[#37 ] 构建安装包

[#30 ] ftp容器增加动态检测并更新dns.conf到share目录
[#30 ] wsl部署测试；更新README
2025-10-30 11:21:05 +08:00 · 2025-10-29 17:15:48 +08:00 · 2025-10-29 16:33:38 +08:00
22 changed files with 718 additions and 12 deletions
--- a/deployment/.gitignore
+++ b/deployment/.gitignore
@@ -0,0 +1 @@
+artifact/
--- a/deployment/build/README.md
+++ b/deployment/build/README.md
@@ -0,0 +1,16 @@
+# 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).
--- a/deployment/build/build_client_package.sh
+++ b/deployment/build/build_client_package.sh
@@ -0,0 +1,56 @@
+#!/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 "$tmpdir"' EXIT
+rsync -a "$latest_dir" "$tmpdir/src" >/dev/null 2>&1 || cp -r "$latest_dir" "$tmpdir/src"
+
+out_name="argus-metric_$(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"
+
+exit 0
+
--- a/deployment/build/build_server_package.sh
+++ b/deployment/build/build_server_package.sh
@@ -0,0 +1,116 @@
+#!/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 $SRC_COMPOSE"; exit 1; }
+awk -f "$BUILD_DIR/templates/docker-compose.filter.awk" -v remove="node-a,node-b,test-node,test-gpu-node" "$SRC_COMPOSE" > "$STAGE/compose/docker-compose.yml"
+cp "$BUILD_DIR/templates/.env.example" "$STAGE/compose/.env.example"
+
+# 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/"
+else
+  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" "$STAGE/scripts"
+cat > "$STAGE/docs/INSTALL_SERVER.md" << 'MD'
+# Argus Server Offline Installation
+
+## Prerequisites
+- Ubuntu 22.04 x86_64
+- Docker & Docker Compose installed
+- Open ports: 32300,9200,5601,9090,9093,8080..8085,21,20,21100-21110 (or auto-fallback to high ports)
+
+## Steps
+1. Extract this package to /opt/argus-deploy/versions/<YYYYMMDD>
+2. cd scripts && sudo ./server-install.sh
+3. Check status: ./server-status.sh
+4. Uninstall: ./server-uninstall.sh
+
+## Notes
+- Selfcheck result is written to logs/selfcheck.json
+- DNS will be managed by internal bind; FTP dns.conf is auto-published to share/dns.conf
+MD
+
+# 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
--- a/deployment/build/common.sh
+++ b/deployment/build/common.sh
@@ -0,0 +1,33 @@
+#!/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"
+}
+
--- a/deployment/build/publish_client.sh
+++ b/deployment/build/publish_client.sh
@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+. "$ROOT_DIR/build/common.sh"
+
+usage() { cat <<'EOF'
+Publish client package to FTP server
+
+Usage: publish_client.sh --version YYYYMMDD --server HOST --user USER --password PASS [--port 21]
+
+It uploads: setup.sh, argus-metric_<YYYYMMDD>.tar.gz, LATEST_VERSION to the FTP share root.
