build/build_images.sh

@@ -43,6 +43,7 @@ no_cache=false
 bundle_date=""
 client_semver=""
 cuda_ver="12.2.2"
+DEFAULT_IMAGE_TAG="latest"
 
 while [[ $# -gt 0 ]]; do
   case $1 in
@@ -126,6 +127,16 @@ 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}")
 
@@ -188,13 +199,31 @@ build_image() {
   echo "   Tag: $tag"
   echo "   Context: $context"
 
-  if docker build "${build_args[@]}" "${extra_args[@]}" -f "$dockerfile_path" -t "$tag" "$context"; then
+  local tries=${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
-  else
-    echo "❌ Failed to build $image_name image"
-    return 1
     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() {
@@ -390,8 +419,10 @@ build_gpu_bundle_image() {
       --build-arg CLIENT_VER="$use_version" \
       --build-arg BUNDLE_DATE="$date_tag"; then
     images_built+=("$image_tag")
-    # also tag latest for convenience
+    # In non-pkg mode, also tag latest for convenience
+    if [[ "${ARGUS_PKG_BUILD:-0}" != "1" ]]; then
       docker tag "$image_tag" argus-sys-metric-test-node-bundle-gpu:latest >/dev/null 2>&1 || true
+    fi
     return 0
   else
     return 1
@@ -427,10 +458,13 @@ build_server_pkg_bundle() {
     argus-metric-ftp argus-metric-prometheus argus-metric-grafana \
     argus-alertmanager argus-web-frontend argus-web-proxy
   )
-  echo "\n🔖 Tagging server images with :$date_tag and collecting digests"
+  echo "\n🔖 Verifying server images with :$date_tag and collecting digests"
-  if ! ensure_version_tags "$date_tag" "${repos[@]}"; then
+  for repo in "${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 "${repos[@]}"; do
     local digest
@@ -457,6 +491,8 @@ build_client_pkg_bundle() {
   local bundle_tag="argus-sys-metric-test-node-bundle-gpu:${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
@@ -472,24 +508,24 @@ build_client_pkg_bundle() {
 }
 
 if [[ "$build_core" == true ]]; then
-  if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:latest"; then
+  if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:${DEFAULT_IMAGE_TAG}"; then
-    images_built+=("argus-elasticsearch:latest")
+    images_built+=("argus-elasticsearch:${DEFAULT_IMAGE_TAG}")
   else
     build_failed=true
   fi
 
   echo ""
 
-  if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:latest"; then
+  if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:${DEFAULT_IMAGE_TAG}"; then
-    images_built+=("argus-kibana:latest")
+    images_built+=("argus-kibana:${DEFAULT_IMAGE_TAG}")
   else
     build_failed=true
   fi
 
   echo ""
 
-  if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:latest"; then
+  if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:${DEFAULT_IMAGE_TAG}"; then
-    images_built+=("argus-bind9:latest")
+    images_built+=("argus-bind9:${DEFAULT_IMAGE_TAG}")
   else
     build_failed=true
   fi
@@ -501,7 +537,7 @@ if [[ "$build_master" == true ]]; then
   echo ""
   echo "🔄 Building Master image..."
   pushd "$master_root" >/dev/null
-  master_args=("--tag" "argus-master:latest")
+  master_args=("--tag" "argus-master:${DEFAULT_IMAGE_TAG}")
   if [[ "$use_intranet" == true ]]; then
     master_args+=("--intranet")
   fi
@@ -515,7 +551,7 @@ if [[ "$build_master" == true ]]; then
     if [[ "$build_master_offline" == true ]]; then
       images_built+=("argus-master:offline")
     else
-      images_built+=("argus-master:latest")
+      images_built+=("argus-master:${DEFAULT_IMAGE_TAG}")
     fi
   else
     build_failed=true
@@ -540,9 +576,9 @@ if [[ "$build_metric" == true ]]; then
   done
 
   metric_builds=(
-    "Metric FTP|src/metric/ftp/build/Dockerfile|argus-metric-ftp:latest|src/metric/ftp/build"
+    "Metric FTP|src/metric/ftp/build/Dockerfile|argus-metric-ftp:${DEFAULT_IMAGE_TAG}|src/metric/ftp/build"
-    "Metric Prometheus|src/metric/prometheus/build/Dockerfile|argus-metric-prometheus:latest|src/metric/prometheus/build"
+    "Metric Prometheus|src/metric/prometheus/build/Dockerfile|argus-metric-prometheus:${DEFAULT_IMAGE_TAG}|src/metric/prometheus/build"
-    "Metric Grafana|src/metric/grafana/build/Dockerfile|argus-metric-grafana:latest|src/metric/grafana/build"
+    "Metric Grafana|src/metric/grafana/build/Dockerfile|argus-metric-grafana:${DEFAULT_IMAGE_TAG}|src/metric/grafana/build"
   )
 
   for build_spec in "${metric_builds[@]}"; do
@@ -614,8 +650,8 @@ if [[ "$build_web" == true || "$build_alert" == true ]]; then
 
   if [[ "$build_web" == true ]]; then
     web_builds=(
-      "Web Frontend|src/web/build_tools/frontend/Dockerfile|argus-web-frontend:latest|."
+      "Web Frontend|src/web/build_tools/frontend/Dockerfile|argus-web-frontend:${DEFAULT_IMAGE_TAG}|."
-      "Web Proxy|src/web/build_tools/proxy/Dockerfile|argus-web-proxy:latest|."
+      "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 <<< "$build_spec"
@@ -630,7 +666,7 @@ if [[ "$build_web" == true || "$build_alert" == true ]]; then
 
   if [[ "$build_alert" == true ]]; then
     alert_builds=(
-      "Alertmanager|src/alert/alertmanager/build/Dockerfile|argus-alertmanager:latest|."
+      "Alertmanager|src/alert/alertmanager/build/Dockerfile|argus-alertmanager:${DEFAULT_IMAGE_TAG}|."
     )
     for build_spec in "${alert_builds[@]}"; do
       IFS='|' read -r image_label dockerfile_path image_tag build_context <<< "$build_spec"

configs/build_user.pkg.conf

@@ -0,0 +1,6 @@
+# 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/.gitignore

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

deployment/build/README.md

@@ -1,16 +0,0 @@
-# Deployment Build Toolkit
-
-This folder provides scripts to produce offline server/client packages and publish the client package to FTP.
-
-Commands
-- build_server_package.sh [--version YYYYMMDD]
-- build_client_package.sh [--version YYYYMMDD]
-- publish_client.sh --version YYYYMMDD --server <host> --user ftpuser --password <pass> [--port 21]
-
-Outputs
-- deployment/artifact/server/<YYYYMMDD>/
-- deployment/artifact/client/<YYYYMMDD>/
-
-Notes
-- Server package contains docker images (single all-images.tar.gz), compose/, scripts/, docs/, private/ skeleton.
-- Client package reuses all-in-one-full artifact, repacked as argus-metric_<YYYYMMDD>.tar.gz (compatible with setup.sh).

deployment/build/build_client_package.sh

@@ -1,90 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-BUILD_DIR="$ROOT_DIR/deployment/build"
-ART_ROOT="$ROOT_DIR/deployment/artifact"
-
-. "$BUILD_DIR/common.sh"
-
-usage() { cat <<'EOF'
-Build Argus Client Offline Package
-
-Usage: build_client_package.sh [--version YYYYMMDD] [--out DIR]
-
-Produces: deployment/artifact/client/<YYYYMMDD>/argus-metric_<YYYYMMDD>.tar.gz
-EOF
-}
-
-VERSION="$(today_version)"
-OUT_DIR=""
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --version) VERSION="$2"; shift 2;;
-    --out) OUT_DIR="$2"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) err "unknown arg: $1"; usage; exit 1;;
-  esac
-done
-
-PKG_DIR="${OUT_DIR:-$ART_ROOT/client/$VERSION}"
-make_dir "$PKG_DIR"
-
-log "Packaging client from all-in-one-full artifact"
-PLUGIN_DIR="$ROOT_DIR/src/metric/client-plugins/all-in-one-full"
-require_cmd bash tar gzip
-
-(cd "$PLUGIN_DIR" && bash scripts/package_artifact.sh --force)
-
-# pick latest artifact dir
-ART_BASE="$PLUGIN_DIR/artifact"
-latest_dir=$(ls -1dt "$ART_BASE"/*/ 2>/dev/null | head -n1 || true)
-[[ -n "$latest_dir" ]] || { err "no client artifact found in $ART_BASE"; exit 1; }
-
-tmpdir=$(mktemp -d)
-trap 'rm -rf "$tmpdir"' EXIT
-# Filter-only copy: keep install_order files + scripts + deps + version.json
-mkdir -p "$tmpdir/src"
-cp -f "$latest_dir/version.json" "$tmpdir/src/version.json"
-if command -v jq >/dev/null 2>&1; then
-  mapfile -t files < <(jq -r '.install_order[]' "$latest_dir/version.json")
-else
-  files=( $(grep -E '"install_order"' -A10 "$latest_dir/version.json" | sed -n 's/\s*"\(.*\.tar\.gz\)".*/\1/p') )
-fi
-for f in "${files[@]}"; do
-  [[ -f "$latest_dir/$f" ]] && cp -f "$latest_dir/$f" "$tmpdir/src/$f"
-done
-for aux in install.sh uninstall.sh check_health.sh check_version.sh sync_dns.sh restart_unhealthy.sh config.env; do
-  [[ -f "$latest_dir/$aux" ]] && cp -f "$latest_dir/$aux" "$tmpdir/src/$aux";
-done
-if [[ -d "$latest_dir/deps" ]]; then
-  mkdir -p "$tmpdir/src/deps" && rsync -a "$latest_dir/deps/" "$tmpdir/src/deps/" >/dev/null 2>&1 || cp -r "$latest_dir/deps/." "$tmpdir/src/deps/";
-fi
-
-out_name="argus-metric_$(echo "$VERSION" | sed 's/\./_/g').tar.gz"
-
-(cd "$tmpdir/src" && tar -czf "$PKG_DIR/$out_name" .)
-
-log "Client package ready: $PKG_DIR/$out_name"
-echo "$VERSION" > "$PKG_DIR/LATEST_VERSION"
-
-# include publish helper and setup.sh for convenience (place first)
-PUBLISH_TPL="$BUILD_DIR/templates/client/publish.sh"
-if [[ -f "$PUBLISH_TPL" ]]; then
-  cp "$PUBLISH_TPL" "$PKG_DIR/publish.sh"
-fi
-
-# also place a copy of setup.sh alongside
-SETUP_SRC="$ROOT_DIR/src/metric/client-plugins/all-in-one-full/scripts/setup.sh"
-[[ -f "$SETUP_SRC" ]] && cp "$SETUP_SRC" "$PKG_DIR/setup.sh" || true
-
-# docs for end users (this may overwrite file modes), then fix execute bits
-CLIENT_DOC_DIR="$BUILD_DIR/templates/client"
-if [[ -d "$CLIENT_DOC_DIR" ]]; then
-  rsync -a "$CLIENT_DOC_DIR/" "$PKG_DIR/" >/dev/null 2>&1 || cp -r "$CLIENT_DOC_DIR/." "$PKG_DIR/"
-fi
-
-# ensure helpers are executable
-chmod +x "$PKG_DIR/publish.sh" "$PKG_DIR/setup.sh" 2>/dev/null || true
-
-exit 0

deployment/build/build_cpu_node_image.sh

@@ -1,39 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-cd "$ROOT_DIR"
-
-usage() {
-  cat <<EOF
-Build CPU node-bundle image (wrapper)
-
-Usage: $(basename "$0") [--client-version YYYYMMDD]
-
-Examples:
-  $(basename "$0") --client-version 20251106
-  $(basename "$0")                # auto-detect artifact version via packaging
-EOF
-}
-
-VERSION=""
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --client-version) VERSION="${2:-}"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) echo "Unknown arg: $1" >&2; usage; exit 1;;
-  esac
-done
-
-CMD=("./deployment/build/build_images.sh" "--with-node-bundle")
-if [[ -n "$VERSION" ]]; then CMD+=("--client-version" "$VERSION"); fi
-
-echo "[CPU-BUNDLE] invoking: ${CMD[*]}"
-"${CMD[@]}"
-
-echo "[CPU-BUNDLE] built image: argus-sys-metric-test-node-bundle:latest"
-docker image inspect argus-sys-metric-test-node-bundle:latest >/dev/null 2>&1 || {
-  echo "[ERR] expected image not found" >&2; exit 1; }
-
-echo "[CPU-BUNDLE] done"
-

