FROM openjdk:8-jdk-slim # FROM amazoncorretto:8 ARG MAVEN_VERSION=3.8.8 ARG BASE_URL=https://apache.osuosl.org/maven/maven-3/${MAVEN_VERSION}/binaries ARG HADOOP_VERSION ARG RSS_VERSION ARG AUTHOR=unknown ARG GIT_BRANCH=unknown ARG GIT_COMMIT=unknown LABEL author=${AUTHOR} LABEL git-branch=${GIT_BRANCH} LABEL git-commit=${GIT_COMMIT} RUN apt-get update && apt-get install -y curl git zlib1g zlib1g-dev lzop lsof netcat dnsutils less procps iputils-ping \ && apt-get clean && rm -rf /var/lib/apt/lists/* # Use EMR on EKS user ID 999 instead RUN addgroup -gid 1000 hadoop \ && useradd -u 999 -g hadoop -ms /bin/bash hadoop \ && echo "hadoop:hadoop" | chpasswd \ && mkdir -p /data/rssadmin/ \ && chown -R 999:1000 /data # install maven RUN mkdir -p /usr/share/maven /usr/share/maven/ref \ && curl -fsSL -o /tmp/apache-maven.tar.gz ${BASE_URL}/apache-maven-${MAVEN_VERSION}-bin.tar.gz \ && tar -xzf /tmp/apache-maven.tar.gz -C /usr/share/maven --strip-components=1 \ && rm -f /tmp/apache-maven.tar.gz \ && ln -s /usr/share/maven/bin/mvn /usr/bin/mvn ENV MAVEN_HOME /usr/share/maven ENV MAVEN_CONFIG "$USER_HOME_DIR/.m2" USER hadoop:hadoop # compile RSS server RUN git clone https://github.com/apache/incubator-uniffle.git /tmp/uniffle WORKDIR /tmp/uniffle # COPY build_distribution.sh . RUN ./build_distribution.sh --spark3-profile 'spark3.2.0' RUN cp rss-*.tgz /data/rssadmin \ && tar -xvf /data/rssadmin/rss-*.tgz --one-top-level=/data/rssadmin/rss --strip-components 1 \ && rm /data/rssadmin/rss/bin/rss-env.sh \ && rm -rf /data/rssadmin/rss-*.tgz rss-*.tgz COPY rss-env.sh /data/rssadmin/rss/bin COPY start.sh /data/rssadmin/rss/bin COPY hadoop-${HADOOP_VERSION}.tar.gz /data/rssadmin RUN tar -zxvf /data/rssadmin/hadoop-*.tar.gz --one-top-level=/data/rssadmin/hadoop --strip-components 1 \ && rm -rf /data/rssadmin/hadoop-*.tar.gz COPY hadoopconfig/ /data/rssadmin/hadoop/etc/hadoop ENV RSS_VERSION ${RSS_VERSION} ENV HADOOP_VERSION ${HADOOP_VERSION} WORKDIR /data/rssadmin/rss CMD bash bin/start.sh