[#49] swarm test重启测试通过

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

@@ -19,10 +19,6 @@ services:
       # Fluent Bit / 日志上报目标（固定域名）
       - ES_HOST=es.log.argus.com
       - ES_PORT=9200
-      - FTPIP=${FTPIP}
-      - BINDIP=${BINDIP}
-      - FTP_USER=${FTP_USER:-ftpuser}
-      - FTP_PASSWORD=${FTP_PASSWORD:-NASPlab1234!}
       - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
       - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
       - AGENT_ENV=${AGENT_ENV}
@@ -31,9 +27,10 @@ services:
       - NVIDIA_VISIBLE_DEVICES=all
       - NVIDIA_DRIVER_CAPABILITIES=compute,utility
       - GPU_MODE=gpu
-    dns:
-      - ${BINDIP}
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - ${AGENT_INSTANCE}.node.argus.com
     volumes:
       - ../private/argus/agent:/private/argus/agent
       - ../logs/infer:/logs/infer

deployment_new/templates/client_gpu/docs/INSTALL_CLIENT_zh.md

@@ -12,7 +12,7 @@
   su - argus -c 'id; docker ps >/dev/null && echo OK || echo NO_DOCKER_PERMISSION'
   ```
   后续解压与执行（config/install/uninstall）均使用 `argus` 账户进行。
-- 从 Server 安装方拿到 `cluster-info.env`（包含 `SWARM_MANAGER_ADDR/BINDIP/FTPIP/SWARM_JOIN_TOKEN_*`）。
+- 从 Server 安装方拿到 `cluster-info.env`（包含 `SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_*`；compose 架构下 BINDIP/FTPIP 不再使用）。
 
 ## 二、解包
 - `tar -xzf client_gpu_YYYYMMDD.tar.gz`
@@ -28,13 +28,13 @@ cp /path/to/cluster-info.env ./   # 或 export CLUSTER_INFO=/abs/path/cluster-in
 脚本做了什么：
 - 读取 `cluster-info.env` 并 `docker swarm join`（幂等）；
 - 自动用 busybox 预热 external overlay `argus-sys-net`，等待最多 60s 直到本机可见；
-- 生成/更新 `compose/.env`：填入 `BINDIP/FTPIP/SWARM_*`，并“保留你已填写的 AGENT_* 与 GPU_NODE_HOSTNAME”（不会覆盖）。
+- 生成/更新 `compose/.env`：填入 `SWARM_*`，并“保留你已填写的 AGENT_* 与 GPU_NODE_HOSTNAME”（不会覆盖）。
 
 看到什么才算成功：
 - 终端输出类似：`已预热 overlay=argus-sys-net 并生成 compose/.env；可执行 scripts/install.sh`；
 - `compose/.env` 至少包含：
   - `AGENT_ENV/AGENT_USER/AGENT_INSTANCE/GPU_NODE_HOSTNAME`（需要你提前填写）；
-  - `BINDIP/FTPIP/SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_*`；
+  - `SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_*`；
  - `NODE_GPU_BUNDLE_IMAGE_TAG=...:YYYYMMDD`。
 
 ### 日志映射（重要）

deployment_new/templates/client_gpu/scripts/config.sh

@@ -50,18 +50,16 @@ fi
 # 预热容器（worker 侧加入 overlay 以便本地可见）
 docker rm -f argus-net-warmup >/dev/null 2>&1 || true
 info "启动 warmup 容器加入 overlay: $NET_NAME"
-docker run -d --rm --name argus-net-warmup --network "$NET_NAME" ${BINDIP:+--dns "$BINDIP"} busybox:latest sleep 600 >/dev/null 2>&1 || true
+docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
 for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && { info "overlay 可见 (t=${i}s)"; break; }; sleep 1; done
 docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 manager 已创建并网络可达"; exit 1; }
 
-# 从 warmup 容器内测试连通性（必须能 ping 通 BINDIP 与 FTPIP）
-ping_ok(){ docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 $1 >/dev/null 2>&1"; }
-if [[ -n "${BINDIP:-}" ]]; then
-  ping_ok "$BINDIP" || { err "容器内无法 ping 通 BINDIP=$BINDIP；请检查 overlay 与 Bind9 容器状态"; exit 1; }
-fi
-if [[ -n "${FTPIP:-}" ]]; then
-  ping_ok "$FTPIP" || { err "容器内无法 ping 通 FTPIP=$FTPIP；请检查 overlay 与 FTP 容器状态"; exit 1; }
+# 通过 warmup 容器测试实际数据通路（alias → master）
+if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
+  err "warmup 容器内无法通过别名访问 master.argus.com；请确认 server compose 已启动并加入 overlay $NET_NAME"
+  exit 1
 fi
+info "warmup 容器内可达 master.argus.com（Docker DNS + alias 正常）"
 
 # 生成/更新 .env（保留人工填写项，不覆盖已有键）
 if [[ ! -f "$ENV_OUT" ]]; then
@@ -70,8 +68,6 @@ fi
 
 set_kv(){ local k="$1" v="$2"; if grep -q "^${k}=" "$ENV_OUT"; then sed -i -E "s#^${k}=.*#${k}=${v}#" "$ENV_OUT"; else echo "${k}=${v}" >> "$ENV_OUT"; fi }
 
-set_kv BINDIP "${BINDIP:-}"
-set_kv FTPIP "${FTPIP:-}"
 set_kv SWARM_MANAGER_ADDR "${SWARM_MANAGER_ADDR:-}"
 set_kv SWARM_JOIN_TOKEN_WORKER "${SWARM_JOIN_TOKEN_WORKER:-}"
 set_kv SWARM_JOIN_TOKEN_MANAGER "${SWARM_JOIN_TOKEN_MANAGER:-}"

