Hadoop2.6 Ha 安装

Hadoop 2.6安装文档

版本说明：hadoop 2.6 linux-64位

Zookeeper3.4.6 jdk 1.7.0_75

1、Ssh无密码

ssh-keygen

vimauthorized_keys

把每台机子上的id_rsa.pub内容拷贝到authorized_keys

Scp到其它机器上

2、jdk安装

解压目录

jdk环境变量

3、Zookeeper安装

详见zookeeper安装文档

4、必要目录创建

NameNode数据目录 /data/nn

DataNode数据目录 /data/dn

JournalNode数据目录 /data/jn

Yarn数据目录 /data/yarn/local

5、修改配置文件

Core-site.xml

Hdfs-site.xml

Slaves

Yarn-site.xml

注：修改对数，详见附件

6、配置环境变量

exportJAVA_HOME=/usr/local/jdk1.7.0_75

exportJRE_HOME=/usr/local/jdk1.7.0_75/jre

exportPATH=$PATH:/usr/local/jdk1.7.0_75/bin

exportCLASSPATH=.:$JAVA_HOME/lib:$JAVA_HOME/jre/lib

exportZOOKEEPER_HOME=/usr/local/zookeeper-3.4.6

PATH=$ZOOKEEPER_HOME/bin:$PATH

exportHADOOP_HOME=/usr/local/hadoop-2.6.0

exportPATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

7、启动集群

启动zookeeper

ZkServer.shstart

格式化zookeeper

bin/hdfszkfc –formatZK

启动journalnode

sbin/hadoop-daemon.shstart journalnode

格式化Namenode

bin/hdfsnamenode -format

启动格式化的namenode

sbin/hadoop-daemon.sh startnamenode

同步namenode

bin/hdfs namenode–bootstrapStandby

启动同步的namenode

sbin/hadoop-daemon.shstart namenode

启动datanode

hdfsdatanode >null 2>&1 &

启动resourcemanager

yarnresourcemanager >null 2>&1 &

启动nodemanager

yarnnodemanager >null 2>&1 &

启动zkfc

hdfszkfc >null 2>&1 &

附件

Core-site.xml

<configuration>

 <property>

    <name>fs.defaultFS</name>

    <value>hdfs://mycluster</value>

  </property>

<property>

<name>ha.zookeeper.quorum</name>

<value>database:2181,spark02:2181,spark03:2181,spark04:2181,spark05:2181</value>

</property>

</configuration>

Slave

spark03

spark04

spark05

yarn-site.xml

<configuration>

<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.log-aggregation-enable</name>

<value>true</value>

</property>

<property>

<description>Listof directories to store localized files in.</description>

<name>yarn.nodemanager.local-dirs</name>

<value>file:///data/yarn/local</value>

</property>

<property>

<description>Classpathfor typical applications.</description>

<name>yarn.application.classpath</name>

<value>

$HADOOP_CONF_DIR,

$HADOOP_COMMON_HOME/*,$HADOOP_COMMON_HOME/lib/*,

$HADOOP_HDFS_HOME/*,$HADOOP_HDFS_HOME/lib/*,

$HADOOP_MAPRED_HOME/*,$HADOOP_MAPRED_HOME/lib/*,

$HADOOP_YARN_HOME/*,$HADOOP_YARN_HOME/lib/*

</value>

</property>

<property>

<name>yarn.resourcemanager.ha.enabled</name>

<value>true</value>

</property>

<property>

<name>yarn.resourcemanager.ha.rm-ids</name>

<value>rm1,rm2</value>

</property>

<property>

<name>yarn.resourcemanager.hostname.rm1</name>

<value>database</value>

</property>

<property>

<name>yarn.resourcemanager.hostname.rm2</name>

<value>spark02</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>

<property>

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

<value>database:2181,spark02:2181,spark03:2181,spark04:2181,spark05:2181</value>

<description>For multiple zk services, separate themwith comma</description>

</property>

<property>

<name>yarn.resourcemanager.cluster-id</name>

<value>yarn-ha</value>

</property>

</configuration>

Hdfs-site.xml

<configuration>
<property>
<name>dfs.permissions.superusergroup</name>
<value>hadoop</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///data/nn</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///data/dn</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.webhdfs.user.provider.user.pattern</name>
<value>^[A-Za-z0-9_][A-Za-z0-9._-]*[$]?$</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>database:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>spark02:8020</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>database:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>spark02:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://database:8485;spark02:8485;spark03:8485/mycluster</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/data/jn</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.mycluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.client.read.shortcircuit</name>
<value>true</value>
</property>
<property> 
<name>dfs.domain.socket.path</name>  
<value>${hadoop.tmp.dir}/sockets/dn._PORT</value> 
</property>
<property>
<name>dfs.client.read.shortcircuit.streams.cache.size</name>
<value>1000</value>
</property>
<property>
<name>dfs.client.read.shortcircuit.streams.cache.expiry.ms</name>
<value>10000</value>
</property>
<property>
<name>dfs.datanode.hdfs-blocks-metadata.enabled</name>
<value>true</value>
</property>
</configuration>