deployment/build/build_gpu_node_image.sh

@@ -1,49 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-cd "$ROOT_DIR"
-
-usage() {
-  cat <<EOF
-Build GPU node-bundle image (wrapper)
-
-Usage: $(basename "$0") [--client-version YYYYMMDD] [--tag IMAGE:TAG]
-
-Defaults:
-  base-image   = argus-sys-metric-test-gpu-node:latest
-  output tag   = argus-sys-metric-test-node-bundle-gpu:latest
-
-Examples:
-  $(basename "$0") --client-version 20251106
-  $(basename "$0") --client-version 20251106 --tag myrepo/node-bundle-gpu:20251106
-EOF
-}
-
-VERSION=""
-OUT_TAG="argus-sys-metric-test-node-bundle-gpu:latest"
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --client-version) VERSION="${2:-}"; shift 2;;
-    --tag) OUT_TAG="${2:-}"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) echo "Unknown arg: $1" >&2; usage; exit 1;;
-  esac
-done
-
-BASE_IMAGE="argus-sys-metric-test-gpu-node:latest"
-
-CMD=("./deployment/build/build_images.sh" "--with-node-bundle" "--base-image" "$BASE_IMAGE")
-if [[ -n "$VERSION" ]]; then CMD+=("--client-version" "$VERSION"); fi
-
-echo "[GPU-BUNDLE] invoking: ${CMD[*]}"
-"${CMD[@]}"
-
-echo "[GPU-BUNDLE] re-tagging to $OUT_TAG"
-docker image inspect argus-sys-metric-test-node-bundle:latest >/dev/null 2>&1 || {
-  echo "[ERR] base bundle image missing: argus-sys-metric-test-node-bundle:latest" >&2; exit 1; }
-docker tag argus-sys-metric-test-node-bundle:latest "$OUT_TAG"
-docker image inspect "$OUT_TAG" >/dev/null 2>&1 || { echo "[ERR] re-tag failed" >&2; exit 1; }
-
-echo "[GPU-BUNDLE] built image: $OUT_TAG (base=$BASE_IMAGE)"
-

deployment/build/build_images.sh

@@ -1,98 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-. "$ROOT_DIR/deployment/build/common.sh"
-
-usage() {
-cat <<EOF
-Build Argus images (optional node-bundle)
-
-Usage: build_images.sh [--with-node-bundle] [--client-version YYYYMMDD] [--base-image NAME[:TAG]]
-
-Examples:
-  ./deployment/build/build_images.sh --with-node-bundle --client-version 20251106
-EOF
-}
-
-WITH_BUNDLE=false
-CLIENT_VERSION=""
-BASE_IMAGE="argus-sys-metric-test-node:latest"
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --with-node-bundle) WITH_BUNDLE=true; shift;;
-    --client-version) CLIENT_VERSION="$2"; shift 2;;
-    --base-image) BASE_IMAGE="$2"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) err "unknown arg: $1"; usage; exit 1;;
-  esac
-done
-
-if [[ "$WITH_BUNDLE" == true ]]; then
-  require_cmd docker tar gzip
-  BUNDLE_DIR="$ROOT_DIR/src/sys/build/node-bundle"
-  CTX_DIR="$BUNDLE_DIR"
-  TMP_BUNDLE="$BUNDLE_DIR/bundle"
-  rm -rf "$TMP_BUNDLE"; mkdir -p "$TMP_BUNDLE"
-
-  # Build or locate client artifact
-  PLUGIN_DIR="$ROOT_DIR/src/metric/client-plugins/all-in-one-full"
-  # CLIENT_VERSION 支持两种形式：
-  #  - 形如 1.42.0 的 artifact 版本（默认）
-  #  - 形如 YYYYMMDD 的打包日期，将从 deployment/artifact/client/ 下解析出内部 artifact 版本
-  if [[ -z "$CLIENT_VERSION" ]]; then
-    pushd "$PLUGIN_DIR" >/dev/null
-    bash scripts/package_artifact.sh --force
-    CLIENT_VERSION=$(cat artifact/*/version.json 2>/dev/null | sed -n 's/.*"version"\s*:\s*"\([^"]\+\)".*/\1/p' | tail -n1)
-    popd >/dev/null
-    [[ -n "$CLIENT_VERSION" ]] || { err "failed to detect client version"; exit 1; }
-  else
-    if [[ "$CLIENT_VERSION" =~ ^[0-9]{8}$ ]]; then
-      PKG_DIR="$ROOT_DIR/deployment/artifact/client/$CLIENT_VERSION"
-      TAR_PKG="$PKG_DIR/argus-metric_${CLIENT_VERSION}.tar.gz"
-      [[ -f "$TAR_PKG" ]] || { err "client date package not found: $TAR_PKG"; exit 1; }
-      # 解包读取内部 version.json
-      tmpd=$(mktemp -d); trap 'rm -rf "$tmpd"' EXIT
-      tar -xzf "$TAR_PKG" -C "$tmpd"
-      if [[ -f "$tmpd/version.json" ]]; then
-        ART_VER=$(sed -n 's/.*"version"\s*:\s*"\([^"]\+\)".*/\1/p' "$tmpd/version.json" | head -n1)
-        [[ -n "$ART_VER" ]] || { err "failed to parse artifact version from date package"; exit 1; }
-        CLIENT_VERSION="$ART_VER"
-        # 直接使用该 tar 作为 bundle 源
-        cp "$TAR_PKG" "$TMP_BUNDLE/argus-metric_$(echo "$ART_VER" | tr '.' '_').tar.gz"
-        # 同时尝试复制 setup.sh（若存在）
-        [[ -f "$PKG_DIR/setup.sh" ]] && cp "$PKG_DIR/setup.sh" "$TMP_BUNDLE/" || true
-      else
-        err "version.json missing in client date package"
-        exit 1
-      fi
-    else
-      # 假定为 artifact 版本目录
-      pushd "$PLUGIN_DIR" >/dev/null
-      [[ -d "artifact/$CLIENT_VERSION" ]] || bash scripts/package_artifact.sh --force
-      popd >/dev/null
-    fi
-  fi
-
-  # 若未通过日期包预置 tar，则从插件 artifact 目录取
-  TAR_NAME="argus-metric_$(echo "$CLIENT_VERSION" | tr '.' '_').tar.gz"
-  if [[ ! -f "$TMP_BUNDLE/$TAR_NAME" ]]; then
-    SRC_TAR="$PLUGIN_DIR/artifact/$CLIENT_VERSION/$TAR_NAME"
-    [[ -f "$SRC_TAR" ]] || { err "missing client tar: $SRC_TAR"; exit 1; }
-    cp "$SRC_TAR" "$TMP_BUNDLE/"
-    # also include setup.sh for fallback
-    if [[ -f "$ROOT_DIR/deployment/artifact/client/$(today_version)/setup.sh" ]]; then
-      cp "$ROOT_DIR/deployment/artifact/client/$(today_version)/setup.sh" "$TMP_BUNDLE/" || true
-    fi
-  fi
-
-  log "Building node-bundle image with client version: $CLIENT_VERSION"
-  DOCKER_BUILDKIT=0 docker build \
-    --build-arg CLIENT_VER="$CLIENT_VERSION" \
-    --build-arg BASE_IMAGE="$BASE_IMAGE" \
-    -t argus-sys-metric-test-node-bundle:latest \
-    -f "$BUNDLE_DIR/Dockerfile" "$BUNDLE_DIR"
-  log "Built image: argus-sys-metric-test-node-bundle:latest"
-fi
-
-log "Done."

deployment/build/build_server_package.sh

@@ -1,139 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-BUILD_DIR="$ROOT_DIR/deployment/build"
-ART_ROOT="$ROOT_DIR/deployment/artifact"
-
-. "$BUILD_DIR/common.sh"
-
-usage() { cat <<'EOF'
-Build Argus Server Offline Package
-
-Usage: build_server_package.sh [--version YYYYMMDD] [--out DIR] [--resave-image]
-
-Outputs into deployment/artifact/server/<YYYYMMDD>/ by default.
-EOF
-}
-
-VERSION="$(today_version)"
-OUT_DIR=""
-RESAVE_IMAGE=false
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --version) VERSION="$2"; shift 2;;
-    --out) OUT_DIR="$2"; shift 2;;
-    --resave-image) RESAVE_IMAGE=true; shift;;
-    -h|--help) usage; exit 0;;
-    *) err "unknown arg: $1"; usage; exit 1;;
-  esac
-done
-
-PKG_DIR="${OUT_DIR:-$ART_ROOT/server/$VERSION}"
-STAGE="$(mktemp -d)"
-trap 'rm -rf "$STAGE"' EXIT
-
-log "Version: $VERSION"
-log "Staging: $STAGE"
-
-# 1) Layout
-make_dir "$STAGE/images"
-make_dir "$STAGE/compose"
-make_dir "$STAGE/scripts"
-make_dir "$STAGE/docs"
-make_dir "$STAGE/private/argus"
-
-# 2) Compose: derive from sys/tests by removing test-only services
-SRC_COMPOSE="$ROOT_DIR/src/sys/tests/docker-compose.yml"
-[[ -f "$SRC_COMPOSE" ]] || { err "missing $SRC_COMPOSE"; exit 1; }
-# 2.1 filter out test services
-tmp_compose1="$STAGE/compose/docker-compose.filtered.yml"
-awk -f "$BUILD_DIR/templates/docker-compose.filter.awk" -v remove="node-a,node-b,test-node,test-gpu-node" "$SRC_COMPOSE" > "$tmp_compose1"
-# 2.2 transform to external overlay network (remove sysnet and per-service blocks)
-awk -f "$BUILD_DIR/templates/docker-compose.overlay.awk" "$tmp_compose1" > "$STAGE/compose/docker-compose.yml"
-cp "$BUILD_DIR/templates/.env.example" "$STAGE/compose/.env.example"
-# fix relative private path to match package layout (compose/ and private/ are siblings)
-sed -i 's#\./private/#../private/#g' "$STAGE/compose/docker-compose.yml"
-# also handle bind mount form without trailing slash
-sed -i -E 's#- \./private:/private#- ../private:/private#g' "$STAGE/compose/docker-compose.yml"
-# drop timezone file bind which may not exist on target distros (e.g. NixOS)
-sed -i '/\/etc\/timezone:\/etc\/timezone:ro/d' "$STAGE/compose/docker-compose.yml"
-
-# sanity-check: ensure test services are absent and external network present
-if grep -E '^(\s{2})(node-a|node-b|test-node|test-gpu-node):\s*$' -n "$STAGE/compose/docker-compose.yml" >/dev/null; then
-  err "compose filter failed: test services still present"; exit 1;
-fi
-if ! grep -q '^networks:' "$STAGE/compose/docker-compose.yml" || ! grep -q 'argus-sys-net:' "$STAGE/compose/docker-compose.yml"; then
-  err "compose overlay transform failed: external network missing"; exit 1;
-fi
-
-# 3) Images (reuse if already exported unless --resave-image)
-existing_images_tar="$PKG_DIR/images/all-images.tar.gz"
-if [[ "$RESAVE_IMAGE" == false && -f "$existing_images_tar" ]]; then
-  log "Reusing existing images tar: $existing_images_tar"
-  cp "$existing_images_tar" "$STAGE/images/"
-elif [[ "$RESAVE_IMAGE" == false ]]; then
-  # Try cross-version reuse from latest server_*.tar.gz
-  latest_pkg=$(ls -1t "$ART_ROOT/server"/server_*.tar.gz 2>/dev/null | head -n1 || true)
-  if [[ -n "$latest_pkg" ]]; then
-    log "Reusing images from: $latest_pkg"
-    mkdir -p "$STAGE/images"
-    # extract matching file regardless of top-level dir
-    if tar -xzf "$latest_pkg" -C "$STAGE" --wildcards '*/images/all-images.tar.gz' 2>/dev/null; then
-      # locate and move
-      found=$(find "$STAGE" -type f -path '*/images/all-images.tar.gz' | head -n1 || true)
-      if [[ -n "$found" ]]; then
-        mv "$found" "$STAGE/images/all-images.tar.gz"
-        # cleanup leftover extracted dir
-        dir_to_clean=$(dirname "$found")
-        rm -rf "${dir_to_clean%/images}" 2>/dev/null || true
-      fi
-    fi
-  fi
-fi
-
-# If still not present, save from local docker daemon
-if [[ ! -f "$STAGE/images/all-images.tar.gz" ]]; then
-  require_cmd docker gzip
-  images=(
-    argus-bind9:latest
-    argus-master:latest
-    argus-elasticsearch:latest
-    argus-kibana:latest
-    argus-metric-ftp:latest
-    argus-metric-prometheus:latest
-    argus-metric-grafana:latest
-    argus-alertmanager:latest
-    argus-web-frontend:latest
-    argus-web-proxy:latest
-  )
-  log "Saving images: ${#images[@]}"
-  tarfile="$STAGE/images/all-images.tar"
-  docker save -o "$tarfile" "${images[@]}"
-  gzip -f "$tarfile"
-fi
-
-# 4) Scripts & Docs
-copy_tree "$BUILD_DIR/templates/scripts" "$STAGE/scripts"
-copy_tree "$BUILD_DIR/templates/docs" "$STAGE/docs"
-find "$STAGE/scripts" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
-
-# 5) Manifests
-gen_manifest "$STAGE" "$STAGE/manifest.txt"
-checksum_dir "$STAGE" "$STAGE/checksums.txt"
-
-# 6) Move to artifact
-make_dir "$PKG_DIR"
-rsync -a "$STAGE/" "$PKG_DIR/" 2>/dev/null || cp -r "$STAGE/." "$PKG_DIR/"
-log "Server package ready: $PKG_DIR"
-
-echo "$VERSION" > "$PKG_DIR/version.json"
-
-# 7) Create distributable tarball
-OUT_TAR_DIR="$(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 "Tarball ready: $OUT_TAR"
-
-exit 0

