus/metric/grafana/plugins" \
-  "$STAGE/private/argus/metric/grafana/provisioning/datasources" \
-  "$STAGE/private/argus/metric/grafana/provisioning/dashboards" \
-  "$STAGE/private/argus/metric/grafana/data/sessions" \
-  "$STAGE/private/argus/metric/grafana/data/dashboards" \
-  "$STAGE/private/argus/metric/grafana/config" \
-  "$STAGE/private/argus/alert/alertmanager" \
-  "$STAGE/private/argus/log/elasticsearch" \
-  "$STAGE/private/argus/log/kibana"
-
-# 7) Manifest & checksums
-gen_manifest "$STAGE" "$STAGE/manifest.txt"
-checksum_dir "$STAGE" "$STAGE/checksums.txt"
-
-# 8) Move to artifact dir and pack
-mkdir -p "$PKG_DIR"
-rsync -a "$STAGE/" "$PKG_DIR/" >/dev/null 2>&1 || cp -r "$STAGE/." "$PKG_DIR/"
-
-OUT_TAR_DIR="$(dirname "$PKG_DIR")"
-OUT_TAR="$OUT_TAR_DIR/server_${VERSION}.tar.gz"
-log "Creating tarball: $OUT_TAR"
-(cd "$PKG_DIR/.." && tar -czf "$OUT_TAR" "$(basename "$PKG_DIR")")
-log "Server package ready: $PKG_DIR"
-echo "$OUT_TAR"

deployment_new/templates/client_gpu/compose/docker-compose.yml

@@ -1,38 +0,0 @@
-version: "3.8"
-
-networks:
-  argus-sys-net:
-    external: true
-
-services:
-  metric-gpu-node:
-    image: ${NODE_GPU_BUNDLE_IMAGE_TAG:-argus-sys-metric-test-node-bundle-gpu:${PKG_VERSION}}
-    container_name: argus-metric-gpu-node-swarm
-    hostname: ${GPU_NODE_HOSTNAME}
-    restart: unless-stopped
-    privileged: true
-    runtime: nvidia
-    environment:
-      - TZ=Asia/Shanghai
-      - DEBIAN_FRONTEND=noninteractive
-      - MASTER_ENDPOINT=${MASTER_ENDPOINT:-http://master.argus.com:3000}
-      # Fluent Bit / 日志上报目标（固定域名）
-      - ES_HOST=es.log.argus.com
-      - ES_PORT=9200
-      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
-      - AGENT_ENV=${AGENT_ENV}
-      - AGENT_USER=${AGENT_USER}
-      - AGENT_INSTANCE=${AGENT_INSTANCE}
-      - NVIDIA_VISIBLE_DEVICES=all
-      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
-      - GPU_MODE=gpu
-    networks:
-      argus-sys-net:
-        aliases:
-          - ${AGENT_INSTANCE}.node.argus.com
-    volumes:
-      - ../private/argus/agent:/private/argus/agent
-      - ../logs/infer:/logs/infer
-      - ../logs/train:/logs/train
-    command: ["sleep", "infinity"]

deployment_new/templates/client_gpu/docs/INSTALL_CLIENT_zh.md

@@ -1,73 +0,0 @@
-# Argus Client‑GPU 安装指南（deployment_new）
-
-## 一、准备条件（开始前确认）
-- GPU 节点安装了 NVIDIA 驱动，`nvidia-smi` 正常；
-- Docker & Docker Compose v2 已安装；
-- 使用统一账户 `argus`（UID=2133，GID=2015）执行安装，并加入 `docker` 组（如已创建可跳过）：
-  ```bash
-  sudo groupadd --gid 2015 argus || true
-  sudo useradd --uid 2133 --gid 2015 --create-home --shell /bin/bash argus || true
-  sudo passwd argus
-  sudo usermod -aG docker argus
-  su - argus -c 'id; docker ps >/dev/null && echo OK || echo NO_DOCKER_PERMISSION'
-  ```
-  后续解压与执行（config/install/uninstall）均使用 `argus` 账户进行。
-- 从 Server 安装方拿到 `cluster-info.env`（包含 `SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_*`；compose 架构下 BINDIP/FTPIP 不再使用）。
-
-## 二、解包
-- `tar -xzf client_gpu_YYYYMMDD.tar.gz`
-- 进入目录：`cd client_gpu_YYYYMMDD/`
-- 你应当看到：`images/`（GPU bundle、busybox）、`compose/`、`scripts/`、`docs/`。
-
-## 三、配置 config（预热 overlay + 生成 .env）
-命令：
-```
-cp /path/to/cluster-info.env ./   # 或 export CLUSTER_INFO=/abs/path/cluster-info.env
-./scripts/config.sh
-```
-脚本做了什么：
-- 读取 `cluster-info.env` 并 `docker swarm join`（幂等）；
-- 自动用 busybox 预热 external overlay `argus-sys-net`，等待最多 60s 直到本机可见；
-- 生成/更新 `compose/.env`：填入 `SWARM_*`，并“保留你已填写的 AGENT_* 与 GPU_NODE_HOSTNAME”（不会覆盖）。
-
-看到什么才算成功：
-- 终端输出类似：`已预热 overlay=argus-sys-net 并生成 compose/.env；可执行 scripts/install.sh`；
-- `compose/.env` 至少包含：
-  - `AGENT_ENV/AGENT_USER/AGENT_INSTANCE/GPU_NODE_HOSTNAME`（需要你提前填写）；
-  - `SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_*`；
- - `NODE_GPU_BUNDLE_IMAGE_TAG=...:YYYYMMDD`。
-
-### 日志映射（重要）
-- 容器内 `/logs/infer` 与 `/logs/train` 已映射到包根 `./logs/infer` 与 `./logs/train`：
-  - 你可以直接在宿主机查看推理/训练日志：`tail -f logs/infer/*.log`、`tail -f logs/train/*.log`；
-  - install 脚本会自动创建这两个目录。
-
-若提示缺少必填项：
-- 打开 `compose/.env` 按提示补齐 `AGENT_*` 与 `GPU_NODE_HOSTNAME`，再次执行 `./scripts/config.sh`（脚本不会覆盖你已填的值）。
-
-## 四、安装 install（加载镜像 + 起容器 + 跟日志）
-命令：
-```
-./scripts/install.sh
-```
-脚本做了什么：
-- 如有必要，先自动预热 overlay；
-- 从 `images/` 导入 `argus-sys-metric-test-node-bundle-gpu-*.tar.gz` 到本地 Docker；
-- `docker compose up -d` 启动 GPU 节点容器，并自动执行 `docker logs -f argus-metric-gpu-node-swarm` 跟踪安装过程。
-
-看到什么才算成功：
-- 日志中出现：`[BOOT] local bundle install OK: version=...` / `dcgm-exporter ... listening` / `node state present: /private/argus/agent/<hostname>/node.json`；
-- `docker exec argus-metric-gpu-node-swarm nvidia-smi -L` 能列出 GPU；
-- 在 Server 侧 Prometheus `/api/v1/targets` 中，GPU 节点 9100（node-exporter）与 9400（dcgm-exporter）至少其一 up。
-
-## 五、卸载 uninstall
-命令：
-```
-./scripts/uninstall.sh
-```
-行为：Compose down（如有 .env），并删除 warmup 容器与节点容器。
-
-## 六、常见问题
-- `本机未看到 overlay`：config/install 已自动预热；若仍失败，请检查与 manager 的网络连通性以及 manager 上是否已创建 `argus-sys-net`。
-- `busybox 缺失`：确保包根 `images/busybox.tar` 在，或主机已有 `busybox:latest`。
-- `加入 Swarm 失败`：确认 `cluster-info.env` 的 `SWARM_MANAGER_ADDR` 与 `SWARM_JOIN_TOKEN_WORKER` 正确，或在 manager 上重新 `docker swarm join-token -q worker` 后更新该文件。

deployment_new/templates/client_gpu/scripts/config.sh

@@ -1,90 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_EX="$PKG_ROOT/compose/.env.example"
-ENV_OUT="$PKG_ROOT/compose/.env"
-
-info(){ echo -e "\033[34m[CONFIG-GPU]\033[0m $*"; }
-err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
-require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
-# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
-require_compose(){
-  if docker compose version >/dev/null 2>&1; then return 0; fi
-  if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
-  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
-}
-require docker curl jq awk sed tar gzip
-require_compose
-
-# 磁盘空间检查（MB）
-check_disk(){ local p="$1"; local need=10240; local free
-  free=$(df -Pm "$p" | awk 'NR==2{print $4+0}')
-  if [[ -z "$free" || "$free" -lt "$need" ]]; then err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)"; return 1; fi
-}
-check_disk "$PKG_ROOT"; check_disk "/var/lib/docker" || true
-
-# 导入 cluster-info.env（默认取当前包根，也可用 CLUSTER_INFO 指定路径）
-CI_IN="${CLUSTER_INFO:-$PKG_ROOT/cluster-info.env}"
-info "读取 cluster-info.env: $CI_IN"
-[[ -f "$CI_IN" ]] || { err "找不到 cluster-info.env（默认当前包根，或设置环境变量 CLUSTER_INFO 指定绝对路径）"; exit 1; }
-set -a; source "$CI_IN"; set +a
-[[ -n "${SWARM_MANAGER_ADDR:-}" && -n "${SWARM_JOIN_TOKEN_WORKER:-}" ]] || { err "cluster-info.env 缺少 SWARM 信息（SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_WORKER）"; exit 1; }
-
-# 加入 Swarm（幂等）
-info "加入 Swarm（幂等）：$SWARM_MANAGER_ADDR"
-docker swarm join --token "$SWARM_JOIN_TOKEN_WORKER" "$SWARM_MANAGER_ADDR":2377 >/dev/null 2>&1 || true
-
-# 导入 busybox 并做 overlay 预热与连通性（总是执行）
-NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
-# 准备 busybox
-if ! docker image inspect busybox:latest >/dev/null 2>&1; then
-  if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then
-    info "加载 busybox.tar 以预热 overlay"
-    docker load -i "$PKG_ROOT/images/busybox.tar" >/dev/null
-  else
-    err "缺少 busybox 镜像（包内 images/busybox.tar 或本地 busybox:latest），无法预热 overlay $NET_NAME"; exit 1
-  fi
-fi
-# 预热容器（worker 侧加入 overlay 以便本地可见）
-docker rm -f argus-net-warmup >/dev/null 2>&1 || true
-info "启动 warmup 容器加入 overlay: $NET_NAME"
-docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
-for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && { info "overlay 可见 (t=${i}s)"; break; }; sleep 1; done
-docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 manager 已创建并网络可达"; exit 1; }
-
-# 通过 warmup 容器测试实际数据通路（alias → master）
-if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
-  err "warmup 容器内无法通过别名访问 master.argus.com；请确认 server compose 已启动并加入 overlay $NET_NAME"
-  exit 1
-fi
-info "warmup 容器内可达 master.argus.com（Docker DNS + alias 正常）"
-
-# 生成/更新 .env（保留人工填写项，不覆盖已有键）
-if [[ ! -f "$ENV_OUT" ]]; then
-  cp "$ENV_EX" "$ENV_OUT"
-fi
-
-set_kv(){ local k="$1" v="$2"; if grep -q "^${k}=" "$ENV_OUT"; then sed -i -E "s#^${k}=.*#${k}=${v}#" "$ENV_OUT"; else echo "${k}=${v}" >> "$ENV_OUT"; fi }
-
-set_kv SWARM_MANAGER_ADDR "${SWARM_MANAGER_ADDR:-}"
-set_kv SWARM_JOIN_TOKEN_WORKER "${SWARM_JOIN_TOKEN_WORKER:-}"
-set_kv SWARM_JOIN_TOKEN_MANAGER "${SWARM_JOIN_TOKEN_MANAGER:-}"
-
-REQ_VARS=(AGENT_ENV AGENT_USER AGENT_INSTANCE GPU_NODE_HOSTNAME)
-missing=()
-for v in "${REQ_VARS[@]}"; do
-  val=$(grep -E "^$v=" "$ENV_OUT" | head -1 | cut -d= -f2-)
-  if [[ -z "$val" ]]; then missing+=("$v"); fi
-done
-if [[ ${#missing[@]} -gt 0 ]]; then
-  err "以下变量必须在 compose/.env 中填写：${missing[*]}（已保留你现有的内容，不会被覆盖）"; exit 1; fi
-
-info "已生成 compose/.env；可执行 scripts/install.sh"
-
-# 准备并赋权宿主日志目录（幂等，便于安装前人工检查/预创建）
-mkdir -p "$PKG_ROOT/logs/train" "$PKG_ROOT/logs/infer"
-chmod 1777 "$PKG_ROOT/logs/train" "$PKG_ROOT/logs/infer" || true
-info "日志目录权限（期待 1777，含粘滞位）:"
-stat -c '%a %U:%G %n' "$PKG_ROOT/logs/train" "$PKG_ROOT/logs/infer" 2>/dev/null || true

deployment_new/templates/client_gpu/scripts/install.sh

@@ -1,72 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_FILE="$PKG_ROOT/compose/.env"
-COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
-
-info(){ echo -e "\033[34m[INSTALL-GPU]\033[0m $*"; }
-err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
-require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
-# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
-require_compose(){
-  if docker compose version >/dev/null 2>&1; then return 0; fi
-  if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
-  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
-}
-require docker nvidia-smi
-require_compose
-
-[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env，请先运行 scripts/config.sh"; exit 1; }
-info "使用环境文件: $ENV_FILE"
-
-# 预热 overlay（当 config 执行很久之前或容器已被清理时，warmup 可能不存在）
-set -a; source "$ENV_FILE"; set +a
-NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
-info "检查 overlay 网络可见性: $NET_NAME"
-if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
-  # 如 Overlay 不可见，尝试用 busybox 预热（仅为确保 worker 节点已加入 overlay）
-  if ! docker image inspect busybox:latest >/dev/null 2>&1; then
-    if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then docker load -i "$PKG_ROOT/images/busybox.tar"; else err "缺少 busybox 镜像（images/busybox.tar 或本地 busybox:latest）"; exit 1; fi
-  fi
-  docker rm -f argus-net-warmup >/dev/null 2>&1 || true
-  docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
-  for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && break; sleep 1; done
-  docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 manager 已创建并网络可达"; exit 1; }
-  info "overlay 已可见（warmup=argus-net-warmup）"
-fi
-
-# 若本函数内重新创建了 warmup 容器，同样测试一次 alias 数据通路
-if docker ps --format '{{.Names}}' | grep -q '^argus-net-warmup$'; then
-  if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
-    err "GPU install 阶段：warmup 容器内无法通过别名访问 master.argus.com；请检查 overlay $NET_NAME 与 server 状态"
-    exit 1
-  fi
-  info "GPU install 阶段：warmup 容器内可达 master.argus.com"
-fi
-
-# 导入 GPU bundle 镜像
-IMG_TGZ=$(ls -1 "$PKG_ROOT"/images/argus-sys-metric-test-node-bundle-gpu-*.tar.gz 2>/dev/null | head -1 || true)
-[[ -n "$IMG_TGZ" ]] || { err "找不到 GPU bundle 镜像 tar.gz"; exit 1; }
-info "导入 GPU bundle 镜像: $(basename "$IMG_TGZ")"
-tmp=$(mktemp); gunzip -c "$IMG_TGZ" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
-
-# 确保日志目录存在（宿主侧，用于映射 /logs/infer 与 /logs/train），并赋权 1777（粘滞位）
-mkdir -p "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train"
-chmod 1777 "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" || true
-info "日志目录已准备并赋权 1777: logs/infer logs/train"
-stat -c '%a %U:%G %n' "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" 2>/dev/null || true
-
-# 启动 compose 并跟踪日志
-PROJECT="${COMPOSE_PROJECT_NAME:-argus-client}"
-info "启动 GPU 节点 (docker compose -p $PROJECT up -d)"
-docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
-docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
-
-# 再次校准宿主日志目录权限，避免容器内脚本对 bind mount 权限回退
-chmod 1777 "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" || true
-stat -c '%a %U:%G %n' "$PKG_ROOT/logs/infer" "$PKG_ROOT/logs/train" 2>/dev/null || true
-
-info "跟踪节点容器日志（按 Ctrl+C 退出）"
-docker logs -f argus-metric-gpu-node-swarm || true

deployment_new/templates/client_gpu/scripts/uninstall.sh

@@ -1,36 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_FILE="$PKG_ROOT/compose/.env"
-COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
-
-# load COMPOSE_PROJECT_NAME if provided in compose/.env
-if [[ -f "$ENV_FILE" ]]; then set -a; source "$ENV_FILE"; set +a; fi
-PROJECT="${COMPOSE_PROJECT_NAME:-argus-client}"
-
-info(){ echo -e "\033[34m[UNINSTALL-GPU]\033[0m $*"; }
-err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
-# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
-require_compose(){
-  if docker compose version >/dev/null 2>&1; then return 0; fi
-  if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
-  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
-}
-require_compose
-
-if [[ -f "$ENV_FILE" ]]; then
-  info "stopping compose project (project=$PROJECT)"
-  docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
-else
-  info "compose/.env not found; attempting to remove container by name"
-fi
-
-# remove warmup container if still running
-docker rm -f argus-net-warmup >/dev/null 2>&1 || true
-
-# remove node container if present
-docker rm -f argus-metric-gpu-node-swarm >/dev/null 2>&1 || true
-
-info "uninstall completed"

deployment_new/templates/server/compose/docker-compose.yml

@@ -1,169 +0,0 @@
-version: "3.8"
-
-networks:
-  argus-sys-net:
-    external: true
-
-services:
-  master:
-    image: ${MASTER_IMAGE_TAG:-argus-master:${PKG_VERSION}}
-    container_name: argus-master-sys
-    environment:
-      - OFFLINE_THRESHOLD_SECONDS=6
-      - ONLINE_THRESHOLD_SECONDS=2
-      - SCHEDULER_INTERVAL_SECONDS=1
-      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
-    ports:
-      - "${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:
-      argus-sys-net:
-        aliases:
-          - master.argus.com
-    restart: unless-stopped
-
-  es:
-    image: ${ES_IMAGE_TAG:-argus-elasticsearch:${PKG_VERSION}}
-    container_name: argus-es-sys
-    environment:
-      - discovery.type=single-node
-      - xpack.security.enabled=false
-      - ES_JAVA_OPTS=-Xms512m -Xmx512m
-      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
-    volumes:
-      - ../private/argus/log/elasticsearch:/private/argus/log/elasticsearch
-      - ../private/argus/etc:/private/argus/etc
-    ports:
-      - "${ES_HTTP_PORT:-9200}:9200"
-    restart: unless-stopped
-    networks:
-      argus-sys-net:
-        aliases:
-          - es.log.argus.com
-
-  kibana:
-    image: ${KIBANA_IMAGE_TAG:-argus-kibana:${PKG_VERSION}}
-    container_name: argus-kibana-sys
-    environment:
-      - ELASTICSEARCH_HOSTS=http://es.log.argus.com:9200
-      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
-    volumes:
-      - ../private/argus/log/kibana:/private/argus/log/kibana
-      - ../private/argus/etc:/private/argus/etc
-    depends_on: [es]
-    ports:
-      - "${KIBANA_PORT:-5601}:5601"
-    restart: unless-stopped
-    networks:
-      argus-sys-net:
-        aliases:
-          - kibana.log.argus.com
-
-  prometheus:
-    image: ${PROM_IMAGE_TAG:-argus-metric-prometheus:${PKG_VERSION}}
-    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
-    networks:
-      argus-sys-net:
-        aliases:
-          - prom.metric.argus.com
-
-  grafana:
-    image: ${GRAFANA_IMAGE_TAG:-argus-metric-grafana:${PKG_VERSION}}
-    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
-    depends_on: [prometheus]
-    networks:
-      argus-sys-net:
-        aliases:
-          - grafana.metric.argus.com
-
-  alertmanager:
-    image: ${ALERT_IMAGE_TAG:-argus-alertmanager:${PKG_VERSION}}
-    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:
-      argus-sys-net:
-        aliases:
-          - alertmanager.alert.argus.com
-    ports:
-      - "${ALERTMANAGER_PORT:-9093}:9093"
-    restart: unless-stopped
-
-  web-frontend:
-    image: ${FRONT_IMAGE_TAG:-argus-web-frontend:${PKG_VERSION}}
-    container_name: argus-web-frontend
-    environment:
-      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
-      - 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:
-      argus-sys-net:
-        aliases:
-          - web.argus.com
-    restart: unless-stopped
-
-  web-proxy:
-    image: ${WEB_PROXY_IMAGE_TAG:-argus-web-proxy:${PKG_VERSION}}
-    container_name: argus-web-proxy
-    depends_on: [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:
-      argus-sys-net:
-        aliases:
-          - proxy.argus.com
-    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

deployment_new/templates/server/docs/INSTALL_SERVER_zh.md

@@ -1,102 +0,0 @@
-# Argus Server 安装指南（deployment_new）
-
-适用：通过 Server 安装包在 Docker Swarm + external overlay 网络一体化部署 Argus 服务端组件。
-
-—— 本文强调“怎么做、看什么、符合了才继续”。
-
-## 一、准备条件（开始前确认）
-- Docker 与 Docker Compose v2 已安装；`docker info` 正常；`docker compose version` 可执行。
-- 具备 root/sudo 权限；磁盘可用空间 ≥ 10GB（包根与 `/var/lib/docker`）。
-- 你知道本机管理地址（SWARM_MANAGER_ADDR），该 IP 属于本机某网卡，可被其他节点访问。
-- 很重要：以统一账户 `argus`（UID=2133，GID=2015）执行后续安装与运维，并将其加入 `docker` 组；示例命令如下（如需不同 UID/GID，请替换为贵方标准）：
-  ```bash
-  # 1) 创建主组（GID=2015，组名 argus；若已存在可跳过）
-  sudo groupadd --gid 2015 argus || true
-
-  # 2) 创建用户 argus（UID=2133、主组 GID=2015，创建家目录并用 bash 作为默认 shell；若已存在可用 usermod 调整）
-  sudo useradd --uid 2133 --gid 2015 --create-home --shell /bin/bash argus || true
-  sudo passwd argus
-
-  # 3) 将 argus 加入 docker 组，使其能调用 Docker Daemon（新登录后生效）
-  sudo usermod -aG docker argus
-
-  # 4) 验证（重新登录或执行 newgrp docker 使组生效）
-  su - argus -c 'id; docker ps >/dev/null && echo OK || echo NO_DOCKER_PERMISSION'
-  ```
-  后续的解压与执行（config/install/selfcheck 等）均使用该 `argus` 账户进行。
-
-## 二、解包与目录结构
-- 解压：`tar -xzf server_YYYYMMDD.tar.gz`。
-- 进入：`cd server_YYYYMMDD/`
-- 你应当能看到：
-  - `images/`（逐服务镜像 tar.gz，如 `argus-master-YYYYMMDD.tar.gz`）
-  - `compose/`（`docker-compose.yml` 与 `.env.example`）
-  - `scripts/`（安装/运维脚本）
-  - `private/argus/`（数据与配置骨架）
-  - `docs/`（中文文档）
-
-## 三、配置 config（生成 .env 与 SWARM_MANAGER_ADDR）
-命令：
-```
-export SWARM_MANAGER_ADDR=<本机管理IP>
-./scripts/config.sh
-```
-脚本做了什么：
-- 检查依赖与磁盘空间；
-- 自动从“端口 20000 起”分配所有服务端口，确保“系统未占用”且“彼此不冲突”；
-- 写入 `compose/.env`（包含端口、镜像 tag、overlay 名称与 UID/GID 等）；
-- 将当前执行账户的 UID/GID 写入 `ARGUS_BUILD_UID/GID`（若主组名是 docker，会改用“与用户名同名的组”的 GID，避免拿到 docker 组 999）；
-- 更新/追加 `cluster-info.env` 中的 `SWARM_MANAGER_ADDR`（不会覆盖其他键）。
-
-看到什么才算成功：
-- 终端输出：`已生成 compose/.env 并更新 cluster-info.env 的 SWARM_MANAGER_ADDR。`
-- `compose/.env` 打开应当看到：
-  - 端口均 ≥20000 且没有重复；
-  - `ARGUS_BUILD_UID/GID` 与 `id -u/-g` 一致；
-  - `SWARM_MANAGER_ADDR=<你的IP>`。
-
-遇到问题：
-- 端口被异常占用：可删去 `.env` 后再次执行 `config.sh`，或手工编辑端口再执行 `install.sh`。
-
-## 四、安装 install（一次到位）
-命令：
-```
-./scripts/install.sh
-```
-脚本做了什么：
-- 若 Swarm 未激活：执行 `docker swarm init --advertise-addr $SWARM_MANAGER_ADDR`；
-- 确保 external overlay `argus-sys-net` 存在；
-- 导入 `images/*.tar.gz` 到本机 Docker；
-- `docker compose up -d` 启动服务；
-- 等待“六项就绪”：
-  - Master `/readyz`=200、ES `/_cluster/health`=200、Prometheus TCP 可达、Grafana `/api/health`=200、Alertmanager `/api/v2/status`=200、Kibana `/api/status` level=available；
-- 校验 Docker DNS + overlay alias：在 `argus-web-proxy` 内通过 `getent hosts` 与 `curl` 检查 `master.argus.com`、`grafana.metric.argus.com` 等域名连通性；
-- 写出 `cluster-info.env`（含 `SWARM_JOIN_TOKEN_{WORKER,MANAGER}/SWARM_MANAGER_ADDR`；compose 架构下不再依赖 BINDIP/FTPIP）；
-- 生成 `安装报告_YYYYMMDD-HHMMSS.md`（端口、健康检查摘要与提示）。
-
-看到什么才算成功：
-- `docker compose ps` 全部是 Up；
-- `安装报告_…md` 中各项 HTTP 检查为 200/available；
-- `cluster-info.env` 包含五个关键键：
-  - `SWARM_MANAGER_ADDR=...`
-  - `SWARM_MANAGER_ADDR=...` `SWARM_JOIN_TOKEN_*=...`
-  - `SWARM_JOIN_TOKEN_WORKER=SWMTKN-...`
-  - `SWARM_JOIN_TOKEN_MANAGER=SWMTKN-...`
-
-## 五、健康自检与常用操作
-- 健康自检：`./scripts/selfcheck.sh`
-  - 期望输出：`selfcheck OK -> logs/selfcheck.json`
-  - 文件 `logs/selfcheck.json` 中 `overlay_net/es/kibana/master_readyz/prometheus/grafana/alertmanager/web_proxy_cors` 为 true。
-- 状态：`./scripts/status.sh`（相当于 `docker compose ps`）。
-- 诊断：`./scripts/diagnose.sh`（收集容器/HTTP/CORS/ES 细节，输出到 `logs/diagnose_*.log`）。
-- 卸载：`./scripts/uninstall.sh`（Compose down）。
-- ES 磁盘水位临时放宽/还原：`./scripts/es-watermark-relax.sh` / `./scripts/es-watermark-restore.sh`。
-
-## 六、下一步：分发 cluster-info.env 给 Client
-- 将 `cluster-info.env` 拷贝给安装 Client 的同事；
-- 对方在 Client 机器的包根放置该文件（或设置 `CLUSTER_INFO=/绝对路径`）即可。
-
-## 七、故障排查快览
-- Proxy 502 或 8080 连接复位：通常是 overlay alias 未生效或 web-proxy 尚未解析到其它服务；重跑 `install.sh`（会重启栈并在容器内校验 DNS），或查看 `logs/diagnose_error.log`。
-- Kibana 不 available：等待 1–2 分钟、查看 `argus-kibana-sys` 日志；
-- cluster-info.env 的 SWARM_MANAGER_ADDR 为空：重新 `export SWARM_MANAGER_ADDR=<IP>; ./scripts/config.sh` 或 `./scripts/install.sh`（会回读 `.env` 补写）。

