如何搭建Hadoop伪分布式集群？

wget http://mirrors.hust.edu.cn/apache/hadoop/common/hadoop-2.6.5/hadoop-2.6.5.tar.gz

mkdir /bigdata
tar -zxvf hadoop-2.6.5.tar.gz -C /bigdata

cd /bigdata/hadoop-2.6.5/etc/hadoop

export JAVA_HOME=/usr/lib/jvm/java

 <configuration>
   <!-- 配置hdfs的namenode的地址-->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://master</value>
    <property>
    <!-- 配置Hadoop运行时产生数据的存储目录，注意：不是临时数据 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/home/hadoop/local/var/hadoop/tmp/hadoop~${user.name}</value>
    </property>
</configuration>

 <configuration>
   <!-- 指定HDFS存储数据的副本数据量-->
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    <property>
</configuration>

 <configuration>
   <!-- 指定MapReduce编程模型运行在YARN上-->
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    <property>
</configuration>

<configuration>
    <!-- 指定YARN的resourcemanager的地址（伪分布式时就是主机名，localhost或IP地址都行） -->
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>master</value>
    <property>

    <!--  MapReduce执行shuffle时获取数据的方式 -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    <property>
</configuration>

192.168.29.188 master

cd hadoop/hadoop-2.6.5/bin

hadoop namenode -format

cd hadoop/hadoop-2.6.5/sbin

//在hadoop-2.x中，推荐使用start-dfs.sh和start-yarn.sh来分别启动
start-all.sh

8707    DataNode
8580    NameNode
9013    ResourceManager
8873    SecondaryNameNode
18057   Application
9308    NodeManager
17644   Jps