#准备工作
准备3台机器，建立相同的用户名和密码，如：root/jiexi_test
分别如下：
10.2.112.31 #namenode
10.2.112.30 #datanode
10.2.112.34 #datanode
重点：
1、使用ssh-keygen生成id_rsa.pub文件，使3台机器可以相互ssh而不需要输入密码。
2、关闭掉防火墙。
参照文章：
http://qinlong.blog.51cto.com/1130504/323086 设置ssh-keygen
========================================================
cd /opt
wget http://ftp.meisei-u.ac.jp/mirror/apache/dist/hadoop/common/hadoop-1.0.2/hadoop-1.0.2.tar.gz
tar -zxvf hadoop-1.0.2.tar.gz
cd /opt/hadoop-1.0.2/conf
vim hadoop-env.sh
#加入
export JAVA_HOME=/opt/j2sdk
vim hadoop-site.xml
#加入namenode
10.2.112.31
vim slaves
#加入datanode
10.2.112.30
10.2.112.34
scp -r /opt/hadoop-1.0.2 root@10.2.112.30:/opt/
scp -r /opt/hadoop-1.0.2 root@10.2.112.34:/opt/
ln -s /opt/hadoop-1.0.2 /opt/hadoop
=======================================================
#在namenode上启动
cd /opt/hadoop
./bin/hadoop namenode -format
./bin/start-all.sh
#查看是否ok？
http://10.2.112.31:50030 #查看jobs
http://10.2.112.3*:50075 #查看hdfs文件
#在namenode上检查运行状况
./bin/hadoop dfsadmin -report
准备3台机器，建立相同的用户名和密码，如：root/jiexi_test
分别如下：
10.2.112.31 #namenode
10.2.112.30 #datanode
10.2.112.34 #datanode
重点：
1、使用ssh-keygen生成id_rsa.pub文件，使3台机器可以相互ssh而不需要输入密码。
2、关闭掉防火墙。
参照文章：
http://qinlong.blog.51cto.com/1130504/323086 设置ssh-keygen
========================================================
cd /opt
wget http://ftp.meisei-u.ac.jp/mirror/apache/dist/hadoop/common/hadoop-1.0.2/hadoop-1.0.2.tar.gz
tar -zxvf hadoop-1.0.2.tar.gz
cd /opt/hadoop-1.0.2/conf
vim hadoop-env.sh
#加入
export JAVA_HOME=/opt/j2sdk
vim hadoop-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://10.2.112.31:9110 </ value >
< description >The name of the default file system. Either the literal string "local" or a host:port for DFS. </ description >
</ property >
< property >
< name >mapred.job.tracker </ name >
< value >hdfs://10.2.112.31:9111 </ 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 >
< property >
< name >hadoop.tmp.dir </ name >
< value >/opt/hadoop/tmp </ value >
< description >A base for other temporary directories. </ description >
</ property >
< property >
< name >dfs.name.dir </ name >
< value >/opt/hadoop/filesystem/name </ value >
< description >Determines where on the local filesystem the DFS name node should store the name table. If this is a comma-delimited list of directories then the name table is replicated in all of the directories, for redundancy. </ description >
</ property >
< property >
< name >dfs.data.dir </ name >
< value >/opt/hadoop/filesystem/data </ value >
< description >Determines where on the local filesystem an DFS data node should store its blocks. If this is a comma-delimited list of directories, then data will be stored in all named directories, typically on different devices. Directories that do not exist are ignored. </ description >
</ property >
< property >
< name >dfs.replication </ name >
< value >1 </ value >
< description >Default block replication. The actual number of replications can be specified when the file is created. The default is used if replication is not specified in create time. </ description >
</ property >
</ configuration >
vim masters
<? 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://10.2.112.31:9110 </ value >
< description >The name of the default file system. Either the literal string "local" or a host:port for DFS. </ description >
</ property >
< property >
< name >mapred.job.tracker </ name >
< value >hdfs://10.2.112.31:9111 </ 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 >
< property >
< name >hadoop.tmp.dir </ name >
