Hadoop 1.0.3 在CentOS 6.2上安装过程 [个人安装通过的全程记录]

 

//安装SSH 

[root@localhost /]# sudo yum install ssh

 

//生成密钥 

 

 

[root@localhost /]# ssh-keygen 

（可以一路回车）

生成下面两个文件：

/root/.ssh/id_rsa

/root/.ssh/id_rsa.pub

 

[root@localhost .ssh]# cd /root/.ssh/ 

 

//实际情况是把公钥复制到另外一台机器上，并且写入到另外一台机器上的authorized_keys文件中 

 

[root@localhost .ssh]# cat ./id_rsa.pub>>./authorized_keys

 

 

 

[root@localhost .ssh]# cd /home

（另外一个更简单的复制方法是使用 ssh-copy-id -i ~/.ssh/id_rsa.pub  root@192.168.1.201）

 

//配置JDK环境变量 

 

[root@localhost opt]# vi /etc/profile

 

 

export JAVA_HOME=/opt/jdk1.6.0_31

export PATH=$JAVA_HOME/bin:$PATH:.

//使配置生效

 

[root@localhost opt]# source /etc/profile

 

//安装Hadoop 1.0.3 

 

 

[root@localhost opt]# rpm -i hadoop-1.0.3-1.x86_64.rpm

 

//查看安装后的Hadoop版本号信息

 

[root@localhost opt]# hadoop version

 

(如果报错，请检查 hadoop-env.sh 中的java路径配置是否正确)

 

 

修改hadoop配置文件（/etc/hadoop）

[root@localhost hadoop]# cd /etc/hadoop  

 

[root@localhost hadoop]# vi hadoop-env.sh

 

 

export JAVA_HOME=/opt/jdk1.6.0_31

 

 

 

[root@localhost hadoop]# vi core-site.xml

 

 

<configuration>

<property>

<name>fs.default.name</name>

<value>hdfs://192.168.1.101:9000</value>

</property>

<property>

<name>hadoop.tmp.dir</name>

<value>/hadoop</value>

</property>

</configuration>

 

 

 

[root@localhost hadoop]# vi hdfs-site.xml

 

 

<configuration>

<property>

<name>dfs.replication</name>

<value>1</value>

</property>

</configuration>

 

 

 

[root@localhost hadoop]# vi mapred-site.xml

 

 

<configuration>

<property>

<name>mapred.job.tracker</name>

<value>192.168.1.101:9001</value>

</property>

</configuration>

 

//格式化文件系统 

 

 

[root@localhost opt]# hadoop namenode -format

 

 

//启动Hadoop相关的所有服务 (/usr/sbin)

[root@localhost sbin]# start-all.sh

或 

[root@localhost opt]# /usr/sbin/start-all.sh

 

 

（如果没有执行权限，需要将/usr/sbin目录下的相关sh文件设置执行权限）

 

说明：

 

start-all.sh

stop-all.sh

start-dfs.sh

stop-dfs.sh

start-mapred.sh

stop-mapred.sh

slaves.sh

 

 

 //jps查看已经启动的服务进程信息

 

 

[root@localhost hadoop]# jps

 

 

5131 NameNode

5242 DataNode

5361 SecondaryNameNode

5583 TaskTracker

5463 JobTracker

6714 Jps

 

 

防火墙需要开放的端口：

9000

9001  

50010

 

 

 

(访问 http://192.168.1.101:50070  http://192.168.1.101:50030)

[root@localhost hadoop]# hadoop dfsadmin -report

 

 

 

为运行例子 wordcount 作准备

[root@localhost opt]# hadoop fs -mkdir input

 

 

[root@localhost opt]# echo "Hello World Bye World" > file01

[root@localhost opt]# echo "Hello Hadoop Goodbye Hadoop" > file02

 

 

[root@localhost opt]# hadoop fs -copyFromLocal ./file0* input

 

 

 

运行例子 wordcount

[root@localhost opt]# hadoop jar /usr/share/hadoop/hadoop-examples-1.0.3.jar wordcount input output

 

 

