[#39] 增加新docker compose部署方式，验证通过gpu部署；剩余fluent-bit logs目录权限问题以及 gpu bundle打包优化问题

2025-11-12 12:07:04 +08:00
parent 6837d96035
commit df1f519355
27 changed files with 1456 additions and 24 deletions
--- a/deployment_new/templates/server/scripts/config.sh
+++ b/deployment_new/templates/server/scripts/config.sh
@@ -0,0 +1,104 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+PKG_ROOT="$ROOT_DIR"
+ENV_EX="$PKG_ROOT/compose/.env.example"
+ENV_OUT="$PKG_ROOT/compose/.env"
+
+info(){ echo -e "\033[34m[CONFIG]\033[0m $*"; }
+err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
+require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
+
+require docker curl jq awk sed tar gzip
+
+# 磁盘空间检查（MB）
+check_disk(){ local p="$1"; local need=10240; local free
+  free=$(df -Pm "$p" | awk 'NR==2{print $4+0}')
+  if [[ -z "$free" || "$free" -lt "$need" ]]; then err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)"; return 1; fi
+}
+
+check_disk "$PKG_ROOT"; check_disk "/var/lib/docker" || true
+
+# 读取/生成 SWARM_MANAGER_ADDR
+SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}
+if [[ -z "${SWARM_MANAGER_ADDR}" ]]; then
+  read -rp "请输入本机管理地址 SWARM_MANAGER_ADDR: " SWARM_MANAGER_ADDR
+fi
+info "SWARM_MANAGER_ADDR=$SWARM_MANAGER_ADDR"
+
+# 校验 IP 属于本机网卡
+if ! ip -o addr | awk '{print $4}' | cut -d'/' -f1 | grep -qx "$SWARM_MANAGER_ADDR"; then
+  err "SWARM_MANAGER_ADDR 非本机地址: $SWARM_MANAGER_ADDR"; exit 1; fi
+
+info "开始分配服务端口（起始=20000，避免系统占用与相互冲突）"
+is_port_used(){ local p="$1"; ss -tulnH 2>/dev/null | awk '{print $5}' | sed 's/.*://g' | grep -qx "$p"; }
+declare -A PRESENT=() CHOSEN=() USED=()
+START_PORT="${START_PORT:-20000}"; cur=$START_PORT
+ORDER=(MASTER_PORT ES_HTTP_PORT KIBANA_PORT PROMETHEUS_PORT GRAFANA_PORT ALERTMANAGER_PORT \
+       WEB_PROXY_PORT_8080 WEB_PROXY_PORT_8081 WEB_PROXY_PORT_8082 WEB_PROXY_PORT_8083 WEB_PROXY_PORT_8084 WEB_PROXY_PORT_8085 \
+       FTP_PORT FTP_DATA_PORT)
+
+# 标记 .env.example 中实际存在的键
+for key in "${ORDER[@]}"; do
+  if grep -q "^${key}=" "$ENV_EX"; then PRESENT[$key]=1; fi
+done
+
+next_free(){ local p="$1"; while :; do if [[ -n "${USED[$p]:-}" ]] || is_port_used "$p"; then p=$((p+1)); else echo "$p"; return; fi; done; }
+
+for key in "${ORDER[@]}"; do
+  [[ -z "${PRESENT[$key]:-}" ]] && continue
+  p=$(next_free "$cur"); CHOSEN[$key]="$p"; USED[$p]=1; cur=$((p+1))
+done
+
+info "端口分配结果：MASTER=${CHOSEN[MASTER_PORT]:-} ES=${CHOSEN[ES_HTTP_PORT]:-} KIBANA=${CHOSEN[KIBANA_PORT]:-} PROM=${CHOSEN[PROMETHEUS_PORT]:-} GRAFANA=${CHOSEN[GRAFANA_PORT]:-} ALERT=${CHOSEN[ALERTMANAGER_PORT]:-} WEB_PROXY(8080..8085)=${CHOSEN[WEB_PROXY_PORT_8080]:-}/${CHOSEN[WEB_PROXY_PORT_8081]:-}/${CHOSEN[WEB_PROXY_PORT_8082]:-}/${CHOSEN[WEB_PROXY_PORT_8083]:-}/${CHOSEN[WEB_PROXY_PORT_8084]:-}/${CHOSEN[WEB_PROXY_PORT_8085]:-}"
+
+cp "$ENV_EX" "$ENV_OUT"
+# 覆盖端口（按唯一化结果写回）
+for key in "${ORDER[@]}"; do
+  val="${CHOSEN[$key]:-}"
+  [[ -z "$val" ]] && continue
+  sed -i -E "s#^$key=.*#$key=${val}#" "$ENV_OUT"
+done
+info "已写入 compose/.env 的端口配置"
+# 覆盖/补充 Overlay 名称
