Claude
33294af477
Spark 4.1.2 requires Java 17 at runtime (it boots a JVM via the bin/spark-submit shell script). The previous Dockerfile only installed curl, ca-certificates, and tar — leaving spark-submit unable to find the 'java' binary. A JRE is sufficient (not the full JDK) because spark-submit does not compile Java at runtime — it loads pre-built JARs from $SPARK_HOME/jars/. JRE-only keeps the image ~160 MB smaller than JDK-headless. Sets JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64 and prepends it to PATH so spark-submit (which checks JAVA_HOME) finds the right JVM. Combined with the prior yarn-REST rewrite, the runtime image now needs exactly three things in addition to python:3.12-slim: - uv (from ghcr.io/astral-sh/uv) - openjdk-17-jre-headless - Spark 4.1.2 from Tsinghua mirror
65 lines
2.0 KiB
Docker
65 lines
2.0 KiB
Docker
# syntax=docker/dockerfile:1
|
|
#
|
|
# Spark Executor MCP — runtime image.
|
|
# Build deps with uv (frozen, prod-only), then drop in the source on top of
|
|
# python:3.12-slim with Spark + YARN configs mounted for the spark-submit /
|
|
# yarn CLI calls inside the MCP tools.
|
|
|
|
FROM python:3.12-slim
|
|
|
|
# --- uv (official binary) ---
|
|
COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /usr/local/bin/
|
|
|
|
# --- Spark + Hadoop config (matches the original Dockerfile) ---
|
|
|
|
ARG SPARK_VERSION=4.1.2
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
curl \
|
|
ca-certificates \
|
|
tar \
|
|
openjdk-17-jre-headless && \
|
|
curl -L \
|
|
https://mirrors.tuna.tsinghua.edu.cn/apache/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop3.tgz \
|
|
-o /tmp/spark.tgz && \
|
|
mkdir -p /opt && \
|
|
tar -xzf /tmp/spark.tgz -C /opt && \
|
|
mv /opt/spark-${SPARK_VERSION}-bin-hadoop3 /opt/spark && \
|
|
rm -f /tmp/spark.tgz && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
ENV JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64
|
|
ENV SPARK_HOME=/opt/spark
|
|
ENV PATH=${JAVA_HOME}/bin:${SPARK_HOME}/bin:${PATH}
|
|
|
|
# Hadoop/Yarn 配置目录（运行时挂载）
|
|
RUN mkdir -p /etc/hadoop/conf
|
|
|
|
# 默认值，可在 docker run 时覆盖
|
|
ENV HADOOP_CONF_DIR=/etc/hadoop/conf
|
|
ENV YARN_CONF_DIR=/etc/hadoop/conf
|
|
|
|
# --- App ---
|
|
WORKDIR /app
|
|
|
|
# Install Python deps first so this layer caches independently of source.
|
|
# --frozen pins to uv.lock exactly; --no-dev skips pytest etc. for a slim
|
|
# production image; --no-install-project defers copying the source.
|
|
COPY pyproject.toml uv.lock ./
|
|
RUN uv sync --index-url=https://pypi.tuna.tsinghua.edu.cn/simple/ --frozen --no-dev --no-install-project
|
|
|
|
# Now copy the source and let uv wire it in.
|
|
COPY main.py ./
|
|
COPY spark_executor ./spark_executor
|
|
COPY common ./common
|
|
RUN uv sync --index-url=https://pypi.tuna.tsinghua.edu.cn/simple/ --frozen --no-dev
|
|
|
|
# Put the venv on PATH so `python` / `uvicorn` resolve to the project env.
|
|
ENV PATH=/app/.venv/bin:$PATH
|
|
ENV PYTHONUNBUFFERED=1
|
|
|
|
EXPOSE 8000
|
|
CMD ["python", "main.py"]
|