deployment/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 $*" >&2; }
-
-require_cmd() {
-  for c in "$@"; do
-    command -v "$c" >/dev/null 2>&1 || { err "missing command: $c"; exit 1; }
-  done
-}
-
-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 "$root" && find . -maxdepth 3 -type f -printf "%p\n" | sort) >> "$out"
-}
-

deployment/build/templates/.env.example

@@ -1,32 +0,0 @@
-# UID/GID for service processes
-ARGUS_BUILD_UID=1000
-ARGUS_BUILD_GID=1000
-
-# Host ports (adjust if occupied)
-MASTER_PORT=32300
-ES_HTTP_PORT=9200
-KIBANA_PORT=5601
-NODE_A_PORT=2020
-NODE_B_PORT=2021
-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
-
-# FTP
-FTP_PORT=21
-FTP_DATA_PORT=20
-FTP_PASSIVE_HOST_RANGE=21100-21110
-FTP_PASSWORD=ZGClab1234!
-FTP_DOMAIN=ftp.metric.argus.com
-
-# GPU profile disabled by default
-ENABLE_GPU=false
-
-# External overlay network (Swarm attachable)
-OVERLAY_NET_NAME=argus-sys-net

deployment/build/templates/client/INSTALL_CLIENT_zh.md

@@ -1,44 +0,0 @@
-# Argus Metric 客户端安装指南（容器内普通用户场景）
-
-## 准备与连通性检查
-- FTP 连接（需要账号密码，默认 `ftpuser / ZGClab1234!`）
-  - `curl -u ftpuser:ZGClab1234! -I ftp://<FTP_IP>:21/LATEST_VERSION`
-  - `curl -u ftpuser:ZGClab1234! -s ftp://<FTP_IP>:21/ | head`
-- 下载安装脚本
-  - `curl -u ftpuser:ZGClab1234! -fsSL ftp://<FTP_IP>:21/setup.sh -o /tmp/setup.sh`
-  - `chmod +x /tmp/setup.sh`
-
-## 元数据与主机名
-- Agent 需要元数据（env/user/instance）与 Master 地址：
-  - 方式A：hostname 形如 `env-user-instance-xxx`（推荐）
-  - 方式B：导出环境变量：
-    - `export AGENT_ENV=dev`
-    - `export AGENT_USER=<your_user>`
-    - `export AGENT_INSTANCE=<node_id>`
-- Master 地址：
-  - `export MASTER_ENDPOINT=http://master.argus.com:3000`
-
-> 安装脚本会在开头检查上述条件，缺失时会终止并给出修复提示。
-
-## 执行安装
-- 以 root 运行（容器内如为非 root 用户请切换为 root）：
-  - `sudo /tmp/setup.sh --server <FTP_IP> --user ftpuser --password 'ZGClab1234!' --port 21`
-- 如需自定义安装根目录：`--install-dir /opt/argus-metric`
-
-提示（容器接入 overlay 网络时）：
-- 在执行 setup 前，先将容器内 DNS 指向 Bind9 的 overlay IP：
-  - `echo "nameserver <BIND_OVERLAY_IP>" > /etc/resolv.conf`
-  - 这样 `master.argus.com`、`es.log.argus.com` 等域名即可解析；首次下载 `setup.sh` 仍建议使用 FTP 的 overlay IP。
-
-更多快速步骤请参考：`QUICK_NODE_DEPLOY_zh.md`。
-
-## 安装后自检（setup 自动执行）
-- setup 会等待最多 5 分钟，确认以下条件后才报告完成：
-  - `/private/argus/agent/<hostname>/node.json` 已生成；
-  - `last_report` 在持续更新；
-  - `health.metric-argus-agent|metric-node-exporter|metric-fluent-bit|metric-dcgm-exporter` 均为 `healthy` 且 `error` 为空。
-
-## 手工验证（可选）
-- `cat /private/argus/agent/$(hostname)/node.json | jq '.'`
-- `curl -s -o /dev/null -w "%{http_code}\n" http://localhost:9100/metrics` 应为 200
-- 查看日志：`/var/log/argus-agent.log`、`/opt/argus-metric/versions/*/.install.log`

deployment/build/templates/client/PUBLISH_CLIENT_zh.md

@@ -1,57 +0,0 @@
-# Argus Metric 客户端发布说明（FTP）
-
-本说明面向“发布人员”，讲清楚如何把客户端离线包发布到 FTP，供各节点通过 `curl` 自动安装。
-
-## 目录结构（构建后）
-- `client-YYYYMMDD/`
-  - `argus-metric_YYYYMMDD.tar.gz` 客户端离线包
-  - `setup.sh` 客户端安装入口脚本（提供给节点用 curl 下载）
-  - `publish.sh` 发布脚本（将上述两项与 `LATEST_VERSION` 上传到 FTP）
-  - `LATEST_VERSION` 文本（内容为 `YYYYMMDD`，或 `YYYYMMDD-rN`）
-  - `INSTALL_CLIENT_zh.md` 本地安装指南（给使用者看，不会上载到 FTP）
-  - `PUBLISH_CLIENT_zh.md` 本说明
-
-> 注意：`publish.sh`/`setup.sh` 为可执行脚本；构建脚本已保证二者具有执行权限。
-
-## 前置条件
-- FTP 服务已运行（默认容器：`argus-ftp`），并打开端口：21、20、21100–21110（被动模式）。
-- FTP 账号：默认 `ftpuser / ZGClab1234!`（如有更改，以实际为准）。
-
-## 发布步骤（在 server 机器或能直连 FTP 的任意机器上）
-1) 进入发布目录：
-- `cd client-YYYYMMDD`
-
-2) 执行发布：
-- `./publish.sh --server <FTP_HOST> --user <USER> --password '<PASS>' [--port 21]`
-- 例如在服务端本机：`./publish.sh --server localhost --user ftpuser --password 'ZGClab1234!' --port 21`
-
-脚本会上传三类文件到 FTP 根：
-- `setup.sh`
-- `argus-metric_YYYYMMDD[ -rN ].tar.gz`
-- `LATEST_VERSION`（内容为当前版本号）
-
-3) 发布后验证：
-- `curl -u ftpuser:****** -I ftp://<FTP_HOST>:21/LATEST_VERSION` 应返回 200
-- `curl -u ftpuser:****** -fsSL ftp://<FTP_HOST>:21/LATEST_VERSION` 内容为版本号（如 `20251104`）
-- `curl -u ftpuser:****** -I ftp://<FTP_HOST>:21/argus-metric_YYYYMMDD.tar.gz` 返回 200
-
-## 节点侧使用方式（摘要）
-- 首次下载用 FTP 的“IP 地址”：
-  - `curl -u ftpuser:****** -fsSL ftp://<FTP_IP>:21/setup.sh -o /tmp/setup.sh && chmod +x /tmp/setup.sh`
-- 执行安装：
-  - 必需元数据：`AGENT_ENV/AGENT_USER/AGENT_INSTANCE`，以及 `MASTER_ENDPOINT=http://master.argus.com:3000`
-  - `sudo /tmp/setup.sh --server <FTP_IP> --user ftpuser --password '******' --port 21`
-- overlay 容器场景：
-  - 先将容器内 DNS 指向 Bind9 的 overlay IP：`echo "nameserver <BIND_OVERLAY_IP>" > /etc/resolv.conf`
-  - 然后再执行上述安装；安装后约 1–2 分钟内 DNS 即可解析 `*.argus.com` 域名。
-
-## 常见问题
-- `530 Access denied`：用户名/密码错误或 FTP 目录无权限；请核对账号与 FTP 容器状态。
-- `Permission denied` 执行 `publish.sh`：为脚本权限问题；`chmod +x publish.sh`。构建脚本已修复默认权限。
-- 被动端口不通导致失败：请开放 21100–21110。
-- 客户端安装后短时 `curl http://master.argus.com:3000` 为 000：服务冷启动或 DNS 同步延迟，等待 1–2 分钟再试。
-
-## 版本与回滚
-- `LATEST_VERSION` 决定客户端默认安装的版本号。
-- 如需回滚：将旧版本号写回 `LATEST_VERSION` 并重新发布（或手动指定 `--version` 安装）。
-

deployment/build/templates/client/QUICK_NODE_DEPLOY_zh.md

@@ -1,58 +0,0 @@
-# Argus Metric 节点快速部署（Overlay 网络容器）
-
-本文档给出在 Docker Swarm external overlay 网络中，快速拉起一个测试节点并完成注册的最小可行步骤。
-
-## 前提
-- 服务端已在 Manager 机安装完成并运行良好（`server-selfcheck` 通过）。
-- Overlay 网络名称：`argus-sys-net`（默认）。
-- 已通过 FTP 发布 `setup.sh` 与客户端包，且能从 FTP 获取 `LATEST_VERSION`。
-- 用于测试的镜像：`argus-sys-metric-test-node:latest` 已存在于目标机器。
-
-## 步骤
-
-- 获取 FTP 和 Bind 的 overlay IP（在 Manager 上执行）
-  - `FTPIP=$(docker inspect -f '{{ (index .NetworkSettings.Networks "argus-sys-net").IPAddress }}' argus-ftp)`
-  - `BINDIP=$(docker inspect -f '{{ (index .NetworkSettings.Networks "argus-sys-net").IPAddress }}' argus-bind-sys)`
-  - `echo "FTP=$FTPIP BIND=$BINDIP"`
-
-- 准备宿主挂载目录（以 s4 为例）
-  - `mkdir -p /home2/yuyr/deploy/test-metric-node/s4`
-
-- 启动测试节点容器（接入 overlay）
-  - `docker run -d --name argus-metric-test-node-s4 \
-      --hostname dev2-yuyr-node002s4 \
-      --network argus-sys-net \
-      -v /home2/yuyr/deploy/test-metric-node/s4:/private/argus/agent \
-      argus-sys-metric-test-node:latest sleep infinity`
-
-- 在容器内执行安装（先用 FTP IP 引导，DNS 指向 Bind）
-  - `docker exec -it argus-metric-test-node-s4 bash`
-  - `echo "nameserver $BINDIP" > /etc/resolv.conf`
-  - `curl --ftp-method nocwd -u ftpuser:ZGClab1234! -fsSL "ftp://$FTPIP:21/setup.sh" -o /tmp/setup.sh`
-  - `chmod +x /tmp/setup.sh`
-  - `export AGENT_ENV=dev2 AGENT_USER=yuyr AGENT_INSTANCE=node002s4`
-  - `export MASTER_ENDPOINT=http://master.argus.com:3000`
-  - `/tmp/setup.sh --server "$FTPIP" --user ftpuser --password 'ZGClab1234!' --port 21`
-  - 说明：setup 会自动执行安装后自检（最多 5 分钟），无需手动轮询。
-
-## 验证（推荐在容器内执行，避免宿主权限问题）
-
-- 查看 node.json 关键字段
-  - `cat /private/argus/agent/dev2-yuyr-node002s4/node.json | jq '{last_report, health}'`
-  - 期望：四个 health 全部 healthy；等待 ≥70s 再查看，`last_report` 持续更新。
-
-- 指标端口
-  - `curl -s -o /dev/null -w '%{http_code}\n' http://localhost:9100/metrics`（期望 200）
-  - （如测试 GPU）`curl -s -o /dev/null -w '%{http_code}\n' http://localhost:9400/metrics`（有 GPU 时 200）
-
-- 与服务端连通（域名经 Bind 解析）
-  - `curl -s -o /dev/null -w '%{http_code}\n' http://master.argus.com:3000/readyz`（期望 200）
-  - `curl -s -o /dev/null -w '%{http_code}\n' http://es.log.argus.com:9200/_cluster/health`（期望 200）
-
-## （可选）在服务器主机侧观察 Prometheus 目标更新
-- `cat /home2/yuyr/deploy/versions/<VERSION>/private/argus/metric/prometheus/nodes.json | jq '.'`
-
-## 常见提示
-- 初次安装后短时 `curl` 域名返回 000/超时属正常，多等待 1–2 分钟 DNS 同步/组件冷启动完成。
-- 如在宿主直接读取挂载的 node.json 报 Permission denied，请使用 `docker exec` 在容器内查看。
-- MASTER_ENDPOINT 固定使用域名 `http://master.argus.com:3000`，客户端无需固定 IP。

