企业内部从零开始安装docker hadoop 提纲

下载apache 项目  http://mirror.bit.edu.cn/apache/

下载 centos 7 安装 盘 iso 大约7G

安装 centos7

copy 光盘盘中的 packages repodata  到硬盘

建立 httpd 服务修改 /etc/httpd/conf/httpd.conf 中的 docmentroot ??

service httpd start   .

如果有selinux  注意semanage  chcon restorecon  命令 保持 与 /var/www 一致的上下文 ,使用 ls -Z 查看

web网站建立后

编写 /etc/yum.repo.d 中的 文件 ,

测试 yum 命令  :  yum clean all ;yum makecache

如果有新的 rpm 也可放到 package目录 不过要使用 createrepo 重新建立 索引数据库

下载 docker 1.9

使用 rpm 安装

测试 service docker start

到 csphere 下载 安装 分析安装sh(找一个centos虚拟机在互联网上安装 然后 使用 docker save ;docker load 装载到企业本地) 主要管理docker 方便

使用网上的一个脚本建立 centos 的docker image https://raw.githubusercontent.com/docker/docker/master/contrib/mkimage-yum.sh

起名 centos

基于centos ,建立 jdk8  sshd 起名 jdk8:centos7

from centos7:7.2.

Add jdk-8u65-linux-x64.gz /usr/sbin
env JAVA_HOME  /usr/sbin/jdk1..0_65
env CLASSPATH   /usr/sbin/jdk1..0_65/lib/dt.jar:/usr/sbin/jdk1..0_65/lib/tool.jar

run echo   "JAVA_HOME=$JAVA_HOME;export JAVA_HOME;" >>/etc/profile
run echo   "CLASSPATH=$CLASSPATH:$JAVA_HOME;export CLASSPATH;" >>/etc/profile
run  echo  "PATH=$PATH:$JAVA_HOME/bin;export  PATH ;">>/etc/profile
run  echo  "PATH=$PATH:$JAVA_HOME/bin;export  PATH ;">>/etc/bashrc
run rm -f /etc/yum.repos.d/Cent*
add   yum.repo /etc/yum.repos.d
run systemctl enable sshd.service
run /usr/lib/systemd/systemd --system &
run yum -y install which  openssl sshd wget net-tools openssh-client openssh-server
run ssh-keygen -t dsa -f /etc/ssh/ssh_host_dsa_key -N ""
run ssh-keygen -t rsa -f /etc/ssh/ssh_host_rsa_key -N ""
run ssh-keygen -t ecdsa -f /etc/ssh/ssh_host_ecdsa_key -N ""
run ssh-keygen -t ed25519 -f /etc/ssh/ssh_host_ed25519_key -N ""
run     /usr/sbin/sshd
run echo root | passwd root --stdin
run yum makecache &&yum clean all
run   ssh-keygen -t rsa -f ~/.ssh/id_rsa -N "";  cat ~/.ssh/id_rsa.pub >>~/.ssh/authorized_keys
run echo "StrictHostKeyChecking no " >>~/.ssh/config

Entrypoint   /usr/sbin/sshd;/bin/bash 

[local]
name=local
baseurl=http://XXX.XXX/yum
enable=
gpgcheck=

yum.repo

基于jdk8:centos7 建立 hadoop2.6

from jdk8:centos7

Add  hadoop-2.6..tar.gz  /home/

run ln -s /home/hadoop-2.6./ /home/hadoop   && cd /home/hadoop

workdir /home/hadoop
expose
copy etc  /home/hadoop/etc/hadoop

run  echo  "export PATH=$PATH:$JAVA_HOME/bin:/home/hadoop/sbin:/home/hadoop/bin;">>/etc/profile
run  echo  "export PATH=$PATH:$JAVA_HOME/bin:/home/hadoop/sbin:/home/hadoop/bin;" >>/etc/bashrc
run systemctl enable sshd.service
run /usr/lib/systemd/systemd --system &

