hadoop高可用-Toy模板网

这篇具有很好参考价值的文章主要介绍了hadoop高可用。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

stop-all.sh

tar -zxvf apache-zookeeper-3.8.3-bin.tar.gz -C /opt/module/
ls /opt/module/

cd /opt/module/apache-zookeeper-3.8.3-bin/conf/
mv zoo_sample.cfg zoo.cfg

pwd
vi /opt/module/apache-zookeeper-3.8.3-bin/conf/zoo.cfg
dataDir=/opt/module/apache-zookeeper-3.8.3-bin/zkData
server.1=192.168.63.101:2888:3888
server.2=192.168.63.102:2888:3888
server.3=192.168.63.103:2888:3888

mkdir -p /opt/module/apache-zookeeper-3.8.3-bin/zkData/
vi /opt/module/apache-zookeeper-3.8.3-bin/zkData/myid

/root/bin/xsync /opt/module/

/opt/module/apache-zookeeper-3.8.3-bin/bin/zkServer.sh start
/opt/module/apache-zookeeper-3.8.3-bin/bin/zkServer.sh status
/opt/module/apache-zookeeper-3.8.3-bin/bin/zkServer.sh restart

hadoop102
/opt/module/apache-zookeeper-3.8.3-bin/bin/zkServer.sh start
/opt/module/apache-zookeeper-3.8.3-bin/bin/zkServer.sh status

环境变量：
vi /etc/profile
#ZK_HOME
export ZK_HOME=/opt/module/apache-zookeeper-3.8.3-bin/
export PATH=$PATH:$ZK_HOME/bin

/root/bin/xsync /etc/profile
source /etc/profile

防火墙：
systemctl stop firewalld&&systemctl disable firewalld
setenforce 0
sed -i '/SELINUX/s/enforcing/disabled/' /etc/selinux/config

配置文件：
cd /opt/module/hadoop-2.7.2/etc/hadoop/

vi core-site.xml
<configuration>

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

<property>
<name>hadoop.tmp.dir</name>
<value>/opt/module/hadoop-2.7.2/data/tmp</value>
</property>
   <property>
       <name>ha.zookeeper.quorum</name>
   <value>hadoop101:2181,hadoop102:2181,hadoop103:2181</value>
   </property>
</configuration>

vi hdfs-site.xml
<configuration>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>

<property>
   <name>dfs.namenode.secondary.http-address</name>
   <value>hadoop103:50090</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>hadoop101:9000</value>
</property>

<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>hadoop102:9000</value>
</property>

<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>hadoop101:50070</value>
</property>

<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>hadoop102:50070</value>
</property>

<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hadoop101:8485;hadoop102:8485;hadoop103:8485/mycluster</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.journalnode.edits.dir</name>
<value>/opt/ha/hadoop-2.7.2/data/jn</value>
</property>

<property>
<name>dfs.permissions.enable</name>
<value>false</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.automatic-failover.enabled</name>
   <value>true</value>
   </property>
</configuration>

vi yarn-site.xml
<configuration>
   
   
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
    
   <property>
   <name>yarn.resourcemanager.ha.enabled</name>
   <value>true</value>
   </property>
   
   <property>
   <name>yarn.resourcemanager.cluster-id</name>
   <value>cluster-yarn1</value>
   </property>
   <property>
   <name>yarn.resourcemanager.ha.rm-ids</name>
   <value>rm1,rm2</value>
   </property>
   <property>
   <name>yarn.resourcemanager.hostname.rm1</name>
        <value>hadoop102</value>
   </property>
   <property>
   <name>yarn.resourcemanager.hostname.rm2</name>
   <value>hadoop103</value>
   </property>

<property>
   <name>yarn.resourcemanager.zk-address</name>
   <value>hadoop101:2181,hadoop102:2181,hadoop103:2181</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>
</configuration>

[hadoop-2.7.2]# hadoop-daemon.sh start journalnode (3台)
[hadoop-2.7.2]# rm -rf /opt/module/hadoop-2.7.2/data/ (3台)

[hadoop-2.7.2]# hdfs namenode -format
/root/bin/xsync /opt/module/hadoop-2.7.2/

hadoop-daemon.sh start namenode (101,102)
hdfs namenode -bootstrapStandby (102)(同步101 namenode)
hadoop-daemon.sh start datanode
hdfs haadmin -transitionToActive nn1 --forcemanual（使活跃）

start-yarn.sh (102) 打开ResourceManager, NodeManager节点
yarn-daemon.sh start resourcemanager（103）打开ResourceManager节点

hadoop高可用,hadoop,大数据,分布式
文章来源地址https://www.toymoban.com/news/detail-752541.html