[TOC]

hadoop283.dockerfile

#hadoop283-jdk.dockerfile
FROM xiaows/debian8-jdk8-ssh:3.0
# MAINTAINER XIAOWS <xiaows08@163.com>

WORKDIR /root

#install hadoop
COPY hadoop-2.8.3/ /usr/local/hadoop-2.8.3
#copy hadoop-config
# COPY hadoop-conf/ $HADOOP_HOME/etc/hadoop/
ENV HADOOP_HOME=/usr/local/hadoop-2.8.3
ENV PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

RUN mkdir -p /data/hdfs/namenode;\
    mkdir -p /data/hdfs/datanode;\
    # mkdir -p $HADOOP_HOME/logs;\
    # ln -s $HADOOP_HOME/etc/hadoop /root/hadoop-conf;\
    rm -rfv $HADOOP_HOME/share/doc/;\
    rm -rfv $HADOOP_HOME/bin/*.cmd;\
    rm -rfv $HADOOP_HOME/sbin/*.cmd;\
    mv $HADOOP_HOME/etc/hadoop/start-hadoop.sh /root/;\
    mv $HADOOP_HOME/etc/hadoop/run-wordcount.sh /root/;\
    mv /root/Dockerfile-debian8-jdk8-ssh /;\
    chmod +x /root/*.sh;\
    hdfs namenode -format

COPY hadoop283-jdk.dockerfile /
# ENTRYPOINT hdfs namenode -format

修改如下配置文件

• $HADOOP_HOME/etc/hadoop/core-site.xml

<?xml version="1.0"?>
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://hadoop-1:9000/</value>
    </property>
</configuration>

• $HADOOP_HOME/etc/hadoop/hadoop-env.sh

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Set Hadoop-specific environment variables here.

# The only required environment variable is JAVA_HOME.  All others are
# optional.  When running a distributed configuration it is best to
# set JAVA_HOME in this file, so that it is correctly defined on
# remote nodes.

# The java implementation to use.
export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64

# The jsvc implementation to use. Jsvc is required to run secure datanodes
# that bind to privileged ports to provide authentication of data transfer
# protocol.  Jsvc is not required if SASL is configured for authentication of
# data transfer protocol using non-privileged ports.
#export JSVC_HOME=${JSVC_HOME}

export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop"}

# Extra Java CLASSPATH elements.  Automatically insert capacity-scheduler.
for f in $HADOOP_HOME/contrib/capacity-scheduler/*.jar; do
  if [ "$HADOOP_CLASSPATH" ]; then
    export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$f
  else
    export HADOOP_CLASSPATH=$f
  fi
done

# The maximum amount of heap to use, in MB. Default is 1000.
#export HADOOP_HEAPSIZE=
#export HADOOP_NAMENODE_INIT_HEAPSIZE=""

# Extra Java runtime options.  Empty by default.
export HADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"

# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_NAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_NAMENODE_OPTS"
export HADOOP_DATANODE_OPTS="-Dhadoop.security.logger=ERROR,RFAS $HADOOP_DATANODE_OPTS"

export HADOOP_SECONDARYNAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_SECONDARYNAMENODE_OPTS"

export HADOOP_NFS3_OPTS="$HADOOP_NFS3_OPTS"
export HADOOP_PORTMAP_OPTS="-Xmx512m $HADOOP_PORTMAP_OPTS"

# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
export HADOOP_CLIENT_OPTS="-Xmx512m $HADOOP_CLIENT_OPTS"
#HADOOP_JAVA_PLATFORM_OPTS="-XX:-UsePerfData $HADOOP_JAVA_PLATFORM_OPTS"

# On secure datanodes, user to run the datanode as after dropping privileges.
# This **MUST** be uncommented to enable secure HDFS if using privileged ports
# to provide authentication of data transfer protocol.  This **MUST NOT** be
# defined if SASL is configured for authentication of data transfer protocol
# using non-privileged ports.
export HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER}