copy hadoop-config.sh  /home/hadoop/libexec
Entrypoint  /usr/sbin/sshd;/bin/bash
 

测试 单节点hadoop 能否启动 (出现java没找到 ,手工修改 /libexec 中的 hadoop-config.sh )

start-dfs.sh start-yarn.sh

zoo image 的 dockerfile

from hadoop
Add  zookeeper-3.4.7.tar.gz /home/
EXPOSE 16020 16202 16010 60000 60010 22 7373 7946 9000 50010 50020 50070 50075 50090 50475 8030 8031 8032 8033 8040 8042 8060 8088 50060 2888 2181 3888 8480 10020 19888
run echo "export ZOOKEEPER_HOME=/home/zookeeper-3.4.7" >>/etc/profile
run echo "export ZOOKEEPER_HOME=/home/zookeeper-3.4.7" >>/etc/bashrc

run  echo  "export PATH=$PATH:$JAVA_HOME/bin:/home/hadoop/sbin:/home/hadoop/bin:/home/zookeeper-3.4.7/bin:/home/zookeeper-3.4.7/conf:/home/hbase-1.0.2/bin" >>/etc/profile
run  echo  "export PATH=$PATH:$JAVA_HOME/bin:/home/hadoop/sbin:/home/hadoop/bin:/home/zookeeper-3.4.7/bin:/home/zookeeper-3.4.7/conf:/home/hbase-1.0.2/bin" >>/etc/bashrc
volume /data/hadoop
copy zoo/zoo.cfg /home/zookeeper-3.4.7/conf/zoo.cfg
copy  ha_etc/core-site.xml /home/hadoop/etc/hadoop/core-site.xml
copy  ha_etc/hdfs-site.xml /home/hadoop/etc/hadoop/hdfs-site.xml
copy  ha_etc/mapred-site.xml /home/hadoop/etc/hadoop/mapred-site.xml
copy  ha_etc/yarn-site.xml /home/hadoop/etc/hadoop/yarn-site.xml
copy  ha_etc/hosts.allow   /data/hadoop/tmp/hosts.allow

copy  ha_etc/slaves_datanode.txt  /home/hadoop/etc/hadoop/slaves
run mkdir /home/zookeeper-3.4.7/data
env   HA_ID rm1

Add hbase-1.0.2-bin.tar.gz   /home/
run sed -i "s/# export JAVA_HOME=\/usr\/java\/jdk1.6.0\//export JAVA_HOME=\/usr\/sbin\/jdk1.8.0_65/g"  /home/hbase-1.0.2/conf/hbase-env.sh
run sed -i "s/# export HBASE_MANAGES_ZK=true/export HBASE_MANAGES_ZK=false/g"  /home/hbase-1.0.2/conf/hbase-env.sh
run echo "export HBASE_MANAGES_ZK=false" >>/etc/profile
run echo "export HBASE_MANAGES_ZK=false" >>/etc/bashrc
Entrypoint  /usr/sbin/sshd;/bin/bash

　　

运行 zookeeper 的docker脚本 ,运行后生成 四个容器 (参数 1 )

 #!/bin/bash
  #更改host
  inner_host=127.0.0.1
     updateHost()
     {
     # read
     inner_host=`cat /etc/hosts | grep ${in_url} | awk '{print $1}'`
     if [ ${inner_host} = ${in_ip} ];then
     echo "${inner_host} ${in_url} ok"
     else
     if [ ${inner_host} != "" ];then
     echo " change is ok "
     else
     inner_ip_map="${in_ip} ${in_url}"
     echo ${inner_ip_map} >> /etc/hosts
     if [ $? =  ]; then
     echo "${inner_ip_map} to hosts success host is `cat /etc/hosts`"
     fi
     echo "shuld appand "
     fi
     fi
     }
 # run N slave containers
 N=$

 # the defaut node number is
 if [ $# =  ]
 then
     N=
 fi

 docker build --rm -t zoo .     

