GPU-Health-eXpert/Dockerfile.ghx-server at main · FanKang2021/GPU-Health-eXpert · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
# GHX (GPU Health Expert) 统一服务Dockerfile
# 整合了数据收集和节点状态查询功能
FROM python:3.9-slim

# 设置工作目录
WORKDIR /app

# 安装系统依赖，使用清华源
RUN sed -i 's|http://deb.debian.org|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/debian.sources \
    && sed -i 's|http://snapshot.debian.org|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/debian.sources \
    && apt-get update && apt-get install -y \
    curl \
    wget \
    gnupg2 \
    lsb-release \
    sqlite3 \
    && rm -rf /var/lib/apt/lists/*

# 安装kubectl
RUN curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" \
    && chmod +x kubectl \
    && mv kubectl /usr/local/bin/

# 安装kubectl-resource-view
COPY kubectl-resource-view /usr/local/bin/kubectl-resource-view
RUN chmod +x /usr/local/bin/kubectl-resource-view

# 复制应用代码和依赖文件
COPY ghx_server.py /app/
COPY backend_rate_limit.py /app/
# COPY job-template.yaml /app/  #已通过configmap传递

# 安装Python依赖（包含频率限制相关依赖）
RUN pip install Flask Flask-CORS Werkzeug flask-limiter kubernetes -i https://pypi.tuna.tsinghua.edu.cn/simple

# 创建共享目录和日志目录
RUN mkdir -p /shared/gpu-inspection-results/cron \
    && mkdir -p /var/log

# 暴露端口（统一使用5000端口）
EXPOSE 5000

# 启动命令
CMD ["python", "ghx_server.py"]