deployment_new/templates/server/docs/SWARM_DEPLOY_zh.md

@@ -1,7 +0,0 @@
-# Docker Swarm 部署要点
-
-- 初始化 Swarm：`docker swarm init --advertise-addr <SWARM_MANAGER_ADDR>`
-- 创建 overlay：`docker network create --driver overlay --attachable argus-sys-net`
-- Server 包 `install.sh` 自动完成上述操作；如需手动执行，确保 `argus-sys-net` 存在且 attachable。
-- Worker 节点加入：`docker swarm join --token <worker_token> <SWARM_MANAGER_ADDR>:2377`。
-

deployment_new/templates/server/docs/TROUBLESHOOTING_zh.md

@@ -1,11 +0,0 @@
-# 故障排查（Server）
-
-- 端口占用：查看 `安装报告_*.md` 中端口表；如需修改，编辑 `compose/.env` 后执行 `docker compose ... up -d`。
-- 组件未就绪：
-  - Master: `curl http://127.0.0.1:${MASTER_PORT}/readyz -I`
-  - ES: `curl http://127.0.0.1:${ES_HTTP_PORT}/_cluster/health`
-  - Grafana: `curl http://127.0.0.1:${GRAFANA_PORT}/api/health`
-  - Prometheus TCP: `exec 3<>/dev/tcp/127.0.0.1/${PROMETHEUS_PORT}`
-- 域名解析：进入 `argus-web-proxy` 或 `argus-master-sys` 容器：`getent hosts master.argus.com`。
-- Swarm/Overlay：检查 `docker network ls | grep argus-sys-net`，或 `docker node ls`。
-

deployment_new/templates/server/scripts/config.sh

@@ -1,108 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_EX="$PKG_ROOT/compose/.env.example"
-ENV_OUT="$PKG_ROOT/compose/.env"
-
-info(){ echo -e "\033[34m[CONFIG]\033[0m $*"; }
-err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
-require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
-# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
-require_compose(){
-  if docker compose version >/dev/null 2>&1; then return 0; fi
-  if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
-  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
-}
-
-require docker curl jq awk sed tar gzip
-require_compose
-
-# 磁盘空间检查（MB）
-check_disk(){ local p="$1"; local need=10240; local free
-  free=$(df -Pm "$p" | awk 'NR==2{print $4+0}')
-  if [[ -z "$free" || "$free" -lt "$need" ]]; then err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)"; return 1; fi
-}
-
-check_disk "$PKG_ROOT"; check_disk "/var/lib/docker" || true
-
-# 读取/生成 SWARM_MANAGER_ADDR
-SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}
-if [[ -z "${SWARM_MANAGER_ADDR}" ]]; then
-  read -rp "请输入本机管理地址 SWARM_MANAGER_ADDR: " SWARM_MANAGER_ADDR
-fi
-info "SWARM_MANAGER_ADDR=$SWARM_MANAGER_ADDR"
-
-# 校验 IP 属于本机网卡
-if ! ip -o addr | awk '{print $4}' | cut -d'/' -f1 | grep -qx "$SWARM_MANAGER_ADDR"; then
-  err "SWARM_MANAGER_ADDR 非本机地址: $SWARM_MANAGER_ADDR"; exit 1; fi
-
-info "开始分配服务端口（起始=20000，避免系统占用与相互冲突）"
-is_port_used(){ local p="$1"; ss -tulnH 2>/dev/null | awk '{print $5}' | sed 's/.*://g' | grep -qx "$p"; }
-declare -A PRESENT=() CHOSEN=() USED=()
-START_PORT="${START_PORT:-20000}"; cur=$START_PORT
-ORDER=(MASTER_PORT ES_HTTP_PORT KIBANA_PORT PROMETHEUS_PORT GRAFANA_PORT ALERTMANAGER_PORT \
-       WEB_PROXY_PORT_8080 WEB_PROXY_PORT_8081 WEB_PROXY_PORT_8082 WEB_PROXY_PORT_8083 WEB_PROXY_PORT_8084 WEB_PROXY_PORT_8085 \
-       FTP_PORT FTP_DATA_PORT)
-
-# 标记 .env.example 中实际存在的键
-for key in "${ORDER[@]}"; do
-  if grep -q "^${key}=" "$ENV_EX"; then PRESENT[$key]=1; fi
-done
-
-next_free(){ local p="$1"; while :; do if [[ -n "${USED[$p]:-}" ]] || is_port_used "$p"; then p=$((p+1)); else echo "$p"; return; fi; done; }
-
-for key in "${ORDER[@]}"; do
-  [[ -z "${PRESENT[$key]:-}" ]] && continue
-  p=$(next_free "$cur"); CHOSEN[$key]="$p"; USED[$p]=1; cur=$((p+1))
-done
-
-info "端口分配结果：MASTER=${CHOSEN[MASTER_PORT]:-} ES=${CHOSEN[ES_HTTP_PORT]:-} KIBANA=${CHOSEN[KIBANA_PORT]:-} PROM=${CHOSEN[PROMETHEUS_PORT]:-} GRAFANA=${CHOSEN[GRAFANA_PORT]:-} ALERT=${CHOSEN[ALERTMANAGER_PORT]:-} WEB_PROXY(8080..8085)=${CHOSEN[WEB_PROXY_PORT_8080]:-}/${CHOSEN[WEB_PROXY_PORT_8081]:-}/${CHOSEN[WEB_PROXY_PORT_8082]:-}/${CHOSEN[WEB_PROXY_PORT_8083]:-}/${CHOSEN[WEB_PROXY_PORT_8084]:-}/${CHOSEN[WEB_PROXY_PORT_8085]:-}"
-
-cp "$ENV_EX" "$ENV_OUT"
-# 覆盖端口（按唯一化结果写回）
-for key in "${ORDER[@]}"; do
-  val="${CHOSEN[$key]:-}"
-  [[ -z "$val" ]] && continue
-  sed -i -E "s#^$key=.*#$key=${val}#" "$ENV_OUT"
-done
-info "已写入 compose/.env 的端口配置"
-# 覆盖/补充 Overlay 名称
-grep -q '^ARGUS_OVERLAY_NET=' "$ENV_OUT" || echo 'ARGUS_OVERLAY_NET=argus-sys-net' >> "$ENV_OUT"
-# 以当前执行账户 UID/GID 写入（避免误选 docker 组）
-RUID=$(id -u)
-PRIMARY_GID=$(id -g)
-PRIMARY_GRP=$(id -gn)
-USER_NAME=$(id -un)
-# 若主组名被解析为 docker，尝试用与用户名同名的组的 GID；否则回退主 GID
-if [[ "$PRIMARY_GRP" == "docker" ]]; then
-  RGID=$(getent group "$USER_NAME" | awk -F: '{print $3}' 2>/dev/null || true)
-  [[ -z "$RGID" ]] && RGID="$PRIMARY_GID"
-else
-  RGID="$PRIMARY_GID"
-fi
-info "使用构建账户 UID:GID=${RUID}:${RGID} (user=$USER_NAME primary_group=$PRIMARY_GRP)"
-if grep -q '^ARGUS_BUILD_UID=' "$ENV_OUT"; then
-  sed -i -E "s#^ARGUS_BUILD_UID=.*#ARGUS_BUILD_UID=${RUID}#" "$ENV_OUT"
-else
-  echo "ARGUS_BUILD_UID=${RUID}" >> "$ENV_OUT"
-fi
-if grep -q '^ARGUS_BUILD_GID=' "$ENV_OUT"; then
-  sed -i -E "s#^ARGUS_BUILD_GID=.*#ARGUS_BUILD_GID=${RGID}#" "$ENV_OUT"
-else
-  echo "ARGUS_BUILD_GID=${RGID}" >> "$ENV_OUT"
-fi
-
-CI="$PKG_ROOT/cluster-info.env"
-if [[ -f "$CI" ]]; then
-  if grep -q '^SWARM_MANAGER_ADDR=' "$CI"; then
-    sed -i -E "s#^SWARM_MANAGER_ADDR=.*#SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}#" "$CI"
-  else
-    echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" >> "$CI"
-  fi
-else
-  echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" > "$CI"
-fi
-info "已生成 compose/.env 并更新 cluster-info.env 的 SWARM_MANAGER_ADDR。"
-info "下一步可执行: scripts/install.sh"

deployment_new/templates/server/scripts/diagnose.sh

@@ -1,109 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-
-ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
-
-ts="$(date -u +%Y%m%d-%H%M%SZ)"
-LOG_DIR="$ROOT/logs"; mkdir -p "$LOG_DIR" || true
-if ! ( : > "$LOG_DIR/.w" 2>/dev/null ); then LOG_DIR="/tmp/argus-logs"; mkdir -p "$LOG_DIR" || true; fi
-
-# load compose project for accurate ps output
-ENV_FILE="$ROOT/compose/.env"
-if [[ -f "$ENV_FILE" ]]; then set -a; source "$ENV_FILE"; set +a; fi
-PROJECT="${COMPOSE_PROJECT_NAME:-argus-server}"
-DETAILS="$LOG_DIR/diagnose_details_${ts}.log"; ERRORS="$LOG_DIR/diagnose_error_${ts}.log"; : > "$DETAILS"; : > "$ERRORS"
-
-logd() { echo "$(date '+%F %T') $*" >> "$DETAILS"; }
-append_err() { echo "$*" >> "$ERRORS"; }
-http_code() { curl -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
-http_body_head() { curl -s --max-time 3 "$1" 2>/dev/null | sed -n '1,5p' || true; }
-header_val() { curl -s -D - -o /dev/null "$@" | awk -F': ' 'BEGIN{IGNORECASE=1}$1=="Access-Control-Allow-Origin"{gsub("\r","",$2);print $2}'; }
-
-section() { local name="$1"; logd "===== [$name] ====="; }
-svc() {
-  local svc_name="$1"; local cname="$2"; shift 2
-  section "$svc_name ($cname)"
-  logd "docker ps:"; docker ps -a --format '{{.Names}}\t{{.Status}}\t{{.Image}}' | awk -v n="$cname" '$1==n' >> "$DETAILS" || true
-  logd "docker inspect:"; docker inspect -f '{{.State.Status}} rc={{.RestartCount}} started={{.State.StartedAt}}' "$cname" >> "$DETAILS" 2>&1 || true
-  logd "last 200 container logs:"; docker logs --tail 200 "$cname" >> "$DETAILS" 2>&1 || true
-  docker logs --tail 200 "$cname" 2>&1 | grep -Ei '\\b(error|failed|fail|exception|panic|fatal|critical|unhealthy|permission denied|forbidden|refused|traceback|错误|失败)\\b' | sed "s/^/[${svc_name}][container] /" >> "$ERRORS" || true
-  if docker exec "$cname" sh -lc 'command -v supervisorctl >/dev/null 2>&1' >/dev/null 2>&1; then
-    logd "supervisorctl status:"; docker exec "$cname" sh -lc 'supervisorctl status' >> "$DETAILS" 2>&1 || true
-    local files; files=$(docker exec "$cname" sh -lc 'ls /var/log/supervisor/*.log 2>/dev/null' || true)
-    for f in $files; do
-      logd "tail -n 80 $f:"; docker exec "$cname" sh -lc "tail -n 80 $f 2>/dev/null || true" >> "$DETAILS" 2>&1 || true
-      docker exec "$cname" sh -lc "tail -n 200 $f 2>/dev/null" 2>/dev/null | grep -Ei '\\b(error|failed|fail|exception|panic|fatal|critical|unhealthy|permission denied|forbidden|refused|traceback|错误|失败)\\b' | sed "s/^/[${svc_name}][supervisor:$(basename $f)] /" >> "$ERRORS" || true
-    done
-  fi
-}
-
-svc master argus-master-sys
-svc es argus-es-sys
-svc kibana argus-kibana-sys
-svc prometheus argus-prometheus
-svc grafana argus-grafana
-svc alertmanager argus-alertmanager
-svc web-frontend argus-web-frontend
-svc web-proxy argus-web-proxy
-
-section HTTP
-logd "ES: $(http_code \"http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health\")"; http_body_head "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" >> "$DETAILS" 2>&1 || true
-logd "Kibana: $(http_code \"http://localhost:${KIBANA_PORT:-5601}/api/status\")"; http_body_head "http://localhost:${KIBANA_PORT:-5601}/api/status" >> "$DETAILS" 2>&1 || true
-logd "Master readyz: $(http_code \"http://localhost:${MASTER_PORT:-32300}/readyz\")"
-logd "Prometheus: $(http_code \"http://localhost:${PROMETHEUS_PORT:-9090}/-/ready\")"
-logd "Grafana: $(http_code \"http://localhost:${GRAFANA_PORT:-3000}/api/health\")"; http_body_head "http://localhost:${GRAFANA_PORT:-3000}/api/health" >> "$DETAILS" 2>&1 || true
-logd "Alertmanager: $(http_code \"http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status\")"
-cors8084=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8084:-8084}/api/v2/status" || true)
-cors8085=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
-logd "Web-Proxy 8080: $(http_code \"http://localhost:${WEB_PROXY_PORT_8080:-8080}/\")"
-logd "Web-Proxy 8083: $(http_code \"http://localhost:${WEB_PROXY_PORT_8083:-8083}/\")"
-logd "Web-Proxy 8084 CORS: ${cors8084}"
-logd "Web-Proxy 8085 CORS: ${cors8085}"
-
-section ES-CHECKS
-ch=$(curl -s --max-time 3 "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" || true)
-status=$(printf '%s' "$ch" | awk -F'\"' '/"status"/{print $4; exit}')
-if [[ -n "$status" ]]; then logd "cluster.status=$status"; fi
-if [[ "$status" != "green" ]]; then append_err "[es][cluster] status=$status"; fi
-if docker ps --format '{{.Names}}' | grep -q '^argus-es-sys$'; then
-  duse=$(docker exec argus-es-sys sh -lc 'df -P /usr/share/elasticsearch/data | awk "NR==2{print \$5}"' 2>/dev/null || true)
-  logd "es.data.df_use=$duse"; usep=${duse%%%}
-  if [[ -n "$usep" ]] && (( usep >= 90 )); then append_err "[es][disk] data path usage=${usep}%"; fi
-fi
-
-section DNS-IN-PROXY
-for d in master.argus.com es.log.argus.com kibana.log.argus.com grafana.metric.argus.com prom.metric.argus.com alertmanager.alert.argus.com; do
-  docker exec argus-web-proxy sh -lc "getent hosts $d || nslookup $d 2>/dev/null | tail -n+1" >> "$DETAILS" 2>&1 || true
-done
-logd "HTTP (web-proxy): master.readyz=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://master.argus.com:3000/readyz\" 2>/dev/null || echo 000)"
-logd "HTTP (web-proxy): es.health=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://es.log.argus.com:9200/_cluster/health\" 2>/dev/null || echo 000)"
-logd "HTTP (web-proxy): kibana.status=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://kibana.log.argus.com:5601/api/status\" 2>/dev/null || echo 000)"
-
-section SYSTEM
-logd "uname -a:"; uname -a >> "$DETAILS"
-logd "docker version:"; docker version --format '{{.Server.Version}}' >> "$DETAILS" 2>&1 || true
-logd "compose ps (project=$PROJECT):"; (cd "$ROOT/compose" && docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f docker-compose.yml ps) >> "$DETAILS" 2>&1 || true
-
-section SUMMARY
-[[ $(http_code "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health") != 200 ]] && echo "[es][http] health not 200" >> "$ERRORS"
-kbcode=$(http_code "http://localhost:${KIBANA_PORT:-5601}/api/status"); [[ "$kbcode" != 200 ]] && echo "[kibana][http] /api/status=$kbcode" >> "$ERRORS"
-[[ $(http_code "http://localhost:${MASTER_PORT:-32300}/readyz") != 200 ]] && echo "[master][http] /readyz not 200" >> "$ERRORS"
-[[ $(http_code "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready") != 200 ]] && echo "[prometheus][http] /-/ready not 200" >> "$ERRORS"
-gfcode=$(http_code "http://localhost:${GRAFANA_PORT:-3000}/api/health"); [[ "$gfcode" != 200 ]] && echo "[grafana][http] /api/health=$gfcode" >> "$ERRORS"
-[[ $(http_code "http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status") != 200 ]] && echo "[alertmanager][http] /api/v2/status not 200" >> "$ERRORS"
-[[ -z "$cors8084" ]] && echo "[web-proxy][cors] 8084 missing Access-Control-Allow-Origin" >> "$ERRORS"
-[[ -z "$cors8085" ]] && echo "[web-proxy][cors] 8085 missing Access-Control-Allow-Origin" >> "$ERRORS"
-sort -u -o "$ERRORS" "$ERRORS"
-
-echo "Diagnostic details -> $DETAILS"
-echo "Detected errors   -> $ERRORS"
-
-if [[ "$LOG_DIR" == "$ROOT/logs" ]]; then
-  ln -sfn "$(basename "$DETAILS")" "$ROOT/logs/diagnose_details.log" 2>/dev/null || cp "$DETAILS" "$ROOT/logs/diagnose_details.log" 2>/dev/null || true
-  ln -sfn "$(basename "$ERRORS")"  "$ROOT/logs/diagnose_error.log"   2>/dev/null || cp "$ERRORS"  "$ROOT/logs/diagnose_error.log"   2>/dev/null || true
-fi
-
-exit 0

deployment_new/templates/server/scripts/es-watermark-relax.sh

@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-HOST="${1:-http://127.0.0.1:9200}"
-echo "设置 ES watermark 为 95%/96%/97%: $HOST"
-curl -fsS -XPUT "$HOST/_cluster/settings" -H 'Content-Type: application/json' -d '{
-  "transient": {
-    "cluster.routing.allocation.disk.watermark.low": "95%",
-    "cluster.routing.allocation.disk.watermark.high": "96%",
-    "cluster.routing.allocation.disk.watermark.flood_stage": "97%"
-  }
-}' && echo "\nOK"

deployment_new/templates/server/scripts/es-watermark-restore.sh

@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-HOST="${1:-http://127.0.0.1:9200}"
-echo "恢复 ES watermark 为默认值: $HOST"
-curl -fsS -XPUT "$HOST/_cluster/settings" -H 'Content-Type: application/json' -d '{
-  "transient": {
-    "cluster.routing.allocation.disk.watermark.low": null,
-    "cluster.routing.allocation.disk.watermark.high": null,
-    "cluster.routing.allocation.disk.watermark.flood_stage": null
-  }
-}' && echo "\nOK"

deployment_new/templates/server/scripts/install.sh

@@ -1,137 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_FILE="$PKG_ROOT/compose/.env"
-COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
-
-info(){ echo -e "\033[34m[INSTALL]\033[0m $*"; }
-err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
-require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
-# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
-require_compose(){
-  if docker compose version >/dev/null 2>&1; then return 0; fi
-  if command -v docker-compose >/devnull 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
-  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
-}
-require docker curl jq awk sed tar gzip
-require_compose
-
-[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env，请先运行 scripts/config.sh"; exit 1; }
-info "使用环境文件: $ENV_FILE"
-set -a; source "$ENV_FILE"; set +a
-# 兼容：若 .env 未包含 SWARM_MANAGER_ADDR，则从已存在的 cluster-info.env 读取以避免写空
-SMADDR="${SWARM_MANAGER_ADDR:-}"
-CI_FILE="$PKG_ROOT/cluster-info.env"
-if [[ -z "$SMADDR" && -f "$CI_FILE" ]]; then
-  SMADDR=$(sed -n 's/^SWARM_MANAGER_ADDR=\(.*\)$/\1/p' "$CI_FILE" | head -n1)
-fi
-SWARM_MANAGER_ADDR="$SMADDR"
-
-# Swarm init & overlay
-if ! docker info 2>/dev/null | grep -q "Swarm: active"; then
-  [[ -n "${SWARM_MANAGER_ADDR:-}" ]] || { err "SWARM_MANAGER_ADDR 未设置，请在 scripts/config.sh 中配置"; exit 1; }
-  info "初始化 Swarm (--advertise-addr $SWARM_MANAGER_ADDR)"
-  docker swarm init --advertise-addr "$SWARM_MANAGER_ADDR" >/dev/null 2>&1 || true
-else
-  info "Swarm 已激活"
-fi
-NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
-if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
-  info "创建 overlay 网络: $NET_NAME"
-  docker network create -d overlay --attachable "$NET_NAME" >/dev/null
-else
-  info "overlay 网络已存在: $NET_NAME"
-fi
-
-# Load images
-IMAGES_DIR="$PKG_ROOT/images"
-shopt -s nullglob
-tars=("$IMAGES_DIR"/*.tar.gz)
-if [[ ${#tars[@]} -eq 0 ]]; then err "images 目录为空，缺少镜像 tar.gz"; exit 1; fi
-total=${#tars[@]}; idx=0
-for tgz in "${tars[@]}"; do
-  idx=$((idx+1))
-  info "导入镜像 ($idx/$total): $(basename "$tgz")"
-  tmp=$(mktemp); gunzip -c "$tgz" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
-done
-shopt -u nullglob
-
-# Compose up
-PROJECT="${COMPOSE_PROJECT_NAME:-argus-server}"
-info "启动服务栈 (docker compose -p $PROJECT up -d)"
-docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
-docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
-
-# Wait readiness (best-effort)
-code(){ curl -4 -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
-prom_ok(){ (exec 3<>/dev/tcp/127.0.0.1/${PROMETHEUS_PORT:-9090}) >/dev/null 2>&1 && return 0 || return 1; }
-kb_ok(){ local body; body=$(curl -s "http://127.0.0.1:${KIBANA_PORT:-5601}/api/status" || true); echo "$body" | grep -q '"level"\s*:\s*"available"'; }
-RETRIES=${RETRIES:-60}; SLEEP=${SLEEP:-5}; ok=0
-info "等待基础服务就绪 (<= $((RETRIES*SLEEP))s)"
-for i in $(seq 1 "$RETRIES"); do
-  e1=$(code "http://127.0.0.1:${MASTER_PORT:-32300}/readyz")
-  e2=$(code "http://127.0.0.1:${ES_HTTP_PORT:-9200}/_cluster/health")
-  e3=000; prom_ok && e3=200
-  e4=$(code "http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health")
-  e5=$(code "http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status")
-  e6=$(kb_ok && echo 200 || echo 000)
-  info "[ready] t=$((i*SLEEP))s master=$e1 es=$e2 prom=$e3 graf=$e4 alert=$e5 kibana=$e6"
-  [[ "$e1" == 200 ]] && ok=$((ok+1))
-  [[ "$e2" == 200 ]] && ok=$((ok+1))
-  [[ "$e3" == 200 ]] && ok=$((ok+1))
-  [[ "$e4" == 200 ]] && ok=$((ok+1))
-  [[ "$e5" == 200 ]] && ok=$((ok+1))
-  [[ "$e6" == 200 ]] && ok=$((ok+1))
-  if [[ $ok -ge 6 ]]; then break; fi; ok=0; sleep "$SLEEP"
-done
-[[ $ok -ge 6 ]] || err "部分服务未就绪（可稍后重试 selfcheck）"
-
-# Swarm join tokens
-TOKEN_WORKER=$(docker swarm join-token -q worker 2>/dev/null || echo "")
-TOKEN_MANAGER=$(docker swarm join-token -q manager 2>/dev/null || echo "")
-
-# cluster-info.env（compose 场景下不再依赖 BINDIP/FTPIP）
-CI="$PKG_ROOT/cluster-info.env"
-info "写入 cluster-info.env (manager/token)"
-{
-  echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
-  echo "SWARM_JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
-  echo "SWARM_JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
-} > "$CI"
-info "已输出 $CI"
-
-# 安装报告
-ts=$(date +%Y%m%d-%H%M%S)
-RPT="$PKG_ROOT/安装报告_${ts}.md"
-{
-  echo "# Argus Server 安装报告 (${ts})"
-  echo
-  echo "## 端口映射"
-  echo "- MASTER_PORT=${MASTER_PORT}"
-  echo "- ES_HTTP_PORT=${ES_HTTP_PORT}"
-  echo "- KIBANA_PORT=${KIBANA_PORT}"
-  echo "- PROMETHEUS_PORT=${PROMETHEUS_PORT}"
-  echo "- GRAFANA_PORT=${GRAFANA_PORT}"
-  echo "- ALERTMANAGER_PORT=${ALERTMANAGER_PORT}"
-  echo "- WEB_PROXY_PORT_8080=${WEB_PROXY_PORT_8080} ... 8085=${WEB_PROXY_PORT_8085}"
-  echo
-  echo "## Swarm/Overlay"
-  echo "- SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}" 
-  echo "- NET=${NET_NAME}"
-  echo "- JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
-  echo "- JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
-  echo
-  echo "## 健康检查（简要）"
-  echo "- master/readyz=$(code http://127.0.0.1:${MASTER_PORT:-32300}/readyz)"
-  echo "- es/_cluster/health=$(code http://127.0.0.1:${ES_HTTP_PORT:-9200}/_cluster/health)"
-  echo "- grafana/api/health=$(code http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health)"
-  echo "- prometheus/tcp=$([[ $(prom_ok; echo $?) == 0 ]] && echo 200 || echo 000)"
-  echo "- alertmanager/api/v2/status=$(code http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status)"
-  echo "- kibana/api/status=$([[ $(kb_ok; echo $?) == 0 ]] && echo available || echo not-ready)"
-} > "$RPT"
-info "已生成报告: $RPT"
-
-info "安装完成。可将 cluster-info.env 分发给 Client-GPU 安装方。"
-docker exec argus-web-proxy nginx -t >/dev/null 2>&1 && docker exec argus-web-proxy nginx -s reload >/dev/null 2>&1 || true