deployment/build/templates/client/publish.sh

@@ -1,54 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-usage() { cat <<'EOF'
-Publish Argus client package to FTP
-
-Usage:
-  ./publish.sh --server HOST --user USER --password PASS [--port 21]
-
-Notes:
-- This script expects to run inside the built client artifact directory.
-- It reads LATEST_VERSION and uploads setup.sh, argus-metric_<ver>.tar.gz, and LATEST_VERSION.
-EOF
-}
-
-HOST=""; USERNAME=""; PASSWORD=""; PORT=21
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --server) HOST="$2"; shift 2;;
-    --user) USERNAME="$2"; shift 2;;
-    --password) PASSWORD="$2"; shift 2;;
-    --port) PORT="$2"; shift 2;;
-    -h|--help) usage; exit 0;;
-    *) echo "unknown arg: $1" >&2; usage; exit 1;;
-  esac
-done
-
-[[ -n "$HOST" && -n "$USERNAME" && -n "$PASSWORD" ]] || { usage; exit 1; }
-
-here="$(pwd)"
-if [[ ! -f "$here/LATEST_VERSION" ]]; then
-  echo "LATEST_VERSION not found in $(pwd)" >&2; exit 1;
-fi
-VER=$(cat "$here/LATEST_VERSION" | tr -d '\n')
-PKG="argus-metric_${VER}.tar.gz"
-
-if [[ ! -f "$here/$PKG" ]]; then
-  echo "client tar not found: $PKG" >&2; exit 1
-fi
-
-# locate setup.sh (prefer colocated, fallback to bundled path if provided)
-SETUP="${here}/setup.sh"
-if [[ ! -f "$SETUP" ]]; then
-  echo "setup.sh not found in $(pwd)" >&2; exit 1
-fi
-
-echo "[PUBLISH] server=$HOST port=$PORT version=$VER"
-
-curl -u "$USERNAME:$PASSWORD" -sfT "$SETUP" "ftp://$HOST:$PORT/setup.sh"
-curl -u "$USERNAME:$PASSWORD" -sfT "$PKG"   "ftp://$HOST:$PORT/$PKG"
-printf "%s" "$VER" | curl -u "$USERNAME:$PASSWORD" -sfT - "ftp://$HOST:$PORT/LATEST_VERSION"
-
-echo "[OK] publish completed"
-

deployment/build/templates/docker-compose.filter.awk

@@ -1,41 +0,0 @@
-#!/usr/bin/awk -f
-# Remove specific service blocks from a docker-compose.yml by service name.
-# Usage: awk -f docker-compose.filter.awk -v remove="node-a,node-b,test-node,test-gpu-node" input.yml > output.yml
-
-BEGIN{
-  split(remove, rm, ",");
-  for(i in rm){
-    gsub(/^\s+|\s+$/,"",rm[i]);
-    if (rm[i] != "") skipname[rm[i]] = 1;
-  }
-  in_services=0; skipping=0;
-}
-
-function service_header(line,   m) {
-  # match exactly two leading spaces followed by name:
-  if (match(line, /^  ([A-Za-z0-9_-]+):[ ]*$/, m)) return m[1];
-  return "";
-}
-
-{
-  # Track top-level sections (no indentation)
-  if ($0 ~ /^[A-Za-z0-9_-]+:[ ]*$/ && $0 !~ /^\s/) {
-    in_services = ($0 ~ /^services:[ ]*$/) ? 1 : 0;
-  }
-
-  if (skipping) {
-    # Stop skipping at next service header or another top-level section
-    if (service_header($0) != "" || ($0 ~ /^(networks|volumes):[ ]*$/ && $0 !~ /^\s/)) {
-      skipping=0;
-    } else {
-      next;
-    }
-  }
-
-  if (in_services) {
-    name = service_header($0);
-    if (name != "" && (name in skipname)) { skipping=1; next; }
-  }
-
-  print;
-}

deployment/build/templates/docker-compose.overlay.awk

@@ -1,74 +0,0 @@
-#!/usr/bin/awk -f
-# Transform docker-compose.yml to use an external overlay network for all services
-# - Remove top-level networks definition
-# - Remove per-service networks block (including ipv4_address and sysnet refs)
-# - Insert per-service networks: [argus-sys-net]
-# - Append external networks mapping at the end
-
-BEGIN{
-  in_top_networks=0; in_services=0; in_service=0; svc_indent=0; curr_name="";
-}
-
-function is_service_header(line){ return svc_name(line)!=""; }
-function svc_name(line,   m){ if (match(line, /^  ([A-Za-z0-9_-]+):[ ]*$/, m)) return m[1]; return ""; }
-
-function indent_len(s,   n){ n=match(s,/[^ ]/)-1; if(n<0) n=0; return n; }
-
-{
-  # Detect entry into top-level sections
-  if ($0 ~ /^[A-Za-z0-9_-]+:[ ]*$/ && $0 !~ /^\s/) {
-    in_services = ($0 ~ /^services:[ ]*$/);
-    # If a new top-level section starts, stop skipping top networks
-    in_top_networks = 0;
-  }
-
-  # Handle removal of initial top-level 'networks:' block
-  if ($0 ~ /^networks:[ ]*$/ && $0 !~ /^\s/) {
-    in_top_networks = 1; next;
-  }
-  if (in_top_networks) {
-    # skip until next top-level section (non-indented key)
-    next;
-  }
-
-  if (in_services) {
-    # Track service boundaries
-    if (is_service_header($0)) {
-      in_service=1; svc_indent=2; networks_inserted=0; curr_name=svc_name($0); print; next;
-    }
-    if (in_service) {
-      # If line is indented <= service indent, we've left this service
-      if (indent_len($0) <= svc_indent && $0 !~ /^\s*$/) {
-        in_service=0;
-      }
-    }
-
-    if (in_service) {
-      # Skip any existing networks block under the service
-      if ($0 ~ /^\s{4}networks:[ ]*$/) { skipping_nets=1; next; }
-      if (skipping_nets) {
-        if (indent_len($0) <= 4) { skipping_nets=0; }
-        else next;
-      }
-
-      # After container_name or image, inject networks once
-      if (!networks_inserted && ($0 ~ /^\s{4}container_name:/ || $0 ~ /^\s{4}image:/)) {
-        print; 
-        print "    networks:";
-        print "      - argus-sys-net";
-        networks_inserted=1; next;
-      }
-      # no host port injection; bind serves DNS inside overlay only
-    }
-  }
-
-  print;
-}
-
-END{
-  print "";
-  print "networks:";
-  print "  argus-sys-net:";
-  print "    external: true";
-  print "    name: ${OVERLAY_NET_NAME:-argus-sys-net}";
-}

deployment/build/templates/docs/INSTALL_SERVER.md

@@ -1,50 +0,0 @@
-# Argus Server Offline Installation
-
-## Prerequisites
-- Linux x86_64 (Ubuntu 22.04 recommended; see OS compatibility for NixOS)
-- Docker & Docker Compose installed
-- Open ports: 32300, 9200, 5601, 9090, 9093, 8080..8085, 21, 20, 21100–21110 (or auto-fallback to high ports)
-
-## Quick Start
-1. Extract to a target dir, e.g. `/opt/argus-deploy/versions/<YYYYMMDD>`
-2. `./server-install.sh` (non‑root is supported: it will precreate minimal dirs and auto-fix Kibana/ES/Bind in containers)
-3. `./server-status.sh`
-4. `./server-selfcheck.sh` (on failure it auto-runs diagnose and writes logs under `logs/`)
-5. `./server-uninstall.sh` to tear down
-
-## What the Installer Does
-- Loads local images (`images/all-images.tar.gz`)
-- Generates OS-compat override (`security_opt: ["label=disable"]`, `userns_mode: host`, bind `tmpfs:/run/named`)
-- Starts server-only services: bind/master/es/kibana/ftp/prometheus/grafana/alertmanager/web-frontend/web-proxy
-- DNS Bootstrap:
-  - Ensure `/private/argus/etc/dns.conf` exists (write `172.31.0.2` if missing);
-  - Run `/private/argus/etc/update-dns.sh` in dependent containers so `/etc/resolv.conf` points to bind;
-  - Wait for `*.argus.com` hint files, then reload bind;
-  - Restart web‑proxy to re-render nginx resolver from `dns.conf`;
-- Writes `logs/selfcheck.json` as final summary
-
-## OS Compatibility
-- NixOS / non-xattr FS: containers run with `security_opt: ["label=disable"]` and `userns_mode: host`.
-- If you cannot use sudo, the installer will:
-  - create minimal data dirs (incl. `private/argus/log/{elasticsearch,kibana}`) with permissive perms when possible;
-  - ensure inside containers: Kibana `data` → `/private/argus/log/kibana`, Elasticsearch `data` → `/private/argus/log/elasticsearch`, and Bind `rndc.key` is generated.
-  (Manual pre-creation scripts are no longer required.)
-
-## Files & Layout
-- `compose/` (docker-compose.yml, .env)
-- `private/` (data mounts)
-- `scripts/` (install/uninstall/status/selfcheck/diagnose)
-- `logs/` (selfcheck + diagnose outputs)
-
-## Troubleshooting (Quick)
-- Run `./server-selfcheck.sh` → see `logs/selfcheck.json`
-- Run `./server-diagnose.sh` → produces timestamped logs:
-  - `logs/diagnose_details_YYYYMMDD-HHMMSSZ.log`
-  - `logs/diagnose_error_YYYYMMDD-HHMMSSZ.log`
-  And updates `diagnose_details.log`/`diagnose_error.log` to the latest
-- Error lines are tagged `[service][source]`, e.g. `[kibana][http] /api/status=503`
-
-Common issues:
-- Kibana 503: wait cold start or fix DNS so `es.log.argus.com` resolves
-- web‑proxy 504: check nginx `resolver` includes `172.31.0.2 127.0.0.11`
-- EACCES/locks: ensure `sudo ./server-prepare-dirs.sh` ran and ownership matches UID:GID

deployment/build/templates/docs/INSTALL_SERVER_zh.md

@@ -1,29 +0,0 @@
-# Argus 服务端离线安装指南
-
-## 先决条件
-- Linux x86_64（推荐 Ubuntu 22.04；NixOS 见“兼容说明”）
-- 已安装 Docker 与 Docker Compose
-- 端口：32300, 9200, 5601, 9090, 9093, 8080..8085, 21, 20, 21100–21110
-
-## 快速开始
-1. 解压到目标目录（例如 `/opt/argus-deploy/versions/<YYYYMMDD>`）
-2. 安装：`./server-install.sh`（支持普通用户：会自动创建最小目录并在容器内修复 Kibana/ES/Bind）
-3. 状态：`./server-status.sh`
-4. 自检：`./server-selfcheck.sh`（失败会自动采集诊断）
-5. 卸载：`./server-uninstall.sh`
-
-## 安装流程要点
-- 仅启动 10 个服务端组件（不包含测试节点）；
-- DNS Bootstrap：补齐首次部署 DNS 依赖（生成/确认 `dns.conf`、统一容器 resolv.conf、写入 `*.argus.com`、reload bind、重启 web‑proxy）；
-- 输出自检结果到 `logs/selfcheck.json`。
-
-## 兼容说明（NixOS 等）
-- 使用 `security_opt: ["label=disable"]` 与 `userns_mode: host`。
-- 非 root 场景：安装器会创建最小目录（含 `private/argus/log/{elasticsearch,kibana}`），并在容器内完成：
-  - Kibana 的 `data` 软链到 `/private/argus/log/kibana`
-  - Elasticsearch 的 `data` 软链到 `/private/argus/log/elasticsearch`
-  - Bind 生成 `/etc/bind/rndc.key`
-
-## 故障排查（见下文 Troubleshooting_zh）
-- `./server-selfcheck.sh` → `logs/selfcheck.json`
-- `./server-diagnose.sh` → `logs/diagnose_error_*.log` / `logs/diagnose_details_*.log`