 # delete old master container and start new master container
 sudo docker rm -f master_hadoop &> /dev/null
 echo "start master container..."
 sudo docker run -d -t --dns 127.0.0.1   -v /etc/hosts:/etc/hosts -p : -P -v /data/hadoop/master:/data/hadoop --name master_hadoop -h master.hantongchao.com -w /root zoo &> /dev/null

 ip0=$(docker inspect --format="{{.NetworkSettings.IPAddress}}" master_hadoop)

 serverid=;
 ((serverid++))
 #zoo
 echo $serverid > myid
 sudo docker cp myid master_hadoop:/home/zookeeper-3.4./data/myid

 # delete old master container and start new nn1 container
 sudo docker rm -f nn1_hadoop &> /dev/null
 echo "start nn1 container..."
 mkdir /data/hadoop/nn1 &> /dev/null
 sudo docker run -d -t --dns 127.0.0.1    -p : -p : -p : -v /etc/hosts:/etc/hosts -e "HA_ID=rm1" -P -v /data/hadoop/nn1:/data/hadoop --name nn1_hadoop -h nn1.hantongchao.com -w /root zoo &> /dev/null
 ip1=$(docker inspect --format="{{.NetworkSettings.IPAddress}}" nn1_hadoop)
 ((serverid++))
 echo $serverid > myid
 sudo docker cp myid nn1_hadoop:/home/zookeeper-3.4./data/myid
 #yarn slaves

 # delete old master container and start new nn2 container
 sudo docker rm -f nn2_hadoop &> /dev/null
 echo "start nn2 container..."
 mkdir /data/hadoop/nn2 &> /dev/null
 sudo docker run -d -t --dns 127.0.0.1   -p : -v /etc/hosts:/etc/hosts -p : -P -v /data/hadoop/nn2:/data/hadoop --name nn2_hadoop -h nn2.hantongchao.com -w /root zoo &> /dev/null
 ip2=$(docker inspect --format="{{.NetworkSettings.IPAddress}}" nn2_hadoop)

 ((serverid++))

 echo $serverid > myid
 sudo docker cp myid nn2_hadoop:/home/zookeeper-3.4./data/myid
 # get the IP address of master container
 FIRST_IP=$(docker inspect --format="{{.NetworkSettings.IPAddress}}" master_hadoop)

 # -

 sudo docker rm -f master1_hadoop &> /dev/null
 echo "start master1 container..."
 sudo docker run -d -t --dns 127.0.0.1    -v /etc/hosts:/etc/hosts  -e "HA_ID=rm2" -P -v /data/hadoop/master1:/data/hadoop --name master1_hadoop -h master1.hantongchao.com -w /root zoo &> /dev/null

 ip4=$(docker inspect --format="{{.NetworkSettings.IPAddress}}" master1_hadoop)

 ((serverid++))
 #zoo
 echo $serverid > myid
 sudo docker cp myid master1_hadoop:/home/zookeeper-3.4./data/myid

 # delete old slave containers and start new slave containers
 i=
 while [ $i -lt $N ]
 do
     sudo docker rm -f slave_hadoop$i &> /dev/null
     echo "start slave_hadoop$i container..."
     mkdir /data/hadoop/$i &> /dev/null
     sudo docker run -d -t --dns 127.0.0.1  -v /etc/hosts:/etc/hosts  -P -v /data/hadoop/$i:/data/hadoop --name slave_hadoop$i -h slave$i.hantongchao.com -e JOIN_IP=$FIRST_IP zoo &> /dev/null
     in_ip=$(docker inspect --format="{{.NetworkSettings.IPAddress}}" slave_hadoop$i)
     in_url=slave$i.hantongchao.com
 ((serverid++))
     echo $serverid > myid
 sudo docker cp myid   slave_hadoop$i:/home/zookeeper-3.4./data/myid
 sudo docker cp ha_etc/slaves_datanode.txt slave_hadoop$i:/home/hadoop/etc/hadoop/slaves
 updateHost
     ((i++))
 done
 echo $in_ip
 in_ip=$ip0
 in_url="master.hantongchao.com"
 updateHost
 #in_url="mycluster"
 #updateHost
 in_ip=$ip1
 in_url="nn1.hantongchao.com"
 updateHost
 in_ip=$ip2
 in_url="nn2.hantongchao.com"
 updateHost