deployment_new/templates/server/scripts/selfcheck.sh

@@ -1,83 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-
-log() { echo -e "\033[0;34m[CHECK]\033[0m $*"; }
-err() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
-
-ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
-
-wait_http() { local url="$1"; local attempts=${2:-120}; local i=1; while ((i<=attempts)); do curl -fsS "$url" >/dev/null 2>&1 && return 0; echo "[..] waiting $url ($i/$attempts)"; sleep 5; ((i++)); done; return 1; }
-code_for() { curl -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
-header_val() { curl -s -D - -o /dev/null "$@" | awk -F': ' 'BEGIN{IGNORECASE=1}$1=="Access-Control-Allow-Origin"{gsub("\r","",$2);print $2}'; }
-
-LOG_DIR="$ROOT/logs"; mkdir -p "$LOG_DIR" || true
-OUT_JSON="$LOG_DIR/selfcheck.json"; tmp=$(mktemp)
-
-ok=1
-
-log "checking overlay network"
-net_ok=false
-if docker network inspect "${ARGUS_OVERLAY_NET:-argus-sys-net}" >/dev/null 2>&1; then
-  if docker network inspect "${ARGUS_OVERLAY_NET:-argus-sys-net}" | grep -q '"Driver": "overlay"'; then net_ok=true; fi
-fi
-[[ "$net_ok" == true ]] || ok=0
-
-log "checking Elasticsearch"
-wait_http "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" 60 || ok=0
-
-log "checking Kibana"
-kb_code=$(code_for "http://localhost:${KIBANA_PORT:-5601}/api/status")
-kb_ok=false
-if [[ "$kb_code" == 200 ]]; then
-  body=$(curl -sS "http://localhost:${KIBANA_PORT:-5601}/api/status" || true)
-  echo "$body" | grep -q '"level"\s*:\s*"available"' && kb_ok=true
-fi
-[[ "$kb_ok" == true ]] || ok=0
-
-log "checking Master"
-[[ $(code_for "http://localhost:${MASTER_PORT:-32300}/readyz") == 200 ]] || ok=0
-
-log "checking Prometheus"
-wait_http "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready" 60 || ok=0
-
-log "checking Grafana"
-gf_code=$(code_for "http://localhost:${GRAFANA_PORT:-3000}/api/health")
-gf_ok=false; if [[ "$gf_code" == 200 ]]; then body=$(curl -sS "http://localhost:${GRAFANA_PORT:-3000}/api/health" || true); echo "$body" | grep -q '"database"\s*:\s*"ok"' && gf_ok=true; fi
-[[ "$gf_ok" == true ]] || ok=0
-
-log "checking Alertmanager"
-wait_http "http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status" 60 || ok=0
-
-log "checking Web-Proxy (CORS)"
-cors8084=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8084:-8084}/api/v2/status" || true)
-cors8085=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
-wp_ok=true
-[[ -n "$cors8084" && -n "$cors8085" ]] || wp_ok=false
-[[ "$wp_ok" == true ]] || ok=0
-
-cat > "$tmp" <<JSON
-{
-  "overlay_net": $net_ok,
-  "es": true,
-  "kibana": $kb_ok,
-  "master_readyz": true,
-  "prometheus": true,
-  "grafana": $gf_ok,
-  "alertmanager": true,
-  "web_proxy_cors": $wp_ok,
-  "timestamp": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
-}
-JSON
-
-mv "$tmp" "$OUT_JSON" 2>/dev/null || cp "$tmp" "$OUT_JSON"
-
-if [[ "$ok" == 1 ]]; then
-  log "selfcheck OK -> $OUT_JSON"
-  exit 0
-else
-  err "selfcheck FAILED -> $OUT_JSON"
-  exit 1
-fi

deployment_new/templates/server/scripts/status.sh

@@ -1,9 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_FILE="$PKG_ROOT/compose/.env"
-COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
-if [[ -f "$ENV_FILE" ]]; then set -a; source "$ENV_FILE"; set +a; fi
-PROJECT="${COMPOSE_PROJECT_NAME:-argus-server}"
-docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps

deployment_new/templates/server/scripts/uninstall.sh

@@ -1,23 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-PKG_ROOT="$ROOT_DIR"
-ENV_FILE="$PKG_ROOT/compose/.env"
-COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
-
-# load COMPOSE_PROJECT_NAME from env file if present
-if [[ -f "$ENV_FILE" ]]; then set -a; source "$ENV_FILE"; set +a; fi
-PROJECT="${COMPOSE_PROJECT_NAME:-argus-server}"
-
-err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
-# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
-require_compose(){
-  if docker compose version >/dev/null 2>&1; then return 0; fi
-  if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
-  err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
-}
-require_compose
-
-echo "[UNINSTALL] stopping compose (project=$PROJECT)"
-docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
-echo "[UNINSTALL] done"

scripts/common/build_user.sh

@@ -37,11 +37,22 @@ _argus_is_number() {
   [[ "$1" =~ ^[0-9]+$ ]]
 }
 
-_argus_read_user_from_files() {
-  local uid_out_var="$1" gid_out_var="$2"; shift 2
-  local uid_val="$ARGUS_BUILD_UID_DEFAULT" gid_val="$ARGUS_BUILD_GID_DEFAULT"
-  local config
-  for config in "$@"; do
+load_build_user() {
+  if [[ "$_ARGUS_BUILD_USER_LOADED" == "1" ]]; then
+    return 0
+  fi
+
+  local project_root config_files config uid gid
+  project_root="$(argus_project_root)"
+  config_files=(
+    "$project_root/configs/build_user.local.conf"
+    "$project_root/configs/build_user.conf"
+  )
+
+  uid="$ARGUS_BUILD_UID_DEFAULT"
+  gid="$ARGUS_BUILD_GID_DEFAULT"
+
+  for config in "${config_files[@]}"; do
     if [[ -f "$config" ]]; then
       while IFS= read -r raw_line || [[ -n "$raw_line" ]]; do
         local line key value
@@ -57,58 +68,42 @@ _argus_read_user_from_files() {
         key="$(_argus_trim "$key")"
         value="$(_argus_trim "$value")"
         case "$key" in
-          UID) uid_val="$value" ;;
-          GID) gid_val="$value" ;;
-          *) echo "[ARGUS build_user] Unknown key '$key' in $config" >&2 ;;
+          UID)
+            uid="$value"
+            ;;
+          GID)
+            gid="$value"
+            ;;
+          *)
+            echo "[ARGUS build_user] Unknown key '$key' in $config" >&2
+            ;;
         esac
       done < "$config"
       break
     fi
   done
-  printf -v "$uid_out_var" '%s' "$uid_val"
-  printf -v "$gid_out_var" '%s' "$gid_val"
-}
 
-load_build_user_profile() {
-  local profile="${1:-default}"
-  if [[ "$_ARGUS_BUILD_USER_LOADED" == "1" ]]; then
-    return 0
+  if [[ -n "${ARGUS_BUILD_UID:-}" ]]; then
+    uid="$ARGUS_BUILD_UID"
+  fi
+  if [[ -n "${ARGUS_BUILD_GID:-}" ]]; then
+    gid="$ARGUS_BUILD_GID"
   fi
-  local project_root uid gid
-  project_root="$(argus_project_root)"
-  case "$profile" in
-    pkg)
-      _argus_read_user_from_files uid gid \
-        "$project_root/configs/build_user.pkg.conf" \
-        "$project_root/configs/build_user.local.conf" \
-        "$project_root/configs/build_user.conf"
-      ;;
-    default|*)
-      _argus_read_user_from_files uid gid \
-        "$project_root/configs/build_user.local.conf" \
-        "$project_root/configs/build_user.conf"
-      ;;
-  esac
-
-  if [[ -n "${ARGUS_BUILD_UID:-}" ]]; then uid="$ARGUS_BUILD_UID"; fi
-  if [[ -n "${ARGUS_BUILD_GID:-}" ]]; then gid="$ARGUS_BUILD_GID"; fi
 
   if ! _argus_is_number "$uid"; then
-    echo "[ARGUS build_user] Invalid UID '$uid'" >&2; return 1
+    echo "[ARGUS build_user] Invalid UID '$uid'" >&2
+    return 1
   fi
   if ! _argus_is_number "$gid"; then
-    echo "[ARGUS build_user] Invalid GID '$gid'" >&2; return 1
+    echo "[ARGUS build_user] Invalid GID '$gid'" >&2
+    return 1
   fi
+
   export ARGUS_BUILD_UID="$uid"
   export ARGUS_BUILD_GID="$gid"
   _ARGUS_BUILD_USER_LOADED=1
 }
 
-load_build_user() {
-  local profile="${ARGUS_BUILD_PROFILE:-default}"
-  load_build_user_profile "$profile"
-}
-
 argus_build_user_args() {
   load_build_user
   printf '%s' "--build-arg ARGUS_BUILD_UID=${ARGUS_BUILD_UID} --build-arg ARGUS_BUILD_GID=${ARGUS_BUILD_GID}"

src/agent/.gitignore

@@ -3,4 +3,3 @@ build/
 __pycache__/
 
 .env
-dist/

src/agent/README.md

@@ -34,18 +34,6 @@ Agent 不再依赖配置文件；所有参数均由环境变量与主机名推
 | `MASTER_ENDPOINT` | 是 | N/A | Master 基础地址，可写 `http://host:3000` 或 `host:3000`（自动补全 `http://`）。 |
 | `REPORT_INTERVAL_SECONDS` | 否 | `60` | 状态上报间隔（秒）。必须为正整数。 |
 | `AGENT_HOSTNAME` | 否 | `$(hostname)` | 覆盖容器内主机名，便于测试或特殊命名需求。 |
-| `AGENT_ENV` | 否 | 来源于主机名 | 运行环境标识（如 `dev`、`prod`）。与 `AGENT_USER`、`AGENT_INSTANCE` 必须同时设置。 |
-| `AGENT_USER` | 否 | 来源于主机名 | 归属用户或团队标识。与 `AGENT_ENV`、`AGENT_INSTANCE` 必须同时设置。 |
-| `AGENT_INSTANCE` | 否 | 来源于主机名 | 实例编号或别名。与 `AGENT_ENV`、`AGENT_USER` 必须同时设置。 |
-
-主机名与元数据的解析优先级：
-
-1. 若设置 `AGENT_ENV` / `AGENT_USER` / `AGENT_INSTANCE` 且全部存在，则直接使用这些值。
-2. 否则检查历史 `node.json`（注册成功后由 Master 返回的信息），若包含 `env` / `user` / `instance` 则沿用。
-3. 若以上均不可用，则按历史约定从主机名解析 `env-user-instance` 前缀。
-4. 如果仍无法得到完整结果，Agent 启动会失败并提示需要提供上述环境变量。
-
-> 提示：在首次部署时需确保环境变量或主机名能够提供完整信息。完成注册后，Agent 会把 Master 返回的元数据写入 `node.json`，后续重启无需再次提供环境变量就能保持一致性。
 
 派生路径：
 

src/agent/app/collector.py

@@ -4,7 +4,6 @@ import os
 import re
 import socket
 import subprocess
-import ipaddress
 from pathlib import Path
 from typing import Any, Dict
 
@@ -17,50 +16,15 @@ _HOSTNAME_PATTERN = re.compile(r"^([^-]+)-([^-]+)-([^-]+)-.*$")
 
 
 def collect_metadata(config: AgentConfig) -> Dict[str, Any]:
-    """汇总节点注册需要的静态信息，带有更智能的 IP 选择。
-
-    规则（从高到低）：
-    1) AGENT_PUBLISH_IP 指定；
-    2) Hostname A 记录（若命中优先网段）；
-    3) 网卡扫描：排除 AGENT_EXCLUDE_IFACES，优先 AGENT_PREFER_NET_CIDRS；
-    4) 默认路由回退（UDP socket 技巧）。
-
-    额外发布：overlay_ip / gwbridge_ip / interfaces，便于 Master 与诊断使用。
-    """
+    """汇总节点注册需要的静态信息。"""
     hostname = config.hostname
-
-    prefer_cidrs = _read_cidrs_env(
-        os.environ.get("AGENT_PREFER_NET_CIDRS", "10.0.0.0/8,172.31.0.0/16")
-    )
-    exclude_ifaces = _read_csv_env(
-        os.environ.get("AGENT_EXCLUDE_IFACES", "docker_gwbridge,lo")
-    )
-
-    # interface inventory
-    interfaces = _list_global_ipv4_addrs()
-    if exclude_ifaces:
-        interfaces = [it for it in interfaces if it[0] not in set(exclude_ifaces)]
-
-    # resolve hostname candidates
-    host_ips = _resolve_hostname_ips(hostname)
-
-    selected_ip, overlay_ip, gwbridge_ip = _select_publish_ips(
-        interfaces=interfaces,
-        host_ips=host_ips,
-        prefer_cidrs=prefer_cidrs,
-    )
-
-    meta: Dict[str, Any] = {
+    env, user, instance = _parse_hostname(hostname)
+    meta = {
         "hostname": hostname,
-        "ip": os.environ.get("AGENT_PUBLISH_IP", selected_ip),  # keep required field
-        "overlay_ip": overlay_ip or selected_ip,
-        "gwbridge_ip": gwbridge_ip,
-        "interfaces": [
-            {"iface": name, "ip": ip} for name, ip in interfaces
-        ],
-        "env": config.environment,
-        "user": config.user,
-        "instance": config.instance,
+        "ip": _detect_ip_address(),
+        "env": env,
+        "user": user,
+        "instance": instance,
         "cpu_number": _detect_cpu_count(),
         "memory_in_bytes": _detect_memory_bytes(),
         "gpu_number": _detect_gpu_count(),
@@ -133,7 +97,7 @@ def _detect_gpu_count() -> int:
 
 
 def _detect_ip_address() -> str:
-    """保留旧接口，作为最终回退：默认路由源地址 → 主机名解析 → 127.0.0.1。"""
+    """尝试通过 UDP socket 获得容器出口 IP，失败则回退解析主机名。"""
     try:
         with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as sock:
             sock.connect(("8.8.8.8", 80))
@@ -145,118 +109,3 @@ def _detect_ip_address() -> str:
     except OSError:
         LOGGER.warning("Unable to resolve hostname to IP; defaulting to 127.0.0.1")
         return "127.0.0.1"
-
-
-def _read_csv_env(raw: str | None) -> list[str]:
-    if not raw:
-        return []
-    return [x.strip() for x in raw.split(",") if x.strip()]
-
-
-def _read_cidrs_env(raw: str | None) -> list[ipaddress.IPv4Network]:
-    cidrs: list[ipaddress.IPv4Network] = []
-    for item in _read_csv_env(raw):
-        try:
-            net = ipaddress.ip_network(item, strict=False)
-            if isinstance(net, (ipaddress.IPv4Network,)):
-                cidrs.append(net)
-        except ValueError:
-            LOGGER.warning("Ignoring invalid CIDR in AGENT_PREFER_NET_CIDRS", extra={"cidr": item})
-    return cidrs
-
-
-def _list_global_ipv4_addrs() -> list[tuple[str, str]]:
-    """列出 (iface, ip) 形式的全局 IPv4 地址。
-    依赖 iproute2：ip -4 -o addr show scope global
-    """
-    results: list[tuple[str, str]] = []
-    try:
-        proc = subprocess.run(
-            ["sh", "-lc", "ip -4 -o addr show scope global | awk '{print $2, $4}'"],
-            check=False,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            text=True,
-            timeout=3,
-        )
-        if proc.returncode == 0:
-            for line in proc.stdout.splitlines():
-                line = line.strip()
-                if not line:
-                    continue
-                parts = line.split()
-                if len(parts) != 2:
-                    continue
-                iface, cidr = parts
-                ip = cidr.split("/")[0]
-                try:
-                    ipaddress.IPv4Address(ip)
-                except ValueError:
-                    continue
-                results.append((iface, ip))
-    except Exception as exc:  # pragma: no cover - defensive
-        LOGGER.debug("Failed to list interfaces", extra={"error": str(exc)})
-    return results
-
-
-def _resolve_hostname_ips(name: str) -> list[str]:
-    ips: list[str] = []
-    try:
-        infos = socket.getaddrinfo(name, None, family=socket.AF_INET)
-        for info in infos:
-            ip = info[4][0]
-            if ip not in ips:
-                ips.append(ip)
-    except OSError:
-        pass
-    return ips
-
-
-def _pick_by_cidrs(candidates: list[str], prefer_cidrs: list[ipaddress.IPv4Network]) -> str | None:
-    for net in prefer_cidrs:
-        for ip in candidates:
-            try:
-                if ipaddress.ip_address(ip) in net:
-                    return ip
-            except ValueError:
-                continue
-    return None
-
-
-def _select_publish_ips(
-    *,
-    interfaces: list[tuple[str, str]],
-    host_ips: list[str],
-    prefer_cidrs: list[ipaddress.IPv4Network],
-) -> tuple[str, str | None, str | None]:
-    """返回 (selected_ip, overlay_ip, gwbridge_ip)。
-
-    - overlay_ip：优先命中 prefer_cidrs（10.0/8 先于 172.31/16）。
-    - gwbridge_ip：若存在 172.22/16 则记录。
-    - selected_ip：优先 AGENT_PUBLISH_IP；否则 overlay_ip；否则 hostname A 记录中的 prefer；否则默认路由回退。
-    """
-    # detect gwbridge (172.22/16)
-    gwbridge_net = ipaddress.ip_network("172.22.0.0/16")
-    gwbridge_ip = None
-    for _, ip in interfaces:
-        try:
-            if ipaddress.ip_address(ip) in gwbridge_net:
-                gwbridge_ip = ip
-                break
-        except ValueError:
-            continue
-
-    # overlay candidate from interfaces by prefer cidrs
-    iface_ips = [ip for _, ip in interfaces]
-    overlay_ip = _pick_by_cidrs(iface_ips, prefer_cidrs)
-
-    # hostname A records filtered by prefer cidrs
-    host_pref = _pick_by_cidrs(host_ips, prefer_cidrs)
-
-    env_ip = os.environ.get("AGENT_PUBLISH_IP")
-    if env_ip:
-        selected = env_ip
-    else:
-        selected = overlay_ip or host_pref or _detect_ip_address()
-
-    return selected, overlay_ip, gwbridge_ip

src/agent/app/config.py

@@ -6,21 +6,14 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Final
 
-from .state import load_node_state
 from .version import VERSION
-from .log import get_logger
 
 DEFAULT_REPORT_INTERVAL_SECONDS: Final[int] = 60
 
-LOGGER = get_logger("argus.agent.config")
-
 
 @dataclass(frozen=True)
 class AgentConfig:
     hostname: str
-    environment: str
-    user: str
-    instance: str
     node_file: str
     version: str
     master_endpoint: str
@@ -54,68 +47,11 @@ def _resolve_hostname() -> str:
     return os.environ.get("AGENT_HOSTNAME") or socket.gethostname()
 
 
-def _load_metadata_from_state(node_file: str) -> tuple[str, str, str] | None:
-    state = load_node_state(node_file)
-    if not state:
-        return None
-
-    meta = state.get("meta_data") or {}
-    env = meta.get("env") or state.get("env")
-    user = meta.get("user") or state.get("user")
-    instance = meta.get("instance") or state.get("instance")
-
-    if env and user and instance:
-        LOGGER.debug("Metadata resolved from node state", extra={"node_file": node_file})
-        return env, user, instance
-
-    LOGGER.warning(
-        "node.json missing metadata fields; ignoring",
-        extra={"node_file": node_file, "meta_data": meta},
-    )
-    return None
-
-
-def _resolve_metadata_fields(hostname: str, node_file: str) -> tuple[str, str, str]:
-    env = os.environ.get("AGENT_ENV")
-    user = os.environ.get("AGENT_USER")
-    instance = os.environ.get("AGENT_INSTANCE")
-
-    if env and user and instance:
-        return env, user, instance
-
-    if any([env, user, instance]):
-        LOGGER.warning(
-            "Incomplete metadata environment variables; falling back to persisted metadata",
-            extra={
-                "has_env": bool(env),
-                "has_user": bool(user),
-                "has_instance": bool(instance),
-            },
-        )
-
-    state_metadata = _load_metadata_from_state(node_file)
-    if state_metadata is not None:
-        return state_metadata
-
-    from .collector import _parse_hostname  # Local import to avoid circular dependency
-
-    env, user, instance = _parse_hostname(hostname)
-
-    if not all([env, user, instance]):
-        raise ValueError(
-            "Failed to determine metadata fields; set AGENT_ENV/USER/INSTANCE or use supported hostname pattern"
-        )
-
-    return env, user, instance
-
-
 def load_config() -> AgentConfig:
     """从环境变量推导配置，移除了外部配置文件依赖。"""
 
     hostname = _resolve_hostname()
     node_file = f"/private/argus/agent/{hostname}/node.json"
-    environment, user, instance = _resolve_metadata_fields(hostname, node_file)
-
     health_dir = f"/private/argus/agent/{hostname}/health/"
 
     master_endpoint_env = os.environ.get("MASTER_ENDPOINT")
@@ -130,9 +66,6 @@ def load_config() -> AgentConfig:
 
     return AgentConfig(
         hostname=hostname,
-        environment=environment,
-        user=user,
-        instance=instance,
         node_file=node_file,
         version=VERSION,
         master_endpoint=master_endpoint,

src/agent/scripts/build_binary.sh

@@ -12,8 +12,6 @@ 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() {
@@ -73,7 +71,6 @@ 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=$(cat <<'INNER'
 set -euo pipefail
@@ -85,10 +82,6 @@ rm -rf build dist
 mkdir -p build/pyinstaller dist
 python3 -m venv --copies build/venv
 source build/venv/bin/activate
-# 若指定忽略代理，则清空常见代理与 pip 镜像环境变量，避免容器内代理不可达
-if [ "${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/agent/tests/docker-compose.yml

@@ -60,36 +60,6 @@ services:
         ipv4_address: 172.28.0.20
     restart: always
 
-  agent_env:
-    image: ubuntu:22.04
-    container_name: argus-agent-env-e2e
-    hostname: host_abc
-    depends_on:
-      - master
-      - bind
-    environment:
-      - MASTER_ENDPOINT=http://master.argus.com:3000
-      - REPORT_INTERVAL_SECONDS=2
-      - AGENT_ENV=prod
-      - AGENT_USER=ml
-      - AGENT_INSTANCE=node-3
-      - AGENT_HOSTNAME=host_abc
-      - "ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}"
-      - "ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}"
-    volumes:
-      - ./private/argus/agent/host_abc:/private/argus/agent/host_abc
-      - ./private/argus/agent/host_abc/health:/private/argus/agent/host_abc/health
-      - ./private/argus/etc:/private/argus/etc
-      - ../dist/argus-agent:/usr/local/bin/argus-agent:ro
-      - ./scripts/agent_entrypoint.sh:/usr/local/bin/agent-entrypoint.sh:ro
-      - ../scripts/agent_deployment_verify.sh:/usr/local/bin/agent_deployment_verify.sh:ro
-    entrypoint:
-      - /usr/local/bin/agent-entrypoint.sh
-    networks:
-      default:
-        ipv4_address: 172.28.0.21
-    restart: always
-
 networks:
   default:
     driver: bridge