deployment/build/templates/docs/SWARM_DEPLOY_zh.md

@@ -1,50 +0,0 @@
-# Argus 多机部署（Docker Swarm + External Overlay）
-
-- 前提：Docker ≥ 20.10；Manager/Worker 节点开放 2377/tcp、7946/tcp+udp、4789/udp。
-- DNS：Bind9 为统一权威，解析 *.argus.com 至部署机固定对外主机 IP。
-
-## 在部署机（Manager）
-- 初始化 Swarm：`docker swarm init --advertise-addr <manager_ip>`
-- 创建 overlay：`docker network create --driver overlay --attachable argus-sys-net`
-- 解压离线包后执行：
-  - `./server-install.sh`（会验证 Swarm 状态、确保 overlay 存在、写入 dns.conf）
-  - `./server-selfcheck.sh`（失败会自动触发诊断）
-
-## 在节点机（Worker 或非 Docker 主机）
-- Swarm Worker：执行 Manager 的 `docker swarm join ...`；
-- 运行客户端容器：
-  - `docker run -d --name argus-metric-node-001 --network argus-sys-net -v /data/argus/agent:/private/argus/agent argus-sys-metric-test-node:latest sleep infinity`
-- 进入容器安装（先 IP 引导，后域名）：
-  - `curl -u ftpuser:*** -fsSL ftp://<FTP_IP>:21/setup.sh -o /tmp/setup.sh && chmod +x /tmp/setup.sh`
-  - `AGENT_ENV=dev AGENT_USER=alice AGENT_INSTANCE=node001 MASTER_ENDPOINT=http://master.argus.com:3000 /tmp/setup.sh --server ftp.argus.com --user ftpuser --password '***' --port 21`
-
-## 关键点
-- 首次必须使用 FTP 的 IP 引导（下载 setup.sh 与 dns.conf）
-- MASTER_ENDPOINT 永远使用域名：`http://master.argus.com:3000`
-- docker compose 改为 external overlay；容器内不使用 Docker 服务名；web-proxy 与组件上游统一用域名
-
-## 找回/轮换 Swarm 加入令牌与解锁密钥
-
-在任意一个 Manager 节点上执行以下命令即可查看或轮换加入令牌（join token）：
-
-- 查看加入 Worker 的命令：
-  - `docker swarm join-token worker`
-- 只打印 Worker 的 token：
-  - `docker swarm join-token -q worker`
-- 查看加入 Manager 的命令：
-  - `docker swarm join-token manager`
-- 只打印 Manager 的 token：
-  - `docker swarm join-token -q manager`
-
-在待加入节点执行（示例，替换 Manager_IP）：
-- `docker swarm join --token <上面查到的token> <Manager_IP>:2377`
-
-轮换 token（怀疑泄露或需要更新时）：
-- 轮换 Worker：`docker swarm join-token --rotate worker`
-- 轮换 Manager：`docker swarm join-token --rotate manager`
-
-如果你指的是“解锁密钥”（autolock 的 unlock key），在 Manager 上：
-- 查看：`docker swarm unlock-key`
-- 轮换：`docker swarm unlock-key --rotate`
-
-提示：当看到 “This node is not a swarm manager.” 时，说明当前节点不是 Manager，需要到 Manager 节点执行，或在现有 Manager 上 `docker node promote <NODE-ID>` 将其提升为 Manager。

deployment/build/templates/docs/TROUBLESHOOTING.md

@@ -1,20 +0,0 @@
-# Troubleshooting
-
-- Status: `scripts/server-status.sh`
-- Selfcheck: `scripts/server-selfcheck.sh`
-- Diagnose: `scripts/server-diagnose.sh`
-
-Outputs:
-- `logs/selfcheck.json`
-- `logs/diagnose_details_*.log` (full details)
-- `logs/diagnose_error_*.log` (tagged errors)
-
-Web‑Proxy:
-- 8083 expects 200/302/403; 8084/8085 must include CORS header
-- nginx resolver should be `172.31.0.2 127.0.0.11`
-
-Kibana/ES:
-- Verify `es.log.argus.com` resolves inside Kibana
-
-Permissions:
-- The installer auto-creates minimal dirs and applies container-side fixes (Kibana/ES/Bind). If you still see EACCES/lock errors, rerun `./server-install.sh` and review diagnose logs.

deployment/build/templates/docs/TROUBLESHOOTING_zh.md

@@ -1,16 +0,0 @@
-# 故障排查
-
-- 状态：`scripts/server-status.sh`
-- 自检：`scripts/server-selfcheck.sh`
-- 诊断：`scripts/server-diagnose.sh`
-
-输出：
-- `logs/selfcheck.json`
-- `logs/diagnose_error_*.log`（错误摘要）
-- `logs/diagnose_details_*.log`（详细信息）
-
-Web‑Proxy：8083=200/302/403；8084/8085 需包含 CORS
-Kibana：确认可解析 `es.log.argus.com`
-权限：
-- 非 root 安装时，安装器会创建最小目录并在容器内修复 Kibana/ES/Bind；
-- 如仍有 `EACCES`/锁文件报错，先重跑 `./server-install.sh`（会重复容器内修复），并查看诊断日志。

deployment/build/templates/scripts/es-watermark-relax.sh

@@ -1,82 +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
-
-ES_URL="http://localhost:${ES_HTTP_PORT:-9200}"
-
-# Tunables (env overrides)
-RELAX_WM_LOW="${RELAX_WM_LOW:-99%}"
-RELAX_WM_HIGH="${RELAX_WM_HIGH:-99%}"
-RELAX_WM_FLOOD="${RELAX_WM_FLOOD:-99%}"
-DISABLE_WATERMARK="${DISABLE_WATERMARK:-1}"
-SET_KIBANA_REPLICAS_ZERO="${SET_KIBANA_REPLICAS_ZERO:-1}"
-CLEAR_READONLY_BLOCKS="${CLEAR_READONLY_BLOCKS:-1}"
-
-echo "[RELAX] Checking Elasticsearch at $ES_URL"
-code=$(curl -s -o /dev/null -w '%{http_code}' "$ES_URL/_cluster/health" || true)
-if [[ "$code" != "200" ]]; then
-  echo "[RELAX][ERROR] ES not reachable (code=$code). Ensure argus-es-sys is running." >&2
-  exit 1
-fi
-
-echo "[RELAX] Applying transient cluster settings (watermarks)"
-th_enabled=$([[ "$DISABLE_WATERMARK" == "1" ]] && echo false || echo true)
-curl -sS -H 'Content-Type: application/json' -X PUT "$ES_URL/_cluster/settings" -d "{
-  \"transient\": {
-    \"cluster.routing.allocation.disk.threshold_enabled\": $th_enabled,
-    \"cluster.routing.allocation.disk.watermark.low\": \"$RELAX_WM_LOW\",
-    \"cluster.routing.allocation.disk.watermark.high\": \"$RELAX_WM_HIGH\",
-    \"cluster.routing.allocation.disk.watermark.flood_stage\": \"$RELAX_WM_FLOOD\"
-  }
-}" | sed -n '1,5p'
-
-if [[ "$CLEAR_READONLY_BLOCKS" == "1" ]]; then
-  echo "[RELAX] Clearing read_only/read_only_allow_delete blocks on all indices (best-effort)"
-  curl -sS -H 'Content-Type: application/json' -X PUT "$ES_URL/_all/_settings" -d '{
-    "index.blocks.read_only": false,
-    "index.blocks.read_only_allow_delete": false
-  }' >/dev/null || true
-fi
-
-if [[ "${SET_KIBANA_REPLICAS_ZERO:-1}" != "0" ]]; then
-  echo "[RELAX] Ensure .kibana* use replicas=0 via index template and per-index settings (best-effort)"
-  # high priority template for .kibana* only, avoid impacting other indices
-  curl -sS -H 'Content-Type: application/json' -X PUT "$ES_URL/_index_template/kibana-replicas-0" -d '{
-    "index_patterns": [".kibana*"],
-    "priority": 200,
-    "template": { "settings": { "number_of_replicas": 0 } }
-  }' >/dev/null || true
-  # set existing .kibana* to replicas=0
-  idxs=$(curl -sS "$ES_URL/_cat/indices/.kibana*?h=index" | awk '{print $1}')
-  for i in $idxs; do
-    [[ -n "$i" ]] || continue
-    curl -sS -H 'Content-Type: application/json' -X PUT "$ES_URL/$i/_settings" -d '{"index":{"number_of_replicas":0}}' >/dev/null || true
-  done
-fi
-
-# Retry failed shard allocations (best-effort)
-curl -sS -H 'Content-Type: application/json' -X POST "$ES_URL/_cluster/reroute?retry_failed=true" -d '{}' >/dev/null || true
-
-echo "[RELAX] Cluster health (post):"
-curl -sS "$ES_URL/_cluster/health?pretty" | sed -n '1,80p'
-
-# Simple current status summary
-ch=$(curl -sS "$ES_URL/_cluster/health" || true)
-status=$(printf '%s' "$ch" | awk -F'"' '/"status"/{print $4; exit}')
-unassigned=$(printf '%s' "$ch" | awk -F'[,: ]+' '/"unassigned_shards"/{print $3; exit}')
-duse=$(docker exec argus-es-sys sh -lc 'df -P /usr/share/elasticsearch/data | awk "NR==2{print \$5}"' 2>/dev/null || true)
-settings=$(curl -sS "$ES_URL/_cluster/settings?flat_settings=true" || true)
-th=$(printf '%s' "$settings" | grep -o '"cluster.routing.allocation.disk.threshold_enabled"[^,}]*' | awk -F: '{gsub(/["} ]/,"",$2);print $2}' | tail -n1)
-low=$(printf '%s' "$settings" | grep -o '"cluster.routing.allocation.disk.watermark.low"[^,}]*' | awk -F: '{gsub(/["} ]/,"",$2);print $2}' | tail -n1)
-high=$(printf '%s' "$settings" | grep -o '"cluster.routing.allocation.disk.watermark.high"[^,}]*' | awk -F: '{gsub(/["} ]/,"",$2);print $2}' | tail -n1)
-flood=$(printf '%s' "$settings" | grep -o '"cluster.routing.allocation.disk.watermark.flood_stage"[^,}]*' | awk -F: '{gsub(/["} ]/,"",$2);print $2}' | tail -n1)
-ks=$(curl -sS "$ES_URL/_cat/shards/.kibana*?h=state" || true)
-total=$(printf '%s' "$ks" | awk 'NF{c++} END{print c+0}')
-started=$(printf '%s' "$ks" | awk '/STARTED/{c++} END{print c+0}')
-unass=$(printf '%s' "$ks" | awk '/UNASSIGNED/{c++} END{print c+0}')
-echo "[RELAX][SUMMARY] status=${status:-?} unassigned=${unassigned:-?} es.data.use=${duse:-?} watermarks(threshold=${th:-?} low=${low:-?} high=${high:-?} flood=${flood:-?}) kibana_shards(total=${total},started=${started},unassigned=${unass})"
-
-echo "[RELAX] Done. Remember to run scripts/es-watermark-restore.sh after freeing disk space and cluster becomes stable."

deployment/build/templates/scripts/es-watermark-restore.sh

@@ -1,37 +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
-
-ES_URL="http://localhost:${ES_HTTP_PORT:-9200}"
-
-echo "[RESTORE] Checking Elasticsearch at $ES_URL"
-code=$(curl -s -o /dev/null -w '%{http_code}' "$ES_URL/_cluster/health" || true)
-if [[ "$code" != "200" ]]; then
-  echo "[RESTORE][ERROR] ES not reachable (code=$code). Ensure argus-es-sys is running." >&2
-  exit 1
-fi
-
-echo "[RESTORE] Re-enabling disk threshold and clearing relaxed watermarks (transient)"
-curl -sS -H 'Content-Type: application/json' -X PUT "$ES_URL/_cluster/settings" -d '{
-  "transient": {
-    "cluster.routing.allocation.disk.threshold_enabled": true,
-    "cluster.routing.allocation.disk.watermark.low": null,
-    "cluster.routing.allocation.disk.watermark.high": null,
-    "cluster.routing.allocation.disk.watermark.flood_stage": null
-  }
-}' | sed -n '1,5p'
-
-# Optionally restore default replicas to 1 (set RESTORE_DEFAULT_REPLICAS=1 to enable)
-if [[ "${RESTORE_DEFAULT_REPLICAS:-0}" == "1" ]]; then
-  echo "[RESTORE] Setting transient default index.number_of_replicas=1"
-  curl -sS -H 'Content-Type: application/json' -X PUT "$ES_URL/_cluster/settings" -d '{"transient":{"index.number_of_replicas":"1"}}' >/dev/null || true
-fi
-
-echo "[RESTORE] Cluster health:"
-curl -sS "$ES_URL/_cluster/health?pretty" | sed -n '1,80p'
-
-echo "[RESTORE] Done. Verify shards and consider keeping replicas=0 for single-node deployments."
-