+grep -q '^ARGUS_OVERLAY_NET=' "$ENV_OUT" || echo 'ARGUS_OVERLAY_NET=argus-sys-net' >> "$ENV_OUT"
+# FTP 默认
+grep -q '^FTP_USER=' "$ENV_OUT" || echo 'FTP_USER=ftpuser' >> "$ENV_OUT"
+grep -q '^FTP_PASSWORD=' "$ENV_OUT" || echo 'FTP_PASSWORD=NASPlab1234!' >> "$ENV_OUT"
+# 以当前执行账户 UID/GID 写入（避免误选 docker 组）
+RUID=$(id -u)
+PRIMARY_GID=$(id -g)
+PRIMARY_GRP=$(id -gn)
+USER_NAME=$(id -un)
+# 若主组名被解析为 docker，尝试用与用户名同名的组的 GID；否则回退主 GID
+if [[ "$PRIMARY_GRP" == "docker" ]]; then
+  RGID=$(getent group "$USER_NAME" | awk -F: '{print $3}' 2>/dev/null || true)
+  [[ -z "$RGID" ]] && RGID="$PRIMARY_GID"
+else
+  RGID="$PRIMARY_GID"
+fi
+info "使用构建账户 UID:GID=${RUID}:${RGID} (user=$USER_NAME primary_group=$PRIMARY_GRP)"
+if grep -q '^ARGUS_BUILD_UID=' "$ENV_OUT"; then
+  sed -i -E "s#^ARGUS_BUILD_UID=.*#ARGUS_BUILD_UID=${RUID}#" "$ENV_OUT"
+else
+  echo "ARGUS_BUILD_UID=${RUID}" >> "$ENV_OUT"
+fi
+if grep -q '^ARGUS_BUILD_GID=' "$ENV_OUT"; then
+  sed -i -E "s#^ARGUS_BUILD_GID=.*#ARGUS_BUILD_GID=${RGID}#" "$ENV_OUT"
+else
+  echo "ARGUS_BUILD_GID=${RGID}" >> "$ENV_OUT"
+fi
+
+CI="$PKG_ROOT/cluster-info.env"
+if [[ -f "$CI" ]]; then
+  if grep -q '^SWARM_MANAGER_ADDR=' "$CI"; then
+    sed -i -E "s#^SWARM_MANAGER_ADDR=.*#SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}#" "$CI"
+  else
+    echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" >> "$CI"
+  fi
+else
+  echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" > "$CI"
+fi
+info "已生成 compose/.env 并更新 cluster-info.env 的 SWARM_MANAGER_ADDR。"
+info "下一步可执行: scripts/install.sh"
--- a/deployment_new/templates/server/scripts/diagnose.sh
+++ b/deployment_new/templates/server/scripts/diagnose.sh
@@ -0,0 +1,109 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
+
+ts="$(date -u +%Y%m%d-%H%M%SZ)"
+LOG_DIR="$ROOT/logs"; mkdir -p "$LOG_DIR" || true
+if ! ( : > "$LOG_DIR/.w" 2>/dev/null ); then LOG_DIR="/tmp/argus-logs"; mkdir -p "$LOG_DIR" || true; fi
+DETAILS="$LOG_DIR/diagnose_details_${ts}.log"; ERRORS="$LOG_DIR/diagnose_error_${ts}.log"; : > "$DETAILS"; : > "$ERRORS"
+
+logd() { echo "$(date '+%F %T') $*" >> "$DETAILS"; }
+append_err() { echo "$*" >> "$ERRORS"; }
+http_code() { curl -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
+http_body_head() { curl -s --max-time 3 "$1" 2>/dev/null | sed -n '1,5p' || true; }
+header_val() { curl -s -D - -o /dev/null "$@" | awk -F': ' 'BEGIN{IGNORECASE=1}$1=="Access-Control-Allow-Origin"{gsub("\r","",$2);print $2}'; }
+
+section() { local name="$1"; logd "===== [$name] ====="; }
+svc() {
+  local svc_name="$1"; local cname="$2"; shift 2
+  section "$svc_name ($cname)"
+  logd "docker ps:"; docker ps -a --format '{{.Names}}\t{{.Status}}\t{{.Image}}' | awk -v n="$cname" '$1==n' >> "$DETAILS" || true
+  logd "docker inspect:"; docker inspect -f '{{.State.Status}} rc={{.RestartCount}} started={{.State.StartedAt}}' "$cname" >> "$DETAILS" 2>&1 || true
+  logd "last 200 container logs:"; docker logs --tail 200 "$cname" >> "$DETAILS" 2>&1 || true
