ubuntu16.04安装Hadoop2.7.2伪分布学习环境

（1）raini@biyuzhe:~$ gedit .bashrc

#java
export JAVA_HOME=/home/raini/app/jdk1.7.0_79
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib:$CLASSPATH
export PATH=${JAVA_HOME}/bin:$JRE_HOME/bin:$PATH

#scala
export SCALA_HOME=/home/raini/app/scala-2.10.6
export PATH=${SCALA_HOME}/bin:$PATH

#spark
export SPARK_HOME=/home/raini/spark1
export PATH=$PATH:$SPARK_HOME/bin:$PATH

# hadoop2.6
export HADOOP_PREFIX=/home/raini/hadoop2
export CLASSPATH=".:$JAVA_HOME/lib:$CLASSPATH"
export PATH="$JAVA_HOME/:$HADOOP_PREFIX/bin:$PATH"
export HADOOP_PREFIX PATH CLASSPATH


（2）raini@biyuzhe:~$ sudo apt-get install rsync

（3）raini@biyuzhe:~$ sudo apt-get install openssh-server

cd ~/.ssh/   # 若没有该目录，请先执行一次ssh localhost
ssh-keygen -t rsa   # 会有提示，都按回车就可以
cat id_rsa.pub >> authorized_keys  # 加入授权
使用ssh localhost试试能否直接登录

（4）raini@biyuzhe:~$ sudo gedit /etc/hosts

127.0.0.1    localhost
127.0.1.1    biyuzhe
#10.155.243.206  biyuzhe
#有的说这里必须修改，否则后面会遇到连接拒绝等问题

# The following lines are desirable for IPv6 capable hosts
::1     ip6-localhost ip6-loopback
fe00::0 ip6-localnet
ff00::0 ip6-mcastprefix
ff02::1 ip6-allnodes
ff02::2 ip6-allrouters

（5）修改配置文件：etc/hadoop/hadoop-env.sh

    export JAVA_HOME=/home/raini/app/jdk
    export HADOOP_COMMON_HOME=/home/raini/hadoop

（6）raini@biyuzhe:~$ gedit .bashrc

    添加export PATH="/home/raini/hadoop/bin:/home/raini/hadoop/sbin:
    如  export PATH="/home/raini/hadoop/bin:/home/raini/hadoop/sbin:   $JAVA_HOME/:$HADOOP_PREFIX/bin:$PATH"

（7）修改文件etc/hadoop/core-site.xml

<configuration>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>file:/home/raini/hadoop/tmp</value>
        <description>Abase for other temporary directories.</description>
    </property>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://localhost:9000</value>
    </property>
  <property>
      <name>io.file.buffer.size</name>
      <value>131072</value>
    </property>
   <property>
       <name>hadoop.proxyuser.master.hosts</name>
        <value>*</value>
   </property>
   <property>
       <name>hadoop.proxyuser.master.groups</name>
       <value>*</value>
   </property>
</configuration>


（8）修改etc/hadoop/hdfs-site.xml:

<configuration>
  <!-- spark 配置主节点名 和 端口号
      <property>
            <name>dfs.namenode.secondary.http-address</name>
            <value>localhost:9001</value>
     </property>-->
  <!-- 虽然只需要配置 fs.defaultFS 和 dfs.replication 就可以运行（官方教程如此），
       不过若没有配置 hadoop.tmp.dir 参数，则默认使用的临时目录为 /tmp/hadoo-hadoop，
       由于系统重启后，找不到namenode进程，这是因为这个目录在重启时有可能被系统清理掉，而导致必须重新执行 format 才行,所以加入下面配置。 -->
     <property>
            <name>dfs.namenode.name.dir</name>
            <value>file:/home/raini/hadoop/tmp/dfs/namenode</value>
     </property>
     <property>
            <name>dfs.datanode.data.dir</name>
            <value>file:/home/raini/hadoop/tmp/dfs/datanode</value>
     </property>

  <!-- 配置副本数 -->
     <property>
            <name>dfs.replication</name>
            <value>1</value>
     </property>
  <!-- 不为ture就不能使用 webhdfs 的 LISTSTATUS（liststatus）,list-filestatus等需要列出文件 文件状态的命令。因为这些信息都是由 namenode 保存的  -->
     <property>
            <name>dfs.webhdfs.enabled</name>
            <value>true</value>
     </property>
</configuration>


（9）修改配置文件mapred-site.xml

<configuration>

    <property>
          <name>mapreduce.framework.name</name>
          <value>yarn</value>
    </property>
<!--
    <property>
          <name>mapred.job.tracker</name>
          <value>localhost:9001</value>  旧的吧？
    </property>
-->
    <property>
          <name>mapreduce.jobhistory.address</name>
          <value>localhost:10020</value>
    </property>

