hadoop 2.7.3 集群安装

三台虚拟机，centos6.5

127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::         localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.59.130 m1
192.168.59.131 s1
192.168.59.132 s2

修改主机名

[root@m1 hadoop]# cat /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=m1

修改主机映射

[root@m1 hadoop]# cat /etc/hosts
127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::         localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.59.130 m1
192.168.59.131 s1
192.168.59.132 s2

ssh免密码登陆（注意！ 要求每台机子互相都能ssh包括本机）

ssh-keygen -t rsa
ssh-copy-id -i ~/.ssh/id_rsa.pub m2

安装jdk

http://www.cnblogs.com/xiaojf/p/6568426.html

安装hadoop2.7.3

解压，重命名

[root@m1 soft]# ll
total
drwxr-xr-x.   root root  Aug    hadoop
drwxr-xr-x.   root root  Mar  : jar
drwxr-xr-x.   uucp    Dec  : jdk
drwxr-xr-x.   root root  Mar  : kafka
drwxrwxr-x.      Mar     scala-2.11.
drwxr-xr-x.   root root  Mar  : tmp
drwxr-xr-x.     Aug    zookeeper-3.4.

创建目录存放日志文件还要有数据文件

mkdir -p /usr/local/soft/tmp/hadoop/tmp
mkdir -p /usr/local/soft/tmp/hadoop/dfs/name
mkdir -p /usr/local/soft/tmp/hadoop/dfs/data

修改配置文件

[root@m1 soft]# cd /usr/local/soft/hadoop/etc/hadoop/
[root@m1 hadoop]# ll
total
-rw-r--r--.  root root   Aug    capacity-scheduler.xml
-rw-r--r--.  root root   Aug    configuration.xsl
-rw-r--r--.  root root    Aug    container-executor.cfg
-rw-r--r--.  root root    Aug    core-site.xml
-rw-r--r--.  root root   Aug    hadoop-env.cmd
-rw-r--r--.  root root   Aug    hadoop-env.sh
-rw-r--r--.  root root   Aug    hadoop-metrics2.properties
-rw-r--r--.  root root   Aug    hadoop-metrics.properties
-rw-r--r--.  root root   Aug    hadoop-policy.xml
-rw-r--r--.  root root    Aug    hdfs-site.xml
-rw-r--r--.  root root   Aug    httpfs-env.sh
-rw-r--r--.  root root   Aug    httpfs-log4j.properties
-rw-r--r--.  root root     Aug    httpfs-signature.secret
-rw-r--r--.  root root    Aug    httpfs-site.xml
-rw-r--r--.  root root   Aug    kms-acls.xml
-rw-r--r--.  root root   Aug    kms-env.sh
-rw-r--r--.  root root   Aug    kms-log4j.properties
-rw-r--r--.  root root   Aug    kms-site.xml
-rw-r--r--.  root root  Aug    log4j.properties
-rw-r--r--.  root root    Aug    mapred-env.cmd
-rw-r--r--.  root root   Aug    mapred-env.sh
-rw-r--r--.  root root   Aug    mapred-queues.xml.template
-rw-r--r--.  root root    Aug    mapred-site.xml.template
-rw-r--r--.  root root     Aug    slaves
-rw-r--r--.  root root   Aug    ssl-client.xml.example
-rw-r--r--.  root root   Aug    ssl-server.xml.example
-rw-r--r--.  root root   Aug    yarn-env.cmd
-rw-r--r--.  root root   Aug    yarn-env.sh
-rw-r--r--.  root root    Aug    yarn-site.xml