12/08/11 12:00:30 INFO input.FileInputFormat: Total input paths to process : 2

12/08/11 12:00:30 INFO util.NativeCodeLoader: Loaded the native-hadoop library

12/08/11 12:00:30 WARN snappy.LoadSnappy: Snappy native library not loaded

12/08/11 12:00:31 INFO mapred.JobClient: Running job: job_201208111137_0001

12/08/11 12:00:32 INFO mapred.JobClient:  map 0% reduce 0%

12/08/11 12:01:05 INFO mapred.JobClient:  map 100% reduce 0%

12/08/11 12:01:20 INFO mapred.JobClient:  map 100% reduce 100%

12/08/11 12:01:25 INFO mapred.JobClient: Job complete: job_201208111137_0001

12/08/11 12:01:25 INFO mapred.JobClient: Counters: 29

12/08/11 12:01:25 INFO mapred.JobClient:   Job Counters 

12/08/11 12:01:25 INFO mapred.JobClient:     Launched reduce tasks=1

12/08/11 12:01:25 INFO mapred.JobClient:     SLOTS_MILLIS_MAPS=49499

12/08/11 12:01:25 INFO mapred.JobClient:     Total time spent by all reduces waiting after reserving slots (ms)=0

12/08/11 12:01:25 INFO mapred.JobClient:     Total time spent by all maps waiting after reserving slots (ms)=0

12/08/11 12:01:25 INFO mapred.JobClient:     Launched map tasks=2

12/08/11 12:01:25 INFO mapred.JobClient:     Data-local map tasks=2

12/08/11 12:01:25 INFO mapred.JobClient:     SLOTS_MILLIS_REDUCES=12839

12/08/11 12:01:25 INFO mapred.JobClient:   File Output Format Counters 

12/08/11 12:01:25 INFO mapred.JobClient:     Bytes Written=41

12/08/11 12:01:25 INFO mapred.JobClient:   FileSystemCounters

12/08/11 12:01:25 INFO mapred.JobClient:     FILE_BYTES_READ=79

12/08/11 12:01:25 INFO mapred.JobClient:     HDFS_BYTES_READ=276

12/08/11 12:01:25 INFO mapred.JobClient:     FILE_BYTES_WRITTEN=64705

12/08/11 12:01:25 INFO mapred.JobClient:     HDFS_BYTES_WRITTEN=41

12/08/11 12:01:25 INFO mapred.JobClient:   File Input Format Counters 

12/08/11 12:01:25 INFO mapred.JobClient:     Bytes Read=50

12/08/11 12:01:25 INFO mapred.JobClient:   Map-Reduce Framework

12/08/11 12:01:25 INFO mapred.JobClient:     Map output materialized bytes=85

12/08/11 12:01:25 INFO mapred.JobClient:     Map input records=2

12/08/11 12:01:25 INFO mapred.JobClient:     Reduce shuffle bytes=85

12/08/11 12:01:25 INFO mapred.JobClient:     Spilled Records=12

12/08/11 12:01:25 INFO mapred.JobClient:     Map output bytes=82

12/08/11 12:01:25 INFO mapred.JobClient:     CPU time spent (ms)=4770

12/08/11 12:01:25 INFO mapred.JobClient:     Total committed heap usage (bytes)=246751232

12/08/11 12:01:25 INFO mapred.JobClient:     Combine input records=8

12/08/11 12:01:25 INFO mapred.JobClient:     SPLIT_RAW_BYTES=226

12/08/11 12:01:25 INFO mapred.JobClient:     Reduce input records=6

12/08/11 12:01:25 INFO mapred.JobClient:     Reduce input groups=5

12/08/11 12:01:25 INFO mapred.JobClient:     Combine output records=6

12/08/11 12:01:25 INFO mapred.JobClient:     Physical memory (bytes) snapshot=391634944

12/08/11 12:01:25 INFO mapred.JobClient:     Reduce output records=5

12/08/11 12:01:25 INFO mapred.JobClient:     Virtual memory (bytes) snapshot=3159781376

12/08/11 12:01:25 INFO mapred.JobClient:     Map output records=8

 

 

 

//查看统计结果

[root@localhost opt]# hadoop fs -cat output/part-r-00000

 

 

Bye1

Goodbye1

Hadoop2

Hello2

World2

 

 

//---------------------------------------

作业日志存放目录：

/var/log/hadoop/root/userlogs/

 

 

//---------------------------------------

安装 hadoop-1.0.3-1 后，存放的目录有：

 

/etc/hadoop

/var/run/hadoop

/var/log/hadoop

/usr/share/hadoop

/usr/share/doc/hadoop

/usr/etc/hadoop

/usr/bin/hadoop（文件）

/usr/include/hadoop