+EOF
+}
+
+VERSION=""; HOST=""; USERNAME=""; PASSWORD=""; PORT=21
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --version) VERSION="$2"; shift 2;;
+    --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;;
+    *) err "unknown arg: $1"; usage; exit 1;;
+  esac
+done
+
+[[ -n "$VERSION" && -n "$HOST" && -n "$USERNAME" && -n "$PASSWORD" ]] || { usage; exit 1; }
+
+CLIENT_DIR="$ROOT_DIR/artifact/client/$VERSION"
+TAR_NAME="argus-metric_${VERSION}.tar.gz"
+PKG="$CLIENT_DIR/$TAR_NAME"
+SETUP_SRC="$ROOT_DIR/../src/sys/tests/private/argus/metric/ftp/share/setup.sh"
+ALT_SETUP="$ROOT_DIR/../src/metric/client-plugins/all-in-one-full/scripts/setup.sh"
+
+[[ -f "$PKG" ]] || { err "missing client package: $PKG"; exit 1; }
+if [[ ! -f "$SETUP_SRC" ]]; then
+  if [[ -f "$ALT_SETUP" ]]; then
+    SETUP_SRC="$ALT_SETUP"
+  else
+    err "missing setup.sh (checked $SETUP_SRC and $ALT_SETUP)"; exit 1
+  fi
+fi
+
+log "Uploading setup.sh"
+curl -u "$USERNAME:$PASSWORD" -sfT "$SETUP_SRC" "ftp://$HOST:$PORT/setup.sh"
+
+log "Uploading client tar: $TAR_NAME"
+curl -u "$USERNAME:$PASSWORD" -sfT "$PKG" "ftp://$HOST:$PORT/$TAR_NAME"
+
+log "Updating LATEST_VERSION -> $VERSION"
+printf "%s" "$VERSION" | curl -u "$USERNAME:$PASSWORD" -sfT - "ftp://$HOST:$PORT/LATEST_VERSION"
+
+log "Publish done"
+
+exit 0
--- a/deployment/build/templates/.env.example
+++ b/deployment/build/templates/.env.example
@@ -0,0 +1,29 @@
+# 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
--- a/deployment/build/templates/docker-compose.filter.awk
+++ b/deployment/build/templates/docker-compose.filter.awk
@@ -0,0 +1,41 @@
+#!/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) skipname[rm[i]] = 1;
+}
+
+function starts_service_line(line,   name) {
+  if (match(line, /^\s{2}([a-zA-Z0-9_-]+):\s*$/, m)) {
+    name = m[1];
+    return name;
+  }
+  return "";
+}
+
+{
+  name = starts_service_line($0);
+  if (name != "") {
+    # detect top-level keys (networks:, services:, etc.)
+    if ($0 ~ /^services:\s*$/) { in_services=1; print; next; }
+    if ($0 ~ /^[a-zA-Z0-9_-]+:\s*$/ && $0 !~ /^\s/) {
+      in_services= ($0 ~ /^services:\s*$/);
+    }
+
+    if (in_services && (name in skipname)) {
+      skipping=1; next;
+    }
+  }
+
+  # end skipping when next top-level service appears
+  if (skipping) {
+    if (starts_service_line($0) != "") { skipping=0; }
+    else if ($0 ~ /^(networks|volumes):\s*$/) { skipping=0; }
+    else { next; }
+  }
+
+  print;
+}
+
--- a/deployment/build/templates/scripts/server-install.sh
+++ b/deployment/build/templates/scripts/server-install.sh
@@ -0,0 +1,72 @@
+#!/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" "$ENV_FILE"
+  # auto-assign ports if busy
+  for key in MASTER_PORT ES_HTTP_PORT KIBANA_PORT NODE_A_PORT NODE_B_PORT PROMETHEUS_PORT GRAFANA_PORT ALERTMANAGER_PORT \
+             WEB_PROXY_PORT_8080 WEB_PROXY_PORT_8081 WEB_PROXY_PORT_8082 WEB_PROXY_PORT_8083 WEB_PROXY_PORT_8084 WEB_PROXY_PORT_8085 \
+             FTP_PORT FTP_DATA_PORT; do
+    val=$(grep -E "^${key}=" "$ENV_FILE" | tail -1 | cut -d= -f2)
+    new=$(find_free_port "$val") || true
+    if [[ -n "${new:-}" && "$new" != "$val" ]]; then
+      sed -i "s/^${key}=.*/${key}=${new}/" "$ENV_FILE"
+      log "port ${key} busy -> ${new}"
+    fi
+  done
+}
+
+load_images() {
+  local tar="$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 "$tar" | docker load >/dev/null
+}
+
+bring_up() {
+  log "starting services via compose"
+  (cd "$PKG_ROOT/compose" && "${COMPOSE[@]}" -p "$PROJECT_NAME" up -d)
+}
+
+selfcheck() {
+  log "running selfcheck"
+  bash "$PKG_ROOT/scripts/server-selfcheck.sh" || { err "selfcheck failed"; exit 1; }
+}
+
+main() {
+  prepare_env
+  load_images
+  bring_up
+  selfcheck
