Hadoop 2.7.1基于QMJ高可用安装配置

Hadoop 2.7.1基于QMJ高可用安装配置

1.修改主机名及hosts文件

10.205.22.185 nn1 （主）作用namenode,resourcemanager,datanode,zk,hive,sqoop
10.205.22.186 nn2 （备）作用namenode,resourcemanager,datanode,zk
10.205.22.187 dn1      作用datanode,zk

1.1配置ssh免密码登录

主节点能免密码登录各个从节点

ssh nn1
ssh nn2
ssh dn1

2. 安装jdk1.8和zookeeper，hive,sqoop可搭建成功后再安装

2.1修改profile文件，配置环境变量

export JAVA_HOME=/usr/java/jdk1.8.0_65
export JRE_HOME=/usr/java/jdk1.8.0_65/jre
export HADOOP_HOME=/app/hadoop-2.7.1
export HIVE_HOME=/app/hive
export SQOOP_HOME=/app/sqoop
export ZOOKEEPER_HOME=/app/zookeeper-3.4.6
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$ZOOKEEPER_HOME/bin:$HIVE_HOME/bin:$SQOOP_HOME/bin:$MAVEN_HOME/bin
export CLASSPATH=.:$JAVA_HOME/lib:$JRE_HOME/lib
ulimit -SHn 65536

2.2 修改zookeeper配置文件zoo.cfg

添加：

server.1= nn1:2888:3888
server.2= nn2:2888:3888
server.3= dn1:2888:3888

3.安装hadoop-2.7.1，修改配置文件

创建相应的目录

mkdir -p /home/hadoop/tmp
mkdir -p /home/hadoop/hdfs/data
mkdir -p /home/hadoop/journal
mkdir -p /home/hadoop/name

修改slaves文件

nn1
nn2
dn1

修改hadoop-env.sh文件

export JAVA_HOME=/usr/java/jdk1.8.0_65

3.1配置hdfs-site.xml

<configuration>
        <property>
              <name>dfs.nameservices</name>
              <value>masters</value>
        </property>
        <property>
              <name>dfs.ha.namenodes.masters</name>
              <value>nn1,nn2</value>
        </property>
        <property>
              <name>dfs.namenode.rpc-address.masters.nn1</name>
              <value>nn1:9000</value>
        </property>
        <property>
              <name>dfs.namenode.http-address.masters.nn1</name>
              <value>nn1:50070</value>
        </property>
        <property>
              <name>dfs.namenode.rpc-address.masters.nn2</name>
              <value>nn2:9000</value>
        </property>
        <property>
              <name>dfs.namenode.http-address.masters.nn2</name>
              <value>nn2:50070</value>
        </property>
        <property>
              <name>dfs.datanode.data.dir</name>
              <value>file:/home/hadoop/hdfs/data</value>
        </property>
        <property>
      　　　　<name>dfs.replication</name>
              <value>2</value>
        </property>
        <property>
              <name>dfs.namenode.name.dir</name>
              <value>file:/home/hadoop/name</value>
        </property>
        <property>
              <name>dfs.namenode.shared.edits.dir</name>
              <value>qjournal://nn1:8485;nn2:8485;dn1:8485/masters</value>
        </property>
        <property>
              <name>dfs.journalnode.edits.dir</name>
              <value>/home/hadoop/journal</value>
        </property>
        <property>
              <name>dfs.ha.automatic-failover.enabled</name>
              <value>true</value>
        </property>
        <property>                                 
　　　　　　　　　<name>dfs.client.failover.proxy.provider.masters</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.fencing.ssh.connect-timeout</name>
              <value>30000</value>
        </property>
</configuration>

3.2配置core-site.xml文件

<configuration>
  <property>
      <name>fs.defaultFS</name>
      <value>hdfs://masters</value>
  </property>
  <property>
      <name>hadoop.tmp.dir</name>
      <value>/home/hadoop/tmp</value>
  </property>
  <property>
      <name>ha.zookeeper.quorum</name>
      <value>nn1:2181,nn2:2181,dn1:2181</value>
  </property>

