This repository has been archived by the owner on Sep 10, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 6
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Build spark/hadoop from source and pip install the local package
- Loading branch information
Showing
1 changed file
with
14 additions
and
19 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,31 +1,26 @@ | ||
FROM quay.io/thoth-station/s2i-thoth-ubi8-py36:v0.15.0 | ||
|
||
ARG PKG_ROOT=/opt/app-root | ||
ARG SPARK_VERSION=2.4.5 | ||
ARG HADOOP_VERSION=2.8.5 | ||
ARG JAVA_VERSION=1.8.0 | ||
ARG SPARK_SOURCE_REPO=https://github.com/apache/spark.git | ||
ARG SPARK_SOURCE_REPO_BRANCH=v${SPARK_VERSION} | ||
ARG SPARK_SOURCE_REPO_TARGET_DIR=spark | ||
ARG SPARK_BUILD_ARGS="-Phive -Phive-thriftserver -Pkubernetes -Dhadoop.version=${HADOOP_VERSION}" | ||
|
||
USER root | ||
# Download and extract the binaries for Spark and Hadoop | ||
RUN wget https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-without-hadoop.tgz &&\ | ||
tar -C ${PKG_ROOT} -zxf spark-${SPARK_VERSION}-bin-without-hadoop.tgz &&\ | ||
mv ${PKG_ROOT}/spark-${SPARK_VERSION}-bin-without-hadoop ${PKG_ROOT}/spark-${SPARK_VERSION} &&\ | ||
rm spark-${SPARK_VERSION}-bin-without-hadoop.tgz | ||
RUN wget https://downloads.apache.org/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz &&\ | ||
tar -C ${PKG_ROOT} -xf hadoop-${HADOOP_VERSION}.tar.gz &&\ | ||
rm hadoop-${HADOOP_VERSION}.tar.gz | ||
|
||
# Install java to execute hadoop jars | ||
# Install openjdk so we can build the hadoop jars | ||
RUN yum -y install java-$JAVA_VERSION-openjdk maven &&\ | ||
yum clean all | ||
|
||
# Setup required env vars for spark and hadoop | ||
ENV JAVA_HOME=/usr/lib/jvm/jre | ||
ENV SPARK_HOME=${PKG_ROOT}/spark-${SPARK_VERSION} | ||
|
||
# Add HADOOP_CONF_DIR to spark-env.sh based on output from running "hadoop classpath" | ||
RUN cp ${PKG_ROOT}/spark-${SPARK_VERSION}/conf/spark-env.sh.template ${PKG_ROOT}/spark-${SPARK_VERSION}/conf/spark-env.sh &&\ | ||
echo "HADOOP_CONF_DIR=$(${PKG_ROOT}/hadoop-${HADOOP_VERSION}/bin/hadoop classpath)" >> ${PKG_ROOT}/spark-${SPARK_VERSION}/conf/spark-env.sh | ||
|
||
USER 1001 | ||
RUN fix-permissions ${PKG_ROOT} | ||
# Build the Apache spark and hadoop binaries from source | ||
# After the build is complete create and install the python wheel file using pip | ||
RUN git clone ${SPARK_SOURCE_REPO} -b ${SPARK_SOURCE_REPO_BRANCH} ${SPARK_SOURCE_REPO_TARGET_DIR} | ||
RUN cd ${SPARK_SOURCE_REPO_TARGET_DIR} &&\ | ||
dev/make-distribution.sh --name spark-${SPARK_VERSION}-hadoop-${HADOOP_VERSION} ${SPARK_BUILD_ARGS} | ||
RUN cd ${SPARK_SOURCE_REPO_TARGET_DIR}/python && python setup.py bdist_wheel && pip install dist/*whl &&\ | ||
cd ${HOME} && rm -rf ${SPARK_SOURCE_REPO_TARGET_DIR} | ||
|
||
RUN fix-permissions /opt/app-root |