Dataproc サーバーレス用 Spark でカスタム コンテナを使用する

# Recommendation: Use Debian 12.
FROM debian:12-slim

# Suppress interactive prompts
ENV DEBIAN_FRONTEND=noninteractive

# Install utilities required by Spark scripts.
RUN apt update && apt install -y procps tini libjemalloc2

# Enable jemalloc2 as default memory allocator
ENV LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.2

# Create the 'spark' group/user.
# The GID and UID must be 1099. Home directory is required.
RUN groupadd -g 1099 spark
RUN useradd -u 1099 -g 1099 -d /home/spark -m spark
USER spark
    

# Recommendation: Use Debian 12.
FROM debian:12-slim

# Suppress interactive prompts
ENV DEBIAN_FRONTEND=noninteractive

# Install utilities required by Spark scripts.
RUN apt update && apt install -y procps tini libjemalloc2

# Enable jemalloc2 as default memory allocator
ENV LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.2

# Install utilities required by XGBoost for Spark.
RUN apt install -y procps libgomp1

# Install and configure Miniconda3.
ENV CONDA_HOME=/opt/miniforge3
ENV PYSPARK_PYTHON=${CONDA_HOME}/bin/python
ENV PATH=${CONDA_HOME}/bin:${PATH}
ADD https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh .
RUN bash Miniforge3-Linux-x86_64.sh -b -p /opt/miniforge3 \
  && ${CONDA_HOME}/bin/conda config --system --set always_yes True \
  && ${CONDA_HOME}/bin/conda config --system --set auto_update_conda False \
  && ${CONDA_HOME}/bin/conda config --system --set channel_priority strict
# Packages ipython and ipykernel are required if using custom conda and want to
# use this container for running notebooks.
RUN ${CONDA_HOME}/bin/mamba install ipython ipykernel

# Install Conda packages.
#
# The following packages are installed in the default image.
# Recommendation: include all packages.
#
# Use mamba to quickly install packages.
RUN ${CONDA_HOME}/bin/mamba install -n base \
    accelerate \
    bigframes \
    cython \
    deepspeed \
    evaluate \
    fastavro \
    fastparquet \
    gcsfs \
    google-cloud-aiplatform \
    google-cloud-bigquery-storage \
    google-cloud-bigquery[pandas] \
    google-cloud-bigtable \
    google-cloud-container \
    google-cloud-datacatalog \
    google-cloud-dataproc \
    google-cloud-datastore \
    google-cloud-language \
    google-cloud-logging \
    google-cloud-monitoring \
    google-cloud-pubsub \
    google-cloud-redis \
    google-cloud-spanner \
    google-cloud-speech \
    google-cloud-storage \
    google-cloud-texttospeech \
    google-cloud-translate \
    google-cloud-vision \
    langchain \
    lightgbm \
    koalas \
    matplotlib \
    mlflow \
    nltk \
    numba \
    numpy \
    openblas \
    orc \
    pandas \
    pyarrow \
    pynvml \
    pysal \
    pytables \
    python \
    pytorch-cpu \
    regex \
    requests \
    rtree \
    scikit-image \
    scikit-learn \
    scipy \
    seaborn \
    sentence-transformers \
    sqlalchemy \
    sympy \
    tokenizers \
    transformers \
    virtualenv \
    xgboost

# Install pip packages.
RUN ${PYSPARK_PYTHON} -m pip install \
    spark-tensorflow-distributor \
    torcheval

# Install R and R libraries.
RUN ${CONDA_HOME}/bin/mamba install -n base \ 
    r-askpass \
    r-assertthat \
    r-backports \
    r-bit \
    r-bit64 \
    r-blob \
    r-boot \
    r-brew \
    r-broom \
    r-callr \
    r-caret \
    r-cellranger \
    r-chron \
    r-class \
    r-cli \
    r-clipr \
    r-cluster \
    r-codetools \
    r-colorspace \
    r-commonmark \
    r-cpp11 \
    r-crayon \
    r-curl \
    r-data.table \
    r-dbi \
    r-dbplyr \
    r-desc \
    r-devtools \
    r-digest \
    r-dplyr \
    r-ellipsis \
    r-evaluate \
    r-fansi \
    r-fastmap \
    r-forcats \
    r-foreach \
    r-foreign \
    r-fs \
    r-future \
    r-generics \
    r-ggplot2 \
    r-gh \
    r-glmnet \
    r-globals \
    r-glue \
    r-gower \
    r-gtable \
    r-haven \
    r-highr \
    r-hms \
    r-htmltools \
    r-htmlwidgets \
    r-httpuv \
    r-httr \
    r-hwriter \
    r-ini \
    r-ipred \
    r-isoband \
    r-iterators \
    r-jsonlite \
    r-kernsmooth \
    r-knitr \
    r-labeling \
    r-later \
    r-lattice \
    r-lava \
    r-lifecycle \
    r-listenv \
    r-lubridate \
    r-magrittr \
    r-markdown \
    r-mass \
    r-matrix \
    r-memoise \
    r-mgcv \
    r-mime \
    r-modelmetrics \
    r-modelr \
    r-munsell \
    r-nlme \
    r-nnet \
    r-numderiv \
    r-openssl \
    r-pillar \
    r-pkgbuild \
    r-pkgconfig \
    r-pkgload \
    r-plogr \
    r-plyr \
    r-praise \
    r-prettyunits \
    r-processx \
    r-prodlim \
    r-progress \
    r-promises \
    r-proto \
    r-ps \
    r-purrr \
    r-r6 \
    r-randomforest \
    r-rappdirs \
    r-rcmdcheck \
    r-rcolorbrewer \
    r-rcpp \
    r-rcurl \
    r-readr \
    r-readxl \
    r-recipes \
    r-recommended \
    r-rematch \
    r-remotes \
    r-reprex \
    r-reshape2 \
    r-rlang \
    r-rmarkdown \
    r-rodbc \
    r-roxygen2 \
    r-rpart \
    r-rprojroot \
    r-rserve \
    r-rsqlite \
    r-rstudioapi \
    r-rvest \
    r-scales \
    r-selectr \
    r-sessioninfo \
    r-shape \
    r-shiny \
    r-sourcetools \
    r-spatial \
    r-squarem \
    r-stringi \
    r-stringr \
    r-survival \
    r-sys \
    r-teachingdemos \
    r-testthat \
    r-tibble \
    r-tidyr \
    r-tidyselect \
    r-tidyverse \
    r-timedate \
    r-tinytex \
    r-usethis \
    r-utf8 \
    r-uuid \
    r-vctrs \
    r-whisker \
    r-withr \
    r-xfun \
    r-xml2 \
    r-xopen \
    r-xtable \
    r-yaml \
    r-zip

ENV R_HOME=/usr/lib/R

# Add extra Python modules.
ENV PYTHONPATH=/opt/python/packages
RUN mkdir -p "${PYTHONPATH}"

# Add extra jars.
ENV SPARK_EXTRA_JARS_DIR=/opt/spark/jars/
ENV SPARK_EXTRA_CLASSPATH='/opt/spark/jars/*'
RUN mkdir -p "${SPARK_EXTRA_JARS_DIR}"

#Uncomment below and replace EXTRA_JAR_NAME with the jar file name.
#COPY "EXTRA_JAR_NAME" "${SPARK_EXTRA_JARS_DIR}"

# Create the 'spark' group/user.
# The GID and UID must be 1099. Home directory is required.
RUN groupadd -g 1099 spark
RUN useradd -u 1099 -g 1099 -d /home/spark -m spark
USER spark