  <property>
      <name>io.compression.codecs</name>
      <value>org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.DefaultCodec,com.hadoop.compression.lzo.LzoCodec,com.hadoop.compression.lzo.LzopCodec,org.apache.hadoop.io.compress.BZip2Codec</value>
  </property>
  <property>
      <name>io.compression.codec.lzo.class</name>
      <value>com.hadoop.compression.lzo.LzoCodec</value>
  </property>
</configuration>

3.3配置yarn-site.xml文件

<configuration>
    <property>
      <name>yarn.resourcemanager.ha.enabled</name>
      <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>rm-cluster</value>
    </property>
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
    </property>
    <property>
        <name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.ha.automatic-failover.embedded</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>nn1</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>nn2</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>nn1:2181,nn2:2181,dn1:2181</value>
    </property>
    <property>
      <name>yarn.resourcemanager.scheduler.address.rm1</name>
      <value>nn1:8030</value>
    </property>
    <property>
      <name>yarn.resourcemanager.scheduler.address.rm2</name>
      <value>nn2:8030</value>
    </property>
    <property>
        <name>yarn.resourcemanager.resource-tracker.address.rm1</name>
      <value>nn1:8031</value>
    </property>
    <property>
      <name>yarn.resourcemanager.resource-tracker.address.rm2</name>
      <value>nn2:8031</value>
    </property>
    <property>
      <name>yarn.resourcemanager.address.rm1</name>
      <value>nn1:8032</value>
    </property>
    <property>
      <name>yarn.resourcemanager.address.rm2</name>
      <value>nn2:8032</value>
    </property>
    <property>
      <name>yarn.resourcemanager.admin.address.rm1</name>
      <value>nn1:8033</value>
    </property>
    <property>
      <name>yarn.resourcemanager.admin.address.rm2</name>
      <value>nn2:8033</value>
    </property>
    <property>
      <name>yarn.resourcemanager.webapp.address.rm1</name>
      <value>nn1:8088</value>
    </property>
    <property>
      <name>yarn.resourcemanager.webapp.address.rm2</name>
      <value>nn2:8088</value>
    </property>
    <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.client.failover-proxy-provider</name>
        <value>org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider</value>
    </property>
</configuration>

3.4配置mapred-site.xml文件

<configuration>
  <property>
      <name>mapreduce.framework.name</name>
      <value>yarn</value>
  </property>
  <property>
      <name>mapreduce.jobhistory.address</name>
      <value>nn1:10020</value>
  </property>
  <property>
      <name>mapreduce.jobhistory.webapp.address</name>
      <value>nn2:19888</value>
  </property>

  <property>
      <name>mapred.compress.map.output</name>
      <value>true</value>
  </property>
  <property>
      <name>mapred.map.output.compression.codec</name>
      <value>com.hadoop.compression.lzo.LzoCodec</value>
  </property>
  <property>
      <name>mapred.child.env</name>
      <value>LD_LIBRARY_PATH=/usr/local/lzo/lib</value>
  </property>
</configuration>

3.5同步hadoop到各个节点，并配置上述相关文件

4.启动服务

4.1在各个节点启动zookeeper，查看状态

zkServer.sh start
zkServer.sh status

在主节点格式化zookeeper

hdfs zkfc -formatZK

4.2在各个节点启日志程序

hadoop-daemon.sh start journalnode

4.3在主namenode节点格式化hadoop

hadoop namenode -format

4.4在主namenode节点启动namenode进程

hadoop-daemon.sh start namenode

4.5在备节点执行命令，这个是把备namenode节点的目录格式化并把元数据从主namenode节点同步过来

hdfs namenode –bootstrapStandby
hadoop-daemon.sh start namenode 启动namenode
yarn-daemon.sh start resourcemanager 启动resourcemanager

4.6启动其他相关服务

start-dfs.sh
start-yarn.sh

4.7 查看高可用状态

hdfs haadmin -getServiceState nn1/nn2 查看namenode
yarn rmadmin -getServiceState rm1/rm2 查看resourcemanager

4.8登录web查看状态

http://nn1:50070
http://nn1:8088

下面关于Hadoop的文章您也可能喜欢，不妨看看：