 in_ip=$ip4
 in_url="master1.hantongchao.com"
 updateHost

 #sudo docker cp ha_etc/slaves_nodemanager.txt master_hadoop:/home/hadoop/etc/hadoop/slaves
 #sudo docker cp ha_etc/slaves_nodemanager.txt master1_hadoop:/home/hadoop/etc/hadoop/slaves

 sudo docker cp ha_etc/slaves_datanode.txt master_hadoop:/home/hadoop/etc/hadoop/slaves
 sudo docker cp ha_etc/slaves_datanode.txt master1_hadoop:/home/hadoop/etc/hadoop/slaves

 sudo docker cp ha_etc/slaves_datanode.txt nn1_hadoop:/home/hadoop/etc/hadoop/slaves
 sudo docker cp ha_etc/slaves_datanode.txt nn2_hadoop:/home/hadoop/etc/hadoop/slaves

 # create a new Bash session in the master container
 sudo docker exec -it master_hadoop /home/zookeeper-3.4./bin/zkServer.sh start
 sudo docker exec -it nn1_hadoop /home/zookeeper-3.4./bin/zkServer.sh start
 sudo docker exec -it nn2_hadoop /home/zookeeper-3.4./bin/zkServer.sh start

 sudo docker exec -it master_hadoop /home/zookeeper-3.4./bin/zkServer.sh status 

 echo "journalnode"
 sudo docker exec -it master_hadoop /home/hadoop/sbin/hadoop-daemon.sh start journalnode
 sudo docker exec -it nn1_hadoop /home/hadoop/sbin/hadoop-daemon.sh start journalnode
 sudo docker exec -it nn2_hadoop /home/hadoop/sbin/hadoop-daemon.sh start journalnode 

 sudo docker exec -it nn1_hadoop  bash -c "/home/hadoop/bin/hdfs namenode -format  -clusterid mycluster"
 #sudo docker exec -it nn1_hadoop  scp -r /data/hadoop/tmp/dfs/namedir nn2.hantongchao.com:/data/hadoop/tmp/dfs/
 echo namenode -format
 #read what
 sudo docker exec -it nn1_hadoop /home/hadoop/sbin/hadoop-daemon.sh  start namenode
 #sudo docker exec -it nn1_hadoop /home/hadoop/sbin/hadoop-daemon.sh  start secondarynamenode

 #echo nn1 start namenode secondarynamenode
 #read what

 sudo docker exec -it nn2_hadoop /home/hadoop/bin/hdfs namenode -bootstrapStandby
 sudo docker exec -it nn2_hadoop /home/hadoop/sbin/hadoop-daemon.sh start namenode

 sudo docker exec -it nn1_hadoop  /home/hadoop/bin/hdfs zkfc -formatZK
 sudo docker exec -it nn1_hadoop  /home/hadoop/sbin/hadoop-daemon.sh start  zkfc
 sudo docker exec -it nn2_hadoop  /home/hadoop/sbin/hadoop-daemon.sh start  zkfc 

 sudo docker exec -it nn1_hadoop  /home/hadoop/bin/hdfs haadmin -getServiceState nn1
 sudo docker exec -it nn2_hadoop  /home/hadoop/bin/hdfs haadmin -getServiceState nn2

 sudo docker exec -it master_hadoop  bash -c ' /usr/bin/sed -i "s/{HA_ID}/rm1/g" /home/hadoop/etc/hadoop/yarn-site.xml '
 sudo docker exec -it master1_hadoop  bash -c ' /usr/bin/sed -i "s/{HA_ID}/rm2/g" /home/hadoop/etc/hadoop/yarn-site.xml '