+  docker logs --tail 200 "$cname" 2>&1 | grep -Ei '\\b(error|failed|fail|exception|panic|fatal|critical|unhealthy|permission denied|forbidden|refused|traceback|错误|失败)\\b' | sed "s/^/[${svc_name}][container] /" >> "$ERRORS" || true
+  if docker exec "$cname" sh -lc 'command -v supervisorctl >/dev/null 2>&1' >/dev/null 2>&1; then
+    logd "supervisorctl status:"; docker exec "$cname" sh -lc 'supervisorctl status' >> "$DETAILS" 2>&1 || true
+    local files; files=$(docker exec "$cname" sh -lc 'ls /var/log/supervisor/*.log 2>/dev/null' || true)
+    for f in $files; do
+      logd "tail -n 80 $f:"; docker exec "$cname" sh -lc "tail -n 80 $f 2>/dev/null || true" >> "$DETAILS" 2>&1 || true
+      docker exec "$cname" sh -lc "tail -n 200 $f 2>/dev/null" 2>/dev/null | grep -Ei '\\b(error|failed|fail|exception|panic|fatal|critical|unhealthy|permission denied|forbidden|refused|traceback|错误|失败)\\b' | sed "s/^/[${svc_name}][supervisor:$(basename $f)] /" >> "$ERRORS" || true
+    done
+  fi
+}
+
+svc 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
+
+section HTTP
+logd "ES: $(http_code \"http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health\")"; http_body_head "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" >> "$DETAILS" 2>&1 || true
+logd "Kibana: $(http_code \"http://localhost:${KIBANA_PORT:-5601}/api/status\")"; http_body_head "http://localhost:${KIBANA_PORT:-5601}/api/status" >> "$DETAILS" 2>&1 || true
+logd "Master readyz: $(http_code \"http://localhost:${MASTER_PORT:-32300}/readyz\")"
+logd "Prometheus: $(http_code \"http://localhost:${PROMETHEUS_PORT:-9090}/-/ready\")"
+logd "Grafana: $(http_code \"http://localhost:${GRAFANA_PORT:-3000}/api/health\")"; http_body_head "http://localhost:${GRAFANA_PORT:-3000}/api/health" >> "$DETAILS" 2>&1 || true
+logd "Alertmanager: $(http_code \"http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status\")"
+cors8084=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8084:-8084}/api/v2/status" || true)
+cors8085=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
+logd "Web-Proxy 8080: $(http_code \"http://localhost:${WEB_PROXY_PORT_8080:-8080}/\")"
+logd "Web-Proxy 8083: $(http_code \"http://localhost:${WEB_PROXY_PORT_8083:-8083}/\")"
+logd "Web-Proxy 8084 CORS: ${cors8084}"
+logd "Web-Proxy 8085 CORS: ${cors8085}"
+
+section ES-CHECKS
+ch=$(curl -s --max-time 3 "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" || true)
+status=$(printf '%s' "$ch" | awk -F'\"' '/"status"/{print $4; exit}')
+if [[ -n "$status" ]]; then logd "cluster.status=$status"; fi
+if [[ "$status" != "green" ]]; then append_err "[es][cluster] status=$status"; fi
+if docker ps --format '{{.Names}}' | grep -q '^argus-es-sys$'; then
+  duse=$(docker exec argus-es-sys sh -lc 'df -P /usr/share/elasticsearch/data | awk "NR==2{print \$5}"' 2>/dev/null || true)
+  logd "es.data.df_use=$duse"; usep=${duse%%%}
+  if [[ -n "$usep" ]] && (( usep >= 90 )); then append_err "[es][disk] data path usage=${usep}%"; fi
+fi
+
+section DNS-IN-PROXY
+for d in master.argus.com es.log.argus.com kibana.log.argus.com grafana.metric.argus.com prom.metric.argus.com alertmanager.alert.argus.com; do