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

@@ -7,10 +7,10 @@ SCRIPTS=(
   "02_up.sh"
   "03_wait_and_assert_registration.sh"
   "04_write_health_files.sh"
-  "05_verify_agent.sh"
-  "06_assert_status_on_master.sh"
-  "07_restart_agent_and_reregister.sh"
-  "08_down.sh"
+  "08_verify_agent.sh"
+  "05_assert_status_on_master.sh"
+  "06_restart_agent_and_reregister.sh"
+  "07_down.sh"
 )
 
 for script in "${SCRIPTS[@]}"; do

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

@@ -41,7 +41,7 @@ compose() {
   fi
 }
 
-docker container rm -f argus-agent-e2e argus-agent-env-e2e argus-master-agent-e2e argus-bind-agent-e2e >/dev/null 2>&1 || true
+docker container rm -f argus-agent-e2e argus-master-agent-e2e argus-bind-agent-e2e >/dev/null 2>&1 || true
 
 docker network rm tests_default >/dev/null 2>&1 || true
 

src/agent/tests/scripts/03_wait_and_assert_registration.sh

@@ -6,14 +6,11 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 TMP_ROOT="$TEST_ROOT/tmp"
 API_BASE="http://localhost:32300/api/v1/master"
 AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
-ENV_AGENT_HOSTNAME="host_abc"
 NODE_FILE="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/node.json"
-ENV_NODE_FILE="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME/node.json"
 
 mkdir -p "$TMP_ROOT"
 
-primary_node_id=""
-env_node_id=""
+node_id=""
 for _ in {1..30}; do
   sleep 2
   response=$(curl -sS "$API_BASE/nodes" || true)
@@ -22,49 +19,24 @@ for _ in {1..30}; do
   fi
   list_file="$TMP_ROOT/nodes_list.json"
   echo "$response" > "$list_file"
-  readarray -t node_ids < <(python3 - "$list_file" "$AGENT_HOSTNAME" "$ENV_AGENT_HOSTNAME" <<'PY'
+  node_id=$(python3 - "$list_file" <<'PY'
 import json, sys
-
 with open(sys.argv[1]) as handle:
     nodes = json.load(handle)
-
-target_primary = sys.argv[2]
-target_env = sys.argv[3]
-
-primary_id = ""
-env_id = ""
-
-for node in nodes:
-    if node.get("name") == target_primary:
-        primary_id = node.get("id", "")
-    if node.get("name") == target_env:
-        env_id = node.get("id", "")
-
-print(primary_id)
-print(env_id)
+print(nodes[0]["id"] if nodes else "")
 PY
-  )
-
-  primary_node_id="${node_ids[0]}"
-  env_node_id="${node_ids[1]}"
-
-  if [[ -n "$primary_node_id" && -n "$env_node_id" ]]; then
+)
+  if [[ -n "$node_id" ]]; then
     break
   fi
  done
 
-if [[ -z "$primary_node_id" ]]; then
-  echo "[ERROR] Primary agent did not register within timeout" >&2
+if [[ -z "$node_id" ]]; then
+  echo "[ERROR] Agent did not register within timeout" >&2
   exit 1
 fi
 
-if [[ -z "$env_node_id" ]]; then
-  echo "[ERROR] Env-variable agent did not register within timeout" >&2
-  exit 1
-fi
-
-echo "$primary_node_id" > "$TMP_ROOT/node_id"
-echo "$env_node_id" > "$TMP_ROOT/node_id_host_abc"
+echo "$node_id" > "$TMP_ROOT/node_id"
 
 if [[ ! -f "$NODE_FILE" ]]; then
   echo "[ERROR] node.json not created at $NODE_FILE" >&2
@@ -78,20 +50,8 @@ with open(sys.argv[1]) as handle:
 assert "id" in node and node["id"], "node.json missing id"
 PY
 
-if [[ ! -f "$ENV_NODE_FILE" ]]; then
-  echo "[ERROR] node.json not created at $ENV_NODE_FILE" >&2
-  exit 1
-fi
-
-python3 - "$ENV_NODE_FILE" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-assert "id" in node and node["id"], "env agent node.json missing id"
-PY
-
 detail_file="$TMP_ROOT/initial_detail.json"
-curl -sS "$API_BASE/nodes/$primary_node_id" -o "$detail_file"
+curl -sS "$API_BASE/nodes/$node_id" -o "$detail_file"
 python3 - "$detail_file" "$TMP_ROOT/initial_ip" <<'PY'
 import json, sys, pathlib
 with open(sys.argv[1]) as handle:
@@ -102,5 +62,4 @@ if not ip:
 pathlib.Path(sys.argv[2]).write_text(ip)
 PY
 
-echo "[INFO] Agent registered with node id $primary_node_id"
-echo "[INFO] Env-variable agent registered with node id $env_node_id"
+echo "[INFO] Agent registered with node id $node_id"

src/agent/tests/scripts/05_assert_status_on_master.sh

@@ -6,8 +6,6 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 TMP_ROOT="$TEST_ROOT/tmp"
 API_BASE="http://localhost:32300/api/v1/master"
 NODE_ID="$(cat "$TMP_ROOT/node_id")"
-ENV_NODE_ID="$(cat "$TMP_ROOT/node_id_host_abc")"
-ENV_HOSTNAME="host_abc"
 NODES_JSON="$TEST_ROOT/private/argus/metric/prometheus/nodes.json"
 
 success=false
@@ -43,36 +41,13 @@ if [[ ! -f "$NODES_JSON" ]]; then
   exit 1
 fi
 
-python3 - "$NODES_JSON" "$NODE_ID" "$ENV_NODE_ID" <<'PY'
+python3 - "$NODES_JSON" <<'PY'
 import json, sys
 with open(sys.argv[1]) as handle:
     nodes = json.load(handle)
-
-expected_primary = sys.argv[2]
-expected_env = sys.argv[3]
-
-ids = {entry.get("node_id") for entry in nodes}
-assert expected_primary in ids, nodes
-assert expected_env in ids, nodes
-assert len(nodes) >= 2, nodes
+assert len(nodes) == 1, nodes
+entry = nodes[0]
+assert entry["node_id"], entry
 PY
 
 echo "[INFO] Master reflects agent health and nodes.json entries"
-
-env_detail_file="$TMP_ROOT/env_agent_detail.json"
-curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_detail_file"
-python3 - "$env_detail_file" "$ENV_HOSTNAME" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-
-expected_name = sys.argv[2]
-
-assert node.get("name") == expected_name, node
-meta = node.get("meta_data", {})
-assert meta.get("env") == "prod", meta
-assert meta.get("user") == "ml", meta
-assert meta.get("instance") == "node-3", meta
-PY
-
-echo "[INFO] Env-variable agent reports expected metadata"

src/agent/tests/scripts/05_verify_agent.sh

@@ -1,60 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-REPO_ROOT="$(cd "$TEST_ROOT/.." && pwd)"
-VERIFY_SCRIPT="$REPO_ROOT/scripts/agent_deployment_verify.sh"
-ENV_NODE_ID_FILE="$TEST_ROOT/tmp/node_id_host_abc"
-PRIMARY_CONTAINER="argus-agent-e2e"
-ENV_CONTAINER="argus-agent-env-e2e"
-PRIMARY_HOSTNAME="dev-e2euser-e2einst-pod-0"
-ENV_HOSTNAME="host_abc"
-
-if ! docker ps --format '{{.Names}}' | grep -q "^${PRIMARY_CONTAINER}$"; then
-  echo "[WARN] agent container not running; skip verification"
-  exit 0
-fi
-
-if docker exec -i "$PRIMARY_CONTAINER" bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
-  echo "[INFO] curl/jq already installed in agent container"
-else
-  echo "[INFO] Installing curl/jq in agent container"
-  docker exec -i "$PRIMARY_CONTAINER" bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
-fi
-
-if [[ ! -f "$VERIFY_SCRIPT" ]]; then
-  echo "[ERROR] Verification script missing at $VERIFY_SCRIPT" >&2
-  exit 1
-fi
-
-run_verifier() {
-  local container="$1" hostname="$2"
-
-  if ! docker ps --format '{{.Names}}' | grep -q "^${container}$"; then
-    echo "[WARN] container $container not running; skip"
-    return
-  fi
-
-  if ! docker exec -i "$container" bash -lc 'command -v /usr/local/bin/agent_deployment_verify.sh >/dev/null'; then
-    echo "[ERROR] /usr/local/bin/agent_deployment_verify.sh missing in $container" >&2
-    exit 1
-  fi
-
-  echo "[INFO] Running verification for $hostname in $container"
-  docker exec -i "$container" env VERIFY_HOSTNAME="$hostname" /usr/local/bin/agent_deployment_verify.sh
-}
-
-run_verifier "$PRIMARY_CONTAINER" "$PRIMARY_HOSTNAME"
-
-if docker ps --format '{{.Names}}' | grep -q "^${ENV_CONTAINER}$"; then
-  if docker exec -i "$ENV_CONTAINER" bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
-    echo "[INFO] curl/jq already installed in env agent container"
-  else
-    echo "[INFO] Installing curl/jq in env agent container"
-    docker exec -i "$ENV_CONTAINER" bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
-  fi
-  run_verifier "$ENV_CONTAINER" "$ENV_HOSTNAME"
-else
-  echo "[WARN] env-driven agent container not running; skip secondary verification"
-fi

src/agent/tests/scripts/06_restart_agent_and_reregister.sh

@@ -6,20 +6,10 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 TMP_ROOT="$TEST_ROOT/tmp"
 API_BASE="http://localhost:32300/api/v1/master"
 NODE_ID="$(cat "$TMP_ROOT/node_id")"
-ENV_NODE_ID_FILE="$TMP_ROOT/node_id_host_abc"
-if [[ ! -f "$ENV_NODE_ID_FILE" ]]; then
-  echo "[ERROR] Env agent node id file missing at $ENV_NODE_ID_FILE" >&2
-  exit 1
-fi
-
-ENV_NODE_ID="$(cat "$ENV_NODE_ID_FILE")"
 AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
-ENV_AGENT_HOSTNAME="host_abc"
 NETWORK_NAME="tests_default"
 NEW_AGENT_IP="172.28.0.200"
-NEW_ENV_AGENT_IP="172.28.0.210"
 ENTRYPOINT_SCRIPT="$SCRIPT_DIR/agent_entrypoint.sh"
-VERIFY_SCRIPT="$TEST_ROOT/../scripts/agent_deployment_verify.sh"
 ENV_FILE="$TEST_ROOT/.env"
 
 # 中文提示：重启场景也需要同样的入口脚本，确保 DNS 注册逻辑一致
@@ -28,11 +18,6 @@ if [[ ! -f "$ENTRYPOINT_SCRIPT" ]]; then
   exit 1
 fi
 
-if [[ ! -f "$VERIFY_SCRIPT" ]]; then
-  echo "[ERROR] agent verification script missing at $VERIFY_SCRIPT" >&2
-  exit 1
-fi
-
 if [[ ! -f "$TMP_ROOT/agent_binary_path" ]]; then
   echo "[ERROR] Agent binary path missing; rerun bootstrap" >&2
   exit 1
@@ -89,37 +74,15 @@ if [[ "$prev_ip" != "$initial_ip" ]]; then
   exit 1
 fi
 
-env_before_file="$TMP_ROOT/env_before_restart.json"
-curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_before_file"
-env_prev_last_updated=$(python3 - "$env_before_file" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-print(node.get("last_updated", ""))
-PY
-)
-env_prev_ip=$(python3 - "$env_before_file" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-print(node["meta_data"].get("ip", ""))
-PY
-)
-
 pushd "$TEST_ROOT" >/dev/null
 compose rm -sf agent
-compose rm -sf agent_env
 popd >/dev/null
 
 docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
-docker container rm -f argus-agent-env-e2e >/dev/null 2>&1 || true
 
 AGENT_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME"
 HEALTH_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/health"
 
-ENV_AGENT_DIR="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME"
-ENV_HEALTH_DIR="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME/health"
-
 # 先以 sleep 方式启动容器，确保我们掌握注册时的网络状态
 if ! docker run -d \
   --name argus-agent-e2e \
@@ -131,7 +94,6 @@ if ! docker run -d \
   -v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
   -v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
   -v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
-  -v "$VERIFY_SCRIPT:/usr/local/bin/agent_deployment_verify.sh:ro" \
   -e MASTER_ENDPOINT=http://master.argus.com:3000 \
   -e REPORT_INTERVAL_SECONDS=2 \
   -e ARGUS_BUILD_UID="$AGENT_UID" \
@@ -179,76 +141,3 @@ if [[ "$success" != true ]]; then
 fi
 
 echo "[INFO] Agent restart produced successful re-registration with IP change"
-
-# ---- Restart env-driven agent without metadata environment variables ----
-
-if [[ ! -d "$ENV_AGENT_DIR" ]]; then
-  echo "[ERROR] Env agent data dir missing at $ENV_AGENT_DIR" >&2
-  exit 1
-fi
-
-if [[ ! -d "$ENV_HEALTH_DIR" ]]; then
-  mkdir -p "$ENV_HEALTH_DIR"
-fi
-
-if ! docker run -d \
-  --name argus-agent-env-e2e \
-  --hostname "$ENV_AGENT_HOSTNAME" \
-  --network "$NETWORK_NAME" \
-  --ip "$NEW_ENV_AGENT_IP" \
-  -v "$ENV_AGENT_DIR:/private/argus/agent/$ENV_AGENT_HOSTNAME" \
-  -v "$ENV_HEALTH_DIR:/private/argus/agent/$ENV_AGENT_HOSTNAME/health" \
-  -v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
-  -v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
-  -v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
-  -v "$VERIFY_SCRIPT:/usr/local/bin/agent_deployment_verify.sh:ro" \
-  -e MASTER_ENDPOINT=http://master.argus.com:3000 \
-  -e REPORT_INTERVAL_SECONDS=2 \
-  -e ARGUS_BUILD_UID="$AGENT_UID" \
-  -e ARGUS_BUILD_GID="$AGENT_GID" \
-  --entrypoint /usr/local/bin/agent-entrypoint.sh \
-  ubuntu:22.04 >/dev/null; then
-  echo "[ERROR] Failed to start env-driven agent container without metadata env" >&2
-  exit 1
-fi
-
-env_success=false
-env_detail_file="$TMP_ROOT/env_post_restart.json"
-for _ in {1..20}; do
-  sleep 3
-  if ! curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_detail_file"; then
-    continue
-  fi
-  if python3 - "$env_detail_file" "$env_prev_last_updated" "$ENV_NODE_ID" "$env_prev_ip" "$NEW_ENV_AGENT_IP" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-prev_last_updated = sys.argv[2]
-expected_id = sys.argv[3]
-old_ip = sys.argv[4]
-expected_ip = sys.argv[5]
-last_updated = node.get("last_updated")
-current_ip = node["meta_data"].get("ip")
-meta = node.get("meta_data", {})
-assert node["id"] == expected_id
-if current_ip != expected_ip:
-    raise SystemExit(1)
-if current_ip == old_ip:
-    raise SystemExit(1)
-if not last_updated or last_updated == prev_last_updated:
-    raise SystemExit(1)
-if meta.get("env") != "prod" or meta.get("user") != "ml" or meta.get("instance") != "node-3":
-    raise SystemExit(1)
-PY
-  then
-    env_success=true
-    break
-  fi
-done
-
-if [[ "$env_success" != true ]]; then
-  echo "[ERROR] Env-driven agent did not reuse persisted metadata after restart" >&2
-  exit 1
-fi
-
-echo "[INFO] Env-driven agent restart succeeded with persisted metadata"

src/agent/tests/scripts/07_down.sh

@@ -13,7 +13,7 @@ compose() {
   fi
 }
 
-docker container rm -f argus-agent-e2e argus-agent-env-e2e >/dev/null 2>&1 || true
+docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
 
 pushd "$TEST_ROOT" >/dev/null
 compose down --remove-orphans

src/agent/tests/scripts/08_verify_agent.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+VERIFY_SCRIPT="$(cd "$TEST_ROOT/.." && pwd)/scripts/agent_deployment_verify.sh"
+
+if ! docker ps --format '{{.Names}}' | grep -q '^argus-agent-e2e$'; then
+  echo "[WARN] agent container not running; skip verification"
+  exit 0
+fi
+
+if docker exec -i argus-agent-e2e bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
+  echo "[INFO] curl/jq already installed in agent container"
+else
+  echo "[INFO] Installing curl/jq in agent container"
+  docker exec -i argus-agent-e2e bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
+fi
+
+if docker exec -i argus-agent-e2e bash -lc 'command -v /usr/local/bin/agent_deployment_verify.sh >/dev/null'; then
+  docker exec -i argus-agent-e2e /usr/local/bin/agent_deployment_verify.sh
+elif [[ -x "$VERIFY_SCRIPT" ]]; then
+  docker exec -i argus-agent-e2e "$VERIFY_SCRIPT"
+else
+  echo "[WARN] agent_deployment_verify.sh not found"
+fi

src/agent/tests/test_config_metadata.py

@@ -1,151 +0,0 @@
-from __future__ import annotations
-
-import os
-import unittest
-from contextlib import contextmanager
-from unittest.mock import patch
-
-from app.config import AgentConfig, load_config
-
-
-@contextmanager
-def temp_env(**overrides: str | None):
-    originals: dict[str, str | None] = {}
-    try:
-        for key, value in overrides.items():
-            originals[key] = os.environ.get(key)
-            if value is None:
-                os.environ.pop(key, None)
-            else:
-                os.environ[key] = value
-        yield
-    finally:
-        for key, original in originals.items():
-            if original is None:
-                os.environ.pop(key, None)
-            else:
-                os.environ[key] = original
-
-
-class LoadConfigMetadataTests(unittest.TestCase):
-    @patch("app.config.Path.mkdir")
-    def test_metadata_from_environment_variables(self, mock_mkdir):
-        with temp_env(
-            MASTER_ENDPOINT="http://master.local",
-            AGENT_HOSTNAME="dev-user-one-pod",
-            AGENT_ENV="prod",
-            AGENT_USER="ops",
-            AGENT_INSTANCE="node-1",
-        ):
-            config = load_config()
-
-        self.assertEqual(config.environment, "prod")
-        self.assertEqual(config.user, "ops")
-        self.assertEqual(config.instance, "node-1")
-        mock_mkdir.assert_called()
-
-    @patch("app.config.Path.mkdir")
-    def test_metadata_falls_back_to_hostname(self, mock_mkdir):
-        with temp_env(
-            MASTER_ENDPOINT="http://master.local",
-            AGENT_HOSTNAME="qa-team-abc-pod-2",
-            AGENT_ENV=None,
-            AGENT_USER=None,
-            AGENT_INSTANCE=None,
-        ):
-            config = load_config()
-
-        self.assertEqual(config.environment, "qa")
-        self.assertEqual(config.user, "team")
-        self.assertEqual(config.instance, "abc")
-        mock_mkdir.assert_called()
-
-    @patch("app.config._load_metadata_from_state", return_value=("prod", "ops", "node-1"))
-    @patch("app.config.Path.mkdir")
-    def test_metadata_from_node_state(self, mock_mkdir, mock_state):
-        with temp_env(
-            MASTER_ENDPOINT="http://master.local",
-            AGENT_HOSTNAME="host_abc",
-            AGENT_ENV=None,
-            AGENT_USER=None,
-            AGENT_INSTANCE=None,
-        ):
-            config = load_config()
-
-        self.assertEqual(config.environment, "prod")
-        self.assertEqual(config.user, "ops")
-        self.assertEqual(config.instance, "node-1")
-        mock_state.assert_called_once()
-        mock_mkdir.assert_called()
-
-    @patch("app.config.Path.mkdir")
-    def test_partial_environment_variables_fallback(self, mock_mkdir):
-        with temp_env(
-            MASTER_ENDPOINT="http://master.local",
-            AGENT_HOSTNAME="stage-ml-001-node",
-            AGENT_ENV="prod",
-            AGENT_USER=None,
-            AGENT_INSTANCE=None,
-        ):
-            config = load_config()
-
-        self.assertEqual(config.environment, "stage")
-        self.assertEqual(config.user, "ml")
-        self.assertEqual(config.instance, "001")
-        mock_mkdir.assert_called()
-
-    @patch("app.config.Path.mkdir")
-    def test_invalid_hostname_raises_error(self, mock_mkdir):
-        with temp_env(
-            MASTER_ENDPOINT="http://master.local",
-            AGENT_HOSTNAME="invalidhostname",
-            AGENT_ENV=None,
-            AGENT_USER=None,
-            AGENT_INSTANCE=None,
-        ):
-            with self.assertRaises(ValueError):
-                load_config()
-
-        mock_mkdir.assert_not_called()
-
-
-class CollectMetadataTests(unittest.TestCase):
-    @patch("app.collector._detect_ip_address", return_value="127.0.0.1")
-    @patch("app.collector._detect_gpu_count", return_value=0)
-    @patch("app.collector._detect_memory_bytes", return_value=1024)
-    @patch("app.collector._detect_cpu_count", return_value=8)
-    def test_collect_metadata_uses_config_fields(
-        self,
-        mock_cpu,
-        mock_memory,
-        mock_gpu,
-        mock_ip,
-    ):
-        config = AgentConfig(
-            hostname="dev-user-001-pod",
-            environment="prod",
-            user="ops",
-            instance="node-1",
-            node_file="/tmp/node.json",
-            version="1.0.0",
-            master_endpoint="http://master.local",
-            report_interval_seconds=60,
-            health_dir="/tmp/health",
-        )
-
-        from app.collector import collect_metadata
-
-        metadata = collect_metadata(config)
-
-        self.assertEqual(metadata["env"], "prod")
-        self.assertEqual(metadata["user"], "ops")
-        self.assertEqual(metadata["instance"], "node-1")
-        self.assertEqual(metadata["hostname"], "dev-user-001-pod")
-        self.assertEqual(metadata["ip"], "127.0.0.1")
-        self.assertEqual(metadata["cpu_number"], 8)
-        self.assertEqual(metadata["memory_in_bytes"], 1024)
-        self.assertEqual(metadata["gpu_number"], 0)
-
-
-if __name__ == "__main__":
-    unittest.main()

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（与本地离线包保持一致）
+# 设置 Alertmanager 版本
 ARG ALERTMANAGER_VERSION=0.28.1
 
-# 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
+# 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
 
 ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
 
-ARG ARGUS_BUILD_UID=2133
-ARG ARGUS_BUILD_GID=2015
-ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID}
-ENV ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+ARG ARGUS_UID=2133
+ARG ARGUS_GID=2015
+ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_GID=${ARGUS_GID}
 
 RUN mkdir -p /usr/share/alertmanager && \
     mkdir -p ${ALERTMANAGER_BASE_PATH} && \
@@ -31,31 +31,18 @@ RUN mkdir -p /usr/share/alertmanager && \
     rm -rf /alertmanager && \
     ln -s ${ALERTMANAGER_BASE_PATH} /alertmanager
 
-# 确保 ubuntu 账户存在并使用 ARGUS_BUILD_UID/GID
-RUN set -eux; \
-    # 确保存在目标 GID 的组；若不存在则优先尝试将 ubuntu 组改为该 GID，否则创建新组
-    if getent group "${ARGUS_BUILD_GID}" >/dev/null; then \
-      :; \
-    else \
-      if getent group ubuntu >/dev/null; then \
-        groupmod -g "${ARGUS_BUILD_GID}" ubuntu || true; \
-      else \
-        groupadd -g "${ARGUS_BUILD_GID}" ubuntu || groupadd -g "${ARGUS_BUILD_GID}" argus || true; \
-      fi; \
-    fi; \
-    # 创建或调整 ubuntu 用户
-    if id ubuntu >/dev/null 2>&1; then \
-      # 设置主组为目标 GID（可用 GID 数字指定）
-      usermod -g "${ARGUS_BUILD_GID}" ubuntu || true; \
-      # 若目标 UID 未被占用，则更新 ubuntu 的 UID
-      if [ "$(id -u ubuntu)" != "${ARGUS_BUILD_UID}" ] && ! getent passwd "${ARGUS_BUILD_UID}" >/dev/null; then \
-        usermod -u "${ARGUS_BUILD_UID}" ubuntu || true; \
-      fi; \
-    else \
-      useradd -m -s /bin/bash -u "${ARGUS_BUILD_UID}" -g "${ARGUS_BUILD_GID}" ubuntu || true; \
-    fi; \
-    # 调整关键目录属主为 ubuntu UID/GID
-    chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" /usr/share/alertmanager /alertmanager ${ALERTMANAGER_BASE_PATH} /private/argus/etc /usr/local/bin || true
+# 创建 alertmanager 用户（可自定义 UID/GID）
+# 创建 alertmanager 用户组
+RUN groupadd -g ${ARGUS_GID} alertmanager
+
+# 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
 
 # 配置内网 apt 源 (如果指定了内网选项)
 RUN if [ "$USE_INTRANET" = "true" ]; then \
@@ -99,3 +86,4 @@ 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_BUILD_UID=${ARGUS_BUILD_UID} \
-  --build-arg ARGUS_BUILD_GID=${ARGUS_BUILD_GID} \
+  --build-arg ARGUS_UID=${ARGUS_UID} \
+  --build-arg ARGUS_GID=${ARGUS_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

