[#49] 移除bind/ftp，改成使用docker 自带域名解析，实现重启后IP变化仍正常访问，完成swarm test通过

2025-11-18 15:10:38 +08:00 · 2025-11-18 15:10:38 +08:00 · 1d38304936
commit 1d38304936
parent 5b617f62a8
9 changed files with 49 additions and 108 deletions
--- a/src/sys/swarm_tests/README.md
+++ b/src/sys/swarm_tests/README.md
@ -4,7 +4,7 @@

 ## 先决条件
 - Docker Engine 已启用 Swarm（脚本会自动 `swarm init` 单机模式）。
- 已构建并加载以下镜像：`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`、以及节点镜像 `argus-sys-metric-test-node-bundle:latest`（见下文）。
+- 已构建并加载以下镜像：`argus-master:latest`、`argus-elasticsearch:latest`、`argus-kibana:latest`、`argus-metric-prometheus:latest`、`argus-metric-grafana:latest`、`argus-alertmanager:latest`、`argus-web-frontend:latest`、`argus-web-proxy:latest`、以及节点镜像 `argus-sys-metric-test-node-bundle:latest`（见下文）。
 - 本地 `UID/GID` 建议通过 `configs/build_user.local.conf` 指定，脚本会读取：
  - `UID=1000`\n`GID=1000`（示例）。

@ -24,7 +24,7 @@ cp .env.example .env

 bash scripts/00_bootstrap.sh
 bash scripts/01_server_up.sh
-bash scripts/02_wait_ready.sh   # 输出 BINDIP/FTPIP 到 .env.nodes
+bash scripts/02_wait_ready.sh   # 写 MASTER_ENDPOINT/AGENT_* 到 .env.nodes
 bash scripts/03_nodes_up.sh
 bash scripts/04_metric_verify.sh
 ```
@ -38,7 +38,7 @@ bash scripts/99_down.sh
 ## 说明与注意事项
 - `00_bootstrap.sh`：先加载 `scripts/common/build_user.sh`，打印并写入 `.env` 中的 `ARGUS_BUILD_UID/GID`，再准备 `private-server/` 与 `private-nodes/` 目录，并 `chown` 到对应 UID/GID。
 - `01_server_up.sh`：启动服务端 compose。可用 `SWARM_FIX_PERMS=1` 打开“容器内 chmod + supervisor 重启”的兜底逻辑，默认关闭。
- `02_wait_ready.sh`：等待 Master/ES/Prom/Grafana 就绪（Kibana 可延迟），随后解析 overlay IP，写入 `.env.nodes` 的 `BINDIP/FTPIP`，供节点 compose 使用。
+- `02_wait_ready.sh`：等待 Master/ES/Prom/Grafana 就绪（Kibana 可延迟），随后写入 `.env.nodes` 的 `MASTER_ENDPOINT/AGENT_*`，供节点 compose 使用（DNS 由 Docker 自带服务负责，不再依赖 BINDIP/FTPIP）。
 - `03_nodes_up.sh`：启动单节点容器（bundle 版）。容器内 `node-bootstrap.sh` 优先本地安装，成功后执行健康检查并等待 `/private/argus/agent/<hostname>/node.json` 出现。
 - `04_metric_verify.sh`：在本套件内执行详细校验（不再直接调用 tests 脚本）：
  - Grafana `/api/health`（database=ok）
--- a/src/sys/swarm_tests/docker-compose.gpu-node.yml
+++ b/src/sys/swarm_tests/docker-compose.gpu-node.yml
@ -16,10 +16,6 @@ services:
      - TZ=Asia/Shanghai
      - DEBIAN_FRONTEND=noninteractive
      - MASTER_ENDPOINT=${MASTER_ENDPOINT:-http://master.argus.com:3000}
-      - FTPIP=${FTPIP}
-      - BINDIP=${BINDIP}
-      - FTP_USER=${FTP_USER:-ftpuser}
-      - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
      - AGENT_ENV=${AGENT_ENV:-dev2}
@ -28,9 +24,10 @@ services:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - GPU_MODE=gpu
-    dns:
-      - ${BINDIP}
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - ${AGENT_INSTANCE}.node.argus.com
    volumes:
      - ./private-gpu-nodes/argus/agent:/private/argus/agent
    command: ["sleep", "infinity"]
--- a/src/sys/swarm_tests/docker-compose.nodes.yml
+++ b/src/sys/swarm_tests/docker-compose.nodes.yml
@ -16,19 +16,16 @@ services:
      - MASTER_ENDPOINT=${MASTER_ENDPOINT:-http://master.argus.com:3000}