+  docker exec argus-web-proxy sh -lc "getent hosts $d || nslookup $d 2>/dev/null | tail -n+1" >> "$DETAILS" 2>&1 || true
+done
+logd "HTTP (web-proxy): master.readyz=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://master.argus.com:3000/readyz\" 2>/dev/null || echo 000)"
+logd "HTTP (web-proxy): es.health=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://es.log.argus.com:9200/_cluster/health\" 2>/dev/null || echo 000)"
+logd "HTTP (web-proxy): kibana.status=$(docker exec argus-web-proxy sh -lc \"curl -s -o /dev/null -w '%{http_code}' http://kibana.log.argus.com:5601/api/status\" 2>/dev/null || echo 000)"
+
+section FTP-SHARE
+docker exec argus-ftp sh -lc 'ls -ld /private/argus/ftp /private/argus/ftp/share; test -w /private/argus/ftp/share && echo "write:OK" || echo "write:FAIL"' >> "$DETAILS" 2>&1 || true
+
+section SYSTEM
+logd "uname -a:"; uname -a >> "$DETAILS"
+logd "docker version:"; docker version --format '{{.Server.Version}}' >> "$DETAILS" 2>&1 || true
+logd "compose ps:"; (cd "$ROOT/compose" && docker compose ps) >> "$DETAILS" 2>&1 || true
+
+section SUMMARY
+[[ $(http_code "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health") != 200 ]] && echo "[es][http] health not 200" >> "$ERRORS"
+kbcode=$(http_code "http://localhost:${KIBANA_PORT:-5601}/api/status"); [[ "$kbcode" != 200 ]] && echo "[kibana][http] /api/status=$kbcode" >> "$ERRORS"
+[[ $(http_code "http://localhost:${MASTER_PORT:-32300}/readyz") != 200 ]] && echo "[master][http] /readyz not 200" >> "$ERRORS"
+[[ $(http_code "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready") != 200 ]] && echo "[prometheus][http] /-/ready not 200" >> "$ERRORS"
+gfcode=$(http_code "http://localhost:${GRAFANA_PORT:-3000}/api/health"); [[ "$gfcode" != 200 ]] && echo "[grafana][http] /api/health=$gfcode" >> "$ERRORS"
+[[ $(http_code "http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status") != 200 ]] && echo "[alertmanager][http] /api/v2/status not 200" >> "$ERRORS"
+[[ -z "$cors8084" ]] && echo "[web-proxy][cors] 8084 missing Access-Control-Allow-Origin" >> "$ERRORS"
+[[ -z "$cors8085" ]] && echo "[web-proxy][cors] 8085 missing Access-Control-Allow-Origin" >> "$ERRORS"
+sort -u -o "$ERRORS" "$ERRORS"
+
+echo "Diagnostic details -> $DETAILS"
+echo "Detected errors   -> $ERRORS"
+
+if [[ "$LOG_DIR" == "$ROOT/logs" ]]; then
+  ln -sfn "$(basename "$DETAILS")" "$ROOT/logs/diagnose_details.log" 2>/dev/null || cp "$DETAILS" "$ROOT/logs/diagnose_details.log" 2>/dev/null || true
+  ln -sfn "$(basename "$ERRORS")"  "$ROOT/logs/diagnose_error.log"   2>/dev/null || cp "$ERRORS"  "$ROOT/logs/diagnose_error.log"   2>/dev/null || true
+fi
+
+exit 0
--- a/deployment_new/templates/server/scripts/es-watermark-relax.sh
+++ b/deployment_new/templates/server/scripts/es-watermark-relax.sh
@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+set -euo pipefail
+HOST="${1:-http://127.0.0.1:9200}"
+echo "设置 ES watermark 为 95%/96%/97%: $HOST"
+curl -fsS -XPUT "$HOST/_cluster/settings" -H 'Content-Type: application/json' -d '{