@@ -1,22 +0,0 @@
-#!/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

@@ -7,8 +7,10 @@ ALERTMANAGER_BASE_PATH=${ALERTMANAGER_BASE_PATH:-/private/argus/alert/alertmanag
 
 echo "[INFO] Alertmanager base path: ${ALERTMANAGER_BASE_PATH}"
 
-# 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"
+# 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
 
 
 # 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=ubuntu
+user=alertmanager
 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_BUILD_UID=1048
-ARGUS_BUILD_GID=1048
+ARGUS_UID=1048
+ARGUS_GID=1048
 
 USE_INTRANET=false

src/alert/tests/.env.example

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

src/alert/tests/docker-compose.yml

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

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

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+set -euo pipefail
+root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
+project_root="$(cd "$root/../../.." && pwd)"
+
+source "$project_root/scripts/common/build_user.sh"
+load_build_user
+
+# 创建新的private目录结构 (基于argus目录结构)
+echo "[INFO] Creating private directory structure for supervisor-based containers..."
+mkdir -p "$root/private/argus/alert/alertmanager"
+mkdir -p "$root/private/argus/etc/"
+
+# 设置数据目录权限
+echo "[INFO] Setting permissions for data directories..."
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/alert/alertmanager" 2>/dev/null || true
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
+
+echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"

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

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+compose_cmd="docker compose"
+if ! $compose_cmd version >/dev/null 2>&1; then
+  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
+    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
+fi
+$compose_cmd -p alert-mvp up -d --remove-orphans
+echo "[OK] 服务已启动：Alertmanager http://localhost:9093"

src/alert/tests/scripts/03_alertmanager_add_alert.sh

@@ -0,0 +1,106 @@
+#!/bin/bash
+set -euo pipefail
+
+# ==========================================================
+# Alertmanager 测试脚本
+# ==========================================================
+
+ALERTMANAGER_URL="http://localhost:9093"
+TEST_ALERT_NAME_CRITICAL="NodeDown"
+TEST_ALERT_NAME_WARNING="HighCPU"
+TMP_LOG="/tmp/test-alertmanager.log"
+
+# 等待参数
+am_wait_attempts=30
+am_wait_interval=2
+
+GREEN="\033[1;32m"
+RED="\033[1;31m"
+YELLOW="\033[1;33m"
+RESET="\033[0m"
+
+# ==========================================================
+# 函数定义
+# ==========================================================
+
+wait_for_alertmanager() {
+  local attempt=1
+  echo "[INFO] 等待 Alertmanager 启动中..."
+  while (( attempt <= am_wait_attempts )); do
+    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
+      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
+      return 0
+    fi
+    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
+    sleep "${am_wait_interval}"
+    (( attempt++ ))
+  done
+  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
+  return 1
+}
+
+log_step() {
+  echo -e "${YELLOW}==== $1 ====${RESET}"
+}
+
+# ==========================================================
+# 主流程
+# ==========================================================
+
+log_step "测试 Alertmanager 开始"
+echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
+
+# Step 1: 等待 Alertmanager 启动
+wait_for_alertmanager
+
+# Step 2: 触发一个critical测试告警
+echo "[INFO] 发送critical测试告警..."
+curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
+  -H "Content-Type: application/json" \
+  -d '[
+    {
+      "labels": {
+        "alertname": "'"${TEST_ALERT_NAME_CRITICAL}"'",
+        "instance": "node-1",
+        "severity": "critical"
+      },
+      "annotations": {
+        "summary": "节点 node-1 宕机"
+      }
+    }
+  ]' \
+  -o "$TMP_LOG"
+
+if [ $? -eq 0 ]; then
+  echo -e "${GREEN}[OK] 已成功发送critical测试告警${RESET}"
+else
+  echo -e "${RED}[ERROR] critical告警发送失败！${RESET}"
+  cat "$TMP_LOG"
+  exit 1
+fi
+
+# Step 3: 触发一个warning测试告警
+echo "[INFO] 发送warning测试告警..."
+curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
+  -H "Content-Type: application/json" \
+  -d '[
+    {
+      "labels": {
+        "alertname": "'"${TEST_ALERT_NAME_WARNING}"'",
+        "instance": "node-1",
+        "severity": "warning"
+      },
+      "annotations": {
+        "summary": "节点 node-1 CPU 使用率过高"
+      }
+    }
+  ]' \
+  -o "$TMP_LOG"
+
+if [ $? -eq 0 ]; then
+  echo -e "${GREEN}[OK] 已成功发送warning测试告警${RESET}"
+else
+  echo -e "${RED}[ERROR] warning告警发送失败！${RESET}"
+  cat "$TMP_LOG"
+  exit 1
+fi

src/alert/tests/scripts/04_query_alerts.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+set -euo pipefail
+
+# ==========================================================
+# Alertmanager 测试脚本（含启动等待）
+# ==========================================================
+
+ALERTMANAGER_URL="http://localhost:9093"
+TEST_ALERT_NAME_CRITICAL="NodeDown"
+TEST_ALERT_NAME_WARNING="HighCPU"
+TMP_LOG="/tmp/test-alertmanager.log"
+
+# 等待参数
+am_wait_attempts=30
+am_wait_interval=2
+
+GREEN="\033[1;32m"
+RED="\033[1;31m"
+YELLOW="\033[1;33m"
+RESET="\033[0m"
+
+# ==========================================================
+# 函数定义
+# ==========================================================
+
+wait_for_alertmanager() {
+  local attempt=1
+  echo "[INFO] 等待 Alertmanager 启动中..."
+  while (( attempt <= am_wait_attempts )); do
+    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
+      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
+      return 0
+    fi
+    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
+    sleep "${am_wait_interval}"
+    (( attempt++ ))
+  done
+  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
+  return 1
+}
+
+log_step() {
+  echo -e "${YELLOW}==== $1 ====${RESET}"
+}
+
+# ==========================================================
+# 主流程
+# ==========================================================
+
+log_step "查询 Alertmanager 当前告警列表开始"
+echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
+
+# Step 1: 等待 Alertmanager 启动
+wait_for_alertmanager
+
+# Step 2: 查询当前告警列表
+echo "[INFO] 查询当前告警..."
+sleep 1
+curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | jq '.' || {
+  echo -e "${RED}[WARN] 无法解析返回 JSON，请检查 jq 是否安装${RESET}"
+  curl -s "${ALERTMANAGER_URL}/api/v2/alerts"
+}
+
+# Step 3: 检查告警是否包含 NodeDown
+if curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | grep -q "${TEST_ALERT_NAME_CRITICAL}"; then
+  echo -e "${GREEN}✅ 测试通过：Alertmanager 已成功接收告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
+else
+  echo -e "${RED}❌ 测试失败：未检测到告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
+fi
+
+log_step "测试结束"

src/alert/tests/scripts/05_down.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+compose_cmd="docker compose"
+if ! $compose_cmd version >/dev/null 2>&1; then
+  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
+    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
+fi
+$compose_cmd -p alert-mvp down
+echo "[OK] 已停止所有容器"
+
+# 清理private目录内容
+echo "[INFO] 清理private目录内容..."
+cd "$(dirname "$0")/.."
+if [ -d "private" ]; then
+    # 删除private目录及其所有内容
+    rm -rf private
+    echo "[OK] 已清理private目录"
+else
+    echo "[INFO] private目录不存在，无需清理"
+fi

src/alert/tests/scripts/e2e_test.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS Alert System End-to-End Test"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(date +%s)
+
+# 函数：等待服务就绪
+wait_for_services() {
+    echo "[INFO] Waiting for all services to be ready..."
+    local max_attempts=${SERVICE_WAIT_ATTEMPTS:-120}
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs http://localhost:9093/api/v2/status >/dev/null 2>&1; then
+            echo "[OK] All services are ready!"
+            return 0
+        fi
+        echo "    Waiting for services... ($attempt/$max_attempts)"
+        sleep 5
+        ((attempt++))
+    done
+
+    echo "[ERROR] Services not ready after $max_attempts attempts"
+    return 1
+}
+
+# 函数：显示测试步骤
+show_step() {
+    echo ""
+    echo "🔄 Step $1: $2"
+    echo "----------------------------------------"
+}
+
+# 函数：验证步骤结果
+verify_step() {
+    if [ $? -eq 0 ]; then
+        echo "✅ $1 - SUCCESS"
+    else
+        echo "❌ $1 - FAILED"
+        exit 1
+    fi
+}
+
+# 开始端到端测试
+show_step "1" "Bootstrap - Initialize environment"
+./scripts/01_bootstrap.sh
+verify_step "Bootstrap"
+
+show_step "2" "Startup - Start all services"
+./scripts/02_up.sh
+verify_step "Service startup"
+
+# 等待服务完全就绪
+wait_for_services || exit 1
+
+# 发送告警数据
+show_step "3" "Add alerts - Send test alerts to Alertmanager"
+./scripts/03_alertmanager_add_alert.sh
+verify_step "Send test alerts"
+
+# 查询告警数据
+show_step "4" "Verify data - Query Alertmanager"
+./scripts/04_query_alerts.sh
+verify_step "Data verification"
+
+
+# 检查服务健康状态
+show_step "Health" "Check service health"
+echo "[INFO] Checking service health..."
+
+# 检查 Alertmanager 状态
+if curl -fs "http://localhost:9093/api/v2/status" >/dev/null 2>&1; then
+    am_status="available"
+    echo "✅ Alertmanager status: $am_status"
+else
+    am_status="unavailable"
+    echo "⚠️  Alertmanager status: $am_status"
+fi
+verify_step "Service health check"
+
+# 清理环境
+show_step "5" "Cleanup - Stop all services"
+./scripts/05_down.sh
+verify_step "Service cleanup"
+
+# 计算总测试时间
+test_end_time=$(date +%s)
+total_time=$((test_end_time - test_start_time))
+
+echo ""
+echo "======================================="
+echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
+echo "======================================="
+echo "📊 Test Summary:"
+echo "   • Total time: ${total_time}s"
+echo "   • Alertmanager status: $am_status"
+echo "   • All services started and stopped successfully"
+echo ""
+echo "✅ The ARGUS Alert system is working correctly!"
+echo ""

src/alert/tests/scripts/verify_alertmanager.sh

@@ -1,113 +0,0 @@
-#!/bin/bash
-# verify_alertmanager.sh
-# 用于部署后验证 Prometheus 与 Alertmanager 通信链路是否正常
-
-set -euo pipefail
-
-#=============================
-# 基础配置
-#=============================
-PROM_URL="${PROM_URL:-http://prom.metric.argus.com:9090}"
-ALERT_URL="${ALERT_URL:-http://alertmanager.alert.argus.com:9093}"
-# TODO: 根据实际部署环境调整规则目录
-DATA_ROOT="${DATA_ROOT:-/private/argus}"
-RULE_DIR = "$DATA_ROOT/metric/prometheus/rules"
-TMP_RULE="/tmp/test_rule.yml"
-
-#=============================
-# 辅助函数
-#=============================
-GREEN="\033[32m"; RED="\033[31m"; YELLOW="\033[33m"; RESET="\033[0m"
-
-log_info()    { echo -e "${YELLOW}[INFO]${RESET} $1"; }
-log_success() { echo -e "${GREEN}[OK]${RESET} $1"; }
-log_error()   { echo -e "${RED}[ERROR]${RESET} $1"; }
-
-fail_exit() { log_error "$1"; exit 1; }
-
-#=============================
-# Step 1: 检查 Alertmanager 是否可访问
-#=============================
-log_info "检查 Alertmanager 状态..."
-if curl -sSf "${ALERT_URL}/api/v2/status" >/dev/null 2>&1; then
-  log_success "Alertmanager 服务正常 (${ALERT_URL})"
-else
-  fail_exit "无法访问 Alertmanager，请检查端口映射与容器状态。"
-fi
-
-#=============================
-# Step 2: 手动发送测试告警
-#=============================
-log_info "发送手动测试告警..."
-curl -s -XPOST "${ALERT_URL}/api/v2/alerts" -H "Content-Type: application/json" -d '[
-  {
-    "labels": {
-      "alertname": "ManualTestAlert",
-      "severity": "info"
-    },
-    "annotations": {
-      "summary": "This is a test alert from deploy verification"
-    },
-    "startsAt": "'$(date -Iseconds)'"
-  }
-]' >/dev/null && log_success "测试告警已成功发送到 Alertmanager"
-
-#=============================
-# Step 3: 检查 Prometheus 配置中是否包含 Alertmanager
-#=============================
-log_info "检查 Prometheus 是否配置了 Alertmanager..."
-if curl -s "${PROM_URL}/api/v1/status/config" | grep -q "alertmanagers"; then
-  log_success "Prometheus 已配置 Alertmanager 目标"
-else
-  fail_exit "Prometheus 未配置 Alertmanager，请检查 prometheus.yml"
-fi
-
-#=============================
-# Step 4: 创建并加载测试告警规则
-#=============================
-log_info "创建临时测试规则 ${TMP_RULE} ..."
-cat <<EOF > "${TMP_RULE}"
-groups:
-- name: deploy-verify-group
-  rules:
-  - alert: DeployVerifyAlert
-    expr: vector(1)
-    labels:
-      severity: warning
-    annotations:
-      summary: "Deployment verification alert"
-EOF
-
-mkdir -p "${RULE_DIR}"
-cp "${TMP_RULE}" "${RULE_DIR}/test_rule.yml"
-
-log_info "重载 Prometheus 以加载新规则..."
-if curl -s -X POST "${PROM_URL}/-/reload" >/dev/null; then
-  log_success "Prometheus 已重载规则"
-else
-  fail_exit "Prometheus reload 失败，请检查 API 可访问性。"
-fi
-
-#=============================
-# Step 5: 等待并验证 Alertmanager 是否收到告警
-#=============================
-log_info "等待告警触发 (约5秒)..."
-sleep 5
-
-if curl -s "${ALERT_URL}/api/v2/alerts" | grep -q "DeployVerifyAlert"; then
-  log_success "Prometheus → Alertmanager 告警链路验证成功"
-else
-  fail_exit "未在 Alertmanager 中检测到 DeployVerifyAlert，请检查网络或配置。"
-fi
-
-#=============================
-# Step 6: 清理测试规则
-#=============================
-log_info "清理临时测试规则..."
-rm -f "${RULE_DIR}/test_rule.yml" "${TMP_RULE}"
-
-curl -s -X POST "${PROM_URL}/-/reload" >/dev/null \
-  && log_success "Prometheus 已清理验证规则" \
-  || log_error "Prometheus reload 清理失败，请手动确认。"
-
-log_success "部署验证全部通过！Prometheus ↔ Alertmanager 通信正常。"

src/bind/build/Dockerfile

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

src/bind/build/dns-monitor.sh

@@ -17,9 +17,6 @@ log_message() {
 
 log_message "DNS监控脚本启动"
 
-log_message "删除DNS备份文件（如果存在）"
-rm -f $DNS_BACKUP
-
 while true; do
     if [ -f "$DNS_CONF" ]; then
         if [ -f "$DNS_BACKUP" ]; then

src/bundle/cpu-node-bundle/.gitignore

@@ -1 +0,0 @@
-.build*/

src/bundle/cpu-node-bundle/Dockerfile

@@ -1,33 +0,0 @@
-FROM ubuntu:22.04
-
-ARG ARGUS_BUILD_UID=2133
-ARG ARGUS_BUILD_GID=2015
-
-ENV DEBIAN_FRONTEND=noninteractive \
-    TZ=Asia/Shanghai \
-    ARGUS_LOGS_WORLD_WRITABLE=1
-
-RUN set -eux; \
-    apt-get update; \
-    apt-get install -y --no-install-recommends \
-      ca-certificates curl wget iproute2 iputils-ping net-tools jq tzdata \
-      cron procps supervisor vim less tar gzip python3; \
-    rm -rf /var/lib/apt/lists/*; \
-    ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
-
-WORKDIR /
-
-# Offline fluent-bit assets and bundle tarball are staged by the build script
-COPY node-bootstrap.sh /usr/local/bin/node-bootstrap.sh
-COPY health-watcher.sh /usr/local/bin/health-watcher.sh
-COPY private/start-fluent-bit.sh /private/start-fluent-bit.sh
-COPY private/etc /private/etc
-COPY private/packages /private/packages
-COPY bundle/ /bundle/
-
-RUN chmod +x /usr/local/bin/node-bootstrap.sh /usr/local/bin/health-watcher.sh /private/start-fluent-bit.sh || true; \
-    mkdir -p /logs/train /logs/infer /buffers /opt/argus-metric; \
-    if [ "${ARGUS_LOGS_WORLD_WRITABLE}" = "1" ]; then chmod 1777 /logs/train /logs/infer || true; else chmod 755 /logs/train /logs/infer || true; fi; \
-    chmod 770 /buffers || true
-
-ENTRYPOINT ["/usr/local/bin/node-bootstrap.sh"]

src/bundle/cpu-node-bundle/health-watcher.sh

@@ -1,59 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# health-watcher.sh (CPU node bundle)
-# 周期执行 check_health.sh 与 restart_unhealthy.sh，用于节点容器内自愈。
-
-INSTALL_ROOT="/opt/argus-metric"
-INTERVAL="${HEALTH_WATCH_INTERVAL:-60}"
-VER_DIR="${1:-}"
-
-log(){ echo "[HEALTH-WATCHER] $*"; }
-
-resolve_ver_dir() {
-  local dir=""
-  if [[ -n "${VER_DIR:-}" && -d "$VER_DIR" ]]; then
-    dir="$VER_DIR"
-  elif [[ -L "$INSTALL_ROOT/current" ]]; then
-    dir="$(readlink -f "$INSTALL_ROOT/current" 2>/dev/null || true)"
-  fi
-  if [[ -z "$dir" ]]; then
-    dir="$(ls -d "$INSTALL_ROOT"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
-  fi
-  echo "$dir"
-}
-
-main() {
-  log "starting with interval=${INTERVAL}s"
-  local dir
-  dir="$(resolve_ver_dir)"
-  if [[ -z "$dir" || ! -d "$dir" ]]; then
-    log "no valid install dir found under $INSTALL_ROOT; exiting"
-    exit 0
-  fi
-
-  local chk="$dir/check_health.sh"
-  local rst="$dir/restart_unhealthy.sh"
-
-  if [[ ! -x "$chk" && ! -x "$rst" ]]; then
-    log "neither check_health.sh nor restart_unhealthy.sh is executable under $dir; exiting"
-    exit 0
-  fi
-
-  log "watching install dir: $dir"
-
-  while :; do
-    if [[ -x "$chk" ]]; then
-      log "running check_health.sh"
-      "$chk" >> "$dir/.health_check.watch.log" 2>&1 || log "check_health.sh reported issues (see .health_check.watch.log)"
-    fi
-    if [[ -x "$rst" ]]; then
-      log "running restart_unhealthy.sh"
-      "$rst" >> "$dir/.restart.watch.log" 2>&1 || log "restart_unhealthy.sh reported issues (see .restart.watch.log)"
-    fi
-    sleep "$INTERVAL"
-  done
-}
-
-main "$@"
-

src/bundle/cpu-node-bundle/node-bootstrap.sh

@@ -1,131 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-echo "[BOOT] CPU node bundle starting"
-
-INSTALL_ROOT="/opt/argus-metric"
-BUNDLE_DIR="/bundle"
-STATE_DIR_BASE="/private/argus/agent"
-
-mkdir -p "$INSTALL_ROOT" "$STATE_DIR_BASE" /logs/train /logs/infer /buffers || true
-
-# Ensure world-writable logs dir with sticky bit (align with deployment_new policy)
-if [[ "${ARGUS_LOGS_WORLD_WRITABLE:-1}" == "1" ]]; then
-  chmod 1777 /logs/train /logs/infer || true
-else
-  chmod 755 /logs/train /logs/infer || true
-fi
-chmod 770 /buffers || true
-
-installed_ok=0
-
-# 1) already installed?
-if [[ -L "$INSTALL_ROOT/current" && -d "$INSTALL_ROOT/current" ]]; then
-  echo "[BOOT] client already installed at $INSTALL_ROOT/current"
-else
-  # 2) try local bundle first (argus-metric_*.tar.gz)
-  tarball=$(ls -1 "$BUNDLE_DIR"/argus-metric_*.tar.gz 2>/dev/null | head -1 || true)
-  if [[ -n "${tarball:-}" ]]; then
-    echo "[BOOT] installing from local bundle: $(basename "$tarball")"
-    tmp=$(mktemp -d)
-    tar -xzf "$tarball" -C "$tmp"
-    # locate root containing version.json
-    root="$tmp"
-    if [[ ! -f "$root/version.json" ]]; then
-      sub=$(find "$tmp" -mindepth 1 -maxdepth 1 -type d | head -n1 || true)
-      [[ -n "$sub" && -f "$sub/version.json" ]] && root="$sub"
-    fi
-    if [[ ! -f "$root/version.json" ]]; then
-      echo "[BOOT][WARN] version.json not found in bundle; fallback to FTP"
-    else
-      ver=$(sed -n 's/.*"version"\s*:\s*"\([^"]\+\)".*/\1/p' "$root/version.json" | head -n1)
-      if [[ -z "$ver" ]]; then
-        echo "[BOOT][WARN] failed to parse version from version.json; fallback to FTP"
-      else
-        target_root="$INSTALL_ROOT"
-        version_dir="$target_root/versions/$ver"
-        mkdir -p "$version_dir"
-        shopt -s dotglob
-        mv "$root"/* "$version_dir/" 2>/dev/null || true
-        shopt -u dotglob
-        if [[ -f "$version_dir/install.sh" ]]; then
-          chmod +x "$version_dir/install.sh" 2>/dev/null || true
-          (
-            export AUTO_START_DCGM="0" # N/A on CPU
-            cd "$version_dir" && ./install.sh "$version_dir"
-          )
-          echo "$ver" > "$target_root/LATEST_VERSION" 2>/dev/null || true
-          ln -sfn "$version_dir" "$target_root/current" 2>/dev/null || true
-          if [[ -L "$target_root/current" && -d "$target_root/current" ]]; then
-            installed_ok=1
-            echo "[BOOT] local bundle install OK: version=$ver"
-          else
-            echo "[BOOT][WARN] current symlink not present after install; will rely on healthcheck to confirm"
-          fi
-        else
-          echo "[BOOT][WARN] install.sh missing under $version_dir; fallback to FTP"
-        fi
-      fi
-    fi
-  fi
-
-  # 3) fallback: use FTP setup if not installed
-  if [[ ! -L "$INSTALL_ROOT/current" && "$installed_ok" -eq 0 ]]; then
-    echo "[BOOT] fallback to FTP setup"
-    if [[ -z "${FTPIP:-}" || -z "${FTP_USER:-}" || -z "${FTP_PASSWORD:-}" ]]; then
-      echo "[BOOT][ERROR] FTP variables not set (FTPIP/FTP_USER/FTP_PASSWORD)" >&2
-      exit 1
-    fi
-    curl -u "$FTP_USER:$FTP_PASSWORD" -fsSL "ftp://$FTPIP:21/setup.sh" -o /tmp/setup.sh
-    chmod +x /tmp/setup.sh
-    /tmp/setup.sh --server "$FTPIP" --user "$FTP_USER" --password "$FTP_PASSWORD" --port 21
-  fi
-fi
-
-# 4) ensure argus-agent is running (best-effort)
-if ! pgrep -x argus-agent >/dev/null 2>&1; then
-  echo "[BOOT] starting argus-agent (not detected)"
-  setsid /usr/local/bin/argus-agent >/var/log/argus-agent.log 2>&1 < /dev/null &
-fi
-
-# 5) post-install selfcheck and state
-ver_dir=""
-if [[ -L "$INSTALL_ROOT/current" ]]; then
-  ver_dir="$(readlink -f "$INSTALL_ROOT/current" 2>/dev/null || true)"
-fi
-if [[ -z "$ver_dir" ]]; then
-  ver_dir="$(ls -d "$INSTALL_ROOT"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
-fi
-
-if [[ -n "$ver_dir" && -x "$ver_dir/check_health.sh" ]]; then
-  echo "[BOOT] running initial health check: $ver_dir/check_health.sh"
-  if "$ver_dir/check_health.sh" >> "$ver_dir/.health_check.init.log" 2>&1; then
-    echo "[BOOT] initial health check completed (see $ver_dir/.health_check.init.log)"
-  else
-    echo "[BOOT][WARN] initial health check reported issues (see $ver_dir/.health_check.init.log)"
-  fi
-else
-  echo "[BOOT][WARN] initial health check skipped (script missing: $ver_dir/check_health.sh)"
-fi
-
-host="$(hostname)"
-state_dir="$STATE_DIR_BASE/${host}"
-mkdir -p "$state_dir" 2>/dev/null || true
-for i in {1..60}; do
-  if [[ -s "$state_dir/node.json" ]]; then
-    echo "[BOOT] node state present: $state_dir/node.json"
-    break
-  fi
-  sleep 2
-done
-
-# 6) spawn health watcher (best-effort, non-blocking)
-if command -v /usr/local/bin/health-watcher.sh >/dev/null 2>&1; then
-  echo "[BOOT] starting health watcher for $ver_dir"
-  setsid /usr/local/bin/health-watcher.sh "${ver_dir:-}" >/var/log/health-watcher.log 2>&1 < /dev/null || true &
-else
-  echo "[BOOT][WARN] health-watcher.sh not found; skip health watcher"
-fi
-
-echo "[BOOT] ready; entering sleep"
-exec sleep infinity

