Hadoop is a free, Java-based programming framework that supports the processing of large data sets in a distributed computing environment. It is part of the Apache project sponsored by the Apache Software Foundation.You can use A10 Cubieboards to build Hadoop cluster base on Lubuntu(v1.04) image which was integrated jdk-1.8 armhf.Need to do configuration: JDK environment, slaves and master ssh sever, hadoop configuration parameters.

Router/ hadoop_0.20.203 /Lubuntu 12.04v1.04(JDK-1.8)/ Power and network cables

1 master 3slaves both work in wlan network ,LAN connection between the nodes can ping each other.

Create a user

sudo addgroup hadoop
sudo adduser -ingroup hadoop hadoop
sudo vim ./etc/sudoers
add:hadoop ALL=(ALL:ALL) ALL

Host&hostname

sudo vim ./etc/hosts
add:
192.168.1.40 master
192.168.1.41 slave1
192.168.1.42 slave2
192.168.1.43 slave3
sudo vim ./etc/hostname
cubieboard -->master

You should do the same things. E.for slave1 add user

sudo addgroup hadoop
sudo adduser -ingroup hadoop hadoop
sudo vim ./etc/sudoers
add:hadoop ALL=(ALL:ALL) ALL

Host&hostname

sudo vim ./etc/hosts
add:
192.168.1.40 master
192.168.1.41 slave1
sudo vim ./etc/hostname
cubieboard -->slave1

==Static IP settings= For each node

sudo vim ./etc/network/interfaces
add
#auto lo
# iface lo inet loopback
#iface lo eth0 dhcp
auto eth0
iface eth0 inet static
address 192.168.1.40
gateway 192.168.1.1
netmask 255.255.255.0
network 192.168.1.0
broadcast 192.168.1.255

sudo vim ./etc/resolvconf/resolv.conf.d/base
add this:

nameserver 192.168.1.1

Master

ssh-keygen –t rsa –P ''
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
chmod 600 ~/.ssh/authorized_keys
ssh localhost
scp ~/.ssh/id_rsa.pub hadoop@192.168.1.40:~/

Slaves

mkdir ~/.ssh
chmod 700 ~/.ssh
cat ~/id_rsa.pub >> ~/.ssh/authorized_keys
chmod 600 ~/.ssh/authorized_keys
rm –r ~/id_rsa.pub

#export JAVA_HOME=/lib/jdk

You should edit core-site.xml hdfs-site.xml mapred-site.xml on /hadoop/hadoop_0.20.203_master/conf

core-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>fs.default.name</name>
<value>hdfs://master:9000</value>
</property>
</configuration>

hdfs-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>dfs.name.dir</name>
<value>/usr/local/hadoop/datalog1,/usr/local/hadoop/datalog2</value>
</property>
<property>
<name>dfs.data.dir</name>
<value>/usr/local/hadoop/data1,/usr/local/hadoop/data2</value>
</property>
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
</configuration>

mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>mapred.job.tracker</name>
<value>master:9001</value>
</property>
</configuration>

bin/hadoop namenode -format

bin/hadoop dfsadmin -report

bin/start-all.sh // start

bin/stop-all.sh // stop

./bin/hadoop jar hadoop-examples-0.20.203.0.jar pi 100 100 //Calculates PI

http://www.cnblogs.com/xia520pi/archive/2012/05/16/2503949.html