OpenStack环境下Hadoop2.2.0环境搭建(3)

3. 安装配置Hadoop2.2.0

假定各node角色划分如下：

hdp-server-01    resourcemanager, nodemanager, proxyserver,historyserver, datanode, namenode
hdp-server-02    datanode, nodemanager
hdp-server-03    datanode, nodemanager

a. 目录准备

mkdir -p ~/yarn_data/tmp
mkdir -p ~/yarn_data/mapred

b. 配置环境变量（追加至~/.bashrc）

#hadoop env
export HADOOP_HOME="$HOME/hadoop-2.2.0"
export HADOOP_PREFIX="$HADOOP_HOME/"
export YARN_HOME=$HADOOP_HOME
export HADOOP_MAPRED_HOME="$HADOOP_HOME"
export HADOOP_COMMON_HOME="$HADOOP_HOME"
export HADOOP_HDFS_HOME="$HADOOP_HOME"
export HADOOP_CONF_DIR="$HADOOP_HOME/etc/hadoop/"
export YARN_CONF_DIR=$HADOOP_CONF_DIR
export PATH="$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH"

c. 修改官方启动脚本

$ cd $YARN_HOME/libexec/
$ vim hadoop-config.sh
#修改第96行代码为：
export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$1"
#保存退出vim

d. 设置配置文件

<!-- $YARN_HOME/etc/hadoop/core-site.xml -->

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="https://www.linuxidc.com/configuration.xsl"?>

<configuration>
  <property>
    <name>fs.defaultFS</name>
    <value>hdfs://hdp-server-01:9000</value>
  </property>
  <property>
    <name>hadoop.tmp.dir</name>
    <value>/home/yarn/yarn_data/tmp/hadoop-grid</value>
  </property>
</configuration>

<!-- $YARN_HOME/etc/hadoop/hdfs-site.xml -->

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="https://www.linuxidc.com/configuration.xsl"?>

<configuration>
  <property>
    <name>dfs.replication</name>
    <value>3</value>
  </property>
</configuration>

<!-- $YARN_HOME/etc/hadoop/yarn-site.xml -->

<?xml version="1.0"?>

<configuration>
  <property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
  </property>
  <property>
    <name>yarn.resourcemanager.address</name>
    <value>hdp-server-01:8032</value>
  </property>
  <property>
      <name>yarn.resourcemanager.resource-tracker.address</name>
      <value>hdp-server-01:8031</value>
  </property>
  <property>
      <name>yarn.resourcemanager.admin.address</name>
      <value>hdp-server-01:8033</value>
  </property>
  <property>
      <name>yarn.resourcemanager.scheduler.address</name>
      <value>hdp-server-01:8030</value>
  </property>
  <property>
      <name>yarn.nodemanager.loacl-dirs</name>
      <value>/home/yarn/yarn_data/mapred/nodemanager</value>
      <final>true</final>
  </property>
  <property>
      <name>yarn.web-proxy.address</name>
      <value>hdp-server-01:8888</value>
  </property>
  <property>
    <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
    <value>org.apache.hadoop.mapred.ShuffleHandler</value>
  </property>
</configuration>

<!-- $YARN_HOME/etc/hadoop/mapred-site.xml -->

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="https://www.linuxidc.com/configuration.xsl"?>

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

至此，配置文件修改完毕，修改完后将 $HOME/hadoop-2.2.0 及 $HOME/yarn_data 两个文件分别拷贝至其他机器的同样位置，注意确保文件所有者为yarn。