yarn-env.sh

[root@m1 hadoop]# vi yarn-env.sh 

# Licensed to the Apache Software Foundation (ASF) under one

# or more contributor license agreements.  See the NOTICE file

# distributed with this work for additional information

# regarding copyright ownership.  The ASF licenses this file

# to you under the Apache License, Version 2.0 (the

# "License"); you may not use this file except in compliance

# with the License.  You may obtain a copy of the License at

#

#     http://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

# 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.

export JAVA_HOME=/usr/local/soft/jdk

slaves

[root@m1 hadoop]# vi slaves 
s1
s2

core-site.xml

<configuration>

      <property>

        <name>fs.defaultFS</name>

       <value>hdfs://m1:9000</value>

    </property>

    <property>

        <name>io.file.buffer.size</name>

        <value></value>

    </property>

    <property>

        <name>hadoop.tmp.dir</name>

       <value>file:/usr/local/soft/tmp/hadoop/tmp</value>

        <description>Abase for other temporary  directories.</description>

    </property>

</configuration>

hdfs-site.xml

<configuration>
       <property>
                <name>dfs.namenode.secondary.http-address</name>
               <value>m1:9001</value>
       </property>
     <property>
             <name>dfs.namenode.name.dir</name>
             <value>file:/usr/hadoop/dfs/name</value>
       </property>
      <property>
              <name>dfs.datanode.data.dir</name>
              <value>file:/usr/hadoop/dfs/data</value>
       </property>
       <property>
               <name>dfs.replication</name>
               <value>2</value>
        </property>
        <property>
                 <name>dfs.webhdfs.enabled</name>
                  <value>true</value>
         </property>
</configuration>

mapred-site.xml

<configuration>

      <property>                                                                 

        <name>mapreduce.framework.name</name>

                <value>yarn</value>

           </property>

          <property>

                 <name>mapreduce.jobhistory.address</name>

                  <value>m1:</value>

          </property>

          <property>

               <name>mapreduce.jobhistory.webapp.address</name>

               <value>m1:</value>

       </property>

</configuration>

yarn-site.xml

<configuration>

<!-- Site specific YARN configuration properties -->

        <property>

              <name>yarn.nodemanager.aux-services</name>

              <value>mapreduce_shuffle</value>

        </property>

        <property>                                                              

<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>

              <value>org.apache.hadoop.mapred.ShuffleHandler</value>

        </property>

        <property>

              <name>yarn.resourcemanager.address</name>

              <value>m1:</value>

       </property>

       <property>

               <name>yarn.resourcemanager.scheduler.address</name>

              <value>m1:</value>

       </property>

       <property>

           <name>yarn.resourcemanager.resource-tracker.address</name>

             <value>m1:</value>

      </property>

      <property>

             <name>yarn.resourcemanager.admin.address</name>

              <value>m1:</value>

       </property>

       <property>

              <name>yarn.resourcemanager.webapp.address</name>

              <value>m1:</value>

       </property>

</configuration>

设置Hadoop环境变量

export HADOOP_HOME=/usr/local/soft/hadoop
export PATH=$PATH:$HADOOP_HOME/sbin:$HADOOP_HOME/bin

分发代码

[root@m1 soft]# scp -r hadoop root@s2:/usr/local/soft/

namenode format

[root@m1 soft]# hdfs namenode -format
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

// :: INFO namenode.NameNode: STARTUP_MSG:
/************************************************************
STARTUP_MSG: Starting NameNode
STARTUP_MSG:   host = m1/192.168.59.130
STARTUP_MSG:   args = [-format]
STARTUP_MSG:   version = 2.7.3

启动

[root@m1 soft]# start-all.sh
This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh
Starting namenodes on [m1]
m1: starting namenode, logging to /usr/local/soft/hadoop/logs/hadoop-root-namenode-m1.out
s1: starting datanode, logging to /usr/local/soft/hadoop/logs/hadoop-root-datanode-s1.out
s2: starting datanode, logging to /usr/local/soft/hadoop/logs/hadoop-root-datanode-s2.out
Starting secondary namenodes [master]
master: ssh: Could not resolve hostname master: Name or service not known
starting yarn daemons
starting resourcemanager, logging to /usr/local/soft/hadoop/logs/yarn-root-resourcemanager-m1.out
s1: starting nodemanager, logging to /usr/local/soft/hadoop/logs/yarn-root-nodemanager-s1.out
s2: starting nodemanager, logging to /usr/local/soft/hadoop/logs/yarn-root-nodemanager-s2.out

验证

[root@m1 soft]# hadoop dfs -ls /
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

[root@m1 soft]# hadoop dfs -mkdir /xiaojf
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

[root@m1 soft]# hadoop dfs -ls /
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

Found  items
drwxr-xr-x   - root supergroup           -- : /xiaojf

完成