+  log "install completed. See logs in $PKG_ROOT/logs/"
+}
+
+main "$@"
+
--- a/deployment/build/templates/scripts/server-selfcheck.sh
+++ b/deployment/build/templates/scripts/server-selfcheck.sh
@@ -0,0 +1,75 @@
+#!/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 $2}'; }
+
+mkdir -p "$ROOT/logs"
+OUT_JSON="$ROOT/logs/selfcheck.json"
+tmp=$(mktemp)
+
+ok=1
+
+log "checking Elasticsearch"
+if curl -fsS "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health?wait_for_status=yellow&timeout=1s" >/dev/null 2>&1; then es_ok=true; else es_ok=false; ok=0; fi
+
+log "checking Kibana"
+kb_code=$(curl -s -o /dev/null -w "%{http_code}" "http://localhost:${KIBANA_PORT:-5601}/api/status" || echo 000)
+kb_ok=false
+if [[ "$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"
+wait_http "http://localhost:${MASTER_PORT:-32300}/readyz" 60 || ok=0
+
+log "checking FTP"
+ftp_root="$ROOT/private/argus/metric/ftp/share"; [[ -d "$ftp_root" && -w "$ftp_root" ]] && ftp_ok=true || { ftp_ok=false; ok=0; }
+
+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:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
+wp_ok=true
+[[ "$p8080" == 200 ]] || wp_ok=false
+([[ "$p8083" == 200 || "$p8083" == 302 ]]) || 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": $wp_ok,
+  "timestamp": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
+}
+JSON
+
+mv "$tmp" "$OUT_JSON"
+[[ "$ok" == 1 ]] && { log "selfcheck OK"; exit 0; } || { err "selfcheck FAILED (see $OUT_JSON)"; exit 1; }
+
--- a/deployment/build/templates/scripts/server-status.sh
+++ b/deployment/build/templates/scripts/server-status.sh
@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(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)"
+
--- a/deployment/build/templates/scripts/server-uninstall.sh
+++ b/deployment/build/templates/scripts/server-uninstall.sh
@@ -0,0 +1,16 @@
+#!/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"
+
--- a/src/metric/client-plugins/all-in-one-full/config/VERSION
+++ b/src/metric/client-plugins/all-in-one-full/config/VERSION
@@ -1 +1 @@
-1.35.0
+1.38.0
--- a/src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/package.sh
+++ b/src/metric/client-plugins/all-in-one-full/plugins/dcgm-exporter/package.sh
@@ -48,6 +48,15 @@ if [[ ${#missing_files[@]} -gt 0 ]]; then
    exit 1
 fi

+# 防御：阻止将 Git LFS 指针文件打包
+for f in bin/dcgm-exporter bin/datacenter-gpu-manager_3.3.9_amd64.deb; do
+  if head -n1 "$f" 2>/dev/null | grep -q '^version https://git-lfs.github.com/spec/v1$'; then
+      echo "[ERROR] $f 是 Git LFS 指针文件，未还原为真实制品"
+      echo "        请在仓库根目录执行: git lfs fetch --all && git lfs checkout"
+      exit 1
+  fi
+done
+
 log_success "所有必要文件检查完成"

 # 创建临时目录
--- a/src/metric/client-plugins/all-in-one-full/plugins/node-exporter/package.sh
+++ b/src/metric/client-plugins/all-in-one-full/plugins/node-exporter/package.sh
@@ -47,6 +47,13 @@ if [[ ${#missing_files[@]} -gt 0 ]]; then
    exit 1
 fi

+# 防御：阻止将 Git LFS 指针文件打包
+if head -n1 bin/node_exporter 2>/dev/null | grep -q '^version https://git-lfs.github.com/spec/v1$'; then
+    echo "[ERROR] bin/node_exporter 是 Git LFS 指针文件，未还原为真实二进制"
+    echo "        请在仓库根目录执行: git lfs fetch --all && git lfs checkout"
+    exit 1
+fi
+
 log_success "所有必要文件检查完成"

 # 创建临时目录
--- a/src/metric/client-plugins/all-in-one-full/scripts/package_artifact.sh
+++ b/src/metric/client-plugins/all-in-one-full/scripts/package_artifact.sh
@@ -216,6 +216,36 @@ if [[ ${#missing_components[@]} -gt 0 ]]; then
    exit 1
 fi

+# 额外校验：阻止将 Git LFS 指针文件打进安装包
+# 仅检查各组件目录下的 bin/ 内文件（常见为二进制或 .deb/.tar.gz 制品）
+is_lfs_pointer() {
+    local f="$1"
+    # 读取首行判断是否为 LFS pointer（无需依赖 file 命令）
+    head -n1 "$f" 2>/dev/null | grep -q '^version https://git-lfs.github.com/spec/v1$'
+}
+
+log_info "检查组件二进制是否已从 LFS 拉取..."
