hadoop伪分布式基本配置

• 安装目录
  

  /home/hadoop/hadoop-1.0.4
  复制代码

• 配置hosts
  

  192.168.0.101   hadoop.master
  复制代码

• 配置core-site.xml
  

  <?xml version="1.0"?>
  <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
  
  <!-- Put site-specific property overrides in this file. -->
  
  <configuration>
   <property>
    <name>fs.default.name</name>
    <value>hdfs://hadoop.master:9000</value>
   </property>
   <property>
    <name>hadoop.tmp.dir</name>
    <value>/home/hadoop/tmp</value>
   </property>
  </configuration>
  复制代码

• 配置hdfs-site.xml
  

  <?xml version="1.0"?>
  <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
  
  <!-- Put site-specific property overrides in this file. -->
  
  <configuration>
   <property>
     <name>dfs.replication</name>
     <value>1</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>
  </configuration>
  复制代码

• 配置mapred-site.xml
  

  <?xml version="1.0"?>
  <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
  
  <!-- Put site-specific property overrides in this file. -->
  
  <configuration>
   <property>
     <name>mapred.job.tracker</name>
     <value>hadoop.master:9001</value>
   </property>
  </configuration>
  复制代码

• 配置hadoop-env.sh
  

  # Set Hadoop-specific environment variables here.
  
  # The only required environment variable is JAVA_HOME.  All others are
  # optional.  When running a distributed configuration it is best to
  # set JAVA_HOME in this file, so that it is correctly defined on
  # remote nodes.
  
  # The java implementation to use.  Required.
   export JAVA_HOME=/usr/jdk1.6.0_22
  
  # Extra Java CLASSPATH elements.  Optional.
    export HADOOP_HOME=/home/hadoop/hadoop-1.0.4
  # export HADOOP_CLASSPATH=
  
  # The maximum amount of heap to use, in MB. Default is 1000.
  # export HADOOP_HEAPSIZE=2000
  
  # Extra Java runtime options.  Empty by default.
  # export HADOOP_OPTS=-server
  
  # Command specific options appended to HADOOP_OPTS when specified
  export HADOOP_NAMENODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_NAMENODE_OPTS"
  export HADOOP_SECONDARYNAMENODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_SECONDARYNAMENODE_OPTS"
  export HADOOP_DATANODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_DATANODE_OPTS"
  export HADOOP_BALANCER_OPTS="-Dcom.sun.management.jmxremote $HADOOP_BALANCER_OPTS"
  export HADOOP_JOBTRACKER_OPTS="-Dcom.sun.management.jmxremote $HADOOP_JOBTRACKER_OPTS"
  # export HADOOP_TASKTRACKER_OPTS=
  # The following applies to multiple commands (fs, dfs, fsck, distcp etc)
  # export HADOOP_CLIENT_OPTS
  
  # Extra ssh options.  Empty by default.
  # export HADOOP_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR"
  
  # Where log files are stored.  $HADOOP_HOME/logs by default.
  # export HADOOP_LOG_DIR=${HADOOP_HOME}/logs
  
  # File naming remote slave hosts.  $HADOOP_HOME/conf/slaves by default.
  # export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
  
  # host:path where hadoop code should be rsync'd from.  Unset by default.
  # export HADOOP_MASTER=master:/home/$USER/src/hadoop
  
  # Seconds to sleep between slave commands.  Unset by default.  This
  # can be useful in large clusters, where, e.g., slave rsyncs can
  # otherwise arrive faster than the master can service them.
  # export HADOOP_SLAVE_SLEEP=0.1
  
  # The directory where pid files are stored. /tmp by default.
  # export HADOOP_PID_DIR=/var/hadoop/pids
  
  # A string representing this instance of hadoop. $USER by default.
  # export HADOOP_IDENT_STRING=$USER
  
  # The scheduling priority for daemon processes.  See 'man nice'.
  # export HADOOP_NICENESS=10
  
    export PATH=$PATH:$HADOOP_HOME/bin
  复制代码