hadoop从入门到放弃（2）docker下载hadoop镜像

1.准备步骤

docker search找下hadoop

然后下载

docker pull sequenceiq/hadoop-docker

用docker images可以查看到镜像

 然后启动

 docker run -it -p 8088:8088 sequenceiq/hadoop-docker /etc/bootstrap.sh -bash

我们测试一下

cd $HADOOP_PREFIX
# run the mapreduce
bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.1.jar grep input output 'dfs[a-z.]+'

# check the output
bin/hdfs dfs -cat output/*

最后输出

 进入yarn控制台

 DockerFile如下

# Creates pseudo distributed hadoop 2.7.1
#
# docker build -t sequenceiq/hadoop .

FROM sequenceiq/pam:centos-6.5
MAINTAINER SequenceIQ

USER root

# install dev tools
RUN yum clean all; 
    rpm --rebuilddb; 
    yum install -y curl which tar sudo openssh-server openssh-clients rsync
# update libselinux. see https://github.com/sequenceiq/hadoop-docker/issues/14
RUN yum update -y libselinux

# passwordless ssh
RUN ssh-keygen -q -N "" -t dsa -f /etc/ssh/ssh_host_dsa_key
RUN ssh-keygen -q -N "" -t rsa -f /etc/ssh/ssh_host_rsa_key
RUN ssh-keygen -q -N "" -t rsa -f /root/.ssh/id_rsa
RUN cp /root/.ssh/id_rsa.pub /root/.ssh/authorized_keys


# java
RUN curl -LO 'http://download.oracle.com/otn-pub/java/jdk/7u71-b14/jdk-7u71-linux-x64.rpm' -H 'Cookie: oraclelicense=accept-securebackup-cookie'
RUN rpm -i jdk-7u71-linux-x64.rpm
RUN rm jdk-7u71-linux-x64.rpm

ENV JAVA_HOME /usr/java/default
ENV PATH $PATH:$JAVA_HOME/bin
RUN rm /usr/bin/java && ln -s $JAVA_HOME/bin/java /usr/bin/java

# download native support
RUN mkdir -p /tmp/native
RUN curl -L https://github.com/sequenceiq/docker-hadoop-build/releases/download/v2.7.1/hadoop-native-64-2.7.1.tgz | tar -xz -C /tmp/native

# hadoop
RUN curl -s http://www.eu.apache.org/dist/hadoop/common/hadoop-2.7.1/hadoop-2.7.1.tar.gz | tar -xz -C /usr/local/
RUN cd /usr/local && ln -s ./hadoop-2.7.1 hadoop

ENV HADOOP_PREFIX /usr/local/hadoop
ENV HADOOP_COMMON_HOME /usr/local/hadoop
ENV HADOOP_HDFS_HOME /usr/local/hadoop
ENV HADOOP_MAPRED_HOME /usr/local/hadoop
ENV HADOOP_YARN_HOME /usr/local/hadoop
ENV HADOOP_CONF_DIR /usr/local/hadoop/etc/hadoop
ENV YARN_CONF_DIR $HADOOP_PREFIX/etc/hadoop

RUN sed -i '/^export JAVA_HOME/ s:.*:export JAVA_HOME=/usr/java/default
export HADOOP_PREFIX=/usr/local/hadoop
export HADOOP_HOME=/usr/local/hadoop
:' $HADOOP_PREFIX/etc/hadoop/hadoop-env.sh
RUN sed -i '/^export HADOOP_CONF_DIR/ s:.*:export HADOOP_CONF_DIR=/usr/local/hadoop/etc/hadoop/:' $HADOOP_PREFIX/etc/hadoop/hadoop-env.sh
#RUN . $HADOOP_PREFIX/etc/hadoop/hadoop-env.sh

RUN mkdir $HADOOP_PREFIX/input
RUN cp $HADOOP_PREFIX/etc/hadoop/*.xml $HADOOP_PREFIX/input

# pseudo distributed
ADD core-site.xml.template $HADOOP_PREFIX/etc/hadoop/core-site.xml.template
RUN sed s/HOSTNAME/localhost/ /usr/local/hadoop/etc/hadoop/core-site.xml.template > /usr/local/hadoop/etc/hadoop/core-site.xml
ADD hdfs-site.xml $HADOOP_PREFIX/etc/hadoop/hdfs-site.xml

ADD mapred-site.xml $HADOOP_PREFIX/etc/hadoop/mapred-site.xml
ADD yarn-site.xml $HADOOP_PREFIX/etc/hadoop/yarn-site.xml

RUN $HADOOP_PREFIX/bin/hdfs namenode -format

# fixing the libhadoop.so like a boss
RUN rm -rf /usr/local/hadoop/lib/native
RUN mv /tmp/native /usr/local/hadoop/lib

ADD ssh_config /root/.ssh/config
RUN chmod 600 /root/.ssh/config
RUN chown root:root /root/.ssh/config

# # installing supervisord
# RUN yum install -y python-setuptools
# RUN easy_install pip
# RUN curl https://bitbucket.org/pypa/setuptools/raw/bootstrap/ez_setup.py -o - | python
# RUN pip install supervisor
#
# ADD supervisord.conf /etc/supervisord.conf

ADD bootstrap.sh /etc/bootstrap.sh
RUN chown root:root /etc/bootstrap.sh
RUN chmod 700 /etc/bootstrap.sh

ENV BOOTSTRAP /etc/bootstrap.sh

# workingaround docker.io build error
RUN ls -la /usr/local/hadoop/etc/hadoop/*-env.sh
RUN chmod +x /usr/local/hadoop/etc/hadoop/*-env.sh
RUN ls -la /usr/local/hadoop/etc/hadoop/*-env.sh

# fix the 254 error code
RUN sed  -i "/^[^#]*UsePAM/ s/.*/#&/"  /etc/ssh/sshd_config
RUN echo "UsePAM no" >> /etc/ssh/sshd_config
RUN echo "Port 2122" >> /etc/ssh/sshd_config

RUN service sshd start && $HADOOP_PREFIX/etc/hadoop/hadoop-env.sh && $HADOOP_PREFIX/sbin/start-dfs.sh && $HADOOP_PREFIX/bin/hdfs dfs -mkdir -p /user/root
RUN service sshd start && $HADOOP_PREFIX/etc/hadoop/hadoop-env.sh && $HADOOP_PREFIX/sbin/start-dfs.sh && $HADOOP_PREFIX/bin/hdfs dfs -put $HADOOP_PREFIX/etc/hadoop/ input

CMD ["/etc/bootstrap.sh", "-d"]

# Hdfs ports
EXPOSE 50010 50020 50070 50075 50090 8020 9000
# Mapred ports
EXPOSE 10020 19888
#Yarn ports
EXPOSE 8030 8031 8032 8033 8040 8042 8088
#Other ports
EXPOSE 49707 2122

。。

。。

。。