+while IFS= read -r component; do
+    component_path=$(grep "^$component:" "$TEMP_DIR/component_paths.txt" | cut -d':' -f2-)
+    bin_dir="$component_path/bin"
+    [[ -d "$bin_dir" ]] || continue
+    while IFS= read -r f; do
+        # 只检查常见可执行/包后缀；无后缀的也检查
+        case "$f" in
+          *.sh) continue;;
+          *) :;;
+        esac
+        if is_lfs_pointer "$f"; then
+            log_error "检测到 Git LFS 指针文件: $f"
+            log_error "请在仓库根目录执行: git lfs fetch --all && git lfs checkout"
+            log_error "或确保 CI 在打包前已还原 LFS 大文件。"
+            rm -rf "$TEMP_DIR"
+            exit 1
+        fi
+    done < <(find "$bin_dir" -maxdepth 1 -type f 2>/dev/null | sort)
+done < "$COMPONENTS_FILE"
+log_success "LFS 校验通过：未发现指针文件"
+
 # 打包各个组件
 log_info "开始打包组件..."

@@ -234,7 +264,19 @@ while IFS= read -r component; do
    
    # 进入组件目录
    cd "$component_path"
-    
+
+    # 组件内二次防御：若包脚本缺失 LFS 校验，这里再次阻断
+    if [[ -d bin ]]; then
+      for f in bin/*; do
+        [[ -f "$f" ]] || continue
+        if head -n1 "$f" 2>/dev/null | grep -q '^version https://git-lfs.github.com/spec/v1$'; then
+          log_error "组件 $component 含 LFS 指针文件: $f"
+          log_error "请执行: git lfs fetch --all && git lfs checkout"
+          cd "$CURRENT_DIR"; rm -rf "$TEMP_DIR"; exit 1
+        fi
+      done
+    fi
+
    # 检查组件是否有 package.sh
    if [[ ! -f "package.sh" ]]; then
        log_error "$component 缺少 package.sh 文件"
--- a/src/metric/ftp/build/Dockerfile
+++ b/src/metric/ftp/build/Dockerfile
@@ -67,7 +67,8 @@ RUN chmod +x /usr/local/bin/start-ftp-supervised.sh
 COPY vsftpd.conf /etc/vsftpd/vsftpd.conf

 COPY dns-monitor.sh /usr/local/bin/dns-monitor.sh
-RUN chmod +x /usr/local/bin/dns-monitor.sh
+COPY dns-publish.sh /usr/local/bin/dns-publish.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh /usr/local/bin/dns-publish.sh

 USER root

--- a/src/metric/ftp/build/README.md
+++ b/src/metric/ftp/build/README.md
@@ -66,6 +66,17 @@ ${FTP_BASE_PATH}/

 /private/argus/etc/
 └── ${DOMAIN}                 # 容器IP记录文件
+
+## DNS 同步到 FTP share（运行期）
+
+- 运行期最新的 DNS 列表由 bind/master 写入挂载点 `/private/argus/etc/dns.conf`。
+- FTP 容器内置 `dns-publish`（Supervised）：每 10s 比较并将该文件原子同步为 `${FTP_BASE_PATH}/share/dns.conf`，供客户端下载安装脚本直接读取。
+- 同步特性：
+  - 原子更新：写入 `${DST}.tmp` 后 `mv -f` 覆盖，避免读到半写文件。
+  - 权限：0644；属主 `${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}`。
+  - 可观测：日志 `/var/log/supervisor/dns-publish.log`。
+
+> 注：构建/发布阶段可能也会将静态 `config/dns.conf` 拷贝到 share；当 FTP 容器运行后，dns-publish 会用运行期最新文件覆盖该静态文件。
 ```

 ## vsftpd 配置说明
@@ -156,4 +167,4 @@ curl -fsS 'ftp://ftpuser:ZGClab1234!@177.177.70.200/setup.sh' -o setup.sh
 # root用户直接执行，非root用户需要使用sudo
 chmod +x setup.sh
 bash setup.sh --server {$域名} --user ftpuser --password 'ZGClab1234!'