+  "transient": {
+    "cluster.routing.allocation.disk.watermark.low": "95%",
+    "cluster.routing.allocation.disk.watermark.high": "96%",
+    "cluster.routing.allocation.disk.watermark.flood_stage": "97%"
+  }
+}' && echo "\nOK"
--- a/deployment_new/templates/server/scripts/es-watermark-restore.sh
+++ b/deployment_new/templates/server/scripts/es-watermark-restore.sh
@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+set -euo pipefail
+HOST="${1:-http://127.0.0.1:9200}"
+echo "恢复 ES watermark 为默认值: $HOST"
+curl -fsS -XPUT "$HOST/_cluster/settings" -H 'Content-Type: application/json' -d '{
+  "transient": {
+    "cluster.routing.allocation.disk.watermark.low": null,
+    "cluster.routing.allocation.disk.watermark.high": null,
+    "cluster.routing.allocation.disk.watermark.flood_stage": null
+  }
+}' && echo "\nOK"
--- a/deployment_new/templates/server/scripts/install.sh
+++ b/deployment_new/templates/server/scripts/install.sh
@@ -0,0 +1,167 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+PKG_ROOT="$ROOT_DIR"
+ENV_FILE="$PKG_ROOT/compose/.env"
+COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
+
+info(){ echo -e "\033[34m[INSTALL]\033[0m $*"; }
+err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
+require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
+require docker curl jq awk sed tar gzip
+
+[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env，请先运行 scripts/config.sh"; exit 1; }
+info "使用环境文件: $ENV_FILE"
+set -a; source "$ENV_FILE"; set +a
+# 兼容：若 .env 未包含 SWARM_MANAGER_ADDR，则从已存在的 cluster-info.env 读取以避免写空
+SMADDR="${SWARM_MANAGER_ADDR:-}"
+CI_FILE="$PKG_ROOT/cluster-info.env"
+if [[ -z "$SMADDR" && -f "$CI_FILE" ]]; then
+  SMADDR=$(sed -n 's/^SWARM_MANAGER_ADDR=\(.*\)$/\1/p' "$CI_FILE" | head -n1)
+fi
+SWARM_MANAGER_ADDR="$SMADDR"
+
+# Swarm init & overlay
+if ! docker info 2>/dev/null | grep -q "Swarm: active"; then
+  [[ -n "${SWARM_MANAGER_ADDR:-}" ]] || { err "SWARM_MANAGER_ADDR 未设置，请在 scripts/config.sh 中配置"; exit 1; }
+  info "初始化 Swarm (--advertise-addr $SWARM_MANAGER_ADDR)"
+  docker swarm init --advertise-addr "$SWARM_MANAGER_ADDR" >/dev/null 2>&1 || true
+else
+  info "Swarm 已激活"
+fi
+NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
+if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
+  info "创建 overlay 网络: $NET_NAME"
+  docker network create -d overlay --attachable "$NET_NAME" >/dev/null
+else
+  info "overlay 网络已存在: $NET_NAME"
+fi
+
+# Load images
+IMAGES_DIR="$PKG_ROOT/images"
+shopt -s nullglob
+tars=("$IMAGES_DIR"/*.tar.gz)
+if [[ ${#tars[@]} -eq 0 ]]; then err "images 目录为空，缺少镜像 tar.gz"; exit 1; fi
+total=${#tars[@]}; idx=0
+for tgz in "${tars[@]}"; do
+  idx=$((idx+1))
+  info "导入镜像 ($idx/$total): $(basename "$tgz")"
+  tmp=$(mktemp); gunzip -c "$tgz" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
+done
+shopt -u nullglob
+
+# Compose up
+info "启动服务栈 (docker compose up -d)"
+docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
+docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
+
+# Wait readiness (best-effort)