 #start-yarn
 sudo docker exec -it master_hadoop     /home/hadoop/sbin/yarn-daemon.sh start resourcemanager
 sudo docker exec -it master1_hadoop    /home/hadoop/sbin/yarn-daemon.sh start resourcemanager
 sleep
 sudo docker exec -it master_hadoop /home/hadoop/sbin/yarn-daemon.sh start nodemanager
 sudo docker exec -it master1_hadoop /home/hadoop/sbin/yarn-daemon.sh start nodemanager
 sudo docker exec -it nn1_hadoop    /home/hadoop/sbin/yarn-daemon.sh start nodemanager
 sudo docker exec -it nn2_hadoop    /home/hadoop/sbin/yarn-daemon.sh start nodemanager
 sleep 

 sudo docker exec -it master_hadoop /home/hadoop/sbin/hadoop-daemon.sh start datanode
 sudo docker exec -it master1_hadoop /home/hadoop/sbin/hadoop-daemon.sh start datanode
 sudo docker exec -it nn1_hadoop    /home/hadoop/sbin/hadoop-daemon.sh start datanode
 sudo docker exec -it nn2_hadoop    /home/hadoop/sbin/hadoop-daemon.sh start datanode

 sudo docker exec -it master_hadoop     /home/hadoop/sbin/yarn-daemon.sh start proxyserver
 sudo docker exec -it master_hadoop     /home/hadoop/sbin/mr-jobhistory-daemon.sh start historyserver
 echo "nn1_hadoop jps "
 docker exec -it nn1_hadoop /usr/sbin/jdk1..0_65/bin/jps
 echo "nn2_hadoop jps "
 docker exec -it nn2_hadoop /usr/sbin/jdk1..0_65/bin/jps
 echo "master_hadoop jps "
 docker exec -it master_hadoop /usr/sbin/jdk1..0_65/bin/jps
 echo "master1_hadoop jps "
 docker exec -it master1_hadoop /usr/sbin/jdk1..0_65/bin/jps

 i=
 echo $N
 while [ $i -lt $N ]
 do
 sudo docker cp nn1_hadoop:/home/hadoop/etc/hadoop/slaves tmp_slaves_datanode.txt
 echo -e "slave$i.hantongchao.com" >>tmp_slaves_datanode.txt
 sudo docker cp tmp_slaves_datanode.txt nn1_hadoop:/home/hadoop/etc/hadoop/slaves
 sudo docker cp tmp_slaves_datanode.txt nn2_hadoop:/home/hadoop/etc/hadoop/slaves
 sudo docker cp tmp_slaves_datanode.txt master_hadoop:/home/hadoop/etc/hadoop/slaves
 sudo docker cp tmp_slaves_datanode.txt master1_hadoop:/home/hadoop/etc/hadoop/slaves

 sudo docker cp tmp_slaves_datanode.txt nn1_hadoop:/home/hbase-1.0./conf/regionservers
 sudo docker cp tmp_slaves_datanode.txt nn2_hadoop:/home/hbase-1.0./conf/regionservers

 sudo docker exec -it slave_hadoop$i /home/hadoop/sbin/yarn-daemon.sh start nodemanager
 sudo docker exec -it slave_hadoop$i /home/hadoop/sbin/hadoop-daemon.sh start datanode
 echo "slave_hadoop$i jps "
 docker exec -it slave_hadoop$i /usr/sbin/jdk1..0_65/bin/jps
     ((i++))
 echo $i
 done 

 sudo docker exec -it nn1_hadoop  ssh nn2.hantongchao.com  ls
 sudo docker exec -it nn1_hadoop  ssh master1.hantongchao.com  ls
 sudo docker exec -it nn1_hadoop  ssh master.hantongchao.com  ls 

 sudo docker exec -it nn2_hadoop  ssh nn1.hantongchao.com  ls
 sudo docker exec -it nn2_hadoop  ssh master1.hantongchao.com  ls
 sudo docker exec -it nn2_hadoop  ssh master.hantongchao.com  ls 

 sudo docker exec -it nn1_hadoop bash

core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed 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. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>

