当前部署情况 - h1: 部署server & client - h2: 部署client - 部署2025-11-25 - 部署目录: /home2/argus/server , /home2/argus/client - 部署使用账号:argus 网络拓扑: - h1 作为docker swarm manager - h2 作为worker加入docker swarm - docker swarm 上创建overlay network 访问方式: - 通过ssh到h1服务器,端口转发 20006-20011 端口到笔记本本地; - 门户网址:http://localhost:20006/dashboard 部署截图:    注意事项: - server各容器使用域名作为overlay network上alias别名,实现域名访问,当前版本禁用bind作为域名解析,原因是容器重启后IP变化场景bind机制复杂且不稳定。 - client 构建是内置安装包,容器启动时执行安装流程,后续重启容器跳过安装步骤。 - UID/GID:部署使用 argus账号 uid=2133, gid=2015。 Reviewed-on: #51 Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn> Reviewed-by: xuxt <xuxt@zgclab.edu.cn> Reviewed-by: huhy <husteryezi@163.com>
39 lines
1.2 KiB
YAML
39 lines
1.2 KiB
YAML
version: "3.8"
|
|
|
|
networks:
|
|
argus-sys-net:
|
|
external: true
|
|
|
|
services:
|
|
metric-gpu-node:
|
|
image: ${NODE_GPU_BUNDLE_IMAGE_TAG:-argus-sys-metric-test-node-bundle-gpu:${PKG_VERSION}}
|
|
container_name: argus-metric-gpu-node-swarm
|
|
hostname: ${GPU_NODE_HOSTNAME}
|
|
restart: unless-stopped
|
|
privileged: true
|
|
runtime: nvidia
|
|
environment:
|
|
- TZ=Asia/Shanghai
|
|
- DEBIAN_FRONTEND=noninteractive
|
|
- MASTER_ENDPOINT=${MASTER_ENDPOINT:-http://master.argus.com:3000}
|
|
# Fluent Bit / 日志上报目标(固定域名)
|
|
- ES_HOST=es.log.argus.com
|
|
- ES_PORT=9200
|
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
|
- AGENT_ENV=${AGENT_ENV}
|
|
- AGENT_USER=${AGENT_USER}
|
|
- AGENT_INSTANCE=${AGENT_INSTANCE}
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
- GPU_MODE=gpu
|
|
networks:
|
|
argus-sys-net:
|
|
aliases:
|
|
- ${AGENT_INSTANCE}.node.argus.com
|
|
volumes:
|
|
- ../private/argus/agent:/private/argus/agent
|
|
- ../logs/infer:/logs/infer
|
|
- ../logs/train:/logs/train
|
|
command: ["sleep", "infinity"]
|