-```
+```
--- a/src/metric/ftp/build/dns-publish.sh
+++ b/src/metric/ftp/build/dns-publish.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+set -uo pipefail
+
+# Publish latest /private/argus/etc/dns.conf to ${FTP_BASE_PATH}/share/dns.conf
+
+SRC="/private/argus/etc/dns.conf"
+FTP_BASE_PATH="${FTP_BASE_PATH:-/private/argus/ftp}"
+DST_DIR="${FTP_BASE_PATH}/share"
+DST="${DST_DIR}/dns.conf"
+UID_VAL="${ARGUS_BUILD_UID:-2133}"
+GID_VAL="${ARGUS_BUILD_GID:-2015}"
+INTERVAL="${DNS_PUBLISH_INTERVAL:-10}"
+
+log() { echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Publish] $*"; }
+
+mkdir -p "$DST_DIR" 2>/dev/null || true
+
+log "service start: SRC=$SRC DST=$DST interval=${INTERVAL}s"
+
+while true; do
+  if [[ -f "$SRC" ]]; then
+    # Only sync when content differs
+    if ! cmp -s "$SRC" "$DST" 2>/dev/null; then
+      tmp="${DST}.tmp"
+      if cp "$SRC" "$tmp" 2>/dev/null; then
+        mv -f "$tmp" "$DST"
+        chown "$UID_VAL":"$GID_VAL" "$DST" 2>/dev/null || true
+        chmod 0644 "$DST" 2>/dev/null || true
+        ts_src=$(date -r "$SRC" '+%Y-%m-%dT%H:%M:%S%z' 2>/dev/null || echo "?")
+        log "synced dns.conf (src mtime=$ts_src) -> $DST"
+      else
+        log "ERROR: copy failed $SRC -> $tmp"
+      fi
+    fi
+  else
+    log "waiting for source $SRC"
+  fi
+  sleep "$INTERVAL"
+done
+
--- a/src/metric/ftp/build/supervisord.conf
+++ b/src/metric/ftp/build/supervisord.conf
@@ -28,6 +28,18 @@ stopwaitsecs=10
 killasgroup=true
 stopasgroup=true

+[program:dns-publish]
+command=/usr/local/bin/dns-publish.sh
+user=root
+stdout_logfile=/var/log/supervisor/dns-publish.log
+stderr_logfile=/var/log/supervisor/dns-publish_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
 [unix_http_server]
 file=/var/run/supervisor.sock
 chmod=0700
--- a/src/sys/tests/.gitignore
+++ b/src/sys/tests/.gitignore
@@ -0,0 +1,7 @@
+
+private/
+private-nodea/
+private-nodeb/
+tmp/
+
+.env
--- a/src/sys/tests/README.md
+++ b/src/sys/tests/README.md
@@ -1,13 +1,17 @@
 # ARGUS 系统级端到端测试（Sys E2E）

-本目录包含将 log 与 agent 两线验证合并后的系统级端到端测试。依赖 bind/master/es/kibana + 两个“日志节点”（每个节点容器内同时运行 Fluent Bit 与 argus-agent）。
+本目录包含将 log、metric 与 agent 三线验证合并后的系统级端到端测试。依赖 bind/master/es/kibana/metric(ftp+prometheus+grafana+alertmanager)/web-proxy/web-frontend + 两个“计算节点”（每个节点容器内同时运行 Fluent Bit 与 argus-agent）。

 ---

 ## 一、如何运行

 - 前置条件
-  - 已构建镜像：`argus-elasticsearch:latest`、`argus-kibana:latest`、`argus-bind9:latest`、`argus-master:latest`
+  - 已构建镜像：
+    - 基座：`argus-elasticsearch:latest`、`argus-kibana:latest`、`argus-bind9:latest`、`argus-master:latest`
+    - 节点：`argus-sys-node:latest`
+    - 指标：`argus-metric-ftp:latest`、`argus-metric-prometheus:latest`、`argus-metric-grafana:latest`、`argus-alertmanager:latest`