     <property>
          <name>mapreduce.jobhistory.webapp.address</name>
          <value>localhost:19888</value>
     </property>

</configuration>


（10）修改配置文件yarn-site.xml

<configuration>  

<!-- Site specific YARN configuration properties-->

    <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>
<!--resourcemanager 的 地址 -->
    <property>
       <name>yarn.resourcemanager.address</name>
       <value>localhost:8032</value>
    </property>
<!--resourcemanager 调度器端口 -->
    <property>
         <name>yarn.resourcemanager.scheduler.address</name>
         <value>localhost:8030</value>
    </property>

    <property>
         <name>yarn.resourcemanager.resource-tracker.address</name>
         <value>localhost:8031</value>
    </property>
<!--resourcemanager 管理器端口-->
     <property>
        <name>yarn.resourcemanager.admin.address</name>
        <value>localhost:8033</value>
    </property>
<!--resourcemanager 的 Web 端口，监控 job 的资源调度 -->
    <property>
         <name>yarn.resourcemanager.webapp.address</name>
         <value>localhost:8088</value>
    </property>

</configuration>


(11)    raini@biyuzhe:~$ source .bashrc
   
    raini@biyuzhe:~/hadoop$ sbin/start-dfs.sh

Starting namenodes on [localhost]
localhost: starting namenode, logging to /home/raini/app/hadoop-2.7.2/logs/hadoop-raini-namenode-biyuzhe.out
biyuzhe: starting datanode, logging to /home/raini/app/hadoop-2.7.2/logs/hadoop-raini-datanode-biyuzhe.out
Starting secondary namenodes [0.0.0.0]
The authenticity of host '0.0.0.0 (0.0.0.0)' can't be established.
ECDSA key fingerprint is SHA256:7Th7Qu6av5WOqmmVLemv3YN+52LAcHw4BuFBNwBt5DU.
Are you sure you want to continue connecting (yes/no)? yes
0.0.0.0: Warning: Permanently added '0.0.0.0' (ECDSA) to the list of known hosts.
0.0.0.0: starting secondarynamenode, logging to /home/raini/app/hadoop-2.7.2/logs/hadoop-raini-secondarynamenode-biyuzhe.out
raini@biyuzhe:~/hadoop$ jps
14242 Jps
14106 SecondaryNameNode
13922 DataNode------------------(无namenode)


(12) raini@biyuzhe:~/hadoop$ hdfs namenode -format

raini@biyuzhe:~/hadoop$ sbin/stop-dfs.sh
Stopping namenodes on [localhost]
localhost: no namenode to stop
biyuzhe: stopping datanode
Stopping secondary namenodes [0.0.0.0]
0.0.0.0: stopping secondarynamenode

raini@biyuzhe:~/hadoop$ sbin/start-dfs.sh
Starting namenodes on [localhost]
localhost: starting namenode, logging to /home/raini/app/hadoop-2.7.2/logs/hadoop-raini-namenode-biyuzhe.out
biyuzhe: starting datanode, logging to /home/raini/app/hadoop-2.7.2/logs/hadoop-raini-datanode-biyuzhe.out
Starting secondary namenodes [0.0.0.0]
0.0.0.0: starting secondarynamenode, logging to /home/raini/app/hadoop-2.7.2/logs/hadoop-raini-secondarynamenode-biyuzhe.out

raini@biyuzhe:~/hadoop$ jps
14919 NameNode-----------------------（namenode）
15407 Jps
15271 SecondaryNameNode
15073 DataNode


（13）raini@biyuzhe:~/hadoop$ sbin/start-yarn.sh  

starting yarn daemons
starting resourcemanager, logging to /home/raini/hadoop/logs/yarn-raini-resourcemanager-biyuzhe.out
biyuzhe: starting nodemanager, logging to /home/raini/app/hadoop-2.7.2/logs/yarn-raini-nodemanager-biyuzhe.out
raini@biyuzhe:~/hadoop$ jps
15625 NodeManager
14919 NameNode
15271 SecondaryNameNode
15073 DataNode
15937 Jps
15501 ResourceManager


（14）验证： yarn：http://localhost:8088/
        http://localhost:50070
  Overview 'localhost:9000' (active)

Started:	Sat Apr 23 14:04:17 CST 2016
Version:	2.7.2, rb165c4fe8a74265c792ce23f546c64604acf0e41
Compiled:	2016-01-26T00:08Z by jenkins from (detached from b165c4f)
Cluster ID:	CID-b0ad8d51-6ea3-4bfc-a1d8-ee0cbc9a8ff6
Block Pool ID:	BP-890697487-127.0.1.1-1461391390144

多谢楼主