deployment_new/templates/client_gpu/scripts/install.sh

@@ -26,24 +26,24 @@ set -a; source "$ENV_FILE"; set +a
 NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
 info "检查 overlay 网络可见性: $NET_NAME"
 if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
-  # 如 Overlay 不可见，尝试用 busybox 预热
+  # 如 Overlay 不可见，尝试用 busybox 预热（仅为确保 worker 节点已加入 overlay）
   if ! docker image inspect busybox:latest >/dev/null 2>&1; then
     if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then docker load -i "$PKG_ROOT/images/busybox.tar"; else err "缺少 busybox 镜像（images/busybox.tar 或本地 busybox:latest）"; exit 1; fi
   fi
   docker rm -f argus-net-warmup >/dev/null 2>&1 || true
-  docker run -d --rm --name argus-net-warmup --network "$NET_NAME" ${BINDIP:+--dns "$BINDIP"} busybox:latest sleep 600 >/dev/null 2>&1 || true
+  docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
   for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && break; sleep 1; done
   docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 manager 已创建并网络可达"; exit 1; }
   info "overlay 已可见（warmup=argus-net-warmup）"
 fi
 
-# 容器内连通性检查：BINDIP 与 FTPIP 可达
-ping_ok(){ docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 $1 >/dev/null 2>&1"; }
-if [[ -n "${BINDIP:-}" ]]; then
-  if ping_ok "$BINDIP"; then info "warmup 内可达 BINDIP=$BINDIP"; else err "容器内无法 ping 通 BINDIP=$BINDIP"; exit 1; fi
-fi
-if [[ -n "${FTPIP:-}" ]]; then
-  if ping_ok "$FTPIP"; then info "warmup 内可达 FTPIP=$FTPIP"; else err "容器内无法 ping 通 FTPIP=$FTPIP"; exit 1; fi
+# 若本函数内重新创建了 warmup 容器，同样测试一次 alias 数据通路
+if docker ps --format '{{.Names}}' | grep -q '^argus-net-warmup$'; then
+  if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
+    err "GPU install 阶段：warmup 容器内无法通过别名访问 master.argus.com；请检查 overlay $NET_NAME 与 server 状态"
+    exit 1
+  fi
+  info "GPU install 阶段：warmup 容器内可达 master.argus.com"
 fi
 
 # 导入 GPU bundle 镜像

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

@@ -5,18 +5,9 @@ networks:
     external: true
 
 services:
-  bind:
-    image: ${BIND_IMAGE_TAG:-argus-bind9:${PKG_VERSION}}
-    container_name: argus-bind-sys
-    networks: [argus-sys-net]
-    volumes:
-      - ../private:/private
-    restart: unless-stopped
-
   master:
     image: ${MASTER_IMAGE_TAG:-argus-master:${PKG_VERSION}}
     container_name: argus-master-sys
-    depends_on: [bind]
     environment:
       - OFFLINE_THRESHOLD_SECONDS=6
       - ONLINE_THRESHOLD_SECONDS=2
@@ -29,7 +20,10 @@ services:
       - ../private/argus/master:/private/argus/master
       - ../private/argus/metric/prometheus:/private/argus/metric/prometheus
       - ../private/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - master.argus.com
     restart: unless-stopped
 
   es:
@@ -47,7 +41,10 @@ services:
     ports:
       - "${ES_HTTP_PORT:-9200}:9200"
     restart: unless-stopped
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - es.log.argus.com
 
   kibana:
     image: ${KIBANA_IMAGE_TAG:-argus-kibana:${PKG_VERSION}}
@@ -63,27 +60,10 @@ services:
     ports:
       - "${KIBANA_PORT:-5601}:5601"
     restart: unless-stopped
-    networks: [argus-sys-net]
-
-  ftp:
-    image: ${FTP_IMAGE_TAG:-argus-metric-ftp:${PKG_VERSION}}
-    container_name: argus-ftp
-    restart: unless-stopped
-    environment:
-      - TZ=Asia/Shanghai
-      - FTP_BASE_PATH=/private/argus/ftp
-      - FTP_PASSWORD=${FTP_PASSWORD:-NASPlab1234!}
-      - DOMAIN=${FTP_DOMAIN:-ftp.metric.argus.com}
-      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
-      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
-    ports:
-      - "${FTP_PORT:-21}:21"
-      - "${FTP_DATA_PORT:-20}:20"
-      - "${FTP_PASSIVE_HOST_RANGE:-21100-21110}:21100-21110"
-    volumes:
-      - ../private/argus/metric/ftp:/private/argus/ftp
-      - ../private/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - kibana.log.argus.com
 
   prometheus:
     image: ${PROM_IMAGE_TAG:-argus-metric-prometheus:${PKG_VERSION}}
@@ -99,7 +79,10 @@ services:
     volumes:
       - ../private/argus/metric/prometheus:/private/argus/metric/prometheus
       - ../private/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - prom.metric.argus.com
 
   grafana:
     image: ${GRAFANA_IMAGE_TAG:-argus-metric-grafana:${PKG_VERSION}}
@@ -122,7 +105,10 @@ services:
       - ../private/argus/metric/grafana:/private/argus/metric/grafana
       - ../private/argus/etc:/private/argus/etc
     depends_on: [prometheus]
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - grafana.metric.argus.com
 
   alertmanager:
     image: ${ALERT_IMAGE_TAG:-argus-alertmanager:${PKG_VERSION}}
@@ -133,7 +119,10 @@ services:
     volumes:
       - ../private/argus/etc:/private/argus/etc
       - ../private/argus/alert/alertmanager:/private/argus/alert/alertmanager
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - alertmanager.alert.argus.com
     ports:
       - "${ALERTMANAGER_PORT:-9093}:9093"
     restart: unless-stopped
@@ -151,19 +140,25 @@ services:
       - EXTERNAL_KIBANA_PORT=${WEB_PROXY_PORT_8083:-8083}
     volumes:
       - ../private/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - web.argus.com
     restart: unless-stopped
 
   web-proxy:
     image: ${WEB_PROXY_IMAGE_TAG:-argus-web-proxy:${PKG_VERSION}}
     container_name: argus-web-proxy
-    depends_on: [bind, master, grafana, prometheus, kibana, alertmanager]
+    depends_on: [master, grafana, prometheus, kibana, alertmanager]
     environment:
       - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
       - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
     volumes:
       - ../private/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - proxy.argus.com
     ports:
       - "${WEB_PROXY_PORT_8080:-8080}:8080"
       - "${WEB_PROXY_PORT_8081:-8081}:8081"
@@ -172,4 +167,3 @@ services:
       - "${WEB_PROXY_PORT_8084:-8084}:8084"
       - "${WEB_PROXY_PORT_8085:-8085}:8085"
     restart: unless-stopped
-

deployment_new/templates/server/docs/INSTALL_SERVER_zh.md

@@ -71,7 +71,7 @@ export SWARM_MANAGER_ADDR=<本机管理IP>
 - 等待“六项就绪”：
   - Master `/readyz`=200、ES `/_cluster/health`=200、Prometheus TCP 可达、Grafana `/api/health`=200、Alertmanager `/api/v2/status`=200、Kibana `/api/status` level=available；
 - 将各服务 overlay IP 写入 `private/argus/etc/<域名>`，Reload Bind9 与 Nginx；
-- 写出 `cluster-info.env`（含 `BINDIP/FTPIP/SWARM_JOIN_TOKEN_{WORKER,MANAGER}/SWARM_MANAGER_ADDR`）；
+- 写出 `cluster-info.env`（含 `SWARM_JOIN_TOKEN_{WORKER,MANAGER}/SWARM_MANAGER_ADDR`；compose 架构下不再依赖 BINDIP/FTPIP）；
 - 生成 `安装报告_YYYYMMDD-HHMMSS.md`（端口、健康检查摘要与提示）。
 
 看到什么才算成功：
@@ -79,7 +79,7 @@ export SWARM_MANAGER_ADDR=<本机管理IP>
 - `安装报告_…md` 中各项 HTTP 检查为 200/available；
 - `cluster-info.env` 包含五个关键键：
   - `SWARM_MANAGER_ADDR=...`
-  - `BINDIP=10.x.x.x` `FTPIP=10.x.x.x`
+  - `SWARM_MANAGER_ADDR=...` `SWARM_JOIN_TOKEN_*=...`
   - `SWARM_JOIN_TOKEN_WORKER=SWMTKN-...`
   - `SWARM_JOIN_TOKEN_MANAGER=SWMTKN-...`
 

deployment_new/templates/server/scripts/install.sh

@@ -88,23 +88,15 @@ for i in $(seq 1 "$RETRIES"); do
 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
+# cluster-info.env（compose 场景下不再依赖 BINDIP/FTPIP）
 CI="$PKG_ROOT/cluster-info.env"
-info "写入 cluster-info.env (manager/token/IP)"
+info "写入 cluster-info.env (manager/token)"
 {
   echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
-  echo "BINDIP=${BINDIP:-}"
-  echo "FTPIP=${FTPIP:-}"
   echo "SWARM_JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
   echo "SWARM_JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
 } > "$CI"
@@ -131,10 +123,6 @@ RPT="$PKG_ROOT/安装报告_${ts}.md"
   echo "- JOIN_TOKEN_WORKER=${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:${ES_HTTP_PORT:-9200}/_cluster/health)"
@@ -146,30 +134,4 @@ RPT="$PKG_ROOT/安装报告_${ts}.md"
 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