Personalizar o ambiente de execução do job do Spark com o Docker no YARN

FROM debian:10-slim

# Suppress interactive prompts.
ENV DEBIAN_FRONTEND=noninteractive

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

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

# Optional: Install and configure Miniconda3.
ENV CONDA_HOME=/opt/miniconda3
ENV PYSPARK_PYTHON=${CONDA_HOME}/bin/python
ENV PYSPARK_DRIVER_PYTHON=${CONDA_HOME}/bin/python

ENV PATH=${CONDA_HOME}/bin:${PATH}
COPY Miniconda3-py39_4.10.3-Linux-x86_64.sh .
RUN bash Miniconda3-py39_4.10.3-Linux-x86_64.sh -b -p /opt/miniconda3 \
  && ${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 --prepend channels conda-forge \
  && ${CONDA_HOME}/bin/conda config --system --set channel_priority strict

# Optional: Install Conda packages.
#
# The following packages are installed in the default image. It is strongly
# recommended to include all of them.
#
# Use mamba to install packages quickly.
RUN ${CONDA_HOME}/bin/conda install mamba -n base -c conda-forge \
    && ${CONDA_HOME}/bin/mamba install \
      conda \
      cython \
      fastavro \
      fastparquet \
      gcsfs \
      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 \
      koalas \
      matplotlib \
      nltk \
      numba \
      numpy \
      openblas \
      orc \
      pandas \
      pyarrow \
      pysal \
      pytables \
      python \
      regex \
      requests \
      rtree \
      scikit-image \
      scikit-learn \
      scipy \
      seaborn \
      sqlalchemy \
      sympy \
      virtualenv

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

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

# Increase the version number when there is a change to avoid referencing
# a cached older image. Avoid reusing the version number, including the default
# `latest` version.
IMAGE=gcr.io/my-project/my-image:1.0.1

# Download the BigQuery connector.
gcloud storage cp \
  gs://spark-lib/bigquery/spark-bigquery-with-dependencies_2.12-0.22.2.jar .

# Download the Miniconda3 installer.
wget https://repo.anaconda.com/miniconda/Miniconda3-py39_4.10.3-Linux-x86_64.sh

# Python module example:
cat >test_util.py <<EOF
def hello(name):
  print("hello {}".format(name))

def read_lines(path):
  with open(path) as f:
    return f.readlines()
EOF

# Build and push the image.
docker build -t "${IMAGE}" .
docker push "${IMAGE}"

# Set the Docker image URI.
IMAGE=(e.g., gcr.io/my-project/my-image:1.0.1)

# Required: Use `#` as the delimiter for properties to avoid conflicts.
JOB_PROPERTIES='^#^'

# Required: Set Spark properties with the Docker image.
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.yarn.appMasterEnv.YARN_CONTAINER_RUNTIME_DOCKER_IMAGE=${IMAGE}"
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.executorEnv.YARN_CONTAINER_RUNTIME_DOCKER_IMAGE=${IMAGE}"

# Optional: Add custom jars to Spark classpath. Don't set these properties if
# there are no customizations.
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.driver.extraClassPath=/opt/spark/jars/*"
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.executor.extraClassPath=/opt/spark/jars/*"

# Optional: Set custom PySpark Python path only if there are customizations.
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.pyspark.python=/opt/miniconda3/bin/python"
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.pyspark.driver.python=/opt/miniconda3/bin/python"

# Optional: Set custom Python module path only if there are customizations.
# Since the `PYTHONPATH` environment variable defined in the Dockerfile is
# overridden by Spark, it must be set as a job property.
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.yarn.appMasterEnv.PYTHONPATH=/opt/python/packages"
JOB_PROPERTIES="${JOB_PROPERTIES}#spark.executorEnv.PYTHONPATH=/opt/python/packages"