deployment/build/templates/scripts/fix-prom-targets-overlay.sh

@@ -1,103 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Quick fix tool: replace 172.22/16 targets in nodes.json with overlay IPs resolved from hostname.
-# Usage: run on server package host: scripts/fix-prom-targets-overlay.sh
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-NODES_JSON="$ROOT/private/argus/metric/prometheus/nodes.json"
-
-require_cmd() { command -v "$1" >/dev/null 2>&1 || { echo "[ERROR] missing command: $1" >&2; exit 1; }; }
-
-backup() {
-  local src="$1"; local ts; ts=$(date -u +%Y%m%d-%H%M%SZ)
-  cp "$src" "${src%.json}_bak_${ts}.json"
-}
-
-prefer_overlay_ip() {
-  local host="$1"
-  # prefer 10.0/8 then 172.31/16
-  getent hosts "$host" | awk '{print $1}' | while read -r ip; do
-    if [[ "$ip" =~ ^10\. ]]; then echo "$ip"; return; fi
-  done
-  getent hosts "$host" | awk '{print $1}' | while read -r ip; do
-    if [[ "$ip" =~ ^172\.31\. ]]; then echo "$ip"; return; fi
-  done
-  # fallback: first A record
-  getent hosts "$host" | awk '{print $1; exit}'
-}
-
-require_cmd awk
-require_cmd sed
-
-if [[ ! -f "$NODES_JSON" ]]; then
-  echo "[WARN] nodes.json not found: $NODES_JSON" >&2
-  exit 0
-fi
-
-backup "$NODES_JSON"
-
-tmp=$(mktemp)
-trap 'rm -f "$tmp"' EXIT
-
-changed=0
-python3 - "$NODES_JSON" <<'PY' > "$tmp" || {
-import ipaddress, json, sys, socket
-path=sys.argv[1]
-data=json.load(open(path)) if path else []
-def resolve(host):
-    try:
-        infos=socket.getaddrinfo(host,None,family=socket.AF_INET)
-        ips=[i[4][0] for i in infos]
-        # prefer 10. over 172.31.
-        for ip in ips:
-            if ip.startswith('10.'): return ip
-        for ip in ips:
-            if ip.startswith('172.31.'): return ip
-        return ips[0] if ips else None
-    except OSError:
-        return None
-gw=ipaddress.ip_network('172.22.0.0/16')
-out=[]
-changed=False
-for item in data:
-    ip=item.get('ip')
-    host=item.get('hostname') or ''
-    try:
-        bad = ip and ipaddress.ip_address(ip) in gw
-    except Exception:
-        bad = False
-    if bad and host:
-        new=resolve(host)
-        if new:
-            item=dict(item)
-            item['ip']=new
-            changed=True
-    out.append(item)
-json.dump(out, sys.stdout, ensure_ascii=False)
-sys.stderr.write('CHANGED' if changed else 'UNCHANGED')
-PY
-
-status=$?
-marker=$(tail -n1 /dev/stderr 2>/dev/null || true)
-if [[ "$status" -ne 0 ]]; then
-  echo "[ERROR] failed to rewrite nodes.json" >&2
-  exit 1
-fi
-
-if grep -q '"ip"\s*:\s*"172\.22\.' "$tmp"; then
-  echo "[WARN] some gwbridge targets remain; manual fix may be required" >&2
-fi
-
-mv "$tmp" "$NODES_JSON"
-echo "[OK] nodes.json updated"
-
-# try to reload Prometheus
-if docker ps --format '{{.Names}}' | grep -q '^argus-prometheus$'; then
-  docker exec argus-prometheus sh -lc 'pidof prometheus >/dev/null 2>&1 && kill -HUP $(pidof prometheus) || supervisorctl restart prometheus' >/dev/null 2>&1 || true
-  echo "[INFO] Prometheus reloaded"
-fi
-
-exit 0
-

deployment/build/templates/scripts/server-diagnose.sh

@@ -1,198 +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 "$LOG_DIR" || true
-# Fallback to /tmp when logs dir is not writable
-if ! ( : > "$LOG_DIR/.w" 2>/dev/null ); then
-  LOG_DIR="/tmp/argus-logs"
-  mkdir -p "$LOG_DIR" || true
-fi
-DETAILS="$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 (state/restartcount):"; 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
-
-  # extract error lines from container logs
-  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] /" >> "$ERRORS" || true
-
-  # supervisor status and logs
-  if docker exec "$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
-    # iterate supervisor logs and collect tails + errors per file
-    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
-}
-
-# Core services
-svc bind argus-bind-sys
-svc master argus-master-sys
-svc es argus-es-sys
-svc kibana argus-kibana-sys
-svc ftp argus-ftp
-svc prometheus argus-prometheus
-svc grafana argus-grafana
-svc alertmanager argus-alertmanager
-svc web-frontend argus-web-frontend
-svc web-proxy argus-web-proxy
-
-# HTTP checks (host side)
-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: ${cors8085}"
-
-# Elasticsearch deep checks: disk watermark and Kibana index status
-section ES-CHECKS
-ch=$(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 ${duse} (>=90%) likely hit high/flood watermarks"
-    echo "HINT: High ES disk usage. Free space or run scripts/es-watermark-relax.sh (then scripts/es-watermark-restore.sh)." >&2
-  fi
-fi
-
-ks=$(curl -s --max-time 3 "http://localhost:${ES_HTTP_PORT:-9200}/_cat/shards/.kibana*?h=index,shard,prirep,state,unassigned.reason" || true)
-if printf '%s' "$ks" | grep -Eiq '\\b(UNASSIGNED|INITIALIZING|RELOCATING)\\b'; then
-  append_err "[kibana][index] .kibana* shards not green"; logd "$ks"
-  echo "HINT: .kibana* shards not green. On single-node, set replicas=0 and ensure ES disk watermarks are not exceeded." >&2
-fi
-
-# Overlay network diagnostics
-section OVERLAY-NET
-if docker network inspect "${OVERLAY_NET_NAME:-argus-sys-net}" >/dev/null 2>&1; then
-  logd "overlay present: ${OVERLAY_NET_NAME:-argus-sys-net}"
-  docker network inspect "${OVERLAY_NET_NAME:-argus-sys-net}" | sed -n '1,60p' >> "$DETAILS" 2>/dev/null || true
-else
-  append_err "[overlay][network] missing ${OVERLAY_NET_NAME:-argus-sys-net}"
-fi
-
-# Domain resolution & reachability from inside web-proxy (bind-backed)
-section DOMAIN
-for d in master.argus.com ftp.argus.com kibana.argus.com es.log.argus.com prom.argus.com grafana.argus.com; do
-  logd "getent $d (web-proxy):"
-  docker exec argus-web-proxy sh -lc "getent hosts $d || true" >> "$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=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://kibana.argus.com:5601/api/status\" 2>/dev/null || echo 000)"
-
-# FTP share writability (container perspective)
-section FTP-SHARE
-docker exec argus-ftp sh -lc 'ls -ld /private/argus/ftp /private/argus/ftp/share; test -w /private/argus/ftp/share && echo "write:OK" || echo "write:FAIL"' >> "$DETAILS" 2>&1 || true
-
-# Collect system info for context
-section SYSTEM
-logd "uname -a:"; uname -a >> "$DETAILS"
-logd "docker version:"; docker version --format '{{.Server.Version}}' >> "$DETAILS" 2>&1 || true
-logd "compose ps:"; (cd "$ROOT/compose" && if docker compose version >/dev/null 2>&1; then docker compose -p argus-sys ps; else docker-compose -p argus-sys ps; fi) >> "$DETAILS" 2>&1 || true
-
-section SUMMARY
-# Add HTTP failures and CORS problems to error log with tags
-[[ $(http_code "http://localhost:${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" >> "$ERRORS"
-
-# Deduplicate errors
-sort -u -o "$ERRORS" "$ERRORS"
-
-# --- Prometheus targets & nodes.json checks ---
-section PROMETHEUS-TARGETS
-nodes_json_path="$ROOT/private/argus/metric/prometheus/nodes.json"
-if [[ -f "$nodes_json_path" ]]; then
-  logd "nodes.json present: $nodes_json_path"
-  # detect gwbridge addresses (172.22/16)
-  if grep -E '"ip"\s*:\s*"172\.22\.' "$nodes_json_path" >/dev/null 2>&1; then
-    append_err "[prometheus][targets] contains gwbridge (172.22/16) addresses; prefer overlay (10.0/8)."
-    echo "HINT: nodes.json has 172.22.x.x targets. Ensure agent publishes overlay_ip and master prefers it." >&2
-  fi
-else
-  logd "nodes.json missing at $nodes_json_path"
-fi
-
-# Query Prometheus activeTargets and list down items when possible
-pt_json=$(curl -s --max-time 3 "http://localhost:${PROMETHEUS_PORT:-9090}/api/v1/targets" || true)
-if command -v jq >/dev/null 2>&1; then
-  downs=$(printf '%s' "$pt_json" | jq -r '.data.activeTargets[] | select(.health=="down") | "[prometheus][activeTargets] down url=\(.scrapeUrl) lastError=\(.lastError)"' 2>/dev/null || true)
-  if [[ -n "$downs" ]]; then
-    printf '%s\n' "$downs" >> "$ERRORS"
-  fi
-else
-  # best-effort grep when jq is unavailable
-  if printf '%s' "$pt_json" | grep -q '"health":"down"'; then
-    append_err "[prometheus][activeTargets] some targets are down (enable jq for detailed reasons)"
-  fi
-fi
-
-echo "Diagnostic details -> $DETAILS"
-echo "Detected errors   -> $ERRORS"
-
-if [[ "$LOG_DIR" == "$ROOT/logs" ]]; then
-  # maintain latest symlinks when writing under package logs
-  ln -sfn "$(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
-else
-  echo "Diagnostic details -> $DETAILS"
-  echo "Detected errors   -> $ERRORS"
-fi
-
-exit 0