+    - 前端与代理：`argus-web-frontend:latest`、`argus-web-proxy:latest`
    - 可用根目录命令构建：`./build/build_images.sh [--intranet]`
  - 主机具备 Docker 与 Docker Compose。

@@ -33,11 +37,12 @@
 - 一键执行
  - `cd src/sys/tests`
  - `./scripts/00_e2e_test.sh`（CPU-only）或 `./scripts/00_e2e_test.sh --enable-gpu`（启用 GPU 流程）
+  - 可选：`--no-clean` 跳过清理，便于失败后现场排查

 - 分步执行（推荐用于排查）
  - `./scripts/01_bootstrap.sh` 生成目录/拷贝 `update-dns.sh`/构建 agent 二进制/写 `.env`
  - `./scripts/02_up.sh` 启动 Compose 栈（工程名 `argus-sys`）
-  - `./scripts/03_wait_ready.sh` 等待 ES/Kibana/Master/Fluent‑Bit/Bind 就绪（Kibana 必须返回 200 且 overall.level=available）
+  - `./scripts/03_wait_ready.sh` 等待 ES/Kibana/Master/Fluent‑Bit/Bind/Prometheus/Grafana/Alertmanager/Web‑Proxy 就绪（Kibana 必须 200 且 overall.level=available；Web‑Proxy 8084/8085 要有 CORS 头）
  - `./scripts/04_verify_dns_routing.sh` 校验 bind 解析与节点内域名解析
  - `./scripts/05_agent_register.sh` 获取两个节点的 `node_id` 与初始 IP，检查本地 `node.json`
  - `./scripts/06_write_health_and_assert.sh` 写健康文件并断言 `nodes.json` 仅包含 2 个在线节点
@@ -58,7 +63,7 @@
 ## 二、测试部署架构（docker-compose）

 - 网络
-  - 自定义 bridge：`argus-sys-net`，子网 `172.31.0.0/16`
+  - 自定义 bridge：`sysnet`（Compose 工程名为 `argus-sys` 时实际为 `argus-sys_sysnet`），子网 `172.31.0.0/16`
  - 固定地址：bind=`172.31.0.2`，master=`172.31.0.10`

 - 服务与端口（宿主机映射端口由 `01_bootstrap.sh` 自动分配并写入 `.env`）
@@ -66,9 +71,15 @@
  - `bind`（`argus-bind9:latest`）：监听 53/tcp+udp；负责同步 `*.argus.com` 记录
  - `master`（`argus-master:latest`）：对外 `${MASTER_PORT}→3000`；API `http://localhost:${MASTER_PORT}`
  - `es`（`argus-elasticsearch:latest`）：`${ES_HTTP_PORT}→9200`；单节点，无安全
-  - `kibana`（`argus-kibana:latest`）：`${KIBANA_PORT}→5601`；通过 `ELASTICSEARCH_HOSTS=http://es:9200` 访问 ES
-  - `node-a`（`ubuntu:22.04`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-nbnyx10-cp2f-pod-0`，`${NODE_A_PORT}→2020`
-  - `node-b`（`ubuntu:22.04`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-uuuu10-ep2f-pod-0`，`${NODE_B_PORT}→2020`
+  - `kibana`（`argus-kibana:latest`）：`${KIBANA_PORT}→5601`
+  - `node-a`（`argus-sys-node:latest`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-nbnyx10-cp2f-pod-0`，`${NODE_A_PORT}→2020`
+  - `node-b`（`argus-sys-node:latest`）：同时运行 Fluent Bit + argus-agent，`hostname=dev-yyrshare-uuuu10-ep2f-pod-0`，`${NODE_B_PORT}→2020`
+  - `ftp`（`argus-metric-ftp:latest`）：`${FTP_PORT}→21`/`${FTP_DATA_PORT}→20`/`${FTP_PASSIVE_HOST_RANGE}` 被动端口
+  - `prometheus`（`argus-metric-prometheus:latest`）：`${PROMETHEUS_PORT}→9090`
+  - `grafana`（`argus-metric-grafana:latest`）：`${GRAFANA_PORT}→3000`
+  - `alertmanager`（`argus-alertmanager:latest`）：`${ALERTMANAGER_PORT}→9093`