src/bundle/gpu-node-bundle/.gitignore

@@ -1 +0,0 @@
-.build*/

src/bundle/gpu-node-bundle/Dockerfile

@@ -1,44 +0,0 @@
-ARG CUDA_VER=12.2.2
-FROM nvidia/cuda:${CUDA_VER}-runtime-ubuntu22.04
-
-ARG CLIENT_VER=0.0.0
-ARG BUNDLE_DATE=00000000
-
-LABEL org.opencontainers.image.title="argus-sys-metric-test-node-bundle-gpu" \
-      org.opencontainers.image.description="GPU node bundle with embedded Argus client artifact" \
-      org.opencontainers.image.version="${CLIENT_VER}" \
-      org.opencontainers.image.revision_date="${BUNDLE_DATE}" \
-      maintainer="Argus"
-
-ENV DEBIAN_FRONTEND=noninteractive \
-    TZ=Asia/Shanghai \
-    ARGUS_LOGS_WORLD_WRITABLE=1 \
-    ES_HOST=es.log.argus.com \
-    ES_PORT=9200 \
-    CLUSTER=local \
-    RACK=dev
-
-RUN set -eux; \
-    apt-get update; \
-    apt-get install -y --no-install-recommends \
-      ca-certificates curl wget iproute2 iputils-ping net-tools jq tzdata cron procps vim less \
-      tar gzip; \
-    rm -rf /var/lib/apt/lists/*; \
-    ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
-
-WORKDIR /
-
-# Expect staged build context to provide these directories/files
-COPY bundle/ /bundle/
-COPY node-bootstrap.sh /usr/local/bin/node-bootstrap.sh
-COPY health-watcher.sh /usr/local/bin/health-watcher.sh
-COPY private/start-fluent-bit.sh /private/start-fluent-bit.sh
-COPY private/etc /private/etc
-COPY private/packages /private/packages
-
-RUN chmod +x /usr/local/bin/node-bootstrap.sh /usr/local/bin/health-watcher.sh /private/start-fluent-bit.sh || true; \
-    mkdir -p /logs/train /logs/infer /buffers /opt/argus-metric; \
-    chmod 1777 /logs/train /logs/infer || true; \
-    chmod 770 /buffers || true
-
-ENTRYPOINT ["/usr/local/bin/node-bootstrap.sh"]

src/bundle/gpu-node-bundle/health-watcher.sh

@@ -1,59 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# health-watcher.sh (GPU bundle)
-# 周期执行 check_health.sh 与 restart_unhealthy.sh，用于 GPU 节点容器内自愈。
-
-INSTALL_ROOT="/opt/argus-metric"
-INTERVAL="${HEALTH_WATCH_INTERVAL:-60}"
-VER_DIR="${1:-}"
-
-log(){ echo "[HEALTH-WATCHER] $*"; }
-
-resolve_ver_dir() {
-  local dir=""
-  if [[ -n "${VER_DIR:-}" && -d "$VER_DIR" ]]; then
-    dir="$VER_DIR"
-  elif [[ -L "$INSTALL_ROOT/current" ]]; then
-    dir="$(readlink -f "$INSTALL_ROOT/current" 2>/dev/null || true)"
-  fi
-  if [[ -z "$dir" ]]; then
-    dir="$(ls -d "$INSTALL_ROOT"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
-  fi
-  echo "$dir"
-}
-
-main() {
-  log "starting with interval=${INTERVAL}s"
-  local dir
-  dir="$(resolve_ver_dir)"
-  if [[ -z "$dir" || ! -d "$dir" ]]; then
-    log "no valid install dir found under $INSTALL_ROOT; exiting"
-    exit 0
-  fi
-
-  local chk="$dir/check_health.sh"
-  local rst="$dir/restart_unhealthy.sh"
-
-  if [[ ! -x "$chk" && ! -x "$rst" ]]; then
-    log "neither check_health.sh nor restart_unhealthy.sh is executable under $dir; exiting"
-    exit 0
-  fi
-
-  log "watching install dir: $dir"
-
-  while :; do
-    if [[ -x "$chk" ]]; then
-      log "running check_health.sh"
-      "$chk" >> "$dir/.health_check.watch.log" 2>&1 || log "check_health.sh reported issues (see .health_check.watch.log)"
-    fi
-    if [[ -x "$rst" ]]; then
-      log "running restart_unhealthy.sh"
-      "$rst" >> "$dir/.restart.watch.log" 2>&1 || log "restart_unhealthy.sh reported issues (see .restart.watch.log)"
-    fi
-    sleep "$INTERVAL"
-  done
-}
-
-main "$@"
-

src/bundle/gpu-node-bundle/node-bootstrap.sh

@@ -1,135 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-echo "[BOOT] GPU node bundle starting"
-
-INSTALL_ROOT="/opt/argus-metric"
-BUNDLE_DIR="/bundle"
-STATE_DIR_BASE="/private/argus/agent"
-
-mkdir -p "$INSTALL_ROOT" "$STATE_DIR_BASE" /logs/train /logs/infer /buffers || true
-
-# Ensure world-writable logs dir with sticky bit (align with deployment_new policy)
-if [[ "${ARGUS_LOGS_WORLD_WRITABLE:-1}" == "1" ]]; then
-  chmod 1777 /logs/train /logs/infer || true
-else
-  chmod 755 /logs/train /logs/infer || true
-fi
-chmod 770 /buffers || true
-
-installed_ok=0
-
-# 1) already installed?
-if [[ -L "$INSTALL_ROOT/current" && -d "$INSTALL_ROOT/current" ]]; then
-  echo "[BOOT] client already installed at $INSTALL_ROOT/current"
-else
-  # 2) try local bundle first (argus-metric_*.tar.gz)
-  tarball=$(ls -1 "$BUNDLE_DIR"/argus-metric_*.tar.gz 2>/dev/null | head -1 || true)
-  if [[ -n "${tarball:-}" ]]; then
-    echo "[BOOT] installing from local bundle: $(basename "$tarball")"
-    tmp=$(mktemp -d)
-    tar -xzf "$tarball" -C "$tmp"
-    # locate root containing version.json
-    root="$tmp"
-    if [[ ! -f "$root/version.json" ]]; then
-      sub=$(find "$tmp" -mindepth 1 -maxdepth 1 -type d | head -n1 || true)
-      [[ -n "$sub" && -f "$sub/version.json" ]] && root="$sub"
-    fi
-    if [[ ! -f "$root/version.json" ]]; then
-      echo "[BOOT][WARN] version.json not found in bundle; fallback to FTP"
-    else
-      ver=$(sed -n 's/.*"version"\s*:\s*"\([^"]\+\)".*/\1/p' "$root/version.json" | head -n1)
-      if [[ -z "$ver" ]]; then
-        echo "[BOOT][WARN] failed to parse version from version.json; fallback to FTP"
-      else
-        target_root="$INSTALL_ROOT"
-        version_dir="$target_root/versions/$ver"
-        mkdir -p "$version_dir"
-        shopt -s dotglob
-        mv "$root"/* "$version_dir/" 2>/dev/null || true
-        shopt -u dotglob
-        if [[ -f "$version_dir/install.sh" ]]; then
-          chmod +x "$version_dir/install.sh" 2>/dev/null || true
-          (
-            export AUTO_START_DCGM="${AUTO_START_DCGM:-1}"
-            export DCGM_EXPORTER_DISABLE_PROFILING="${DCGM_EXPORTER_DISABLE_PROFILING:-1}"
-            export DCGM_EXPORTER_LISTEN="${DCGM_EXPORTER_LISTEN:-:9400}"
-            cd "$version_dir" && ./install.sh "$version_dir"
-          )
-          echo "$ver" > "$target_root/LATEST_VERSION" 2>/dev/null || true
-          ln -sfn "$version_dir" "$target_root/current" 2>/dev/null || true
-          if [[ -L "$target_root/current" && -d "$target_root/current" ]]; then
-            installed_ok=1
-            echo "[BOOT] local bundle install OK: version=$ver"
-          else
-            echo "[BOOT][WARN] current symlink not present after install; will rely on healthcheck to confirm"
-          fi
-        else
-          echo "[BOOT][WARN] install.sh missing under $version_dir; fallback to FTP"
-        fi
-      fi
-    fi
-  fi
-
-  # 3) fallback: use FTP setup if not installed
-  if [[ ! -L "$INSTALL_ROOT/current" && "$installed_ok" -eq 0 ]]; then
-    echo "[BOOT] fallback to FTP setup"
-    if [[ -z "${FTPIP:-}" || -z "${FTP_USER:-}" || -z "${FTP_PASSWORD:-}" ]]; then
-      echo "[BOOT][ERROR] FTP variables not set (FTPIP/FTP_USER/FTP_PASSWORD)" >&2
-      exit 1
-    fi
-    curl -u "$FTP_USER:$FTP_PASSWORD" -fsSL "ftp://$FTPIP:21/setup.sh" -o /tmp/setup.sh
-    chmod +x /tmp/setup.sh
-    /tmp/setup.sh --server "$FTPIP" --user "$FTP_USER" --password "$FTP_PASSWORD" --port 21
-  fi
-fi
-
-# 4) ensure argus-agent is running (best-effort)
-if ! pgrep -x argus-agent >/dev/null 2>&1; then
-  echo "[BOOT] starting argus-agent (not detected)"
-  setsid /usr/local/bin/argus-agent >/var/log/argus-agent.log 2>&1 < /dev/null &
-fi
-
-# 5) post-install selfcheck (run once) and state
-# prefer current version dir; fallback to first version under /opt/argus-metric/versions
-ver_dir=""
-if [[ -L "$INSTALL_ROOT/current" ]]; then
-  ver_dir="$(readlink -f "$INSTALL_ROOT/current" 2>/dev/null || true)"
-fi
-if [[ -z "$ver_dir" ]]; then
-  # pick the latest by name (semver-like); best-effort
-  ver_dir="$(ls -d "$INSTALL_ROOT"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
-fi
-
-if [[ -n "$ver_dir" && -x "$ver_dir/check_health.sh" ]]; then
-  echo "[BOOT] running initial health check: $ver_dir/check_health.sh"
-  if "$ver_dir/check_health.sh" >> "$ver_dir/.health_check.init.log" 2>&1; then
-    echo "[BOOT] initial health check completed (see $ver_dir/.health_check.init.log)"
-  else
-    echo "[BOOT][WARN] initial health check reported issues (see $ver_dir/.health_check.init.log)"
-  fi
-else
-  echo "[BOOT][WARN] initial health check skipped (script missing: $ver_dir/check_health.sh)"
-fi
-
-host="$(hostname)"
-state_dir="$STATE_DIR_BASE/${host}"
-mkdir -p "$state_dir" 2>/dev/null || true
-for i in {1..60}; do
-  if [[ -s "$state_dir/node.json" ]]; then
-    echo "[BOOT] node state present: $state_dir/node.json"
-    break
-  fi
-  sleep 2
-done
-
-# 6) spawn health watcher (best-effort, non-blocking)
-if command -v /usr/local/bin/health-watcher.sh >/dev/null 2>&1; then
-  echo "[BOOT] starting health watcher for $ver_dir"
-  setsid /usr/local/bin/health-watcher.sh "${ver_dir:-}" >/var/log/health-watcher.log 2>&1 < /dev/null || true &
-else
-  echo "[BOOT][WARN] health-watcher.sh not found; skip health watcher"
-fi
-
-echo "[BOOT] ready; entering sleep"
-exec sleep infinity

src/log/fluent-bit/build/app/update_fluent_config.py

@@ -1,637 +0,0 @@
-#!/usr/bin/env python3
-"""
-定时任务脚本：每小时执行一次，根据node.json配置文件生成fluent-bit配置文件
-支持配置文件变更检测和Fluent Bit热重启
-"""
-
-import requests
-import os
-import json
-import time
-import logging
-import hashlib
-import subprocess
-from datetime import datetime
-from pathlib import Path
-import re
-import socket
-
-# 配置日志
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(levelname)s - %(message)s',
-    handlers=[
-        logging.FileHandler('/var/log/config_generator.log'),
-        logging.StreamHandler()
-    ]
-)
-logger = logging.getLogger(__name__)
-
-class KibanaDataViewManager:
-    """Kibana Data View 管理器"""
-
-    def __init__(self):
-        self.kibana_host = os.environ.get("KIBANA_HOST", "kibana")
-        self.kibana_port = os.environ.get("KIBANA_PORT", "5601")
-        self.kibana_user = os.environ.get("KIBANA_USER", "elastic")
-        self.kibana_password = os.environ.get("KIBANA_PASSWORD", "")
-        self.es_host = os.environ.get("ES_HOST")
-        self.es_port = os.environ.get("ES_PORT", "9200")
-        self.fb_user = os.environ.get("AGENT_USER", "unknown_user")
-
-        self.base_url = f"http://{self.kibana_host}:{self.kibana_port}"
-        self.auth = (self.kibana_user, self.kibana_password)
-
-        # Data View名称模板
-        self.data_view_name = f"custom"
-        self.data_view_pattern = f"custom-*"
-
-        # 请求超时设置
-        self.timeout = 30
-
-    def _get_headers(self):
-        """获取请求头"""
-        return {
-            "kbn-xsrf": "true",
-            "Content-Type": "application/json"
-        }
-
-    def check_kibana_available(self):
-        """检查Kibana服务是否可用"""
-        try:
-            url = f"{self.base_url}/api/status"
-            response = requests.get(
-                url,
-                auth=self.auth,
-                timeout=self.timeout,
-                headers=self._get_headers()
-            )
-
-            if response.status_code == 200:
-                status = response.json().get("status", {}).get("overall", {}).get("level")
-                if status == "available":
-                    logger.info("Kibana服务可用")
-                    return True
-                else:
-                    logger.warning(f"Kibana服务状态: {status}")
-                    return False
-            else:
-                logger.warning(f"Kibana状态检查失败: {response.status_code}")
-                return False
-
-        except requests.exceptions.ConnectionError:
-            logger.error("无法连接到Kibana服务")
-            return False
-        except requests.exceptions.Timeout:
-            logger.error("连接Kibana服务超时")
-            return False
-        except Exception as e:
-            logger.error(f"检查Kibana服务失败: {e}")
-            return False
-
-    def get_existing_data_views(self):
-        """获取现有的Data View列表"""
-        try:
-            url = f"{self.base_url}/api/data_views"
-            response = requests.get(
-                url,
-                auth=self.auth,
-                timeout=self.timeout,
-                headers=self._get_headers()
-            )
-
-            if response.status_code == 200:
-                response_data = response.json()
-                data_views = response_data.get("data_view", [])
-                logger.info(f"获取到 {len(data_views)} 个Data View")
-                return data_views
-            else:
-                logger.warning(f"获取Data View列表失败: {response.status_code}")
-                return []
-
-        except Exception as e:
-            logger.error(f"获取Data View列表失败: {e}")
-            return []
-
-    def check_data_view_exists(self):
-        """检查custom Data View是否存在"""
-        data_views = self.get_existing_data_views()
-
-        for data_view in data_views:
-            if data_view.get("name") == self.data_view_name:
-                logger.info(f"Data View '{self.data_view_name}' 已存在")
-                return True
-
-        logger.info(f"Data View '{self.data_view_name}' 不存在")
-        return False
-
-    def create_data_view(self):
-        """创建Data View"""
-        try:
-            # 检查对应的索引是否存在
-            index_exists = self._check_index_exists()
-            if not index_exists:
-                logger.warning(f"索引模式 '{self.data_view_pattern}' 对应的索引不存在，但将继续创建Data View")
-
-            url = f"{self.base_url}/api/data_views/data_view"
-
-            # Data View配置
-            data_view_config = {
-                "data_view": {
-                    "title": self.data_view_pattern,
-                    "name": self.data_view_name,
-                    "timeFieldName": "@timestamp"
-                }
-            }
-
-            response = requests.post(
-                url,
-                auth=self.auth,
-                json=data_view_config,
-                timeout=self.timeout,
-                headers=self._get_headers()
-            )
-
-            if response.status_code == 200:
-                result = response.json()
-                logger.info(f"成功创建Data View: {result.get('data_view', {}).get('name')}")
-                return True
-            elif response.status_code == 409:
-                logger.info(f"Data View已存在: {response.json().get('message', 'Unknown error')}")
-                return True
-            else:
-                error_msg = response.json().get('message', 'Unknown error')
-                logger.error(f"创建Data View失败 {response.status_code}: {error_msg}")
-                return False
-
-        except Exception as e:
-            logger.error(f"创建Data View异常: {e}")
-            return False
-
-    def _check_index_exists(self):
-        """检查ES中是否存在对应的索引"""
-        try:
-            es_url = f"http://{self.es_host}:{self.es_port}"
-            index_url = f"{es_url}/{self.data_view_pattern}"
-
-            response = requests.head(
-                index_url,
-                auth=(self.kibana_user, self.kibana_password) if self.kibana_password else None,
-                timeout=self.timeout
-            )
-
-            return response.status_code == 200
-
-        except Exception as e:
-            logger.warning(f"检查索引存在失败: {e}")
-            return False
-
-
-    def manage_data_view(self):
-        """管理Data View：检查并创建"""
-        logger.info("开始管理Kibana Data View")
-
-        # 检查Kibana是否可用
-        if not self.check_kibana_available():
-            logger.warning("Kibana服务不可用，跳过Data View管理")
-            return False
-
-        # 检查Data View是否存在
-        if self.check_data_view_exists():
-            logger.info(f"Data View '{self.data_view_name}' 已存在，无需创建")
-            return True
-
-        # 创建Data View
-        logger.info(f"创建Data View: {self.data_view_name}")
-        if self.create_data_view():
-            logger.info(f"Data View '{self.data_view_name}' 创建成功")
-
-            return True
-        else:
-            logger.error(f"Data View '{self.data_view_name}' 创建失败")
-            return False
-
-class ConfigGenerator:
-    def __init__(self):
-        # 获取主机名
-        self.hostname = self._get_hostname()
-
-        # 获取用户帐号
-        self.fb_user = self._get_fb_user()
-
-        # 基础路径
-        self.base_path = Path("/private/argus/agent")
-        self.inputs_dir = Path("/etc/fluent-bit/inputs.d")
-        self.outputs_dir = Path("/etc/fluent-bit/outputs.d")
-
-        # 配置文件路径
-        self.config_file = self.base_path / self.hostname / "node.json"
-        # 配置文件hash值，校验配置是否发生变更
-        hash_file = self.base_path / self.hostname / "node_json_hash.txt"
-
-        # 配置文件哈希值存储文件
-        self.config_hash_file = Path(hash_file)
-
-        # 需要保留的文件
-        self.inputs_to_keep = ["10-train.conf", "20-infer.conf"]
-        self.outputs_to_keep = ["10-es.conf"]
-
-        # 生成的配置文件前缀
-        self.generated_prefix = "custom_"
-
-        # Kibana Data View管理器
-        self.kibana_manager = KibanaDataViewManager()
-
-        # 确保目录存在
-        self._ensure_directories()
-
-    def _get_hostname(self):
-        """获取容器主机名"""
-        return os.environ.get("AGENT_HOSTNAME") or socket.gethostname()
-
-    def _get_fb_user(self):
-        """获取容器用户"""
-        return os.environ.get("AGENT_USER", "unknown_user")
-
-    def _ensure_directories(self):
-        """确保必要的目录存在"""
-        directories = [
-            self.base_path / self.hostname,
-            self.inputs_dir,
-            self.outputs_dir
-        ]
-
-        for directory in directories:
-            directory.mkdir(parents=True, exist_ok=True)
-            logger.debug(f"确保目录存在: {directory}")
-
-    def _get_config_hash(self, config_content):
-        """计算配置内容的哈希值"""
-        return hashlib.md5(config_content.encode('utf-8')).hexdigest()
-
-    def _save_config_hash(self, config_hash):
-        """保存配置哈希值"""
-        try:
-            with open(self.config_hash_file, 'w') as f:
-                f.write(config_hash)
-            logger.debug(f"保存配置哈希值: {config_hash}")
-        except Exception as e:
-            logger.warning(f"保存配置哈希值失败: {e}")
-
-    def _load_config_hash(self):
-        """加载保存的配置哈希值"""
-        if not self.config_hash_file.exists():
-            return None
-
-        try:
-            with open(self.config_hash_file, 'r') as f:
-                return f.read().strip()
-        except Exception as e:
-            logger.warning(f"加载配置哈希值失败: {e}")
-            return None
-
-    def _has_config_changed(self, current_config):
-        """检查配置是否发生变化"""
-        # 生成当前配置的哈希值
-        config_str = json.dumps(current_config, sort_keys=True)
-        current_hash = self._get_config_hash(config_str)
-
-        # 获取之前保存的哈希值
-        saved_hash = self._load_config_hash()
-
-        if saved_hash is None:
-            # 没有保存的哈希值，说明是第一次运行
-            logger.info("首次运行，未找到保存的配置哈希值")
-            self._save_config_hash(current_hash)
-            return True
-
-        # 比较哈希值
-        if current_hash == saved_hash:
-            logger.info("配置文件未发生变化")
-            return False
-        else:
-            logger.info(f"配置文件发生变化: {saved_hash[:8]} -> {current_hash[:8]}")
-            self._save_config_hash(current_hash)
-            return True
-
-    def _load_node_config(self):
-        """加载node.json配置文件"""
-        if not self.config_file.exists():
-            logger.warning(f"配置文件不存在: {self.config_file}")
-            return None, None
-
-        try:
-            with open(self.config_file, 'r') as f:
-                config = json.load(f)
-
-            # 获取log路径列表
-            log_configs = config.get("config", {}).get("log", [])
-            paths = [log.get("path") for log in log_configs if log.get("path")]
-
-            logger.info(f"从配置文件中读取到 {len(paths)} 个日志路径")
-            return paths, config
-
-        except json.JSONDecodeError as e:
-            logger.error(f"配置文件JSON格式错误: {e}")
-            return None, None
-        except Exception as e:
-            logger.error(f"读取配置文件失败: {e}")
-            return None, None
-
-    def _clean_generated_files(self):
-        """只清理生成的配置文件，保留系统文件"""
-        try:
-            # 清理inputs.d目录中生成的配置文件
-            for file_path in self.inputs_dir.glob(f"{self.generated_prefix}*.conf"):
-                if file_path.is_file() and file_path.name not in self.inputs_to_keep:
-                    try:
-                        file_path.unlink()
-                        logger.debug(f"已删除生成的input文件: {file_path}")
-                    except Exception as e:
-                        logger.warning(f"删除文件失败 {file_path}: {e}")
-
-            # 清理outputs.d目录中生成的配置文件
-            for file_path in self.outputs_dir.glob(f"{self.generated_prefix}*.conf"):
-                if file_path.is_file() and file_path.name not in self.outputs_to_keep:
-                    try:
-                        file_path.unlink()
-                        logger.debug(f"已删除生成的output文件: {file_path}")
-                    except Exception as e:
-                        logger.warning(f"删除文件失败 {file_path}: {e}")
-
-            logger.info("已清理生成的配置文件")
-
-        except Exception as e:
-            logger.error(f"清理生成的配置文件失败: {e}")
-            raise
-
-    def _generate_input_config(self, paths):
-        """生成input配置文件"""
-        configs = []
-
-        for i, path in enumerate(paths, 1):
-            # 清理路径，移除非法字符用于文件名
-            safe_name = re.sub(r'[^\w\-_]', '_', path.replace('/', '_').replace('*', 'all'))
-            filename = f"{self.generated_prefix}{safe_name}_input.conf"
-            filepath = self.inputs_dir / filename
-
-            # 生成配置内容
-            config_content = self._create_input_config(path, i)
-
-            # 写入文件
-            with open(filepath, 'w') as f:
-                f.write(config_content)
-
-            configs.append(filepath)
-            logger.info(f"生成input配置文件: {filepath}")
-
-        return configs
-
-    def _create_input_config(self, path, index):
-        """创建单个input配置"""
-        config = f"""[INPUT]
-    name             tail
-    path             {path}
-    tag              app.custom
-    Path_Key         log_path
-    refresh_interval 5
-    skip_long_lines  on
-    storage.type     filesystem
-    multiline.parser python,go,java
-    DB               /buffers/{self.fb_user}_custom.db
-    Mem_Buf_Limit    50MB
-    Buffer_Chunk_Size 1MB
-    Buffer_Max_Size  5MB
-    Rotate_Wait      30
-    Ignore_Older     24h
-
-"""
-        return config
-
-    def _generate_output_config(self):
-        """生成output配置文件，生成一个output配置文件"""
-        filename = f"{self.generated_prefix}output.conf"
-        filepath = self.outputs_dir / filename
-
-        # 检查是否已存在
-        if filepath.exists():
-            logger.info(f"Output配置文件已存在: {filepath}")
-            return [filepath]
-
-        # 生成配置内容
-        config_content = self._create_output_config()
-
-        # 写入文件
-        with open(filepath, 'w') as f:
-            f.write(config_content)
-
-        logger.info(f"生成output配置文件: {filepath}")
-        return [filepath]
-
-    def _create_output_config(self):
-        """创建单个output配置"""
-        config = f"""# Source: customer log path
-[OUTPUT]
-    name      es
-    Match     app.custom
-    Host      ${{ES_HOST}}
-    Port      ${{ES_PORT}}
-    Logstash_Format     On
-    Logstash_Prefix     custom-${{FB_USER}}
-    Replace_Dots        On
-    Generate_ID         On
-    Retry_Limit         False
-    Suppress_Type_Name  On
-
-"""
-        return config
-
-    def _reload_fluentbit(self):
-        """重新加载Fluent Bit配置"""
-        try:
-            # 方法1: 使用SIGHUP信号（如果支持）
-            logger.info("尝试使用SIGHUP信号重新加载Fluent Bit...")
-            result = subprocess.run(
-                ["pkill", "-HUP", "fluent-bit"],
-                capture_output=True,
-                text=True,
-                timeout=30
-            )
-
-            if result.returncode == 0:
-                logger.info("成功发送SIGHUP信号重新加载Fluent Bit")
-                return True
-
-            # 方法2: 使用fluent-bit的热重载（如果支持）
-            logger.info("尝试使用热重载命令...")
-            result = subprocess.run(
-                ["fluent-bit", "-R"],
-                capture_output=True,
-                text=True,
-                timeout=30
-            )
-
-            if result.returncode == 0:
-                logger.info("成功执行Fluent Bit热重载")
-                return True
-
-            logger.error("所有重载方法都失败")
-            return False
-
-        except subprocess.TimeoutExpired:
-            logger.error("Fluent Bit重载操作超时")
-            return False
-        except Exception as e:
-            logger.error(f"重载Fluent Bit失败: {e}")
-            return False
-
-    def _check_fluentbit_status(self):
-        """检查Fluent Bit运行状态"""
-        try:
-            # 方法1: 检查进程
-            result = subprocess.run(
-                ["pgrep", "fluent-bit"],
-                capture_output=True,
-                text=True
-            )
-
-            if result.returncode == 0:
-                logger.info("Fluent Bit进程正在运行")
-                return True
-
-            # 方法2: 检查服务状态
-            result = subprocess.run(
-                ["systemctl", "is-active", "fluent-bit"],
-                capture_output=True,
-                text=True
-            )
-
-            if result.returncode == 0 and result.stdout.strip() == "active":
-                logger.info("Fluent Bit服务正在运行")
-                return True
-
-            logger.warning("Fluent Bit未运行")
-            return False
-
-        except Exception as e:
-            logger.error(f"检查Fluent Bit状态失败: {e}")
-            return False
-
-    def run(self):
-        """执行主逻辑：检查配置文件更新；生成fluent bit配置文件并热启动进程；检查kinbana data view"""
-        logger.info("=" * 50)
-        logger.info(f"开始执行配置生成任务 - {datetime.now()}")
-        logger.info(f"主机名: {self.hostname}")
-
-        try:
-            # 1. 加载配置文件
-            paths, config = self._load_node_config()
-            if not paths or not config:
-                logger.warning("未找到有效的日志路径配置，跳过本次执行")
-                return False
-
-            # 2. 检查配置是否发生变化
-            config_str = json.dumps(config, sort_keys=True)
-            current_hash = self._get_config_hash(config_str)
-            saved_hash = self._load_config_hash()
-
-            # 如果没有变化，检查Fluent Bit状态后退出
-            if saved_hash and current_hash == saved_hash:
-                logger.info("配置文件未发生变化，跳过配置生成")
-                # 检查Fluent Bit状态
-                if not self._check_fluentbit_status():
-                    logger.warning("Fluent Bit未运行，尝试启动...")
-                    self._reload_fluentbit()
-                return True
-
-            # 保存新的哈希值
-            self._save_config_hash(current_hash)
-            logger.info("配置文件发生变化，重新生成配置")
-
-            # 3. 清理之前生成的配置文件
-            self._clean_generated_files()
-
-            # 4. 生成新的配置文件
-            input_files = self._generate_input_config(paths)
-            output_files = self._generate_output_config()
-
-            logger.info(f"生成 {len(input_files)} 个input配置，{len(output_files)} 个output配置")
-
-            # 重新加载Fluent Bit
-            logger.info("配置文件已更新，重新加载Fluent Bit...")
-            if self._reload_fluentbit():
-                logger.info("Fluent Bit重载成功")
-            else:
-                logger.warning("Fluent Bit重载失败，但配置文件已更新")
-
-            # 不论配置是否变更，每次执行都检查custom视图是否存在，避免视图创建失败后，若配置不再变更则无法创建
-            # 检查kibana data view 并进行创建data view
-            logger.info("开始管理Kibana Data View...")
-            self.kibana_manager.manage_data_view()
-
-            logger.info("任务完成")
-            return True
-
-        except Exception as e:
-            logger.error(f"任务执行失败: {e}", exc_info=True)
-            return False
-
-
-class Scheduler:
-    """定时调度器"""
-
-    def __init__(self, interval_seconds=3600):
-        self.interval_hours = interval_seconds/3600
-        self.interval_seconds = interval_seconds
-        self.running = False
-        self.generator = ConfigGenerator()
-
-    def run(self):
-        """执行任务"""
-        return self.generator.run()
-
-    def start(self):
-        """启动定时调度"""
-        self.running = True
-        logger.info(f"启动定时调度器，每隔 {self.interval_hours} 小时执行一次")
-
-        try:
-            while self.running:
-                # 记录下次执行时间
-                next_run = datetime.now().timestamp() + self.interval_seconds
-                next_time_str = datetime.fromtimestamp(next_run).strftime('%Y-%m-%d %H:%M:%S')
-
-                # 执行任务
-                logger.info(f"开始执行定时任务 - {datetime.now()}")
-                self.run()
-
-                # 等待到下次执行时间
-                logger.info(f"下次执行时间: {next_time_str}")
-
-                # 使用递减等待
-                for _ in range(self.interval_seconds):
-                    if not self.running:
-                        break
-                    time.sleep(1)
-
-        except Exception as e:
-            logger.error(f"调度器运行异常: {e}")
-        finally:
-            self.stop()
-
-    def stop(self):
-        """停止调度器"""
-        self.running = False
-        logger.info("调度器已停止")
-
-
-def main():
-    # 定时调度，设置调度周期
-    scheduler = Scheduler(3600)
-
-    # 启动调度器
-    scheduler.start()
-
-
-if __name__ == "__main__":
-    main()