deployment/build/templates/scripts/server-install.sh

@@ -1,365 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-PKG_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"   # version root
-
-PROJECT_NAME="argus-sys"
-
-log() { echo -e "\033[0;34m[INSTALL]\033[0m $*"; }
-err() { echo -e "\033[0;31m[ERROR ]\033[0m $*" >&2; }
-
-require() { command -v "$1" >/dev/null 2>&1 || { err "missing command: $1"; exit 1; }; }
-
-require docker
-if docker compose version >/dev/null 2>&1; then COMPOSE=(docker compose); else require docker-compose; COMPOSE=(docker-compose); fi
-
-ENV_FILE="$PKG_ROOT/compose/.env"
-ENV_TEMPLATE="$PKG_ROOT/compose/.env.example"
-
-find_free_port() {
-  local prefer="$1"; local start=${2:-20000}; local max=${3:-65000};
-  if ! ss -ltnH 2>/dev/null | awk -v pat=":"$prefer"$" '$4 ~ pat{f=1} END{exit f?0:1}'; then echo "$prefer"; return; fi
-  for ((p=start; p<=max; p++)); do
-    if ! ss -ltnH 2>/dev/null | awk -v pat=":"$p"$" '$4 ~ pat{f=1} END{exit f?0:1}'; then echo "$p"; return; fi
-  done
-  return 1
-}
-
-prepare_env() {
-  if [[ -f "$ENV_FILE" ]]; then log ".env exists, keep as-is"; return; fi
-  [[ -f "$ENV_TEMPLATE" ]] || { err "missing $ENV_TEMPLATE"; exit 1; }
-  cp "$ENV_TEMPLATE" "$ENV_FILE"
-  # overlay 模式下，避免为不同服务分配到同一新端口；保持模板端口不做自动改写
-}
-
-# read VAR from .env (simple parser)
-_read_env_var() { local var="$1"; local f="$ENV_FILE"; [[ -f "$f" ]] || return 1; awk -F'=' -v k="$var" 'BEGIN{found=0} $1==k{print substr($0,index($0,"=")+1); found=1; exit} END{exit found?0:1}' "$f"; }
-
-# set or append VAR=VAL in .env atomically
-_set_env_var() {
-  local var="$1"; local val="$2"; local f="$ENV_FILE"; local tmp="$ENV_FILE.tmp$$"
-  if [[ -f "$f" ]] && grep -qE "^${var}=" "$f"; then
-    sed -E "s#^(${var}=).*#\\1${val}#" "$f" >"$tmp" && mv "$tmp" "$f"
-  else
-    [[ -f "$f" ]] || : >"$f"
-    printf "%s=%s\n" "$var" "$val" >>"$f"
-  fi
-}
-
-auto_assign_ports() {
-  local enable="${AUTO_ASSIGN_PORTS:-true}"
-  case "$enable" in
-    0|false|no|off) log "AUTO_ASSIGN_PORTS disabled"; return;;
-  esac
-  [[ -f "$ENV_FILE" ]] || return 0
-  log "auto-assigning free host ports (with fallback)"
-  cp "$ENV_FILE" "$ENV_FILE.bak.$(date +%Y%m%d-%H%M%S)" || true
-
-  # list of VAR:default pairs to try; FTP 相关端口与被动端口范围不自动改写
-  local pairs=(
-    "MASTER_PORT:32300"
-    "ES_HTTP_PORT:9200"
-    "KIBANA_PORT:5601"
-    "PROMETHEUS_PORT:9090"
-    "ALERTMANAGER_PORT:9093"
-    "GRAFANA_PORT:3000"
-    "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"
-  )
-
-  # track ports reserved in this run to avoid duplicates
-  declare -A reserved=()
-  # pre-mark currently listening ports to avoid choosing them twice within the same run
-  while read -r lp; do reserved["$lp"]=1; done < <(ss -ltnH 2>/dev/null | awk '{print $4}' | sed -n 's#.*:##p')
-
-  for ent in "${pairs[@]}"; do
-    local var=${ent%%:*}; local def=${ent##*:}
-    local cur
-    if ! cur=$(_read_env_var "$var"); then cur="$def"; fi
-    # strip quotes if any
-    cur=${cur%\r}; cur=${cur%\n}; cur=${cur//\"/}
-    # find a free port, avoiding ones we already reserved in this loop
-    local cand="$cur"
-    # if already in use or reserved, pick a free one
-    if ss -ltnH 2>/dev/null | awk -v pat=":"$cand"$" '$4 ~ pat{f=1} END{exit f?0:1}'; then
-      cand=$(find_free_port "$cand" 20000 65000)
-    fi
-    # avoid duplicates chosen in this loop
-    local attempts=0
-    while [[ -n "${reserved[$cand]:-}" ]]; do
-      attempts=$((attempts+1))
-      local start=$((cand+1)); [[ $start -lt 20000 ]] && start=20000
-      local next
-      next=$(find_free_port "$start" "$start" 65000 || true)
-      if [[ -z "$next" ]]; then
-        next=$(find_free_port 20000 20000 65000 || true)
-      fi
-      if [[ -z "$next" || "$next" == "$cand" ]]; then
-        err "no free port available while assigning for $var (last tried: $cand)"; exit 1
-      fi
-      cand="$next"
-      if (( attempts > 1000 )); then err "port assignment loop exceeded for $var"; exit 1; fi
-    done
-    reserved["$cand"]=1
-    if [[ "$cand" != "$cur" ]]; then
-      log "  port reassigned: $var $cur -> $cand"
-      _set_env_var "$var" "$cand"
-    else
-      # ensure the var exists in .env for clarity
-      _set_env_var "$var" "$cand"
-    fi
-  done
-}
-
-prepare_data_dirs() {
-  if [[ $EUID -ne 0 ]]; then
-    echo -e "\033[1;33m[WARN]\033[0m running as non-root: will not chown data dirs."
-    echo -e "\033[1;33m[WARN]\033[0m If you hit Permission denied, run: sudo $SCRIPT_DIR/server-prepare-dirs.sh"
-    # still ensure basic directories exist (no chown)
-    mkdir -p \
-      "$PKG_ROOT/private/argus/etc" \
-      "$PKG_ROOT/private/argus/log/elasticsearch" \
-      "$PKG_ROOT/private/argus/log/kibana" \
-      "$PKG_ROOT/private/argus/metric/prometheus" \
-      "$PKG_ROOT/private/argus/metric/prometheus/data" \
-      "$PKG_ROOT/private/argus/metric/prometheus/rules" \
-      "$PKG_ROOT/private/argus/metric/grafana" \
-      "$PKG_ROOT/private/argus/metric/grafana/data" \
-      "$PKG_ROOT/private/argus/metric/grafana/logs" \
-      "$PKG_ROOT/private/argus/metric/grafana/plugins" \
-      "$PKG_ROOT/private/argus/metric/grafana/provisioning/datasources" \
-      "$PKG_ROOT/private/argus/metric/grafana/provisioning/dashboards" \
-      "$PKG_ROOT/private/argus/metric/grafana/data/sessions" \
-      "$PKG_ROOT/private/argus/metric/grafana/data/dashboards" \
-      "$PKG_ROOT/private/argus/alert/alertmanager" \
-      "$PKG_ROOT/private/argus/metric/ftp/share"
-    # non-root: relax permissions to avoid container UID mismatch blocking writes
-    chmod -R a+rwx "$PKG_ROOT/private/argus" 2>/dev/null || true
-  fi
-}
-
-ensure_swarm_and_overlay() {
-  local net_name="${OVERLAY_NET_NAME:-argus-sys-net}"
-  # Require swarm active
-  local state
-  state=$(docker info --format '{{.Swarm.LocalNodeState}}' 2>/dev/null || echo "")
-  if [[ "$state" != "active" ]]; then
-    err "Docker Swarm is not active. On this host run:"
-    err "  docker swarm init --advertise-addr <this_host_ip>"
-    exit 1
-  fi
-  # Create attachable overlay if missing
-  if ! docker network inspect "$net_name" >/dev/null 2>&1; then
-    log "creating attachable overlay network: $net_name"
-    docker network create --driver overlay --attachable "$net_name" >/dev/null
-  fi
-}
-
-bootstrap_dns_conf() {
-  local etc_dir="$PKG_ROOT/private/argus/etc"
-  mkdir -p "$etc_dir"
-  local dns_file="$etc_dir/dns.conf"
-  if [[ ! -s "$dns_file" ]]; then
-    # detect host primary IP
-    local host_ip
-    host_ip=$(ip route get 1.1.1.1 2>/dev/null | awk '/src/ {print $7; exit}')
-    [[ -z "$host_ip" ]] && host_ip=$(hostname -I 2>/dev/null | awk '{print $1}')
-    if [[ -n "$host_ip" ]]; then
-      echo "$host_ip" > "$dns_file"
-      log "wrote initial dns.conf with host IP: $host_ip"
-    else
-      err "failed to determine host IP for dns.conf; please edit $dns_file manually"
-    fi
-  fi
-}
-
-load_images() {
-  local tar="$PKG_ROOT/images/all-images.tar.gz"
-  [[ -f "$tar" ]] || { err "missing images tar: $tar"; exit 1; }
-  log "loading images from $(basename "$tar") (may take minutes)"
-  gunzip -c "$tar" | docker load >/dev/null
-}
-
-bring_up() {
-  log "starting services via compose"
-  ensure_swarm_and_overlay
-  bootstrap_dns_conf
-  local ov="$PKG_ROOT/compose/docker-compose.os-compat.override.yml"
-  if [[ ! -f "$ov" ]]; then
-    cat > "$ov" <<'YAML'
-services:
-  bind:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-    tmpfs:
-      - /run/named
-  master:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  es:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  kibana:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  ftp:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  prometheus:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  grafana:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  alertmanager:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-    # ensure runtime path matches container expectation
-    volumes:
-      - ../private/argus/etc:/private/argus/etc
-      - ../private/argus/alert/alertmanager:/alertmanager
-  web-frontend:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-  web-proxy:
-    security_opt: ["label=disable"]
-    userns_mode: "host"
-YAML
-    log "generated OS-compat override: $(basename "$ov")"
-  fi
-  # 仅启动服务端组件，避免误起测试节点（node-a/node-b/test-node/test-gpu-node）
-  local services=(bind master es kibana ftp prometheus grafana alertmanager web-frontend web-proxy)
-  log "services: ${services[*]}"
-  (cd "$PKG_ROOT/compose" && "${COMPOSE[@]}" -p "$PROJECT_NAME" -f docker-compose.yml -f $(basename "$ov") up -d "${services[@]}")
-}
-
-# Post bootstrap container-side fixes that do not require sudo on host.
-post_bootstrap_fixes() {
-  # Kibana: ensure /usr/share/kibana/data is a symlink into mounted path to avoid EACCES
-  if docker ps --format '{{.Names}}' | grep -q '^argus-kibana-sys$'; then
-    docker exec argus-kibana-sys bash -lc '
-      set -e
-      mkdir -p /private/argus/log/kibana && chmod 777 /private/argus/log/kibana || true
-      if [ -d /usr/share/kibana/data ] && [ ! -L /usr/share/kibana/data ]; then rm -rf /usr/share/kibana/data; fi
-      if [ ! -e /usr/share/kibana/data ]; then ln -s /private/argus/log/kibana /usr/share/kibana/data; fi
-    ' >/dev/null 2>&1 || true
-  fi
-  # Elasticsearch: ensure data path points to mounted path and is writable
-  if docker ps --format '{{.Names}}' | grep -q '^argus-es-sys$'; then
-    docker exec argus-es-sys bash -lc '
-      set -e
-      mkdir -p /private/argus/log/elasticsearch && chmod 777 /private/argus/log/elasticsearch || true
-      if [ -d /usr/share/elasticsearch/data ] && [ ! -L /usr/share/elasticsearch/data ]; then rm -rf /usr/share/elasticsearch/data; fi
-      if [ ! -e /usr/share/elasticsearch/data ]; then ln -s /private/argus/log/elasticsearch /usr/share/elasticsearch/data; fi
-    ' >/dev/null 2>&1 || true
-  fi
-  # Bind9: ensure rndc.key exists
-  if docker ps --format '{{.Names}}' | grep -q '^argus-bind-sys$'; then
-    docker exec argus-bind-sys bash -lc '
-      set -e
-      mkdir -p /etc/bind
-      if [ ! -f /etc/bind/rndc.key ]; then rndc-confgen -a -c /etc/bind/rndc.key; fi
-      chmod 644 /etc/bind/rndc.key || true
-    ' >/dev/null 2>&1 || true
-  fi
-}
-
-dns_bootstrap() {
-  log "DNS bootstrap: initializing shared dns.conf and container resolv.conf"
-  local etc_dir="$PKG_ROOT/private/argus/etc"
-  mkdir -p "$etc_dir"
-  # 1) ensure dns.conf exists (fallback to bind IP 172.31.0.2)
-  if [[ ! -s "$etc_dir/dns.conf" ]]; then
-    if echo "172.31.0.2" > "$etc_dir/dns.conf" 2>/dev/null; then
-      log "wrote fallback dns.conf with 172.31.0.2"
-    else
-      # host-side write denied (ownership 1000:1000); write via bind container instead
-      if docker ps --format '{{.Names}}' | grep -q '^argus-bind-sys$'; then
-        docker exec argus-bind-sys sh -lc 'echo 172.31.0.2 > /private/argus/etc/dns.conf && chmod 644 /private/argus/etc/dns.conf' || true
-        log "fallback dns.conf written via bind container"
-      else
-        log "bind not ready; skip writing fallback dns.conf"
-      fi
-    fi
-  fi
-  # 2) wait briefly for bind to copy update-dns.sh into shared etc (bind startup.sh does this)
-  local i=0
-  while [[ ! -x "$etc_dir/update-dns.sh" && $i -lt 20 ]]; do
-    sleep 0.5; ((i++));
-  done
-  if [[ ! -x "$etc_dir/update-dns.sh" ]]; then
-    log "update-dns.sh not present yet; continuing with existing resolv.conf"
-  fi
-  # 3) run update-dns.sh inside key containers so /etc/resolv.conf points to bind
-  local c
-  for c in argus-master-sys argus-es-sys argus-kibana-sys argus-grafana argus-prometheus argus-ftp argus-web-frontend argus-web-proxy argus-alertmanager; do
-    if docker ps --format '{{.Names}}' | grep -q "^${c}$"; then
-      docker exec "$c" sh -lc 'test -x /private/argus/etc/update-dns.sh && /private/argus/etc/update-dns.sh || true' >/dev/null 2>&1 || true
-    fi
-  done
-  # 4) wait for service A-record hint files generated by services (best-effort)
-  local need=( es.log.argus.com kibana.log.argus.com master.argus.com grafana.metric.argus.com prom.metric.argus.com alertmanager.alert.argus.com )
-  local waited=0; local missing=1
-  while (( waited < 15 )); do
-    missing=0
-    for f in "${need[@]}"; do [[ -s "$etc_dir/$f" ]] || { missing=1; break; }; done
-    [[ $missing -eq 0 ]] && break
-    sleep 1; ((waited++))
-  done
-  # 5) reload bind zone (script uses supervisor to restart bind9)
-  if docker ps --format '{{.Names}}' | grep -q '^argus-bind-sys$'; then
-    docker exec argus-bind-sys sh -lc '/usr/local/bin/reload-bind9.sh' >/dev/null 2>&1 || true
-  fi
-  # 6) restart web-proxy once to re-render nginx resolver with latest dns.conf
-  if docker ps --format '{{.Names}}' | grep -q '^argus-web-proxy$'; then
-    docker restart argus-web-proxy >/dev/null 2>&1 || true
-  fi
-}
-
-selfcheck() {
-  # Initial selfcheck with retries to absorb cold starts
-  local max_retries="${SELF_CHECK_RETRIES:-5}"   # 重试次数（不含首次），默认 5
-  local wait_seconds="${SELF_CHECK_WAIT_SECONDS:-30}"  # 每次重试前等待秒数，默认 30s
-
-  local attempt=0
-  while :; do
-    attempt=$((attempt+1))
-    if (( attempt == 1 )); then
-      log "running selfcheck (attempt ${attempt})"
-    else
-      log "running selfcheck (attempt ${attempt}/${max_retries}+1)"
-    fi
-
-    if bash "$PKG_ROOT/scripts/server-selfcheck.sh"; then
-      return 0
-    fi
-
-    # failed
-    if (( attempt > max_retries )); then
-      err "selfcheck failed after ${attempt} attempt(s)"
-      exit 1
-    fi
-    log "selfcheck not ready yet; retrying in ${wait_seconds}s..."
-    sleep "$wait_seconds"
-  done
-}
-
-main() {
-  mkdir -p "$PKG_ROOT/logs"
-  prepare_env
-  auto_assign_ports
-  prepare_data_dirs
-  load_images
-  bring_up
-  post_bootstrap_fixes
-  dns_bootstrap
-  selfcheck
-  log "install completed. See logs in $PKG_ROOT/logs/"
-}
-
-main "$@"

