note

groupadd hadoop
useradd hadoop -G hadoop -g hadoop -p 123456


ssh-keygen -t rsa
cat *pub >>authorized_keys
service sshd restart

ssh-copy-id -i master.pub hadoop@slave2
ssh-copy-id -i master.pub hadoop@slave1
ssh-copy-id -i *pub hadoop@master

chmod 644 authorized_keys
/*
scp *pub hadoop@slave1:~/.ssh/
scp *pub hadoop@slave2:~/.ssh/
*/

cat *master* >> authorized_keys

vi .bash_profile
export HADOOP_HOME=/home/hadoop/hadoop-2.2.0
PATH=$PATH:$HOME/bin:$HADOOP_HOME/bin

source .bash_profile

mkdir -p  ~/dfs/name

mkdir -p  ~/dfs/data

mkdir -p  ~/temp

cd /home/hadoop/hadoop-2.2.0/etc/hadoop


vi core-site.xml

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

vi hdfs-site.xml

<property>
    <name>dfs.namenode.secondary.http-address</name>
    <value>master:9001</value>
</property>
<property>
    <name>dfs.namenode.name.dir</name>
    <value>file:/home/hadoop/dfs/name</value>
</property>
<property>
    <name>dfs.datanode.data.dir</name>
    <value>file:/home/hadoop/dfs/data</value>
</property>
<property>
    <name>dfs.replication</name>
    <value>3</value>
</property>
<property>
    <name>dfs.webhdfs.enabled</name>
    <value>true</value>
</property>

cp mapred-site.xml.template mapred-site.xml
vi mapred-site.xml
<property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
</property>
<property>
    <name>mapreduce.jobhistory.address</name>
    <value>master:10020</value>
</property>
<property>
    <name>mapreduce.jobhistory.webapp.address</name>
    <value>master:19888</value>
</property>



<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:8031</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>


scp -r hadoop-2.2.0 hadoop@slave2:/home/hadoop/


hdfs namenode –format

[hadoop@master hadoop-2.2.0]$ sbin/start-dfs.sh
Starting namenodes on [master]
master: starting namenode, logging to /home/hadoop/hadoop-2.2.0/logs/hadoop-hadoop-namenode-master.out
slave1: starting datanode, logging to /home/hadoop/hadoop-2.2.0/logs/hadoop-hadoop-datanode-slave1.out
slave2: starting datanode, logging to /home/hadoop/hadoop-2.2.0/logs/hadoop-hadoop-datanode-slave2.out
Starting secondary namenodes [master]
master: starting secondarynamenode, logging to /home/hadoop/hadoop-2.2.0/logs/hadoop-hadoop-secondarynamenode-master.out


[hadoop@master hadoop-2.2.0]$ sbin/start-yarn.sh
starting yarn daemons
starting resourcemanager, logging to /home/hadoop/hadoop-2.2.0/logs/yarn-hadoop-resourcemanager-master.out
slave2: starting nodemanager, logging to /home/hadoop/hadoop-2.2.0/logs/yarn-hadoop-nodemanager-slave2.out
slave1: starting nodemanager, logging to /home/hadoop/hadoop-2.2.0/logs/yarn-hadoop-nodemanager-slave1.out