diff --git a/infra/docker/worker.Dockerfile b/infra/docker/worker.Dockerfile index b11078b8f..4fc1ff980 100755 --- a/infra/docker/worker.Dockerfile +++ b/infra/docker/worker.Dockerfile @@ -1,48 +1,104 @@ # ============================================================ -# Worker Dockerfile - 专门用于 Celery Worker -# 优化:依赖分层缓存,基础大包和业务依赖分开 +# Worker Dockerfile - 优化版(多阶段构建 + 镜像瘦身) +# 优化项: +# 1. 多阶段构建:builder 阶段安装编译依赖,runtime 阶段只保留运行时 +# 2. ffmpeg 静态编译替换:从 apt 安装(457MB) 改为静态二进制(~80MB) +# 3. Python 依赖瘦身:strip .so 调试符号 + 清理测试文件 + 清理缓存 # ============================================================ -# 基础镜像:Python 3.12 + ffmpeg -FROM git.xiaoxiajianji.com/xiaoxia/base/python:3.12-slim +# ==================== Builder 阶段 ==================== +FROM git.xiaoxiajianji.com/xiaoxia/base/python:3.12-slim AS builder -# 构建参数:版本号(CI 传入 commit hash) +# 使用阿里云镜像加速 +RUN sed -i 's|deb.debian.org|mirrors.aliyun.com|g' /etc/apt/sources.list.d/debian.sources 2>/dev/null || \ + sed -i 's|deb.debian.org|mirrors.aliyun.com|g' /etc/apt/sources.list 2>/dev/null || true + +# 安装编译工具(仅 builder 需要) +RUN apt-get update && apt-get install -y --no-install-recommends \ + gcc \ + g++ \ + python3-dev \ + binutils \ + wget \ + xz-utils \ + && rm -rf /var/lib/apt/lists/* + +# ---- 下载静态编译 ffmpeg ---- +# 使用 johnvansickle.com 的静态编译版本(业界标准) +RUN cd /tmp \ + && wget -q https://johnvansickle.com/ffmpeg/releases/ffmpeg-release-amd64-static.tar.xz \ + && tar xf ffmpeg-release-amd64-static.tar.xz \ + && cp ffmpeg-*-amd64-static/ffmpeg /usr/local/bin/ffmpeg \ + && cp ffmpeg-*-amd64-static/ffprobe /usr/local/bin/ffprobe \ + && chmod +x /usr/local/bin/ffmpeg /usr/local/bin/ffprobe \ + && rm -rf ffmpeg-* + +# ---- 安装 Python 依赖 ---- +WORKDIR /tmp + +# 创建 venv +RUN python -m venv /opt/venv +ENV PATH="/opt/venv/bin:$PATH" + +# 基础依赖 +COPY requirements-base.txt /tmp/requirements-base.txt +RUN pip install --no-cache-dir -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com \ + -r /tmp/requirements-base.txt \ + && rm /tmp/requirements-base.txt + +# Worker 专属大包 +COPY requirements-worker.txt /tmp/requirements-worker.txt +RUN pip install --no-cache-dir -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com \ + -r /tmp/requirements-worker.txt \ + && rm /tmp/requirements-worker.txt + +# 业务依赖 +COPY requirements.txt /tmp/requirements.txt +RUN pip install --no-cache-dir -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com \ + -r /tmp/requirements.txt \ + && rm /tmp/requirements.txt + +# ---- Python 依赖瘦身 ---- +# 1. strip .so 文件的调试符号(节省约 80-100MB) +RUN find /opt/venv -name "*.so" -type f -exec strip --strip-all {} \; 2>/dev/null || true + +# 2. 清理测试文件(节省约 20MB) +RUN find /opt/venv -type d -name "tests" -exec rm -rf {} + 2>/dev/null; \ + find /opt/venv -type d -name "test" -exec rm -rf {} + 2>/dev/null; \ + find /opt/venv -name "test_*.py" -delete 2>/dev/null || true + +# 3. 清理 .pyc 缓存和 __pycache__(节省约 10MB,运行时按需生成) +RUN find /opt/venv -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null; \ + find /opt/venv -name "*.pyc" -delete 2>/dev/null || true + +# 4. 清理 dist-info 中的文档 +RUN find /opt/venv -name "*.dist-info" -type d -exec sh -c 'rm -f "$1"/DESCRIPTION.rst "$1"/INSTALLER "$1"/LICENSE* "$1"/WHEEL "$1"/entry_points.txt' _ {} \; 2>/dev/null || true + +# ==================== Runtime 阶段 ==================== +FROM git.xiaoxiajianji.com/xiaoxia/base/python:3.12-slim AS runtime + +# 构建参数:版本号 ARG APP_VERSION=dev # 使用阿里云镜像加速 RUN sed -i 's|deb.debian.org|mirrors.aliyun.com|g' /etc/apt/sources.list.d/debian.sources 2>/dev/null || \ sed -i 's|deb.debian.org|mirrors.aliyun.com|g' /etc/apt/sources.list 2>/dev/null || true -# 安装系统依赖 +# 安装最小运行时依赖(opencv-python-headless 需要 libglib2.0-0) RUN apt-get update && apt-get install -y --no-install-recommends \ - ffmpeg \ - libsm6 \ - libxext6 \ - libgl1 \ + libglib2.0-0 \ && rm -rf /var/lib/apt/lists/* +# 从 builder 复制 ffmpeg 静态二进制 +COPY --from=builder /usr/local/bin/ffmpeg /usr/local/bin/ffmpeg +COPY --from=builder /usr/local/bin/ffprobe /usr/local/bin/ffprobe + +# 从 builder 复制 Python 虚拟环境 +COPY --from=builder /opt/venv /opt/venv + # 设置工作目录 WORKDIR /app -# ---- 依赖分层:基础依赖(变化少,缓存命中率高)---- -COPY requirements-base.txt /tmp/requirements-base.txt - -RUN python -m venv /opt/venv \ - && /opt/venv/bin/pip install --no-cache-dir -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com -r /tmp/requirements-base.txt \ - && rm /tmp/requirements-base.txt - -# ---- 依赖分层:Worker 专属大包(视频处理,变化极少)---- -COPY requirements-worker.txt /tmp/requirements-worker.txt - -RUN /opt/venv/bin/pip install --no-cache-dir -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com -r /tmp/requirements-worker.txt \ - && rm /tmp/requirements-worker.txt - -# ---- 依赖分层:业务依赖(变化频繁)---- -COPY requirements.txt /tmp/requirements.txt - -RUN /opt/venv/bin/pip install --no-cache-dir -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com -r /tmp/requirements.txt \ - && rm /tmp/requirements.txt - # 复制应用代码 COPY apps/worker/ /app/apps/worker/ COPY apps/api/app/config.py /app/apps/api/app/config.py @@ -51,7 +107,7 @@ COPY packages/ /app/packages/ COPY alembic.ini /app/alembic.ini COPY migrations/ /app/migrations/ -# 复制 Worker 启动脚本(支持 WORKER_CONCURRENCY 环境变量) +# 复制 Worker 启动脚本 COPY infra/docker/entrypoint-worker.sh /usr/local/bin/entrypoint-worker.sh RUN chmod +x /usr/local/bin/entrypoint-worker.sh