= Deploy Hadoop to PC Classroom using DRBL =

 * java is required for Hadoop, so you need to install java runtime or jdk first.
{{{
~$ echo "deb http://free.nchc.org.tw/debian/ etch non-free" > /tmp/etch-non-free.list
~$ sudo mv /tmp/etch-non-free.list /etc/apt/sources.list.d/.
~$ sudo apt-get update
~$ sudo apt-get install sun-java5-jdk
}}}
 * download Hadoop 0.18.2 
{{{
~$ wget http://ftp.twaren.net/Unix/Web/apache/hadoop/core/hadoop-0.18.2/hadoop-0.18.2.tar.gz
~$ tar zxvf hadoop-0.18.2.tar.gz
}}}
 * setup JAVA_HOME environment variable
{{{
~$ echo "export JAVA_HOME=/usr/lib/jvm/java-1.5.0-sun" >> ~/.bash_profile
~$ source ~/.bash_profile
}}}
 * edit hadoop-0.18.2/conf/hadoop-env.sh
{{{
#!diff
--- hadoop-0.18.2/conf/hadoop-env.sh.org        2008-11-06 22:57:40.000000000 +0800
+++ hadoop-0.18.2/conf/hadoop-env.sh    2008-11-06 22:58:42.000000000 +0800
@@ -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-1.5.0-sun
+export HADOOP_HOME=/home/jazz/hadoop-0.18.2
+export HADOOP_CONF_DIR=$HADOOP_HOME/conf

 # Extra Java CLASSPATH elements.  Optional.
 # export HADOOP_CLASSPATH=
}}}
 * here is current DRBL setup
{{{
******************************************************
          NIC    NIC IP                    Clients
+------------------------------+
|         DRBL SERVER          |
|                              |
|    +-- [eth0] X.X.X.X        +- to WAN
|                              |
|    +-- [eth1] 192.168.61.254 +- to clients group 1 [ 16 clients, their IP
|                              |             from 192.168.61.1 - 192.168.61.16]
+------------------------------+
******************************************************
Total clients: 16
******************************************************
}}}
 * 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 "192.168.61.$i" >> .dsh/machines.list; done
}}}
 * edit hadoop-0.18.2/conf/hadoop-site.xml
{{{
#!diff
--- hadoop-0.18.2/conf/hadoop-site.xml.org      2008-11-06 23:11:18.000000000 +0800
+++ hadoop-0.18.2/conf/hadoop-site.xml  2008-11-07 17:05:11.000000000 +0800
@@ -4,5 +4,31 @@
 <!-- Put site-specific property overrides in this file. -->

 <configuration>
-
+  <property>
+    <name>fs.default.name</name>
+    <value>hdfs://192.168.61.254:9000/</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>192.168.61.254:9001</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>
}}}
 * 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
+/home/jazz/hadoop-0.18.2/bin/hadoop namenode -format
+/home/jazz/hadoop-0.18.2/bin/hadoop-daemon.sh start namenode
+/home/jazz/hadoop-0.18.2/bin/hadoop-daemon.sh start jobtracker
+/home/jazz/hadoop-0.18.2/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:"
        /home/jazz/hadoop-0.18.2/bin/hadoop-daemon.sh start datanode
        echo "[OK]"
        ;;
  stop)
        echo -n "stoping datanode:"
        /home/jazz/hadoop-0.18.2/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://192.168.61.254:50070 for DFS status

== Known Issue ==

 * 如果要讓 DRBL Clients 都掛起硬碟來存資料，hadoop-site.xml 必須加入
{{{
  <property>
    <name>dfs.data.dir</name>
    <value>預採用的路徑(Ex:/home/jazz/hadoop)</value>
    <final>true</final>
  </property>
}}}
 * 記得 namenode 要 format 否則會無法連接上 namenode
 * 有掛載硬碟時，當 datanode 第二次啟動，會出現錯誤訊息
{{{
2009-03-21 01:03:49,814 INFO org.apache.hadoop.dfs.Storage: Cannot lock storage /home/jazz/hadoop. The directory is already locked.
2009-03-21 01:03:49,915 ERROR org.apache.hadoop.dfs.DataNode: java.io.IOException: Cannot lock storage /home/jazz/hadoop. The directory is already locked.
        at org.apache.hadoop.dfs.Storage$StorageDirectory.lock(Storage.java:447)
        at org.apache.hadoop.dfs.Storage$StorageDirectory.analyzeStorage(Storage.java:300)
        at org.apache.hadoop.dfs.DataStorage.recoverTransitionRead(DataStorage.java:105)
        at org.apache.hadoop.dfs.DataNode.startDataNode(DataNode.java:306)
        at org.apache.hadoop.dfs.DataNode.<init>(DataNode.java:223)
        at org.apache.hadoop.dfs.DataNode.makeInstance(DataNode.java:3071)
        at org.apache.hadoop.dfs.DataNode.instantiateDataNode(DataNode.java:3026)
        at org.apache.hadoop.dfs.DataNode.createDataNode(DataNode.java:3034)
        at org.apache.hadoop.dfs.DataNode.main(DataNode.java:3156)

2009-03-21 01:03:49,915 INFO org.apache.hadoop.dfs.DataNode: SHUTDOWN_MSG:
/************************************************************
SHUTDOWN_MSG: Shutting down DataNode at pc144/192.168.100.44
************************************************************/
}}}