<property>
	<name>fs.default.name</name>
	<value>hdfs://mycluster</value>
</property>

<property>
	<name>fs.defaultFS</name>
	<value>hdfs://mycluster</value>
</property>
<property>
	<name>hadoop.tmp.dir</name>
	<value>/data/hadoop/tmp</value>
</property>
  <property>
        <name>dfs.datanode.data.dir</name>
        <value>/data/hadoop/tmp/dfs/data</value>
    </property>
<property>
			  <name>dfs.journalnode.edits.dir</name>
			  <value>/data/hadoop/tmp/dfs/journal</value>
			</property>
<property>
		<name>ha.zookeeper.quorum</name>
		<value>nn1.hantongchao.com:2181,nn2.hantongchao.com:2181,master.hantongchao.com:2181</value>
</property>
 <property>
  <name>hadoop.proxyuser.spark.hosts</name>
  <value>*</value>
 </property>
<property>
  <name>hadoop.proxyuser.spark.groups</name>
  <value>*</value>
 </property>
</configuration>

　　hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed 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. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>
<property>
        <name>dfs.replication</name>
        <value>3</value>
    </property>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>/data/hadoop/tmp/dfs/name</value>
    </property>

    <!--
    <property>
        <name>dfs.hosts</name>
        <value>/data/hadoop/tmp/hosts.allow</value>
    </property>
    -->
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>/data/hadoop/tmp/dfs/data</value>
    </property>
     <property>
        <name>dfs.name.dir</name>
        <value>/data/hadoop/tmp/dfs/namedir</value>
    </property>

      <property>
        <name>dfs.data.dir</name>
        <value>/data/hadoop/tmp/dfs/hdsfdata</value>
    </property>
    <property>
			  <name>dfs.nameservices</name>
			  <value>mycluster</value>
    </property>

		 <property>
		  <name>dfs.ha.namenodes.mycluster</name>
		  <value>nn1,nn2</value>
		 </property>
			<property>
			  <name>dfs.namenode.rpc-address.mycluster.nn1</name>
			  <value>nn1.hantongchao.com:9000</value>
			</property>
			<property>
			  <name>dfs.namenode.http-address.mycluster.nn1</name>
			  <value>nn1.hantongchao.com:50070</value>
			</property>

			<property>
			  <name>dfs.namenode.rpc-address.mycluster.nn2</name>
			  <value>nn2.hantongchao.com:9000</value>
			</property>
			<property>
			  <name>dfs.namenode.http-address.mycluster.nn2</name>
			  <value>nn2.hantongchao.com:50070</value>
			</property>

			<property>
			  <name>dfs.namenode.shared.edits.dir</name>
			  <value>qjournal://nn1.hantongchao.com:8485;nn2.hantongchao.com:8485;master.hantongchao.com:8485/mycluster</value>
			</property>
			<property>
			  <name>dfs.journalnode.edits.dir</name>
			  <value>/data/hadoop/tmp/dfs/journal</value>
			</property>