< value >/opt/hadoop/tmp </ value >
< description >A base for other temporary directories. </ description >
</ property >
< property >
< name >dfs.name.dir </ name >
< value >/opt/hadoop/filesystem/name </ value >
< description >Determines where on the local filesystem the DFS name node should store the name table. If this is a comma-delimited list of directories then the name table is replicated in all of the directories, for redundancy. </ description >
</ property >
< property >
< name >dfs.data.dir </ name >
< value >/opt/hadoop/filesystem/data </ value >
< description >Determines where on the local filesystem an DFS data node should store its blocks. If this is a comma-delimited list of directories, then data will be stored in all named directories, typically on different devices. Directories that do not exist are ignored. </ description >
</ property >
< property >
< name >dfs.replication </ name >
< value >1 </ value >
< description >Default block replication. The actual number of replications can be specified when the file is created. The default is used if replication is not specified in create time. </ description >
</ property >
</ configuration >
#加入namenode
10.2.112.31
vim slaves
#加入datanode
10.2.112.30
10.2.112.34
scp -r /opt/hadoop-1.0.2 root@10.2.112.30:/opt/
scp -r /opt/hadoop-1.0.2 root@10.2.112.34:/opt/
ln -s /opt/hadoop-1.0.2 /opt/hadoop
=======================================================
#在namenode上启动
cd /opt/hadoop
./bin/hadoop namenode -format
./bin/start-all.sh
#查看是否ok？
http://10.2.112.31:50030 #查看jobs
http://10.2.112.3*:50075 #查看hdfs文件
#在namenode上检查运行状况
./bin/hadoop dfsadmin -report
Configured Capacity: 301634404352 (280.92 GB)
Present Capacity: 228165107712 (212.5 GB)
DFS Remaining: 227872616448 (212.22 GB)
DFS Used: 292491264 (278.94 MB)
DFS Used%: 0.13%
Under replicated blocks: 1
Blocks with corrupt replicas: 0
Missing blocks: 0
-------------------------------------------------
Datanodes available: 2 (2 total, 0 dead)
Name: 10.2.112.30:50010
Decommission Status : Normal
Configured Capacity: 150817202176 (140.46 GB)
DFS Used: 142901248 (136.28 MB)
Non DFS Used: 36415545344 (33.91 GB)
DFS Remaining: 114258755584(106.41 GB)
DFS Used%: 0.09%
DFS Remaining%: 75.76%
Last contact: Wed Apr 11 19:26:10 CST 2012
Name: 10.2.112.34:50010
Decommission Status : Normal
Configured Capacity: 150817202176 (140.46 GB)
DFS Used: 149590016 (142.66 MB)
Non DFS Used: 37053751296 (34.51 GB)
DFS Remaining: 113613860864(105.81 GB)
DFS Used%: 0.1%
DFS Remaining%: 75.33%
Last contact: Wed Apr 11 19:26:11 CST 2012
Present Capacity: 228165107712 (212.5 GB)
DFS Remaining: 227872616448 (212.22 GB)
DFS Used: 292491264 (278.94 MB)
DFS Used%: 0.13%
Under replicated blocks: 1
Blocks with corrupt replicas: 0
Missing blocks: 0
-------------------------------------------------
Datanodes available: 2 (2 total, 0 dead)
Name: 10.2.112.30:50010
Decommission Status : Normal
Configured Capacity: 150817202176 (140.46 GB)
DFS Used: 142901248 (136.28 MB)
Non DFS Used: 36415545344 (33.91 GB)
DFS Remaining: 114258755584(106.41 GB)
DFS Used%: 0.09%
DFS Remaining%: 75.76%
Last contact: Wed Apr 11 19:26:10 CST 2012
Name: 10.2.112.34:50010
Decommission Status : Normal
Configured Capacity: 150817202176 (140.46 GB)
DFS Used: 149590016 (142.66 MB)
Non DFS Used: 37053751296 (34.51 GB)
DFS Remaining: 113613860864(105.81 GB)
DFS Used%: 0.1%
DFS Remaining%: 75.33%
Last contact: Wed Apr 11 19:26:11 CST 2012
提示2个datanode，包括使用情况。
本文转自博客园沉睡森林@漂在北京的博客，原文链接：hadoop安装小记，如需转载请自行联系原博主。