      - ES_HOST=es.log.argus.com
      - ES_PORT=9200
-      - FTPIP=${FTPIP}
-      - BINDIP=${BINDIP}
-      - FTP_USER=${FTP_USER:-ftpuser}
-      - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
      - AGENT_ENV=${AGENT_ENV:-dev2}
      - AGENT_USER=${AGENT_USER:-yuyr}
      - AGENT_INSTANCE=${AGENT_INSTANCE:-node001sX}
      - CLIENT_VERSION=${CLIENT_VERSION:-}
-    dns:
-      - ${BINDIP}
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - ${AGENT_INSTANCE}.node.argus.com
    volumes:
      - ./private-nodes/argus/agent:/private/argus/agent
    command: ["sleep", "infinity"]
--- a/src/sys/swarm_tests/docker-compose.server.yml
+++ b/src/sys/swarm_tests/docker-compose.server.yml
@ -5,18 +5,10 @@ networks:
    external: true

 services:
-  bind:
-    image: ${BIND_IMAGE_TAG:-argus-bind9:latest}
-    container_name: argus-bind-sys
-    networks: [argus-sys-net]
-    volumes:
-      - ./private-server:/private
-    restart: unless-stopped
-
  master:
    image: ${MASTER_IMAGE_TAG:-argus-master:latest}
    container_name: argus-master-sys
-    depends_on: [bind]
+    depends_on: []
    environment:
      - OFFLINE_THRESHOLD_SECONDS=6
      - ONLINE_THRESHOLD_SECONDS=2
@ -29,7 +21,10 @@ services:
      - ./private-server/argus/master:/private/argus/master
      - ./private-server/argus/metric/prometheus:/private/argus/metric/prometheus
      - ./private-server/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - master.argus.com
    restart: unless-stopped

  es:
@ -47,7 +42,10 @@ 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: ${KIBANA_IMAGE_TAG:-argus-kibana:latest}
@ -63,27 +61,10 @@ services:
    ports:
      - "${KIBANA_PORT:-5601}:5601"
    restart: unless-stopped
-    networks: [argus-sys-net]
-
-  ftp:
-    image: ${FTP_IMAGE_TAG:-argus-metric-ftp:latest}
-    container_name: argus-ftp
-    restart: unless-stopped
-    environment:
-      - TZ=Asia/Shanghai
-      - FTP_BASE_PATH=/private/argus/ftp
-      - FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
-      - 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-server/argus/metric/ftp:/private/argus/ftp
-      - ./private-server/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:latest}
@ -99,7 +80,10 @@ services:
    volumes:
      - ./private-server/argus/metric/prometheus:/private/argus/metric/prometheus
      - ./private-server/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:latest}
@ -122,7 +106,10 @@ services:
      - ./private-server/argus/metric/grafana:/private/argus/metric/grafana
      - ./private-server/argus/etc:/private/argus/etc
    depends_on: [prometheus]
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - grafana.metric.argus.com

  alertmanager:
    image: ${ALERT_IMAGE_TAG:-argus-alertmanager:latest}
@ -133,7 +120,10 @@ services:
    volumes:
      - ./private-server/argus/etc:/private/argus/etc
      - ./private-server/argus/alert/alertmanager:/private/argus/alert/alertmanager
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - alertmanager.alert.argus.com