+  - `web-frontend`（`argus-web-frontend:latest`）：内部访问页面，使用 `web-proxy` 暴露的对外端口渲染超链
+  - `web-proxy`（`argus-web-proxy:latest`）：多端口转发 8080..8085（首页、Grafana、Prometheus、Kibana、Alertmanager、Master API）

 - 卷与目录
  - 核心服务（bind/master/es/kibana）共享宿主 `./private` 挂载到容器 `/private`
@@ -83,7 +94,7 @@

 - 节点入口
  - `scripts/node_entrypoint.sh`：
-    - 复制 `/assets/fluent-bit/*` 到容器 `/private`，后台启动 Fluent Bit（监听 2020）
+    - 离线优先：将 `/assets/fluent-bit/packages` 与 `etc` 拷贝到 `/private`，执行 `/private/start-fluent-bit.sh` 安装/拉起 Fluent Bit（监听 2020）
    - 以运行用户（映射 UID/GID）前台启动 `argus-agent`
  - 节点环境变量：`MASTER_ENDPOINT=http://master.argus.com:3000`、`REPORT_INTERVAL_SECONDS=2`、`ES_HOST=es`、`ES_PORT=9200`、`CLUSTER=local`、`RACK=dev`

@@ -106,6 +117,10 @@
    - Master `/readyz` 成功
    - Fluent Bit 指标接口 `:2020/:2021` 可访问
    - bind `named-checkconf` 通过
+    - Prometheus `/-/ready` 可用
+    - Grafana `GET /api/health` 返回 200 且 `database=ok`
+    - Alertmanager `GET /api/v2/status` 成功
+    - Web‑Proxy：8080 首页 200；8083 首页 200/302；8084/8085 对来自 8080 的请求需返回 `Access-Control-Allow-Origin`（CORS）

 - `04_verify_dns_routing.sh`
  - 目的：验证从 bind → 节点容器的解析链路
@@ -142,6 +157,28 @@

 ---

+## 注意事项（2025‑10‑29 更新）
+
+- 宿主 inotify 限制导致 03 卡住（Fluent Bit in_tail EMFILE）
+  - 现象：`03_wait_ready.sh` 一直等待 `:2020/:2021 /api/v2/metrics`；节点日志出现 `tail_fs_inotify.c errno=24 Too many open files`，Fluent Bit 启动失败。
+  - 根因：宿主 `fs.inotify.max_user_instances` 上限过低（常见默认 128），被其他进程占满；并非容器内 `ulimit -n` 过低。
+  - 处理：在宿主执行（临时）：
+    - `sudo sysctl -w fs.inotify.max_user_instances=1024 fs.inotify.max_user_watches=1048576`
+    - 建议永久：写入 `/etc/sysctl.d/99-argus-inotify.conf` 后 `sudo sysctl --system`
+  - 提示：节点入口里对 sysctl 的写操作不影响宿主；需在宿主调整。
+
+- Metric 安装制品包含 Git LFS 指针导致 node‑exporter 启动失败
+  - 现象：第 11 步在线安装后，日志显示 `Node Exporter 服务启动失败`；容器内 `/usr/local/bin/node-exporter` 头部是文本：`version https://git-lfs.github.com/spec/v1`。
+  - 根因：发布到 FTP 的安装包在打包前未执行 `git lfs fetch/checkout`，将指针文件打入制品。
+  - 处理：在仓库根目录执行 `git lfs fetch --all && git lfs checkout` 后，重跑 `src/metric/tests/scripts/02_publish_artifact.sh` 再重试 `11_metric_node_install.sh`。
+  - 防呆：已在 `all-in-one-full/scripts/package_artifact.sh` 与组件 `plugins/*/package.sh` 增加 LFS 指针校验，发现即失败并提示修复。
+
+建议：
+- 运行前检查宿主 inotify 值（≥1024/≥1048576）与宿主端口占用（8080..8085、9200/5601/9090/9093/2020/2021/32300 等）。
+- 如需排查失败，使用 `--no-clean` 保留现场，配合 `docker logs`、`curl` 与 `tmp/*.json` 进行定位。
+
+---
+
 如需更严格的断言（例如 Kibana 载入具体插件、ES 文档字段校验），可在 `07_*.sh` 中追加查询与校验逻辑。

 ---
Author	SHA1	Message	Date
yuyr	af7cfbe74b	[#37 ] 构建安装包	2025-10-30 11:21:05 +08:00
yuyr	3e38770473	[#30 ] ftp容器增加动态检测并更新dns.conf到share目录	2025-10-29 17:15:48 +08:00
yuyr	d130924b1a	[#30 ] wsl部署测试；更新README	2025-10-29 16:33:38 +08:00
@@ -1 +1 @@
 .35.0
 .38.0