1、启动脚本文件
hadoop-env.sh
yarn-env.sh
2、参数配置文件
core-site.xml
hdfs-site.xml
yarn-site.xml
mapred-site.xml
3、集群主机文件
slaves
文件内容:
hadoop-env.sh添加:
export JAVA_HOME=/usr/java/jdk1.8.0_51 export HADOOP_CONF_DIR=/home/hadoop/hadoop/etc/hadoop
yarn-env.sh添加:
export JAVA_HOME=/usr/java/jdk1.8.0_51 export YARN_CONF_DIR=/home/hadoop/hadoop/etc/hadoop
core-site.xml
<configuration> <property> <name>hadoop.tmp.dir</name> <value>/home/hadoop/hdfs/tmp</value> <final>true</final> <description>A base for other temporary directories.</description> </property> <property> <name>fs.defaultFS</name> <value>hdfs://rhel01:8020</value> <final>true</final> </property> </configuration>
hdfs-site.xml
<configuration> <property> <name>dfs.replication</name> <value>2</value> </property> <property> <name>dfs.name.dir</name> <value>/home/hadoop/hdfs/name</value> </property> <property> <name>dfs.data.dir</name> <value>/home/hadoop/hdfs/data</value> </property> <property> <name>dfs.permissions</name> <value>false</value> </property> </configuration>
yarn-site.xml
<configuration> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> </configuration>
mapred-site.xml
<configuration> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> </configuration>
slaves
node01
node02
node03
环境变量:
.bash_profile
export JAVA_HOME=/usr/java/jdk1.8.0_51
export HADOOP_HOME=$HOME/hadoop
export SPARK_HOME=$HOME/spark
export HIVE_HOME=$HOME/hive
PATH=$PATH:$HOME/bin:$HOME/hadoop/bin:$HOME/hadoop/sbin:$HIVE_HOME/bin:$SPARK_HOME/bin
export JAVA_HOME=/usr/java/jdk1.8.0_51
export PATH=${JAVA_HOME}/bin:$PATH
export SCALA_HOME=/usr/scala
export PATH=${SCALA_HOME}/bin:$PATH
export HADOOP_HOME=/home/hadoop/hadoop
export LD_LIBRARY_PATH=$HADOOP_HOME/lib/native