+code(){ curl -4 -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
+prom_ok(){ (exec 3<>/dev/tcp/127.0.0.1/${PROMETHEUS_PORT:-9090}) >/dev/null 2>&1 && return 0 || return 1; }
+kb_ok(){ local body; body=$(curl -s "http://127.0.0.1:${KIBANA_PORT:-5601}/api/status" || true); echo "$body" | grep -q '"level"\s*:\s*"available"'; }
+RETRIES=${RETRIES:-60}; SLEEP=${SLEEP:-5}; ok=0
+info "等待基础服务就绪 (<= $((RETRIES*SLEEP))s)"
+for i in $(seq 1 "$RETRIES"); do
+  e1=$(code "http://127.0.0.1:${MASTER_PORT:-32300}/readyz")
+  e2=$(code "http://127.0.0.1:${ES_HTTP_PORT:-9200}/_cluster/health")
+  e3=000; prom_ok && e3=200
+  e4=$(code "http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health")
+  e5=$(code "http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status")
+  e6=$(kb_ok && echo 200 || echo 000)
+  info "[ready] t=$((i*SLEEP))s master=$e1 es=$e2 prom=$e3 graf=$e4 alert=$e5 kibana=$e6"
+  [[ "$e1" == 200 ]] && ok=$((ok+1))
+  [[ "$e2" == 200 ]] && ok=$((ok+1))
+  [[ "$e3" == 200 ]] && ok=$((ok+1))
+  [[ "$e4" == 200 ]] && ok=$((ok+1))
+  [[ "$e5" == 200 ]] && ok=$((ok+1))
+  [[ "$e6" == 200 ]] && ok=$((ok+1))
+  if [[ $ok -ge 6 ]]; then break; fi; ok=0; sleep "$SLEEP"
+done
+[[ $ok -ge 6 ]] || err "部分服务未就绪（可稍后重试 selfcheck）"
+
+# Resolve overlay IPs
+bind_c=argus-bind-sys; ftp_c=argus-ftp
+BINDIP=$(docker inspect -f '{{ (index .NetworkSettings.Networks "'$NET_NAME'").IPAddress }}' "$bind_c" 2>/dev/null || true)
+FTPIP=$(docker inspect -f '{{ (index .NetworkSettings.Networks "'$NET_NAME'").IPAddress }}' "$ftp_c" 2>/dev/null || true)
+info "解析 overlay IP: BINDIP=${BINDIP:-<empty>} FTPIP=${FTPIP:-<empty>}"
+
+# Swarm join tokens
+TOKEN_WORKER=$(docker swarm join-token -q worker 2>/dev/null || echo "")
+TOKEN_MANAGER=$(docker swarm join-token -q manager 2>/dev/null || echo "")
+
+# cluster-info.env
+CI="$PKG_ROOT/cluster-info.env"
+info "写入 cluster-info.env (manager/token/IP)"
+{
+  echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
+  echo "BINDIP=${BINDIP:-}"
+  echo "FTPIP=${FTPIP:-}"
+  echo "SWARM_JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
+  echo "SWARM_JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
+} > "$CI"
+info "已输出 $CI"
+
+# 安装报告
+ts=$(date +%Y%m%d-%H%M%S)
+RPT="$PKG_ROOT/安装报告_${ts}.md"
+{
+  echo "# Argus Server 安装报告 (${ts})"
+  echo
+  echo "## 端口映射"
+  echo "- MASTER_PORT=${MASTER_PORT}"
+  echo "- ES_HTTP_PORT=${ES_HTTP_PORT}"
+  echo "- KIBANA_PORT=${KIBANA_PORT}"
+  echo "- PROMETHEUS_PORT=${PROMETHEUS_PORT}"
+  echo "- GRAFANA_PORT=${GRAFANA_PORT}"
+  echo "- ALERTMANAGER_PORT=${ALERTMANAGER_PORT}"
+  echo "- WEB_PROXY_PORT_8080=${WEB_PROXY_PORT_8080} ... 8085=${WEB_PROXY_PORT_8085}"
+  echo
+  echo "## Swarm/Overlay"
+  echo "- SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}" 
+  echo "- NET=${NET_NAME}"
+  echo "- JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
+  echo "- JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
+  echo
+  echo "## Overlay IPs"
+  echo "- BINDIP=${BINDIP:-}"
+  echo "- FTPIP=${FTPIP:-}"
+  echo
