主要參考 [http://trac.nchc.org.tw/grid/wiki/jazz/DRBL_Hadoop Jazz: DRBL_Hadoop ]

 * drbl server 作業環境：
|| debian || etch (4.0) || server - 64 bit ||

 * 安裝drbl 

 * 安裝 java 6 

在套件庫裡 /etc/apt/sources.list 加入 non-free 庫以及 backports 網址才能安裝 sun-java6
{{{
deb http://opensource.nchc.org.tw/debian/ etch main contrib non-free
deb-src http://opensource.nchc.org.tw/debian/ etch main contrib non-free
deb http://security.debian.org/ etch/updates main contrib non-free
deb-src http://security.debian.org/ etch/updates main contrib non-free
deb http://www.backports.org/debian etch-backports main non-free
deb http://free.nchc.org.tw/drbl-core drbl stable
}}}
安裝key及java6
{{{
$ wget http://www.backports.org/debian/archive.key
$ sudo apt-key add archive.key
$ apt-get update
$ apt-get install sun-java6-bin  sun-java6-jdk sun-java6-jre
}}}


 = Hadoop Install = 

 * download Hadoop 0.18.3 
{{{
$ cd /opt
$ wget http://ftp.twaren.net/Unix/Web/apache/hadoop/core/hadoop-0.18.3/hadoop-0.18.3.tar.gz
$ tar zxvf hadoop-0.18.3.tar.gz
hadoop:/opt# ln -sf hadoop-0.18.3 hadoop
}}}
 * setup JAVA_HOME environment variable
{{{
$ echo "export JAVA_HOME=/usr/lib/jvm/java-6-sun" >> ~/.bash_profile
$ source ~/.bash_profile
}}}
 * edit hadoop-0.18.3/conf/hadoop-env.sh
{{{
#!diff
--- hadoop-0.18.3/conf/hadoop-env.sh.org
+++ hadoop-0.18.3/conf/hadoop-env.sh
@@ -6,7 +6,9 @@
 # remote nodes.

 # The java implementation to use.  Required.
-# export JAVA_HOME=/usr/lib/j2sdk1.5-sun
+export JAVA_HOME=/usr/lib/jvm/java-6-sun
+export HADOOP_HOME=/opt/hadoop-0.18.3
+export HADOOP_CONF_DIR=$HADOOP_HOME/conf

 # Extra Java CLASSPATH elements.  Optional.
 # export HADOOP_CLASSPATH=
}}}

 * edit hadoop-0.18.3/conf/hadoop-site.xml
{{{
#!diff
--- hadoop-0.18.3/conf/hadoop-site.xml.org
+++ hadoop-0.18.3/conf/hadoop-site.xml
@@ -4,5 +4,31 @@
 <!-- Put site-specific property overrides in this file. -->

 <configuration>
-
+  <property>
+    <name>fs.default.name</name>
+    <value>hdfs://192.168.1.254:9000/</value>
+    <description>
+      The name of the default file system. Either the literal string
+      "local" or a host:port for NDFS.
+    </description>
+  </property>
+  <property>
+    <name>mapred.job.tracker</name>
+    <value>hdfs://192.168.1.254:9001</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>
}}}

 = DRBL setup =
 
 == Environment == 
{{{
******************************************************
          NIC    NIC IP                    Clients
+------------------------------+
|         DRBL SERVER          |
|                              |
|    +-- [eth0] X.X.X.X        +- to WAN
|                              |
|    +-- [eth1] 192.168.1.254 +- to clients group 1 [ 16 clients, their IP
|                              |             from 192.168.1.1 - 192.168.1.16]
+------------------------------+
******************************************************
Total clients: 16
******************************************************
}}}
 == ssh ==
 * Hadoop will use ssh connections for internal connection, thus we have to do SSH key exchange.
{{{
$ ssh-keygen
$ cp .ssh/id_rsa.pub .ssh/authorized_keys
$ sudo apt-get install dsh
$ mkdir -p .dsh
$ for ((i=1;i<=16;i++)); do echo "192.168.1.$i" >> .dsh/machines.list; done
}}}

 == DRBL Server as Hadoop namenode ==
 * edit /etc/rc.local for DRBL Server as Hadoop namenode
{{{
#!diff
--- /etc/rc.local.org   2008-11-07 18:09:10.000000000 +0800
+++ /etc/rc.local       2008-11-07 17:58:14.000000000 +0800
@@ -11,4 +11,7 @@
 #
 # By default this script does nothing.

+echo 3 > /proc/sys/vm/drop_caches
+/opt/hadoop-0.18.3/bin/hadoop namenode -format
+/opt/hadoop-0.18.3/bin/hadoop-daemon.sh start namenode
+/opt/hadoop-0.18.3/bin/hadoop-daemon.sh start jobtracker
+/opt/hadoop-0.18.3/bin/hadoop-daemon.sh start tasktracker
 exit 0
}}}
 * edit hadoop_datanode for DRBL client as datanode
{{{
$ cat > hadoop_datanode << EOF
}}}


{{{
#! /bin/sh
set -e

# /etc/init.d/hadoop_datanode: start and stop Hadoop DFS datanode for DRBL Client

export PATH="${PATH:+$PATH:}/usr/sbin:/sbin"

case "\$1" in
  start)
        echo -n "starting datanode:"
        /opt/hadoop-0.18.3/bin/hadoop-daemon.sh start datanode
        echo "[OK]"
        ;;
  stop)
        echo -n "stoping datanode:"
        /opt/hadoop-0.18.3/bin/hadoop-daemon.sh stop datanode
        echo "[OK]"
        ;;

  *)
        echo "Usage: /etc/init.d/hadoop_datanode {start|stop}"
        exit 1
esac

exit 0
EOF
}}}
{{{
$ chmod a+x hadoop_datanode
$ sudo /opt/drbl/sbin/drbl-cp-host hadoop_datanode /etc/init.d/
$ sudo /opt/drbl/bin/drbl-doit update-rc.d hadoop_datanode defaults 99
}}}
 * shutdown DRBL clients
 * reboot DRBL server
 * use "Wake on LAN" for DRBL clients
 * browse http://192.168.1.254:50070 for DFS status