ubuntu 16.0安装 hadoop2.8.3

环境：ubuntu 16.0

需要软件：jdk ssh

https://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common/

2.8.3

安装 jdk并配置环境变量

安装ssh和rshync，主要设置免密登录

sudo apt-get install ssh

sudo apt-get install rshync

sh-keygen -t dsa -P '' -f ~/.ssh/id_dsa

cat ~/.ssh/id_dsa.pub >> ~/.ssh/authorized_keys

ssh

安装hadoop

root@hett-virtual-machine:/usr/local/hadoop# tar -xzvf /home/hett/Downloads/hadoop-2.8.3.tar.gz
root@hett-virtual-machine:/usr/local/hadoop# mv hadoop-2.8.3 hadoop
root@hett-virtual-machine:/usr/local# cd hadoop/
root@hett-virtual-machine:/usr/local/hadoop# mkdir tmp
root@hett-virtual-machine:/usr/local/hadoop# mkdir hdfs
root@hett-virtual-machine:/usr/local/hadoop# mkdir hdfs/data
root@hett-virtual-machine:/usr/local/hadoop# mkdir hdfs/name
root@hett-virtual-machine:/usr/local/hadoop# nano /etc/profile

配置
export HADOOP_HOME=/usr/local/hadoop
export JAVA_HOME=/usr/local/jdk1.8.0_151
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH:$HADOOP_HOME/bin

root@hett-virtual-machine:/usr/local/hadoop# source /etc/profile

root@hett-virtual-machine:/usr/local/hadoop# cd etc/hadoop/
root@hett-virtual-machine:/usr/local/hadoop/etc/hadoop# ls
capacity-scheduler.xml      httpfs-env.sh            mapred-env.sh
configuration.xsl           httpfs-log4j.properties mapred-queues.xml.template
container-executor.cfg      httpfs-signature.secret mapred-site.xml.template
core-site.xml               httpfs-site.xml          slaves
hadoop-env.cmd              kms-acls.xml             ssl-client.xml.example
hadoop-env.sh               kms-env.sh               ssl-server.xml.example
hadoop-metrics2.properties kms-log4j.properties     yarn-env.cmd
hadoop-metrics.properties   kms-site.xml             yarn-env.sh
hadoop-policy.xml           log4j.properties         yarn-site.xml
hdfs-site.xml               mapred-env.cmd
root@hett-virtual-machine:/usr/local/hadoop/etc/hadoop#

root@hett-virtual-machine:/usr/local/hadoop/etc/hadoop# nano hadoop-env.sh

export JAVA_HOME=/usr/local/jdk1.8.0_151

配置yarn-env.sh

export JAVA_HOME=/usr/local/jdk1.8.0_151

3）配置core-site.xml
添加如下配置：

<configuration>
 <property>
    <name>fs.default.name</name>
    <value>hdfs://localhost:9000</value>
    <description>HDFS的URI，文件系统://namenode标识:端口号</description>
</property>

<property>
    <name>hadoop.tmp.dir</name>
    <value>/usr/hadoop/tmp</value>
    <description>namenode上本地的hadoop临时文件夹</description>
</property>
</configuration>

4），配置hdfs-site.xml
添加如下配置

<configuration>
<!—hdfs-site.xml-->
<property>
    <name>dfs.name.dir</name>
    <value>/usr/hadoop/hdfs/name</value>
    <description>namenode上存储hdfs名字空间元数据 </description> 
</property>

<property>
    <name>dfs.data.dir</name>
    <value>/usr/hadoop/hdfs/data</value>
    <description>datanode上数据块的物理存储位置</description>
</property>

<property>
    <name>dfs.replication</name>
    <value>1</value>
    <description>副本个数，配置默认是3,应小于datanode机器数量</description>
</property>
</configuration>

5），配置mapred-site.xml
添加如下配置：

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

6），配置yarn-site.xml
添加如下配置：

<configuration>
<property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
</property>
<property>
        <name>yarn.resourcemanager.webapp.address</name>
        <value>192.168.241.128:8099</value>
</property>
</configuration>

4，Hadoop启动
1）格式化namenode

$ bin/hdfs namenode –format

2）启动NameNode 和 DataNode 守护进程

$ sbin/start-dfs.sh

3）启动ResourceManager 和 NodeManager 守护进程

$ sbin/start-yarn.sh

$ 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

root@hett-virtual-machine:~# cd /usr/local/hadoop/
root@hett-virtual-machine:/usr/local/hadoop# sbin/start-all.sh
This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh
Starting namenodes on [localhost]
localhost: starting namenode, logging to /usr/local/hadoop/logs/hadoop-root-namenode-hett-virtual-machine.out
localhost: starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-hett-virtual-machine.out
........

5，启动验证
1）执行jps命令，有如下进程，说明Hadoop正常启动

# jps
6097 NodeManager
11044 Jps
7497 -- process information unavailable
8256 Worker
5999 ResourceManager
5122 SecondaryNameNode
8106 Master
4836 NameNode
4957 DataNode