deployment/build/templates/scripts/server-prepare-dirs.sh

@@ -1,73 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-PKG_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-
-if [[ $EUID -ne 0 ]]; then
-  echo "[PREPARE] This script requires root (sudo)." >&2
-  echo "          Try: sudo $0" >&2
-  exit 1
-fi
-
-ENV_FILE="$PKG_ROOT/compose/.env"
-[[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
-UIDV="${ARGUS_BUILD_UID:-1000}"; GIDV="${ARGUS_BUILD_GID:-1000}"
-
-echo "[PREPARE] Using owner ${UIDV}:${GIDV}"
-
-# Core etc and service data dirs (aligned with src/sys/tests/scripts/01_bootstrap.sh)
-mkdir -p \
-  "$PKG_ROOT/private/argus/etc" \
-  "$PKG_ROOT/private/argus/bind" \
-  "$PKG_ROOT/private/argus/master" \
-  "$PKG_ROOT/private/argus/agent" \
-  "$PKG_ROOT/private/argus/log/elasticsearch" \
-  "$PKG_ROOT/private/argus/log/kibana"
-
-# Prometheus
-mkdir -p \
-  "$PKG_ROOT/private/argus/metric/prometheus" \
-  "$PKG_ROOT/private/argus/metric/prometheus/data" \
-  "$PKG_ROOT/private/argus/metric/prometheus/rules" \
-  "$PKG_ROOT/private/argus/metric/prometheus/targets"
-
-# Grafana
-mkdir -p \
-  "$PKG_ROOT/private/argus/metric/grafana" \
-  "$PKG_ROOT/private/argus/metric/grafana/data" \
-  "$PKG_ROOT/private/argus/metric/grafana/logs" \
-  "$PKG_ROOT/private/argus/metric/grafana/plugins" \
-  "$PKG_ROOT/private/argus/metric/grafana/provisioning/datasources" \
-  "$PKG_ROOT/private/argus/metric/grafana/provisioning/dashboards" \
-  "$PKG_ROOT/private/argus/metric/grafana/data/sessions" \
-  "$PKG_ROOT/private/argus/metric/grafana/data/dashboards" \
-  "$PKG_ROOT/private/argus/metric/grafana/config"
-
-# FTP
-mkdir -p "$PKG_ROOT/private/argus/metric/ftp/share"
-
-# Alertmanager
-mkdir -p "$PKG_ROOT/private/argus/alert/alertmanager"
-
-chown -R "$UIDV":"$GIDV" \
-  "$PKG_ROOT/private/argus/etc" \
-  "$PKG_ROOT/private/argus/bind" \
-  "$PKG_ROOT/private/argus/master" \
-  "$PKG_ROOT/private/argus/agent" \
-  "$PKG_ROOT/private/argus/log/elasticsearch" \
-  "$PKG_ROOT/private/argus/log/kibana" \
-  "$PKG_ROOT/private/argus/metric/prometheus" \
-  "$PKG_ROOT/private/argus/metric/grafana" \
-  "$PKG_ROOT/private/argus/metric/ftp" \
-  "$PKG_ROOT/private/argus/alert"
-
-chmod -R g+w "$PKG_ROOT/private/argus/alert" "$PKG_ROOT/private/argus/etc" || true
-
-# Ensure parent directories also owned by runtime user for consistency
-chown "$UIDV":"$GIDV" \
-  "$PKG_ROOT/private/argus" \
-  "$PKG_ROOT/private/argus/log" \
-  "$PKG_ROOT/private/argus/metric" || true
-
-echo "[PREPARE] Done. You can now run server-install.sh"

deployment/build/templates/scripts/server-selfcheck.sh

@@ -1,104 +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=$(mktemp)
-
-ok=1
-
-log "checking overlay network"
-net_ok=false
-if docker network inspect "${OVERLAY_NET_NAME:-argus-sys-net}" >/dev/null 2>&1; then
-  if docker network inspect "${OVERLAY_NET_NAME:-argus-sys-net}" | grep -q '"Driver": "overlay"'; then net_ok=true; fi
-fi
-[[ "$net_ok" == true ]] || ok=0
-
-log "checking Elasticsearch (via domain inside web-proxy)"
-if docker exec argus-web-proxy sh -lc "curl -fsS http://es.log.argus.com:9200/_cluster/health?wait_for_status=yellow&timeout=1s" >/dev/null 2>&1; then es_ok=true; else es_ok=false; ok=0; fi
-
-log "checking Kibana (via domain inside web-proxy)"
-kb_code=$(docker exec argus-web-proxy sh -lc "curl -s -o /dev/null -w '%{http_code}' http://kibana.log.argus.com:5601/api/status" || echo 000)
-kb_ok=false
-if [[ "$kb_code" == "200" ]]; then body=$(curl -sS "http://localhost:${KIBANA_PORT:-5601}/api/status"); echo "$body" | grep -q '"level":"available"' && kb_ok=true; fi
-[[ "$kb_ok" == true ]] || ok=0
-
-log "checking Master (via domain inside web-proxy)"
-if docker exec argus-web-proxy sh -lc "curl -fsS http://master.argus.com:3000/readyz" >/dev/null 2>&1; then true; else ok=0; fi
-
-log "checking FTP"
-if docker ps --format '{{.Names}}' | grep -q '^argus-ftp$'; then
-  if docker exec argus-ftp sh -lc 'test -w /private/argus/ftp/share'; then ftp_ok=true; else ftp_ok=false; ok=0; fi
-else
-  ftp_ok=false; ok=0;
-fi
-
-log "checking Prometheus"
-wait_http "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready" 60 || ok=0
-
-log "checking Grafana"
-gf_code=$(curl -s -o /dev/null -w "%{http_code}" "http://localhost:${GRAFANA_PORT:-3000}/api/health" || echo 000)
-gf_ok=false; if [[ "$gf_code" == "200" ]]; then body=$(curl -sS "http://localhost:${GRAFANA_PORT:-3000}/api/health"); echo "$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"
-p8080=$(code_for "http://localhost:${WEB_PROXY_PORT_8080:-8080}/")
-p8083=$(code_for "http://localhost:${WEB_PROXY_PORT_8083:-8083}/")
-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
-# 有些环境首页可能 403，此处接受 200/403
-([[ "$p8080" == 200 || "$p8080" == 403 ]]) || wp_ok=false
-([[ "$p8083" == 200 || "$p8083" == 302 || "$p8083" == 403 ]]) || wp_ok=false
-[[ -n "$cors8084" && -n "$cors8085" ]] || wp_ok=false
-[[ "$wp_ok" == true ]] || ok=0
-
-cat > "$tmp" <<JSON
-{
-  "es": $es_ok,
-  "kibana": $kb_ok,
-  "master_readyz": true,
-  "ftp_share_writable": $ftp_ok,
-  "prometheus": true,
-  "grafana": $gf_ok,
-  "alertmanager": true,
-  "web_proxy": $wp_ok,
-  "overlay_net": $net_ok,
-  "timestamp": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
-}
-JSON
-
-if ! mv "$tmp" "$OUT_JSON" 2>/dev/null; then
-  # fallback when logs dir not writable (no sudo allowed)
-  OUT_JSON="/tmp/selfcheck_$(date -u +%Y%m%d-%H%M%SZ).json"
-  cp "$tmp" "$OUT_JSON"
-  log "selfcheck.json written to $OUT_JSON (logs dir not writable)"
-fi
-if [[ "$ok" == 1 ]]; then
-  log "selfcheck OK"
-  exit 0
-else
-  err "selfcheck FAILED (see $OUT_JSON)"
-  # If diagnose script exists, run it to collect more details
-  if [[ -x "$SCRIPT_DIR/server-diagnose.sh" ]]; then
-    # run diagnose; it will print the actual timestamped file paths and update 'latest' symlinks
-    "$SCRIPT_DIR/server-diagnose.sh" || true
-  fi
-  exit 1
-fi

deployment/build/templates/scripts/server-status.sh

@@ -1,28 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-
-PROJECT_NAME="argus-sys"
-
-if docker compose version >/dev/null 2>&1; then COMPOSE=(docker compose); else COMPOSE=(docker-compose); fi
-
-echo "== Containers =="
-(cd "$ROOT/compose" && "${COMPOSE[@]}" -p "$PROJECT_NAME" ps)
-
-echo
-echo "== Key Endpoints =="
-ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
-printf "master    http://localhost:%s/readyz\n" "${MASTER_PORT:-32300}"
-printf "es        http://localhost:%s/_cluster/health\n" "${ES_HTTP_PORT:-9200}"
-printf "kibana    http://localhost:%s/api/status\n" "${KIBANA_PORT:-5601}"
-printf "prom      http://localhost:%s/-/ready\n" "${PROMETHEUS_PORT:-9090}"
-printf "grafana   http://localhost:%s/api/health\n" "${GRAFANA_PORT:-3000}"
-printf "alert     http://localhost:%s/api/v2/status\n" "${ALERTMANAGER_PORT:-9093}"
-printf "web       http://localhost:%s/ (8080)\n" "${WEB_PROXY_PORT_8080:-8080}"
-
-echo
-echo "== Selfcheck result =="
-cat "$ROOT/logs/selfcheck.json" 2>/dev/null || echo "(no selfcheck yet)"
-

deployment/build/templates/scripts/server-uninstall.sh

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-PKG_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-
-PROJECT_NAME="argus-sys"
-
-log() { echo -e "\033[0;34m[UNINSTALL]\033[0m $*"; }
-
-if docker compose version >/dev/null 2>&1; then COMPOSE=(docker compose); else COMPOSE=(docker-compose); fi
-
-(cd "$PKG_ROOT/compose" && "${COMPOSE[@]}" -p "$PROJECT_NAME" down -v || true)
-log "compose stack removed"
-log "you may remove data under $PKG_ROOT/private if you want a clean slate"
-

scripts/common/build_user.sh

@@ -37,22 +37,11 @@ _argus_is_number() {
   [[ "$1" =~ ^[0-9]+$ ]]
 }
 
-load_build_user() {
+_argus_read_user_from_files() {
-  if [[ "$_ARGUS_BUILD_USER_LOADED" == "1" ]]; then
+  local uid_out_var="$1" gid_out_var="$2"; shift 2
-    return 0
+  local uid_val="$ARGUS_BUILD_UID_DEFAULT" gid_val="$ARGUS_BUILD_GID_DEFAULT"
-  fi
+  local config
-
+  for config in "$@"; do
-  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
@@ -68,42 +57,58 @@ load_build_user() {
         key="$(_argus_trim "$key")"
         value="$(_argus_trim "$value")"
         case "$key" in
-          UID)
+          UID) uid_val="$value" ;;
-            uid="$value"
+          GID) gid_val="$value" ;;
-            ;;
+          *) echo "[ARGUS build_user] Unknown key '$key' in $config" >&2 ;;
-          GID)
-            gid="$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"
+}
 
-  if [[ -n "${ARGUS_BUILD_UID:-}" ]]; then
+load_build_user_profile() {
-    uid="$ARGUS_BUILD_UID"
+  local profile="${1:-default}"
-  fi
+  if [[ "$_ARGUS_BUILD_USER_LOADED" == "1" ]]; then
-  if [[ -n "${ARGUS_BUILD_GID:-}" ]]; then
+    return 0
-    gid="$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
+    echo "[ARGUS build_user] Invalid UID '$uid'" >&2; return 1
-    return 1
   fi
   if ! _argus_is_number "$gid"; then
-    echo "[ARGUS build_user] Invalid GID '$gid'" >&2
+    echo "[ARGUS build_user] Invalid GID '$gid'" >&2; return 1
-    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/metric/client-plugins/all-in-one-full/config/VERSION

@@ -1 +1 @@
-1.43.0
+1.44.0

src/web/.gitignore

@@ -7,6 +7,7 @@ playwright-report/
 # Build output
 /dist
 /build
+/test-results
 
 # Dependency directories
 jspm_packages/