Table of Contents
Install Hadoop eco-system singlemode
install openjdk debian
sudo apt-get install openjdk-7-jdk ssh rsync sudo addgroup hadoop sudo adduser --ingroup hadoop hduser su - hduser ssh-keygen -t rsa -P "" cat $HOME/.ssh/id_rsa.pub >> $HOME/.ssh/authorized_keys
Edit ~/.bashrc
export HADOOP_HOME=/usr/local/hadoop/jre export JAVA_HOME=/usr/lib/jvm/java-7-openjdk-amd64 export ZOOKEEPER_PREFIX=/usr/local/zookeeper unalias hfs &> /dev/null alias hfs="hadoop fs" unalias hls &> /dev/null alias hls="fs -ls" lzohead () { hadoop fs -cat $1 | lzop -dc | head -1000 | less } export PATH=$PATH:$HADOOP_HOME/bin
Install Hadoop
cd /tmp wget http://apache.mivzakim.net/hadoop/common/stable/hadoop-2.5.0.tar.gz tar xzf hadoop-2.5.0.tar.gz sudo mv hadoop-2.5.0 /usr/local/ sudo ln -s /usr/local/hadoop-* /usr/local/hadoop sudo chown -R hduser:hadoop /usr/local/hadoop*
Edit /usr/local/hadoop/etc/hadoop/mapred-site.xml
<?xml version="1.0"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <configuration> <property> <name>mapred.job.tracker</name> <value>localhost:54311</value> <description>The host and port that the MapReduce job tracker runs at. If "local", then jobs are run in-process as a single map and reduce task. </description> </property> </configuration>
Edit /usr/local/hadoop/etc/conf/core-site.xml
<configuration> <property> <name>hadoop.tmp.dir</name> <value>/home/hduser/hadoop.tmp</value> <description>A base for other temporary directories.</description> </property> <property> <name>fs.default.name</name> <value>hdfs://localhost:54310</value> <description>The name of the default file system. A URI whose scheme and authority determine the FileSystem implementation. The uri's scheme determines the config property (fs.SCHEME.impl) naming the FileSystem implementation class. The uri's authority is used to determine the host, port, etc. for a filesystem.</description> </property> </configuration>
Format
cd /usr/local/hadoop/ bin/hadoop namenode -format
Zookeeper
wget http://apache.spd.co.il/zookeeper/stable/zookeeper-3.4.6.tar.gz tar -zxvf zookeeper* sudo mv zookeeper-3.4.6 /usr/local/ sudo ln -s /usr/local/zookeeper-* /usr/local/zookeeper sudo chown -R hduser:hadoop /usr/local/zookeeper*
vi /usr/local/zookeeper/conf/zoo.cfg
tickTime=2000 dataDir=/var/zookeeper clientPort=2181
sudo mkdir /var/zookeeper sudo chown -R hduser:hadoop /var/zookeeper
HBase
wget http://apache.mivzakim.net/hbase/stable/hbase-0.98.5-hadoop2-bin.tar.gz tar -zxvf hbase* sudo mv hbase-0.98.5-hadoop2 /usr/local/ sudo ln -s /usr/local/hbase-* /usr/local/hbase sudo chown -R hduser:hadoop /usr/local/hbase*
Edit /usr/local/hbase/conf/hbase-env.sh
export JAVA_HOME=/usr/lib/jvm/java-7-openjdk-amd64
Edit /usr/local/hbase/conf/hbase-site.xml
<configuration> <property> <name>hbase.rootdir</name> <value>file:///home/hduser/hbase</value> </property> <property> <name>hbase.zookeeper.property.dataDir</name> <value>/home/hduser/zookeeper</value> </property> </configuration>
Start ALL
cd /usr/local/hadoop sbin/start-all.sh cd /usr/local/zookeeper bin/zkServer.sh start cd /usr/local/hbase bin/start-hbase.sh #start hbase shell ./bin/hbase shell