src/log/fluent-bit/build/etc/fluent-bit.conf

@@ -1,11 +1,9 @@
 [SERVICE]
     Daemon       Off
-    Parsers_File /etc/fluent-bit/parsers.conf
+    Parsers_File parsers.conf
     HTTP_Server  On
     HTTP_Listen  0.0.0.0
     HTTP_Port    2020
-    Hot_Reload   On
-    Hot_Reload.Period 5
     storage.path /buffers
     storage.sync normal
     storage.checksum on
@@ -33,7 +31,7 @@
 [FILTER]
     Name   lua
     Match  app.*
-    script /etc/fluent-bit/inject_labels.lua
+    script inject_labels.lua
     call   add_labels
 
 @INCLUDE outputs.d/*.conf

src/log/fluent-bit/build/etc/parsers.conf

@@ -22,7 +22,8 @@
 [PARSER]
     Name   timestamp_parser
     Format regex
-    Regex  ^(?<timestamp>\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:Z|[+-]\d{2}:?\d{2}))\s+(?<level>\w+)\s+(?<message>.*)$
+    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-%dT%H:%M:%S%z
+    Time_Format %Y-%m-%d %H:%M:%S
+    Time_Offset +0800
     Time_Keep On

src/log/fluent-bit/build/start-fluent-bit.sh

@@ -1,246 +1,47 @@
 #!/bin/bash
 set -euo pipefail
 
-echo "[INFO] Starting Fluent Bit setup in Ubuntu container (offline-first)..."
+echo "[INFO] Starting Fluent Bit setup in Ubuntu container..."
 
+# 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
 
-# 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/
-cp -r /private/app /tmp
-mkdir -p /tmp/flb/packages
-cp -r /private/packages/* /tmp/flb/packages/ 2>/dev/null || true
+# 解压bundle到/tmp
+echo "[INFO] Extracting fluent-bit bundle..."
+cp -r /private/etc /tmp
+cp -r /private/packages /tmp
+cd /tmp
 
-# 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
+# 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
 
+# 验证 Fluent Bit 可以运行
 echo "[INFO] Fluent Bit version:"
-/opt/fluent-bit/bin/fluent-bit --version || { echo "[ERROR] fluent-bit not installed or libraries missing" >&2; exit 1; }
+/opt/fluent-bit/bin/fluent-bit --version
 
-# Place configuration
+# 创建配置目录
 mkdir -p /etc/fluent-bit
-cp -r /tmp/flb/etc/* /etc/fluent-bit/
+cp -r /tmp/etc/* /etc/fluent-bit/
 
-# 创建定时脚本目录，并复制脚本
-mkdir -p /etc/fluent-bit/app/
-cp -r /tmp/app/* /etc/fluent-bit/app/
-
-# Create logs/buffers dirs
+# 创建日志和缓冲区目录
 mkdir -p /logs/train /logs/infer /buffers
+chmod 755 /logs/train /logs/infer /buffers
 
-# 控制日志目录权限：默认对宿主 bind mount 目录采用 1777（可由环境变量关闭）
-: "${ARGUS_LOGS_WORLD_WRITABLE:=1}"
-if [[ "${ARGUS_LOGS_WORLD_WRITABLE}" == "1" ]]; then
-  chmod 1777 /logs/train /logs/infer || true
-else
-  chmod 755 /logs/train /logs/infer || true
-fi
-
-# 缓冲目录仅供进程使用，不对外开放写入
-chmod 770 /buffers || true
-
-# 目录属主设置为 fluent-bit（不影响 1777 粘滞位）
-chown -R fluent-bit:fluent-bit /logs /buffers 2>/dev/null || true
-
-# 检查Python基础环境
-echo "[INFO] Checking Python environment..."
-
-echo "[INFO] Fixing broken dependencies..."
-apt-get -f install -y -qq 2>/dev/null || true
-
-# 检查python3是否安装
-if ! command -v python3 >/dev/null 2>&1; then
-  echo "[INFO] Installing python3..."
-  apt-get update -qq || true
-  # 尝试安装最小化的python3（不安装推荐包，减少依赖冲突）
-  apt-get install -y -qq --no-install-recommends python3-minimal 2>/dev/null || {
-    echo "[WARN] Failed to install python3 via apt, trying alternative approach..."
-
-    # 如果apt安装失败，检查是否已有python3二进制文件
-    if [ -f /usr/bin/python3 ] && python3 --version 2>/dev/null; then
-      echo "[INFO] Python3 binary exists but not in PATH"
-    fi
-  }
-fi
-
-# 检查pip是否可用
-if ! command -v pip3 >/dev/null 2>&1; then
-  # 尝试安装pip
-  echo "[INFO] Installing pip..."
-  apt-get update -qq || true
-  apt-get install -y -qq python3-pip 2>/dev/null || true
-fi
-
-# 检查Python脚本依赖的包
-check_python_packages() {
-  local missing_packages=""
-
-  # 根据脚本内容确定需要的包
-  local required_packages=(
-    "requests"        # HTTP请求库（脚本中最关键的依赖）
-  )
-
-  # 检查requests是否安装（必须）
-  if ! python3 -c "import requests" 2>/dev/null; then
-    echo "[WARN] 'requests' package not found, installing..."
-    if command -v pip3 >/dev/null 2>&1; then
-      # 尝试使用清华镜像源
-      PIP_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
-      echo "[INFO] Installing requests using pip with mirror..."
-      pip3 install --no-cache-dir --index-url "$PIP_INDEX_URL" requests 2>/dev/null || {
-        # 如果镜像失败，尝试官方源
-        echo "[INFO] Trying official PyPI source..."
-        pip3 install --no-cache-dir requests 2>/dev/null || {
-          echo "[ERROR] Failed to install requests via pip"
-          return 1
-        }
-      }
-    else
-      echo "[ERROR] pip3 not available, cannot install requests"
-      return 1
-    fi
-  fi
-
-  # 检查其他必需包
-  for pkg in "${required_packages[@]}"; do
-    if ! python3 -c "import $pkg" 2>/dev/null; then
-      missing_packages="$missing_packages $pkg"
-    fi
-  done
-
-  echo "$missing_packages"
-}
-
-# 安装Python包依赖
-echo "[INFO] Installing Python package dependencies..."
-missing_py_deps=$(check_python_packages)
-
-if [[ -n "$missing_py_deps" ]]; then
-  echo "[INFO] Installing missing Python packages:$missing_py_deps"
-  # 如果还有缺失的包，尝试安装
-  if command -v pip3 >/dev/null 2>&1; then
-    for pkg in $missing_py_deps; do
-      pip3 install --no-cache-dir "$pkg" 2>/dev/null || true
-    done
-  fi
-fi
-
-# 验证Python脚本依赖
-echo "[INFO] Verifying Python dependencies..."
-if python3 -c "import requests; import json; import time; import logging; import hashlib; import subprocess; from datetime import datetime; from pathlib import Path; import re; import socket; print('All required modules imported successfully')" 2>/dev/null; then
-  echo "[INFO] Python dependencies verified successfully"
-else
-  echo "[WARN] Some Python modules may be missing"
-  # 尝试查看具体缺少什么
-  python3 -c "
-import sys
-modules = ['requests', 'json', 'time', 'logging', 'hashlib', 'subprocess', 'datetime', 'pathlib', 're', 'socket']
-missing = []
-for module in modules:
-    try:
-        __import__(module)
-        print(f'✓ {module}')
-    except ImportError as e:
-        print(f'✗ {module}: {e}')
-        missing.append(module)
-if missing:
-    sys.exit(1)
-  " 2>/dev/null || true
-fi
-
-# 查找并运行Python脚本
-echo "[INFO] Looking for Python configuration generator script..."
-PYTHON_SCRIPT="/etc/fluent-bit/app/update_fluent_config.py"
-
-if [ -f "$PYTHON_SCRIPT" ]; then
-  echo "[INFO] Found Python script: $PYTHON_SCRIPT"
-
-  # 检查脚本是否可执行，如果不可执行则添加执行权限
-  if [ ! -x "$PYTHON_SCRIPT" ]; then
-    echo "[INFO] Adding execute permission to Python script..."
-    chmod +x "$PYTHON_SCRIPT" 2>/dev/null || true
-  fi
-
-  # 运行Python脚本（后台运行）
-  echo "[INFO] Starting configuration generator script..."
-  python3 "$PYTHON_SCRIPT" &
-  CONFIG_GEN_PID=$!
-  echo "[INFO] Configuration generator started with PID: $CONFIG_GEN_PID"
-else
-  echo "[WARN] Python configuration generator script not found"
-fi
-
-# 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} 2>/dev/null; then
-    exec 3<&- 3>&-
-    echo "[INFO] Elasticsearch is ready"
-    break
-  fi
-  [[ $i -eq 120 ]] && { echo "[ERROR] ES not reachable" >&2; exit 1; }
-  sleep 1
+# 等待 Elasticsearch 就绪
+echo "[INFO] Waiting for Elasticsearch to be ready..."
+while ! curl -fs http://${ES_HOST}:${ES_PORT}/_cluster/health >/dev/null 2>&1; do
+    echo "  Waiting for ES at ${ES_HOST}:${ES_PORT}..."
+    sleep 5
 done
+echo "[INFO] Elasticsearch is ready"
 
-echo "[INFO] Command: starting python task..."
-# 启动配置生成器
-#exec nohup python3 /etc/fluent-bit/app/update_fluent_config.py &
-
+# 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/kibana/build/kibana-post-start.sh

@@ -2,7 +2,7 @@
 set -euo pipefail
 
 ES_HOST="${ELASTICSEARCH_HOSTS:-http://es:9200}"
-KB_HOST="${KB_HOST:-http://127.0.0.1:5601}"
+KB_HOST="http://localhost:5601"
 
 echo "[INFO] Starting Kibana post-start configuration..."
 
@@ -83,37 +83,50 @@ fix_replicas_idempotent() {
 }
 
 # 幂等创建数据视图
-create_or_ensure_data_view() {
-    local name="$1"
-    local title="$2"
-
-    local list_response
-    list_response=$(curl -fsS "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null || echo "")
-
-    if [ -z "$list_response" ]; then
-        echo "[WARN] Failed to list data views, skipping creation check for $title"
-        return
-    fi
-
-    if echo "$list_response" | grep -Fq "\"title\":\"$title\""; then
-        echo "[INFO] Data view $title already exists, skipping"
-        return
-    fi
-
-    echo "[INFO] Creating data view for $title indices (allowNoIndex)"
-
-    curl -fsS -X POST "$KB_HOST/api/data_views/data_view?allowNoIndex=true" \
-        -H 'kbn-xsrf: true' \
-        -H 'Content-Type: application/json' \
-        -d "{\"data_view\":{\"name\":\"$name\",\"title\":\"$title\",\"timeFieldName\":\"@timestamp\",\"allowNoIndex\":true}}" \
-        >/dev/null && echo "[OK] Created $name data view" || echo "[WARN] Failed to create $name data view"
-}
-
 create_data_views_idempotent() {
     echo "[INFO] Checking and creating data views..."
 
-    create_or_ensure_data_view "train" "train-*"
-    create_or_ensure_data_view "infer" "infer-*"
+    # 检查是否存在匹配的索引
+    local train_indices=$(curl -s "$ES_HOST/_cat/indices/train-*?h=index" 2>/dev/null | wc -l || echo "0")
+    local infer_indices=$(curl -s "$ES_HOST/_cat/indices/infer-*?h=index" 2>/dev/null | wc -l || echo "0")
+
+    # 创建 train 数据视图
+    if [ "$train_indices" -gt 0 ]; then
+        # 检查数据视图是否已存在
+        local train_exists=$(curl -s "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null | grep '"title":"train-\*"' | wc -l )
+
+        if [ "$train_exists" -eq 0 ]; then
+            echo "[INFO] Creating data view for train-* indices"
+            curl -fsS -X POST "$KB_HOST/api/data_views/data_view" \
+                -H 'kbn-xsrf: true' \
+                -H 'Content-Type: application/json' \
+                -d '{"data_view":{"name":"train","title":"train-*","timeFieldName":"@timestamp"}}' \
+                >/dev/null && echo "[OK] Created train data view" || echo "[WARN] Failed to create train data view"
+        else
+            echo "[INFO] Train data view already exists, skipping"
+        fi
+    else
+        echo "[INFO] No train-* indices found, skipping train data view creation"
+    fi
+
+    # 创建 infer 数据视图
+    if [ "$infer_indices" -gt 0 ]; then
+        # 检查数据视图是否已存在
+        local infer_exists=$(curl -s "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null | grep '"title":"infer-\*"' | wc -l )
+
+        if [ "$infer_exists" -eq 0 ]; then
+            echo "[INFO] Creating data view for infer-* indices"
+            curl -fsS -X POST "$KB_HOST/api/data_views/data_view" \
+                -H 'kbn-xsrf: true' \
+                -H 'Content-Type: application/json' \
+                -d '{"data_view":{"name":"infer","title":"infer-*","timeFieldName":"@timestamp"}}' \
+                >/dev/null && echo "[OK] Created infer data view" || echo "[WARN] Failed to create infer data view"
+        else
+            echo "[INFO] Infer data view already exists, skipping"
+        fi
+    else
+        echo "[INFO] No infer-* indices found, skipping infer data view creation"
+    fi
 }
 
 # 主逻辑

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

@@ -32,42 +32,3 @@ 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/log/tests/scripts/03_send_test_host01.sh

@@ -28,11 +28,11 @@ fi
 docker exec "$container_name" mkdir -p /logs/train /logs/infer
 
 # 写入训练日志 (host01)
-docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=1 loss=1.23 model=bert\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/train/train-demo.log"
-docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=2 loss=1.15 model=bert\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=1 loss=1.23 model=bert\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=2 loss=1.15 model=bert\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
 
 # 写入推理日志 (host01)
-docker exec "$container_name" sh -c "printf '%s ERROR [host01] inference failed on batch=1\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/infer/infer-demo.log"
+docker exec "$container_name" sh -c "printf '%s ERROR [host01] inference failed on batch=1\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
 docker exec "$container_name" sh -c "cat <<'STACK' >> /logs/infer/infer-demo.log
 Traceback (most recent call last):
   File \"inference.py\", line 15, in <module>

src/log/tests/scripts/03_send_test_host02.sh

@@ -28,13 +28,13 @@ fi
 docker exec "$container_name" mkdir -p /logs/train /logs/infer
 
 # 写入训练日志 (host02)
-docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=1 loss=1.45 model=gpt\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/train/train-demo.log"
-docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=2 loss=1.38 model=gpt\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/train/train-demo.log"
-docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=3 loss=1.32 model=gpt\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=1 loss=1.45 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=2 loss=1.38 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=3 loss=1.32 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
 
 # 写入推理日志 (host02)  
-docker exec "$container_name" sh -c "printf '%s WARN [host02] inference slow on batch=5 latency=2.3s\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/infer/infer-demo.log"
-docker exec "$container_name" sh -c "printf '%s INFO [host02] inference completed batch=6 latency=0.8s\n' \"\$(date -u +%Y-%m-%dT%H:%M:%SZ)\" >> /logs/infer/infer-demo.log"
+docker exec "$container_name" sh -c "printf '%s WARN [host02] inference slow on batch=5 latency=2.3s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] inference completed batch=6 latency=0.8s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
 
 echo "[OK] 已通过docker exec写入测试日志到 host02 容器内："
 echo " - /logs/train/train-demo.log"

src/log/tests/scripts/e2e_test.sh

@@ -115,32 +115,20 @@ show_step "Health" "Check service health"
 echo "[INFO] Checking service health..."
 
 # 检查 Elasticsearch 健康状态
-health_check_ok=1
 es_health=$(curl -s "http://localhost:9200/_cluster/health" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
 if [ "$es_health" = "green" ] || [ "$es_health" = "yellow" ]; then
     echo "✅ Elasticsearch health: $es_health"
 else
     echo "❌ Elasticsearch health: $es_health"
-    health_check_ok=0
 fi
 
 # 检查 Kibana 状态
 if curl -fs "http://localhost:5601/api/status" >/dev/null 2>&1; then
     kb_status="available"
     echo "✅ Kibana status: $kb_status"
-
-    data_views_json=$(curl -fs "http://localhost:5601/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null || true)
-    if echo "$data_views_json" | grep -F '"title":"train-*"' >/dev/null 2>&1 && \
-       echo "$data_views_json" | grep -F '"title":"infer-*"' >/dev/null 2>&1; then
-        echo "✅ Kibana data views: train-* and infer-* present"
-    else
-        echo "❌ Kibana data views missing: train-* or infer-*"
-        health_check_ok=0
-    fi
 else
     kb_status="unavailable"
     echo "⚠️  Kibana status: $kb_status"
-    health_check_ok=0
 fi
 