    ports:
      - "${ALERTMANAGER_PORT:-9093}:9093"
    restart: unless-stopped
@ -151,19 +141,25 @@ services:
      - EXTERNAL_KIBANA_PORT=${WEB_PROXY_PORT_8083:-8083}
    volumes:
      - ./private-server/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - web.argus.com
    restart: unless-stopped

  web-proxy:
    image: ${WEB_PROXY_IMAGE_TAG:-argus-web-proxy:latest}
    container_name: argus-web-proxy
-    depends_on: [bind, master, grafana, prometheus, kibana, alertmanager]
+    depends_on: [master, grafana, prometheus, kibana, alertmanager]
    environment:
      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
    volumes:
      - ./private-server/argus/etc:/private/argus/etc
-    networks: [argus-sys-net]
+    networks:
+      argus-sys-net:
+        aliases:
+          - proxy.argus.com
    ports:
      - "${WEB_PROXY_PORT_8080:-8080}:8080"
      - "${WEB_PROXY_PORT_8081:-8081}:8081"
--- a/src/sys/swarm_tests/scripts/00_bootstrap.sh
+++ b/src/sys/swarm_tests/scripts/00_bootstrap.sh
@ -42,7 +42,6 @@ echo "[BOOT] preparing private directories (server/nodes)"
 # Server-side dirs (align with sys/tests 01_bootstrap.sh)
 mkdir -p \
  "$ROOT/private-server/argus/etc" \
-  "$ROOT/private-server/argus/bind" \
  "$ROOT/private-server/argus/master" \
  "$ROOT/private-server/argus/metric/prometheus" \
  "$ROOT/private-server/argus/metric/prometheus/data" \
@ -72,11 +71,9 @@ chown -R "$uid":"$gid" \
  "$ROOT/private-server/argus/metric/grafana" \
  "$ROOT/private-server/argus/metric/prometheus" \
  "$ROOT/private-server/argus/alert" \
-  "$ROOT/private-server/argus/metric/ftp" \
  "$ROOT/private-server/argus/agent" \
  "$ROOT/private-server/argus/etc" 2>/dev/null || true

-# group-writable for etc/alert as in sys/tests
 chmod -R g+w "$ROOT/private-server/argus/alert" "$ROOT/private-server/argus/etc" 2>/dev/null || true

 # ensure .env carries the resolved UID/GID for compose env interpolation
@ -91,11 +88,4 @@ else
  echo "ARGUS_BUILD_GID=${gid}" >> "$ENV_FILE"
 fi

-# distribute update-dns.sh
-BIND_UPDATE_SRC="$REPO_ROOT/src/bind/build/update-dns.sh"
-BIND_UPDATE_DEST="$ROOT/private-server/argus/etc/update-dns.sh"
-if [[ -f "$BIND_UPDATE_SRC" ]]; then
-  cp "$BIND_UPDATE_SRC" "$BIND_UPDATE_DEST" && chmod +x "$BIND_UPDATE_DEST" || true
-fi
-
 echo "[BOOT] done"
--- a/src/sys/swarm_tests/scripts/02_wait_ready.sh
+++ b/src/sys/swarm_tests/scripts/02_wait_ready.sh
@ -36,49 +36,12 @@ done

 if [[ $ok -lt 4 ]]; then echo "[ERROR] services not ready" >&2; exit 1; fi

-echo "[READY] resolving overlay IPs"
-BINDIP=$(docker inspect -f '{{ (index .NetworkSettings.Networks "argus-sys-net").IPAddress }}' argus-bind-sys)
-FTPIP=$(docker inspect -f '{{ (index .NetworkSettings.Networks "argus-sys-net").IPAddress }}' argus-ftp)
-echo "BINDIP=$BINDIP FTPIP=$FTPIP"
-
 ENV_NODES="$ROOT/.env.nodes"
 cat > "$ENV_NODES" <<EOF
-BINDIP=$BINDIP
-FTPIP=$FTPIP
 MASTER_ENDPOINT=http://master.argus.com:3000
-FTP_USER=ftpuser
-FTP_PASSWORD=ZGClab1234!
