hadoop2.6.1 的搭建与启动

hadoop2.6.1的配置

cd hadoop2.6.1/etc/hadoop

vim hadoop-env.sh

添加Java环境

export JAVA_HOME=/usr/local/src/jdk1.8.0_172

 

vim yarn-env.sh

 添加Java环境

export JAVA_HOME=/usr/local/jdk1.8.0_172

 

vim slaves

添加如下：

slave1

slave2

 

vim  core-site.xml

<configuration>
    <property>
       <name>fs.defaultFS</name>
        <!-- 这个是HDFS的路径-->
       <value>hdfs://master:9000</value>  
     </property>

     <property>
        <name>hadoop.tmp.dir</name>
        <value>file:/usr/local/src/hadoop-2.6.1/tmp</value>
     </property>

</configuration>

 

vim hdfs-site.xml

<configuration>
   <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>master:9001</value>
   </property>
   <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:/usr/local/src/hadoop-2.6.1/dfs/name</value>
   </property>

   <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:/usr/local/src/hadoop-2.6.1/dfs/data</value>
   </property>
   <property>
        <name>dfs.replication</name>
        <value>3</value>
   </property>

</configuration>

vim mapred-site.xml

<configuration>
   <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
   </property>
</configuration>

 

vim yarn-site.xml

<configuration>
    <property>
         <name>yarn.nodemanager.aux-services</name>
         <value>mapreduce_shuffle</value>
    </property>
    <property>
         <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
         <value>org.apache.hadoop.mapred.ShuffleHandler</value>
    </property>
    <property>
         <name>yarn.resourcemanager.address</name>
         <value>master:8032</value>
    </property>
    <property>
         <name>yarn.resourcemanager.scheduler.address</name>
         <value>master:8030</value>
    </property>
    <property>
         <name>yarn.resourcemanager.resource-tracker.address</name>
         <value>master:8035</value>
    </property>
    <property>
         <name>yarn.resourcemanager.admin.address</name>
         <value>master:8033</value>
    </property>
    <property>
         <name>yarn.resourcemanager.webapp.address</name>
         <value>master:8088</value>
    </property>
</configuration> 

 

2.创建临时目录和文件

mkdir /usr/local/src/hadoop-2.6.1/tmp

mkdir -p /usr/local/src/hadoop-2.6.1/dfs/name

mkdir -p /usr/local/src/hadoop-2.6.1/dfs/data

 

配置环境变量

vim  ~/.bashrc

export HADOOP_HOME=/usr/local/src/hadoop-2.6.1
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

环境变量生效

source  ~/.bashrc

4、拷贝安装包

scp -r /usr/local/src/hadoop-2.6.1 root@slave1:/usr/local/src/hadoop-2.6.1

scp -r /usr/local/src/hadoop-2.6.1 root@slave2:/usr/local/src/hadoop-2.6.1

 

5.启动集群

初始化 Namenode

hadoop namenode -format

./sbin/start-all.sh

Jps

http://master:8088  --> 网页查看界面

 

6、验证集群是否正常

hadoop fs -ls /

hadoop fs -put /etc/passwd /

hadoop fs -ls /         ---> （看到说明成功，但是mapreduce没跑可能看出来不准确）

hadoop fs -cat /passwd

 

----------------------------------------------------------------------------

配置Mapreduce，wordcount

cd /home/ badou

ls

mkdir badou_test

ls

cd /usr/local/src/

mv mapreduce_wordcount_python/  /home/badou/badou_test/

cd mapreduce_wordcount_python/

ls

hadoop fs -put 1.data /

hadoop fs -ls /1.data

vim run.sh