# Where log files are stored.  $HADOOP_HOME/logs by default.
#export HADOOP_LOG_DIR=${HADOOP_LOG_DIR}/$USER

# Where log files are stored in the secure data environment.
export HADOOP_SECURE_DN_LOG_DIR=${HADOOP_LOG_DIR}/${HADOOP_HDFS_USER}

###
# HDFS Mover specific parameters
###
# Specify the JVM options to be used when starting the HDFS Mover.
# These options will be appended to the options specified as HADOOP_OPTS
# and therefore may override any similar flags set in HADOOP_OPTS
#
# export HADOOP_MOVER_OPTS=""

###
# Advanced Users Only!
###

# The directory where pid files are stored. /tmp by default.
# NOTE: this should be set to a directory that can only be written to by 
#       the user that will run the hadoop daemons.  Otherwise there is the
#       potential for a symlink attack.
export HADOOP_PID_DIR=${HADOOP_PID_DIR}
export HADOOP_SECURE_DN_PID_DIR=${HADOOP_PID_DIR}

# A string representing this instance of hadoop. $USER by default.
export HADOOP_IDENT_STRING=$USER

• $HADOOP_HOME/etc/hadoop/hdfs-site.xml

<?xml version="1.0"?>
<configuration>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:///data/hdfs/namenode</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:///data/hdfs/datanode</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
</configuration>

• $HADOOP_HOME/etc/hadoop/mapred-site.xml

<?xml version="1.0"?>
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>

• $HADOOP_HOME/etc/hadoop/slaves

hadoop-1
hadoop-2
hadoop-3
#hadoop-4

• $HADOOP_HOME/etc/hadoop/yarn-site.sh

<?xml version="1.0"?>
<configuration>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
        <value>org.apache.hadoop.mapred.ShuffleHandler</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>hadoop-1</value>
    </property>
</configuration>

• $HADOOP_HOME/etc/hadoop/run-wordcount.sh [可選]

#!/bin/bash

# test the hadoop cluster by running wordcount

# create input files 
mkdir input
echo "Hello Docker" >input/file2.txt
echo "Hello Hadoop" >input/file1.txt

# create input directory on HDFS
hadoop fs -mkdir -p input

# put input files to HDFS
hdfs dfs -put ./input/* input

# run wordcount 
hadoop jar $HADOOP_HOME/share/hadoop/mapreduce/sources/hadoop-mapreduce-examples-2.8.3-sources.jar org.apache.hadoop.examples.WordCount input output

# print the input files
echo -e "\ninput file1.txt:"
hdfs dfs -cat input/file1.txt

echo -e "\ninput file2.txt:"
hdfs dfs -cat input/file2.txt

# print the output of wordcount
echo -e "\nwordcount output:"
hdfs dfs -cat output/part-r-00000

• run-container.sh

#start-cluster.sh
#!/bin/bash

if [ $# = 0 ]
then
    echo "1. Please specify the docker-image of cluster !"
    echo "2. Please specify name of cluster service !"
    exit 1
fi

image_name=$1
service_name=$2
net_name=${3:-cluster}
docker rm -f ${service_name}-{1,2,3}
i=1
while [ $i -lt 4 ]
do
    echo "start ${service_name}-$i container..."
    docker run -itd \
        --net=${net_name} \
        --hostname ${service_name}-$i \
        --name ${service_name}-$i \
        --restart=always \
        $image_name
    i=$(( $i + 1 ))
done

docker exec -it ${service_name}-1 bash

• 為了使鏡像構(gòu)建的盡量小比勉，可以刪除Hadoop中的doc/文檔 src/源碼以及bin/.cmd sbin/.cmd
• 構(gòu)建鏡像
  docker build -f hadoop283.dockerfile -t xiaows/hadoop283:3.0 .
• 啟動Hadoop集群
  ./run-containeer.sh xiaows/hadoop283:3.0 hadoop