+  echo "## 健康检查（简要）"
+  echo "- master/readyz=$(code http://127.0.0.1:${MASTER_PORT:-32300}/readyz)"
+  echo "- es/_cluster/health=$(code http://127.0.0.1:${ES_HTTP_PORT:-9200}/_cluster/health)"
+  echo "- grafana/api/health=$(code http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health)"
+  echo "- prometheus/tcp=$([[ $(prom_ok; echo $?) == 0 ]] && echo 200 || echo 000)"
+  echo "- alertmanager/api/v2/status=$(code http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status)"
+  echo "- kibana/api/status=$([[ $(kb_ok; echo $?) == 0 ]] && echo available || echo not-ready)"
+} > "$RPT"
+info "已生成报告: $RPT"
+
+info "安装完成。可将 cluster-info.env 分发给 Client-GPU 安装方。"
+
+# 写入域名→overlay IP 并热更新 Bind/Nginx
+ETC_DIR="$PKG_ROOT/private/argus/etc"; mkdir -p "$ETC_DIR"
+declare -A MAP
+MAP[web-frontend]=web.argus.com
+MAP[argus-grafana]=grafana.metric.argus.com
+MAP[argus-prometheus]=prom.metric.argus.com
+MAP[argus-kibana-sys]=kibana.log.argus.com
+MAP[argus-alertmanager]=alertmanager.alert.argus.com
+MAP[argus-master-sys]=master.argus.com
+changed=0
+for cname in "${!MAP[@]}"; do
+  domain="${MAP[$cname]}"; fpath="$ETC_DIR/$domain"
+  ip=$(docker inspect -f '{{ (index .NetworkSettings.Networks "'$NET_NAME'").IPAddress }}' "$cname" 2>/dev/null || true)
+  [[ -z "$ip" ]] && { echo "[DNS-FIX][WARN] $domain: container $cname no overlay IP yet"; continue; }
+  cur=$(cat "$fpath" 2>/dev/null || echo "")
+  if [[ "$cur" != "$ip" ]]; then
+    echo "$ip" > "$fpath"; echo "[DNS-FIX][SET] $domain = $ip (was: ${cur:-<empty>})"; changed=1
+  else
+    echo "[DNS-FIX][OK] $domain already $ip"
+  fi
+done
+if [[ $changed -eq 1 ]]; then
+  docker exec argus-bind-sys /usr/local/bin/reload-bind9.sh >/dev/null 2>&1 || docker exec argus-bind-sys rndc reload >/dev/null 2>&1 || true
+  sleep 1
+fi
+docker exec argus-web-proxy nginx -t >/dev/null 2>&1 && docker exec argus-web-proxy nginx -s reload >/dev/null 2>&1 || true
--- a/deployment_new/templates/server/scripts/selfcheck.sh
+++ b/deployment_new/templates/server/scripts/selfcheck.sh
@@ -0,0 +1,89 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+log() { echo -e "\033[0;34m[CHECK]\033[0m $*"; }
+err() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
+
+ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
+
+wait_http() { local url="$1"; local attempts=${2:-120}; local i=1; while ((i<=attempts)); do curl -fsS "$url" >/dev/null 2>&1 && return 0; echo "[..] waiting $url ($i/$attempts)"; sleep 5; ((i++)); done; return 1; }
+code_for() { curl -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
+header_val() { curl -s -D - -o /dev/null "$@" | awk -F': ' 'BEGIN{IGNORECASE=1}$1=="Access-Control-Allow-Origin"{gsub("\r","",$2);print $2}'; }
+
+LOG_DIR="$ROOT/logs"; mkdir -p "$LOG_DIR" || true
+OUT_JSON="$LOG_DIR/selfcheck.json"; tmp=$(mktemp)
+
+ok=1
+
+log "checking overlay network"
+net_ok=false
+if docker network inspect "${ARGUS_OVERLAY_NET:-argus-sys-net}" >/dev/null 2>&1; then
+  if docker network inspect "${ARGUS_OVERLAY_NET:-argus-sys-net}" | grep -q '"Driver": "overlay"'; then net_ok=true; fi
