Hadoop运行环境搭建

虚拟机配置要求

关闭防火墙

关闭防火墙开机自启

虚拟机可正常上网

安装vim

SSH无密登录配置

修改主机名称

[root@guo147 .ssh]# vim /etc/hostname

 主机名称映射

 后期会有很多配置IP地址的地方如后续需修改IP地址则改需要改动的地方较多设置映射后只需要改变一处即可

[root@guo147 .ssh]# vim /etc/hosts

生成公钥和私钥

[root@localhost ~]# ssh-keygen -t rsa -P ""

 输入命令后敲回车中间再敲一次回车就会生成两个文件id_rsa(私钥)、id_rsa.pub(公钥)

 

 将公钥拷贝到本地的authorized_keys和要免密登录的目标机器上

[root@localhost .ssh]# cat ./id_rsa.pub >> authorized_keys

[root@localhost .ssh]# ssh-copy-id -i ./id_rsa.pub -p22 root@192.168.153.146

远程登录

[root@localhost .ssh]# ssh -p22 root@192.168.153.146

 同步时间系统时间不正确时可设置

//安装同步时间插件
[root@localhost .ssh]# yum install -y ntpdate

//同步时间
[root@localhost .ssh]# ntpdate time.windows.com

定时更新时间
[root@localhost .ssh]# crontab -e
*/5 * * * * /usr/sbin/ntpdate -u time.windows.com
启动定时任务
[root@localhost .ssh]# service crond start/stop/restart/reload/status

安装JDK

解压文件到指定目录

 通过xftp把压缩包添加到install目录

[root@localhost install]# tar -zxvf ./jdk-8u321-linux-x64.tar.gz -C ../soft/

//同时把hadoop的压缩包也解压方便后续操作
[root@localhost install]# tar -zxvf ./hadoop-3.1.3.tar.gz -C ../soft/

配置JDK环境变量 

[root@localhost soft]# vim /etc/profile

# JAVA_HOME
export JAVA_HOME=/opt/soft/jdk180
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export PATH=$PATH:$JAVA_HOME/bin

//刷新配置文件
[root@localhost soft]# source /etc/profile

[root@localhost soft]# java -version

 出现以下内容配置成功

安装Hadoop

修改hadoop313文件及子目录文件的所有者

[root@guo147 hadoop313]# chown -R root:root ../hadoop313/

 修改配置文件

修改core-site.xml 

<configuration>
  <property>
    <name>fs.defaultFS</name>
    <value>hdfs://guo147:9000</value>
  </property>
  <property>
    <name>hadoop.tmp.dir</name>
    <value>/opt/soft/hadoop313/data</value>
    <description>namenode上本地的hadoop临时文件夹</description>
  </property>
  <property>
    <name>hadoop.http.staticuser.user</name>
    <value>root</value>
  </property>
  <property>
    <name>io.file.buffer.size</name>
    <value>131072</value>
    <description>读写队列缓存128K</description>
  </property>
  <property>
    <name>hadoop.proxyuser.root.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.root.groups</name>
    <value>*</value>
  </property>
</configuration> 

修改hadoop-env.sh 第54行内容 

54  export JAVA_HOME=/opt/soft/jdk18

 修改hdfs-site.xml

<configuration>
  <property>
    <name>dfs.replication</name>
    <value>1</value>
    <description>hadoop中每一个block文件的备份数量</description>
  </property>
  <property>
    <name>dfs.namenode.name.dir</name>
    <value>/opt/soft/hadoop313/data/dfs/name</value>
    <description>namenode上存储hdfsq名字空间元数据的目录</description>
  </property>
  <property>
    <name>dfs.datanode.data.dir</name>
    <value>/opt/soft/hadoop313/data/dfs/data</value>
    <description>datanode上数据块的物理存储位置目录</description>
  </property>
  <property>
    <name>dfs.permissions.enabled</name>
    <value>false</value>
    <description>关闭权限验证</description>
  </property>
</configuration>

修改mapred-site.xml

<property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
    <description>job执行框架 local, classic or yarn</description>
    <final>true</final>
  </property>
  <property>
    <name>mapreduce.application.classpath</name>
    <value>/opt/soft/hadoop313/etc/hadoop:/opt/soft/hadoop313/share/hadoop/common/lib/*:/opt/soft/hadoop313/share/hadoop/common/*:/opt/soft/hadoop313/share/hadoop/hdfs/*:/opt/soft/hadoop313/share/hadoop/hdfs/lib/*:/opt/soft/hadoop313/share/hadoop/mapreduce/*:/opt/soft/hadoop313/share/hadoop/mapreduce/lib/*:/opt/soft/hadoop313/share/hadoop/yarn/*:/opt/soft/hadoop313/share/hadoop/yarn/lib/*</value>
  </property>

  <property>
    <name>mapreduce.jobhistory.address</name>
    <value>guo147:10020</value>
  </property>
  <property>
    <name>mapreduce.jobhistory.webapp.address</name>
    <value>guo147:19888</value>
  </property>

  <property>
    <name>mapreduce.map.memory.mb</name>
    <value>1024</value>
  </property>
  <property>
    <name>mapreduce.reduce.memory.mb</name>
    <value>1024</value>
  </property>

修改yarn-site.xml

<property>
    <name>yarn.resourcemanager.connect.retry-interval.ms</name>
    <value>20000</value>
  </property>

  
  <property>
    <name>yarn.resourcemanager.scheduler.class</name>
    <value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler</value>
  </property>

  <property>
    <name>yarn.nodemanager.localizer.address</name>
    <value>guo147:8040</value>
  </property>

  <property>
    <name>yarn.nodemanager.address</name>
    <value>guo147:8050</value>
  </property>

  <property>
    <name>yarn.nodemanager.webapp.address</name>
    <value>guo147:8042</value>
  </property>

  <property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
  </property>

  <property>
    <name>yarn.nodemanager.local-dirs</name>
    <value>/opt/soft/hadoop313/yarndata/yarn</value>
  </property>

  <property>
    <name>yarn.nodemanager.log-dirs</name>
    <value>/opt/soft/hadoop313/yarndata/log</value>
  </property>

添加hadoop环境变量 

[root@guo147 hadoop]# vim /etc/profile

# HADOOP_HOME
export HADOOP_HOME=/opt/soft/hadoop313
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/lib
export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export HDFS_JOURNALNODE_USER=root
export HDFS_ZKFC_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export HADOOP_YARN_HOME=$HADOOP_HOME
export HADOOP_INSTALL=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_LIBEXEC_DIR=$HADOOP_HOME/libexec
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop

刷新配置文件 

[root@guo147 hadoop]# source /etc/profile

[root@guo147 hadoop]# echo $HADOOP_HOME

格式化hadoop配置

[root@guo147 hadoop]# hdfs namenode -format

启动服务 

[root@guo147 hadoop]# start-all.sh

[root@guo147 data]# jps

 出现以下六个服务配置完成