 # 检查 Fluent-Bit 指标
@@ -151,13 +139,6 @@ if [ "$fb_host01_uptime" -gt 0 ] && [ "$fb_host02_uptime" -gt 0 ]; then
     echo "✅ Fluent-Bit services: host01 uptime=${fb_host01_uptime}s, host02 uptime=${fb_host02_uptime}s"
 else
     echo "⚠️  Fluent-Bit services: host01 uptime=${fb_host01_uptime}s, host02 uptime=${fb_host02_uptime}s"
-    health_check_ok=0
-fi
-
-if [ "$health_check_ok" -eq 1 ]; then
-    true
-else
-    false
 fi
 
 verify_step "Service health check"

src/master/app/config.py

@@ -13,8 +13,6 @@ class AppConfig:
     scheduler_interval_seconds: int
     node_id_prefix: str
     auth_mode: str
-    target_prefer_net_cidrs: str
-    target_reachability_check: bool
 
 
 def _get_int_env(name: str, default: int) -> int:
@@ -29,12 +27,6 @@ def _get_int_env(name: str, default: int) -> int:
 
 def load_config() -> AppConfig:
     """读取环境变量生成配置对象，方便统一管理运行参数。"""
-    def _bool_env(name: str, default: bool) -> bool:
-        raw = os.environ.get(name)
-        if raw is None or raw.strip() == "":
-            return default
-        return raw.strip().lower() in ("1", "true", "yes", "on")
-
     return AppConfig(
         db_path=os.environ.get("DB_PATH", "/private/argus/master/db.sqlite3"),
         metric_nodes_json_path=os.environ.get(
@@ -45,6 +37,4 @@ def load_config() -> AppConfig:
         scheduler_interval_seconds=_get_int_env("SCHEDULER_INTERVAL_SECONDS", 30),
         node_id_prefix=os.environ.get("NODE_ID_PREFIX", "A"),
         auth_mode=os.environ.get("AUTH_MODE", "disabled"),
-        target_prefer_net_cidrs=os.environ.get("TARGET_PREFER_NET_CIDRS", "10.0.0.0/8,172.31.0.0/16"),
-        target_reachability_check=_bool_env("TARGET_REACHABILITY_CHECK", False),
     )

src/master/app/scheduler.py

@@ -1,10 +1,8 @@
 from __future__ import annotations
 
-import ipaddress
 import logging
-import socket
 import threading
-from typing import Optional, Iterable, Dict, Any, List
+from typing import Optional
 
 from .config import AppConfig
 from .storage import Storage
@@ -36,117 +34,10 @@ class StatusScheduler:
         self._pending_nodes_json.set()
 
     def generate_nodes_json(self) -> None:
-        """根据在线节点生成 Prometheus 抓取目标，优先 overlay IP。
-
-        候选顺序：meta.overlay_ip > hostname A 记录（命中偏好网段）> meta.ip。
-        可选 reachability 检查：TARGET_REACHABILITY_CHECK=true 时，对 9100/9400 做一次 1s TCP 连接测试，
-        选择首个可达的候选；全部失败则按顺序取第一个并记录日志。
-        """
         with self._nodes_json_lock:
-            rows = self._storage.get_online_nodes_meta()
-            prefer_cidrs = self._parse_cidrs(self._config.target_prefer_net_cidrs)
-            reachability = self._config.target_reachability_check
-
-            result: List[Dict[str, Any]] = []
-            for row in rows:
-                meta = row.get("meta", {})
-                hostname = meta.get("hostname") or row.get("name")
-                labels = row.get("labels") or []
-
-                overlay_ip = meta.get("overlay_ip")
-                legacy_ip = meta.get("ip")
-                host_candidates = self._resolve_host_ips(hostname)
-                host_pref = self._pick_by_cidrs(host_candidates, prefer_cidrs)
-
-                candidates: List[str] = []
-                for ip in [overlay_ip, host_pref, legacy_ip]:
-                    if ip and ip not in candidates:
-                        candidates.append(ip)
-
-                chosen = None
-                if reachability:
-                    ports = [9100]
-                    try:
-                        if int(meta.get("gpu_number", 0)) > 0:
-                            ports.append(9400)
-                    except Exception:
-                        pass
-                    for ip in candidates:
-                        if any(self._reachable(ip, p, 1.0) for p in ports):
-                            chosen = ip
-                            break
-                if not chosen:
-                    chosen = candidates[0] if candidates else legacy_ip
-                if not chosen:
-                    # ultimate fallback: 127.0.0.1 (should not happen)
-                    chosen = "127.0.0.1"
-                    self._logger.warning("No candidate IPs for node; falling back", extra={"node": row.get("node_id")})
-
-                if chosen and ipaddress.ip_address(chosen) in ipaddress.ip_network("172.22.0.0/16"):
-                    self._logger.warning(
-                        "Prometheus target uses docker_gwbridge address; prefer overlay",
-                        extra={"node": row.get("node_id"), "ip": chosen},
-                    )
-
-                result.append(
-                    {
-                        "node_id": row.get("node_id"),
-                        "user_id": meta.get("user"),
-                        "ip": chosen,
-                        "hostname": hostname,
-                        "labels": labels if isinstance(labels, list) else [],
-                    }
-                )
-
-            atomic_write_json(self._config.metric_nodes_json_path, result)
-            self._logger.info("nodes.json updated", extra={"count": len(result)})
-
-    # ---------------------------- helpers ----------------------------
-    @staticmethod
-    def _parse_cidrs(raw: str) -> List[ipaddress.IPv4Network]:
-        nets: List[ipaddress.IPv4Network] = []
-        for item in (x.strip() for x in (raw or "").split(",")):
-            if not item:
-                continue
-            try:
-                net = ipaddress.ip_network(item, strict=False)
-                if isinstance(net, ipaddress.IPv4Network):
-                    nets.append(net)
-            except ValueError:
-                continue
-        return nets
-
-    @staticmethod
-    def _resolve_host_ips(hostname: str) -> List[str]:
-        ips: List[str] = []
-        try:
-            infos = socket.getaddrinfo(hostname, None, family=socket.AF_INET)
-            for info in infos:
-                ip = info[4][0]
-                if ip not in ips:
-                    ips.append(ip)
-        except OSError:
-            pass
-        return ips
-
-    @staticmethod
-    def _pick_by_cidrs(candidates: Iterable[str], prefer: List[ipaddress.IPv4Network]) -> str | None:
-        for net in prefer:
-            for ip in candidates:
-                try:
-                    if ipaddress.ip_address(ip) in net:
-                        return ip
-                except ValueError:
-                    continue
-        return None
-
-    @staticmethod
-    def _reachable(ip: str, port: int, timeout: float) -> bool:
-        try:
-            with socket.create_connection((ip, port), timeout=timeout):
-                return True
-        except OSError:
-            return False
+            online_nodes = self._storage.get_online_nodes()
+            atomic_write_json(self._config.metric_nodes_json_path, online_nodes)
+            self._logger.info("nodes.json updated", extra={"count": len(online_nodes)})
 
     # ------------------------------------------------------------------
     # internal loop

src/master/app/storage.py

@@ -324,35 +324,9 @@ class Storage:
                 {
                     "node_id": row["id"],
                     "user_id": meta.get("user"),
-                    "ip": meta.get("ip"),  # kept for backward-compat; preferred IP selection handled in scheduler
+                    "ip": meta.get("ip"),
                     "hostname": meta.get("hostname", row["name"]),
                     "labels": labels if isinstance(labels, list) else [],
                 }
             )
         return result
-
-    def get_online_nodes_meta(self) -> List[Dict[str, Any]]:
-        """返回在线节点的原始 meta 与名称、标签，交由上层选择目标 IP。
-
-        每项包含：{ node_id, name, meta, labels }
-        """
-        with self._lock:
-            cur = self._conn.execute(
-                "SELECT id, name, meta_json, labels_json FROM nodes WHERE status = ? ORDER BY id ASC",
-                ("online",),
-            )
-            rows = cur.fetchall()
-
-        result: List[Dict[str, Any]] = []
-        for row in rows:
-            meta = json.loads(row["meta_json"]) if row["meta_json"] else {}
-            labels = json.loads(row["labels_json"]) if row["labels_json"] else []
-            result.append(
-                {
-                    "node_id": row["id"],
-                    "name": row["name"],
-                    "meta": meta if isinstance(meta, dict) else {},
-                    "labels": labels if isinstance(labels, list) else [],
-                }
-            )
-        return result

src/master/scripts/build_images.sh

@@ -3,13 +3,12 @@ set -euo pipefail
 
 usage() {
   cat >&2 <<'USAGE'
-Usage: $0 [--intranet] [--offline] [--tag <image_tag>] [--no-cache]
+Usage: $0 [--intranet] [--offline] [--tag <image_tag>]
 
 Options:
   --intranet           使用指定的 PyPI 镜像源（默认清华镜像）。
   --offline            完全离线构建，依赖 offline_wheels/ 目录中的离线依赖包。
   --tag <image_tag>    自定义镜像标签，默认 argus-master:latest。
-  --no-cache           不使用 Docker 构建缓存。
 USAGE
 }
 
@@ -20,7 +19,6 @@ IMAGE_TAG="${IMAGE_TAG:-argus-master:latest}"
 DOCKERFILE="src/master/Dockerfile"
 BUILD_ARGS=()
 OFFLINE_MODE=0
-NO_CACHE=0
 
 source "$PROJECT_ROOT/scripts/common/build_user.sh"
 load_build_user
@@ -47,11 +45,6 @@ while [[ "$#" -gt 0 ]]; do
       IMAGE_TAG="$2"
       shift 2
       ;;
-    --no-cache)
-      NO_CACHE=1
-      BUILD_ARGS+=("--no-cache")
-      shift
-      ;;
     -h|--help)
       usage
       exit 0

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/artifact/
+/client-plugins/all-in-one-full/

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

@@ -4,15 +4,6 @@
 
 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"

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

@@ -200,22 +200,22 @@ parse_version_info() {
         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"' "$VERSION_FILE_PATH" | grep -v '"artifact_list"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
+        # 解析 artifact_list
+        grep -A 100 '"artifact_list"' "$VERSION_FILE_PATH" | 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"' "$VERSION_FILE_PATH" | grep -v '"checksums"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
+        # 解析 checksums
+        grep -A 100 '"checksums"' "$VERSION_FILE_PATH" | 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"' "$VERSION_FILE_PATH" | grep -v '"install_order"' | grep -E '^\s*"[^"]+"' | while read line; do
+        # 解析 install_order
+        grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -E '^\s*"[^"]+"' | while read line; do
             component=$(echo "$line" | sed 's/.*"\([^"]*\)".*/\1/')
             echo "$component" >> "$TEMP_DIR/install_order.txt"
         done
@@ -317,152 +317,85 @@ create_install_dirs() {
     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: $VERSION_ID，尝试使用ubuntu22"
-            echo "ubuntu22"
-            ;;
-    esac
-}
-
 # 安装系统依赖包
 install_system_deps() {
     log_info "检查系统依赖包..."
-
+    
     local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
     local deps_dir="$script_dir/deps"
-
+    
     # 检查deps目录是否存在
     if [[ ! -d "$deps_dir" ]]; then
         log_info "deps 目录不存在，跳过系统依赖包安装"
         return 0
     fi
-
-    # 获取系统版本对应的依赖目录
-    local system_version=$(get_system_version)
-    local version_deps_dir="$deps_dir/$system_version"
     
-    log_info "检测到系统版本: $system_version"
-    
-    # 检查版本特定的依赖目录是否存在
-    if [[ ! -d "$version_deps_dir" ]]; then
-        log_warning "未找到 $system_version 版本的依赖目录: $version_deps_dir"
-        # 回退到旧的逻辑，检查根deps目录
-        local deps_count=$(find "$deps_dir" -name "*.tar.gz" | wc -l)
-        if [[ $deps_count -eq 0 ]]; then
-            log_info "deps 目录中没有 tar.gz 文件，跳过系统依赖包安装"
-            return 0
-        fi
-        version_deps_dir="$deps_dir"
-    else
-        # 检查版本目录中是否有tar.gz文件
-        local deps_count=$(find "$version_deps_dir" -name "*.tar.gz" | wc -l)
-        if [[ $deps_count -eq 0 ]]; then
-            log_info "$system_version 版本目录中没有 tar.gz 文件，跳过系统依赖包安装"
-            return 0
-        fi
+    # 检查是否有tar.gz文件
+    local deps_count=$(find "$deps_dir" -name "*.tar.gz" | wc -l)
+    if [[ $deps_count -eq 0 ]]; then
+        log_info "deps 目录中没有 tar.gz 文件，跳过系统依赖包安装"
+        return 0
     fi
-
-    log_info "找到 $system_version 版本的依赖包，开始安装..."
-
+    
+    log_info "找到 $deps_count 个系统依赖包，开始安装..."
+    
     # 创建临时目录用于解压依赖包
-    local deps_temp_dir="${TEMP_DIR:-/tmp}/deps"
+    local deps_temp_dir="$TEMP_DIR/deps"
     mkdir -p "$deps_temp_dir"
-
-    # 定义要检查的核心依赖
-    local CORE_DEPS=(jq cron curl)
-    local FAILED_DEPS=()
-
+    
     # 处理每个tar.gz文件
-    find "$version_deps_dir" -name "*.tar.gz" | while read tar_file; do
+    find "$deps_dir" -name "*.tar.gz" | while read tar_file; do
         local tar_basename=$(basename "$tar_file")
         local extract_name="${tar_basename%.tar.gz}"
-
+        
         log_info "处理依赖包: $tar_basename"
-
+        
         # 解压到临时目录
         local extract_dir="$deps_temp_dir/$extract_name"
         mkdir -p "$extract_dir"
-
+        
         if tar -xzf "$tar_file" -C "$extract_dir" 2>/dev/null; then
             log_success "  $tar_basename 解压完成"
         else
             log_error "  $tar_basename 解压失败"
             continue
         fi
-
+        
         # 进入解压目录，查找deb包
-        cd "$extract_dir" || continue
-        local deb_files=(*.deb)
-        if [[ ${#deb_files[@]} -gt 0 ]]; then
-            log_info "  找到 ${#deb_files[@]} 个 deb 包，开始安装..."
-
-            for deb in "${deb_files[@]}"; do
-                local pkg_name
-                pkg_name=$(dpkg-deb -f "$deb" Package 2>/dev/null)
-
-                # 如果已安装，则跳过
-                if dpkg -s "$pkg_name" &>/dev/null; then
-                    log_success "  $pkg_name 已安装，跳过"
-                    continue
-                fi
-
-                # 尝试安装
-                log_info "  安装 $pkg_name..."
-                if DEBIAN_FRONTEND=noninteractive dpkg -i "$deb" &>/dev/null; then
-                    log_success "  $pkg_name 安装成功"
+        cd "$extract_dir"
+        local deb_count=$(find . -name "*.deb" | wc -l)
+        
+        if [[ $deb_count -gt 0 ]]; then
+            log_info "  找到 $deb_count 个 deb 包，开始安装..."
+            
+            # 1. 先尝试安装所有deb包
+            log_info "  第1步：批量安装deb包..."
+            if dpkg -i *.deb 2>/dev/null; then
+                log_success "  所有deb包安装成功"
+            else
+                log_warning "  部分deb包安装失败，可能存在依赖问题"
+                
+                # 2. 使用apt-get修复依赖
+                log_info "  第2步：修复依赖关系..."
+                if apt-get install -f -y; then
+                    log_success "  依赖关系修复完成"
                 else
-                    log_warning "  $pkg_name 安装失败，尝试修复依赖..."
-                    if DEBIAN_FRONTEND=noninteractive apt-get install -f -y &>/dev/null; then
-                        if dpkg -s "$pkg_name" &>/dev/null; then
-                            log_success "  $pkg_name 修复安装成功"
-                        else
-                            log_error "  $pkg_name 仍未安装成功"
-                            FAILED_DEPS+=("$pkg_name")
-                        fi
-                    else
-                        log_error "  $pkg_name 自动修复失败"
-                        FAILED_DEPS+=("$pkg_name")
-                    fi
+                    log_error "  依赖关系修复失败"
+                    # 继续处理其他包，不退出
                 fi
-            done
+            fi
         else
             log_info "  $tar_basename 中没有找到deb包，跳过"
         fi
-
+        
         # 返回到依赖临时目录
-        cd "$deps_temp_dir" || continue
+        cd "$deps_temp_dir"
     done
-
+    
     # 检查并启动 cron 服务
     start_cron_service
-
-    # 总结安装结果
-    if [[ ${#FAILED_DEPS[@]} -gt 0 ]]; then
-        log_error "以下系统依赖未能成功安装，安装终止，请手动安装后重试："
-        for f in "${FAILED_DEPS[@]}"; do
-            echo "  - $f"
-        done
-        exit 1
-    else
-        log_success "系统依赖包安装完成，全部就绪"
-    fi
+    
+    log_success "系统依赖包安装完成"
 }
 
 # 启动 cron 服务
@@ -704,18 +637,6 @@ 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" "$temp_cron"; then
-        return 0  # 任务已存在
-    else
-        return 1  # 任务不存在
-    fi
-}
-
 # 设置健康检查定时任务
 setup_health_check_cron() {
     log_info "设置健康检查定时任务..."
@@ -740,7 +661,7 @@ setup_health_check_cron() {
     crontab -l 2>/dev/null > "$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" "$temp_cron"; then
+    if grep -q "check_health.sh" "$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"
@@ -795,7 +716,7 @@ setup_dns_sync_cron() {
     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" "$temp_cron"; then
+    if grep -q "sync_dns.sh" "$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"
@@ -803,15 +724,16 @@ setup_dns_sync_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）
+    # 添加新的定时任务（每30秒执行一次）
     # 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"
+    echo "* * * * * sleep 30; $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 "  执行频率: 每30秒"
         log_info "  日志文件: $INSTALL_DIR/.dns_sync.log"
         log_info "  查看定时任务: crontab -l"
         log_info "  删除定时任务: crontab -e"
@@ -849,7 +771,7 @@ setup_version_check_cron() {
     crontab -l > "$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" "$temp_cron"; then
+    if grep -q "check_version.sh" "$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"
@@ -902,7 +824,7 @@ setup_restart_cron() {
     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" "$temp_cron"; then
+    if grep -q "restart_unhealthy.sh" "$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"
@@ -963,9 +885,9 @@ main() {
     check_system
     find_version_file
     create_install_dirs
-    install_system_deps     
-    parse_version_info    
+    parse_version_info
     verify_checksums
+    install_system_deps
     install_components
     copy_config_files
     create_install_record
@@ -973,20 +895,6 @@ main() {
     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
 }
 

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

@@ -29,68 +29,26 @@ log_error() {
 show_help() {
     echo "Argus-Metric Artifact 发布脚本"
     echo
-    echo "用法: $0 <版本号> [选项]"
+    echo "用法: $0 <版本号>"
     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 "  <版本号>    要发布的版本号，对应 artifact 目录中的版本"
     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 "  $0 1.20.0    # 发布 1.20.0 版本"
     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
+# 检查参数
+if [[ $# -ne 1 ]]; then
     log_error "请提供版本号参数"
     show_help
     exit 1
 fi
 
+VERSION="$1"
 ARTIFACT_DIR="artifact/$VERSION"
+PUBLISH_DIR="/Users/sundapeng/Project/nlp/aiops/client-plugins/all-in-one/publish/"
 
 # 检查版本目录是否存在
 if [[ ! -d "$ARTIFACT_DIR" ]]; then
@@ -99,32 +57,11 @@ if [[ ! -d "$ARTIFACT_DIR" ]]; then
 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"
 
-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 "$TEMP_PACKAGE_DIR"
@@ -230,28 +167,17 @@ cd "$TEMP_PACKAGE_DIR"
 tar -czf "$PUBLISH_DIR/$TAR_NAME" *
 cd - > /dev/null
 
-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 "$VERSION" > "$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: $PUBLISH_DIR/dns.conf"
 else
     log_warning "未找到 config/dns.conf 文件，跳过 DNS 配置文件复制"
@@ -261,9 +187,6 @@ fi
 if [[ -f "scripts/setup.sh" ]]; then
     log_info "复制 setup.sh 到发布目录..."
     cp "scripts/setup.sh" "$PUBLISH_DIR/"
-    if [[ "$NEED_CHOWN" == true ]]; then
-        chown "$OWNER" "$PUBLISH_DIR/setup.sh"
-    fi
 fi
 
 # 显示发布结果

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

@@ -2,15 +2,6 @@
 
 # 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"

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

@@ -1,143 +1,244 @@
 #!/bin/bash
+
+# DNS 同步脚本
+# 比较 FTP 根目录的 dns.conf 和本地的 dns.conf，如果有变化则同步到 /etc/resolv.conf
+
 set -e
 
-# 颜色
-RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; BLUE='\033[0;34m'; NC='\033[0m'
+# 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} $1" >&2; }
-log_success() { echo -e "${GREEN}[SUCCESS]${NC} $1" >&2; }
-log_warning() { echo -e "${YELLOW}[WARNING]${NC} $1" >&2; }
-log_error() { echo -e "${RED}[ERROR]${NC} $1" >&2; }
+# 日志函数 - 输出到 stderr 避免影响函数返回值
+log_info() {
+    echo -e "${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)"
 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=""
+RESOLV_CONF="/etc/resolv.conf"
+LOG_FILE="/opt/argus-metric/.dns_sync.log"
 
-# 获取 FTP 配置
+# 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 "$FTP_PASSWORD" ]]; then
-        [[ -f "$SCRIPT_DIR/config.env" ]] && source "$SCRIPT_DIR/config.env"
+        local config_file="$SCRIPT_DIR/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="${FTP_PASSWORD:-ZGClab1234!}"
+    
+    # 构建远程 DNS 配置文件 URL
     REMOTE_DNS_CONF_URL="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/dns.conf"
+    
+    log_info "FTP 配置来源: ${FTP_CONFIG_SOURCE:-环境变量/配置文件}"
 }
 
-# 下载远程 dns.conf
+# 下载远程 DNS 配置文件
 download_remote_dns_conf() {
-    local tmp="/tmp/dns.remote.$$"
+    local temp_file="/tmp/dns.conf.remote.$$"
+    
+    log_info "从 FTP 服务器下载 DNS 配置文件..."
+    log_info "远程地址: $REMOTE_DNS_CONF_URL"
+    log_info "FTP 服务器: $FTP_SERVER"
+    log_info "FTP 用户: $FTP_USER"
+    
+    # 先测试 FTP 连接
     log_info "测试 FTP 连接..."
-    if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null; 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: ${dns_ips[*]}"
+    if curl -u "${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 "无法写入 $target_file，可能被系统锁定"
+        log_error "无法连接到 FTP 服务器: $FTP_SERVER"
+        log_error "请检查:"
+        log_error "  1. FTP 服务器是否运行"
+        log_error "  2. 网络连接是否正常"
+        log_error "  3. 服务器地址是否正确"
+        return 1
+    fi
+    
+    # 测试 dns.conf 文件是否存在
+    log_info "检查远程 dns.conf 文件是否存在..."
+    if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/dns.conf" >/dev/null 2>&1; then
+        log_success "远程 dns.conf 文件存在"
+    else
+        log_error "远程 dns.conf 文件不存在或无法访问"
+        log_error "请检查 FTP 服务器根目录下是否有 dns.conf 文件"
+        return 1
+    fi
+    
+    # 尝试下载文件
+    log_info "开始下载 dns.conf 文件..."
+    if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sf "ftp://${FTP_SERVER}/dns.conf" -o "$temp_file" 2>/dev/null; then
+        log_success "远程 DNS 配置文件下载成功"
+        echo "$temp_file"
+    else
+        log_error "下载 dns.conf 文件失败"
+        log_error "尝试手动测试命令:"
+        log_error "  curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_SERVER}/dns.conf"
+        rm -f "$temp_file"
+        return 1
     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
+# 比较两个文件是否相同
+compare_files() {
+    local file1="$1"
+    local file2="$2"
+    
+    if [[ ! -f "$file1" || ! -f "$file2" ]]; then
+        return 1
+    fi
+    
+    # 使用 diff 比较文件内容
+    if diff -q "$file1" "$file2" >/dev/null 2>&1; then
+        return 0  # 文件相同
+    else
+        return 1  # 文件不同
+    fi
+}
 
-    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
+# 将 DNS 配置追加到 /etc/resolv.conf
+update_resolv_conf() {
+    local dns_conf_file="$1"
+    
+    log_info "更新 /etc/resolv.conf 文件..."
+    
+    # 备份原始文件
+    if [[ -f "$RESOLV_CONF" ]]; then
+        cp "$RESOLV_CONF" "${RESOLV_CONF}.backup.$(date +%Y%m%d_%H%M%S)"
+        log_info "已备份原始 resolv.conf 文件"
+    fi
+    
+    # 读取 DNS 配置文件并追加到 resolv.conf
+    while IFS= read -r line; do
+        # 跳过空行和注释行
+        [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+        
+        # 验证是否为有效的 IP 地址
+        if [[ "$line" =~ ^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$ ]]; then
+            # 检查是否已存在相同的 nameserver 行
+            if ! grep -q "nameserver $line" "$RESOLV_CONF" 2>/dev/null; then
+                echo "nameserver $line" >> "$RESOLV_CONF"
+                log_info "添加 DNS 服务器: $line"
+            else
+                log_info "DNS 服务器已存在，跳过: $line"
+            fi
+        else
+            log_warning "跳过无效的 DNS 地址: $line"
         fi
-    done
-    log_info "/etc/resolv.conf 已包含所有 DNS"
+    done < "$dns_conf_file"
+    
+    # 设置文件权限
+    chmod 644 "$RESOLV_CONF"
+    
+    log_success "/etc/resolv.conf 文件更新完成"
 }
 
-log_sync() { echo "[$(date '+%F %T')] $1" >>"$LOG_FILE"; }
+# 记录同步日志
+log_sync() {
+    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 DNS 同步检查..."
-    mkdir -p /opt/argus-metric
-
+    log_sync "DNS 同步检查开始"
+    
+    # 确保系统目录存在
+    mkdir -p "/opt/argus-metric"
+    
+    # 获取 FTP 配置
     get_ftp_config
-    local remote_file
-    if ! remote_file=$(download_remote_dns_conf); then
-        log_error "下载失败"; log_sync "同步失败"; exit 1
-    fi
-
+    
+    # 检查本地 DNS 配置文件是否存在
     if [[ ! -f "$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"
+        log_warning "本地 DNS 配置文件不存在: $LOCAL_DNS_CONF"
+        log_warning "将下载远程配置文件并更新系统 DNS 设置"
+        
+        # 下载远程配置文件
+        if remote_file=$(download_remote_dns_conf); then
+            # 复制到本地
             cp "$remote_file" "$LOCAL_DNS_CONF"
+            log_success "远程 DNS 配置文件已保存到本地"
+            
+            # 更新 resolv.conf
             update_resolv_conf "$LOCAL_DNS_CONF"
-            log_sync "DNS 配置同步完成"
+            log_sync "首次同步完成，DNS 配置已更新"
+            
+            # 清理临时文件
+            rm -f "$remote_file"
+        else
+            log_error "无法下载远程 DNS 配置文件，同步失败"
+            log_sync "同步失败：无法下载远程配置文件"
+            exit 1
+        fi
+    else
+        log_info "本地 DNS 配置文件存在: $LOCAL_DNS_CONF"
+        
+        # 下载远程配置文件进行比较
+        if remote_file=$(download_remote_dns_conf); then
+            # 比较文件
+            if compare_files "$LOCAL_DNS_CONF" "$remote_file"; then
+                log_info "DNS 配置文件无变化，无需更新"
+                log_sync "DNS 配置文件无变化"
+            else
+                log_info "检测到 DNS 配置文件有变化，开始同步..."
+                log_sync "检测到 DNS 配置文件变化，开始同步"
+                
+                # 更新本地配置文件
+                cp "$remote_file" "$LOCAL_DNS_CONF"
+                log_success "本地 DNS 配置文件已更新"
+                
+                # 更新 resolv.conf
+                update_resolv_conf "$LOCAL_DNS_CONF"
+                log_sync "DNS 配置同步完成"
+            fi
+            
+            # 清理临时文件
+            rm -f "$remote_file"
+        else
+            log_error "无法下载远程 DNS 配置文件，跳过本次同步"
+            log_sync "同步失败：无法下载远程配置文件"
+            exit 1
         fi
     fi
-
-    rm -f "$remote_file"
-    log_success "DNS 同步流程完成"
+    
+    log_success "DNS 同步检查完成"
+    log_sync "DNS 同步检查完成"
 }
 
+# 脚本入口
 if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
     main "$@"
 fi