			<!-- 开启NameNode失败自动切换 -->
        <property>
                <name>dfs.ha.automatic-failover.enabled</name>
                <value>true</value>
        </property>
        <!-- 配置失败自动切换实现方式 -->
        <property>
                <name>dfs.client.failover.proxy.provider.mycluster</name>
                <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
        </property>
        <!-- 配置隔离机制方法，多个机制用换行分割，即每个机制暂用一行-->
        <property>
                <name>dfs.ha.fencing.methods</name>
                <value>shell(/bin/true)</value>
        </property>
        <!-- 使用sshfence隔离机制时需要ssh免登陆 -->
        <property>
                <name>dfs.ha.fencing.ssh.private-key-files</name>
                <value>/root/.ssh/id_rsa</value>
        </property>
        <!-- 配置sshfence隔离机制超时时间 -->
        <property>
                <name>dfs.ha.fencing.ssh.connect-timeout</name>
                <value>30000</value>
        </property>
</configuration>

　　mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed 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. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>

<property>
<name>mapreduce.map.memory.mb</name>
<value>2046</value>
</property>

<property>
<name>mapreduce.reduce.memory.mb</name>
<value>2046</value>
</property>

<property>
<name>mapred.child.java.opts</name>
<value>-Xmx1024m</value>
</property>
<property>
<name>mapred.reduce.child.java.opts</name>
<value>-Xmx1024m</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>master.hantongchao.com:10020</value>
</property>

<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>master.hantongchao.com:19888</value>
</property>

<property>
<name>mapreduce.jobhistory.intermediate-done-dir</name>
<value>/data/hadoop/tmp/mr_history</value>
</property>

<property>
<name>mapreduce.jobhistory.done-dir</name>
<value>/data/hadoop/tmp/mr_history</value>
</property>
</configuration>

　　yarn-site.xml

<?xml version="1.0"?>
<!--
  Licensed 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. See accompanying LICENSE file.
-->
<configuration>

<!-- Site specific YARN configuration properties -->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>

<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>2024</value>
</property>
<property>

<name>yarn.scheduler.maximum-allocation-mb</name>
<value>8096</value>
</property>

<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>

<property>
<name>yarn.nodemanager.vmem-pmem-ratio</name>
<value>2.1</value>
</property>

</property>
 <!-- 开启RM高可靠 -->
        <property>
                <name>yarn.resourcemanager.ha.enabled</name>
                <value>true</value>
        </property>
        <!-- 指定RM的cluster id -->
        <property>
                <name>yarn.resourcemanager.cluster-id</name>
                <value>rm-cluster</value>
        </property>
        <!-- 指定RM的名字 -->
        <property>
                <name>yarn.resourcemanager.ha.rm-ids</name>
                <value>rm1,rm2</value>
        </property>
        <!-- 分别指定RM的地址 -->
        <property>
                <name>yarn.resourcemanager.hostname.rm1</name>
                <value>master.hantongchao.com</value>
        </property>
        <property>
                <name>yarn.resourcemanager.hostname.rm2</name>
                <value>master1.hantongchao.com</value>
        </property>

        <property>
                    <name>yarn.resourcemanager.resource-tracker.address.rm1</name>
                    <value>master.hantongchao.com:8031</value>
                </property>
                 <property>
                    <name>yarn.resourcemanager.resource-tracker.address.rm2</name>
                    <value>master1.hantongchao.com:8031</value>
                </property>
        <property>
                <name>yarn.resourcemanager.ha.id</name>
                <value>{HA_ID}</value>
        </property>       

        <property>
                <name>yarn.resourcemanager.recovery.enabled</name>
                <value>true</value>
        </property>

        <property>
                <name>yarn.resourcemanager.store.class</name>
                <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
        </property>
        <!-- 指定zk集群地址 -->
        <property>
                <name>yarn.resourcemanager.zk-address</name>
                <value>nn1.hantongchao.com:2181,nn2.hantongchao.com:2181,master.hantongchao.com:2181</value>
        </property>
        <property>
                <name>yarn.nodemanager.aux-services</name>
                <value>mapreduce_shuffle</value>
        </property>
<property>
                <name>yarn.log-aggregation-enable</name>
                <value>true</value>
 </property>
</configuration>

salve

master.hantongchao.com
master1.hantongchao.com
nn1.hantongchao.com
nn2.hantongchao.com