+fi
+[[ "$net_ok" == true ]] || ok=0
+
+log "checking Elasticsearch"
+wait_http "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" 60 || ok=0
+
+log "checking Kibana"
+kb_code=$(code_for "http://localhost:${KIBANA_PORT:-5601}/api/status")
+kb_ok=false
+if [[ "$kb_code" == 200 ]]; then
+  body=$(curl -sS "http://localhost:${KIBANA_PORT:-5601}/api/status" || true)
+  echo "$body" | grep -q '"level"\s*:\s*"available"' && kb_ok=true
+fi
+[[ "$kb_ok" == true ]] || ok=0
+
+log "checking Master"
+[[ $(code_for "http://localhost:${MASTER_PORT:-32300}/readyz") == 200 ]] || ok=0
+
+log "checking FTP"
+if docker ps --format '{{.Names}}' | grep -q '^argus-ftp$'; then
+  docker exec argus-ftp sh -lc 'test -w /private/argus/ftp/share' >/dev/null 2>&1 || ok=0
+else ok=0; fi
+
+log "checking Prometheus"
+wait_http "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready" 60 || ok=0
+
+log "checking Grafana"
+gf_code=$(code_for "http://localhost:${GRAFANA_PORT:-3000}/api/health")
+gf_ok=false; if [[ "$gf_code" == 200 ]]; then body=$(curl -sS "http://localhost:${GRAFANA_PORT:-3000}/api/health" || true); echo "$body" | grep -q '"database"\s*:\s*"ok"' && gf_ok=true; fi
+[[ "$gf_ok" == true ]] || ok=0
+
+log "checking Alertmanager"
+wait_http "http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status" 60 || ok=0
+
+log "checking Web-Proxy (CORS)"
+cors8084=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8084:-8084}/api/v2/status" || true)
+cors8085=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
+wp_ok=true
+[[ -n "$cors8084" && -n "$cors8085" ]] || wp_ok=false
+[[ "$wp_ok" == true ]] || ok=0
+
+cat > "$tmp" <<JSON
+{
+  "overlay_net": $net_ok,
+  "es": true,
+  "kibana": $kb_ok,
+  "master_readyz": true,
+  "ftp_share_writable": true,
+  "prometheus": true,
+  "grafana": $gf_ok,
+  "alertmanager": true,
+  "web_proxy_cors": $wp_ok,
+  "timestamp": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
+}
+JSON
+
+mv "$tmp" "$OUT_JSON" 2>/dev/null || cp "$tmp" "$OUT_JSON"
+
+if [[ "$ok" == 1 ]]; then
+  log "selfcheck OK -> $OUT_JSON"
+  exit 0
+else
+  err "selfcheck FAILED -> $OUT_JSON"
+  exit 1
+fi
--- a/deployment_new/templates/server/scripts/status.sh
+++ b/deployment_new/templates/server/scripts/status.sh
@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -euo pipefail
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+PKG_ROOT="$ROOT_DIR"
+ENV_FILE="$PKG_ROOT/compose/.env"
+COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
+docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
--- a/deployment_new/templates/server/scripts/uninstall.sh
+++ b/deployment_new/templates/server/scripts/uninstall.sh
@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+set -euo pipefail
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+PKG_ROOT="$ROOT_DIR"
+ENV_FILE="$PKG_ROOT/compose/.env"
+COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
+echo "[UNINSTALL] stopping compose"
+docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
+echo "[UNINSTALL] done"