 AGENT_ENV=dev2
 AGENT_USER=yuyr
 AGENT_INSTANCE=node001sX
 EOF

-echo "[READY] wrote $ENV_NODES"
-
-# Inline: fix domain records -> actual overlay IPs and reload bind/nginx (best-effort)
-echo "[READY] fixing domain records to overlay IPs"
-ETC_DIR="$ROOT/private-server/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=$(docker inspect -f '{{ (index .NetworkSettings.Networks "argus-sys-net").IPAddress }}' "$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 || true
-  sleep 1
-fi
-docker exec argus-web-proxy nginx -s reload >/dev/null 2>&1 || true
+echo "[READY] wrote $ENV_NODES (MASTER_ENDPOINT/AGENT_* only)"
--- a/src/sys/swarm_tests/scripts/04_metric_verify.sh
+++ b/src/sys/swarm_tests/scripts/04_metric_verify.sh
@ -81,8 +81,8 @@ fi
 docker exec argus-grafana sh -lc "grep -E 'url:\s*http://$PROM_DOMAIN' '$DS_FILE'" >/dev/null 2>&1 || fail "datasource not pointing to $PROM_DOMAIN"
 ok "datasource points to domain"

-# ---- DNS resolution inside grafana ----
-info "bind resolution inside grafana"
+# ---- DNS resolution inside grafana (via Docker DNS + FQDN alias) ----
+info "FQDN resolution inside grafana (Docker DNS)"
 tries=0
 until docker exec argus-grafana getent hosts prom.metric.argus.com >/dev/null 2>&1; do
  tries=$((tries+1)); (( tries > 24 )) && fail "grafana cannot resolve prom.metric.argus.com"
--- a/src/sys/swarm_tests/scripts/05a_net_warmup.sh
+++ b/src/sys/swarm_tests/scripts/05a_net_warmup.sh
@ -21,7 +21,6 @@ else
  docker run -d --rm \
    --name "$WARMUP_NAME" \
    --network "$NET_NAME" \
-    ${BINDIP:+--dns "$BINDIP"} \
    "$WARMUP_IMAGE" sleep "$WARMUP_SECONDS"
  rc=$?
  set -e
@ -43,4 +42,3 @@ done

 echo "[WARN] network still not inspectable locally after 60s, but warmup container is running. Compose may still pass; proceed to run GPU compose and retry if needed." >&2
 exit 0
-
--- a/src/sys/swarm_tests/tmp/metric-verify/prom_targets.json
+++ b/src/sys/swarm_tests/tmp/metric-verify/prom_targets.json
@ -1 +1 @@
-{"status":"success","data":{"activeTargets":[{"discoveredLabels":{"__address__":"10.0.1.13:9400","__meta_filepath":"/private/argus/metric/prometheus/targets/dcgm_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.13","job":"dcgm","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.13","job":"dcgm","node_id":"A1","user_id":"yuyr"},"scrapePool":"dcgm","scrapeUrl":"http://10.0.1.13:9400/metrics","globalUrl":"http://10.0.1.13:9400/metrics","lastError":"","lastScrape":"2025-11-14T16:20:36.702023128+08:00","lastScrapeDuration":0.001054193,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"},{"discoveredLabels":{"__address__":"10.0.1.13:9100","__meta_filepath":"/private/argus/metric/prometheus/targets/node_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.13","job":"node","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.13","job":"node","node_id":"A1","user_id":"yuyr"},"scrapePool":"node","scrapeUrl":"http://10.0.1.13:9100/metrics","globalUrl":"http://10.0.1.13:9100/metrics","lastError":"","lastScrape":"2025-11-14T16:20:34.338081675+08:00","lastScrapeDuration":0.019183536,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"}],"droppedTargets":[],"droppedTargetCounts":{"dcgm":0,"node":0}}}
+{"status":"success","data":{"activeTargets":[{"discoveredLabels":{"__address__":"10.0.1.20:9400","__meta_filepath":"/private/argus/metric/prometheus/targets/dcgm_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.20","job":"dcgm","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"dcgm-exporter-A1","ip":"10.0.1.20","job":"dcgm","node_id":"A1","user_id":"yuyr"},"scrapePool":"dcgm","scrapeUrl":"http://10.0.1.20:9400/metrics","globalUrl":"http://10.0.1.20:9400/metrics","lastError":"","lastScrape":"2025-11-18T15:02:15.071897295+08:00","lastScrapeDuration":0.001115439,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"},{"discoveredLabels":{"__address__":"10.0.1.20:9100","__meta_filepath":"/private/argus/metric/prometheus/targets/node_exporter.json","__metrics_path__":"/metrics","__scheme__":"http","__scrape_interval__":"15s","__scrape_timeout__":"10s","hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.20","job":"node","node_id":"A1","user_id":"yuyr"},"labels":{"hostname":"swarm-metric-node-001","instance":"node-exporter-A1","ip":"10.0.1.20","job":"node","node_id":"A1","user_id":"yuyr"},"scrapePool":"node","scrapeUrl":"http://10.0.1.20:9100/metrics","globalUrl":"http://10.0.1.20:9100/metrics","lastError":"","lastScrape":"2025-11-18T15:02:12.57609087+08:00","lastScrapeDuration":0.020143969,"health":"up","scrapeInterval":"15s","scrapeTimeout":"10s"}],"droppedTargets":[],"droppedTargetCounts":{"dcgm":0,"node":0}}}