hadoop集群搭建
1.配置jdk环境
##jdk1.8
export JAVA_HOME=/mydata/jdk1.8.0_151
export PATH=$JAVA_HOME/bin:$PATH
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
2.解压tar包
3.配置hadoop环境
#hadoop
export HADOOP_HOME=/mydata/hadoop-2.7.4
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
4.修改主机名，配置host解析文件
hostnamectl set-hostname hadoop1
172.16.233.173 hadoop3
172.16.233.174 hadoop1
172.16.233.175 hadoop2
5.配置免密登录
ssh-copy-id -i .ssh/id_rsa.pub 172.16.233.174
ssh-copy-id -i .ssh/id_rsa.pub hadoop1
6.配置hadoop文件
hdfs-site.xml
<!-- 设置secondarynamenode的http通讯地址 -->
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop1:50090</value>
</property><!-- 设置namenode存放的路径 -->
<property>
<name>dfs.namenode.name.dir</name>
<value>/mydata/hadoop-2.7.4/hdfs/name</value>
</property><!-- 设置hdfs副本数量 -->
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
<!-- 设置datanode存放的路径 -->
<property>
<name>dfs.datanode.data.dir</name>
<value>/mydata/hadoop-2.7.4/hdfs/data</value>
</property>
core-site.xml
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop1:9000</value>
</property>
<!-- 指定hadoop运行时产生文件的存储目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/mydata/hadoop-2.7.4/hdfs/tmp</value>
</property>
yarn-site.xml
<property>
<name>yarn.resourcemanager.address</name>
<value>hadoop1:18040</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>hadoop1:18030</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>hadoop1:8088</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>hadoop1:18025</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>hadoop1:18141</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<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.nodemanager.resource.cpu-vcores</name>
<value>1</value>
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>1600</value>
</property>
mapred-site.xml
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<!-- 历史服务器端地址 -->
<property>
<name>mapreduce.jobhistory.address</name>
<value>hadoop1:10020</value>
</property>
<!-- 历史服务器web端地址 -->
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>hadoop1:19888</value>
</property>
启动历史服务器： mr-jobhistory-daemon.sh start historyserver
7.将hadoop文件夹拷贝到其他服务器
8.初始化主节点的namenode
hdfs namenode -format
9.启动集群 start-all.sh
10.页面观察hadoop集群运行情况
8088端口