Hadoop 搭建高可用完全分布式集群

来源：互联网发布：网络电视浏览器下载编辑：程序博客网时间：2024/05/03 10:26

部署规划

主机

用途

rm01.hadoop.com

ResourceManager01

192.168.137.11

nn01.hadoop.com

NameNode01、DFSZKFailoverController

192.168.137.12

rm02.hadoop.com

(backup resourcemanager)

ResourceManager02

192.168.137.13

nn02.hadoop.com

(backup namenode)

NameNode02、DFSZKFailoverController

192.168.137.14

dn01.hadoop.com

DataNode、NodeManager、QuorumPeerMain、JournalNode

192.168.137.21

dn02.hadoop.com

DataNode、NodeManager、QuorumPeerMain、JournalNode

192.168.137.22

dn03.hadoop.com

DataNode、NodeManager、QuorumPeerMain、JournalNode

192.168.137.23

[hadoop@dn01 ~]$ tar -zxf /nfs_share/software/zookeeper-3.4.11.tar.gz -C ~

[hadoop@dn01 ~]$ vi .bashrc

export ZOOKEEPER_HOME=/home/hadoop/zookeeper-3.4.11

export PATH=$PATH:/home/hadoop/zookeeper-3.4.11/bin

[hadoop@dn01 ~]$ source .bashrc

[hadoop@dn01 ~]$ cd zookeeper-3.4.11/conf

[hadoop@dn01 conf]$ mv zoo_sample.cfg zoo.cfg

[hadoop@dn01 conf]$ vi zoo.cfg

dataLogDir=/home/hadoop/zookeeper-3.4.11/log

dataDir=/home/hadoop/zookeeper-3.4.11/data

server.1=192.168.137.21:2888:3888

server.2=192.168.137.22:2888:3888

server.3=192.168.137.23:2888:3888

[hadoop@dn01 conf]$ cd ..

[hadoop@dn01 zookeeper-3.4.11]$ mkdir data && mkdir log && cd data && echo "1">>myid

[hadoop@dn01 zookeeper-3.4.11]$ cd

[hadoop@dn01 ~]$ scp -r zookeeper-3.4.11dn02.hadoop.com:/home/hadoop

[hadoop@dn01 ~]$ scp -r zookeeper-3.4.11dn03.hadoop.com:/home/hadoop

[hadoop@dn01 ~]$ sshhadoop@dn02.hadoop.com 'cd /home/hadoop/zookeeper-3.4.11/data && echo "2">myid'

[hadoop@dn01 ~]$ ssh hadoop@dn03.hadoop.com 'cd /home/hadoop/zookeeper-3.4.11/data && echo "3">myid'

[hadoop@dn01 ~]$ zkServer.sh start

[hadoop@dn02 ~]$ zkServer.sh start

[hadoop@dn03 ~]$ zkServer.sh start

[hadoop@dn01 ~]$ zkServer.sh status

[hadoop@dn02 ~]$ zkServer.sh status

[hadoop@dn03 ~]$ zkServer.sh status

[hadoop@dn01 ~]$ cd hadoop-2.9.0 && mkdir journal

[hadoop@dn02 ~]$ cd hadoop-2.9.0 && mkdir journal

[hadoop@dn03 ~]$ cd hadoop-2.9.0 && mkdir journal

[hadoop@nn01 ~]$ cd hadoop-2.9.0/etc/hadoop/

[hadoop@nn01 hadoop]$ vi core-site.xml

<name>fs.defaultFS</name>

</property>

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

<value>file:/home/hadoop/hadoop-2.9.0/tmp</value>

</property>

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

</property>

<name>hadoop.proxyuser.hadoop.hosts</name>

</property>

<name>hadoop.proxyuser.hadoop.groups</name>

</property>

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

<value>dn01.hadoop.com:2181,dn02.hadoop.com:2181,dn03.hadoop.com:2181</value>

</property>

<name>ha.zookeeper.session-timeout.ms</name>

</property>

</configuration>

[hadoop@nn01 hadoop]$ vihdfs-site.xml

<name>dfs.namenode.name.dir</name>

<value>/home/hadoop/hadoop-2.9.0/dfs/name</value>

</property>

<name>dfs.datanode.data.dir</name>

<value>/home/hadoop/hadoop-2.9.0/dfs/data</value>

</property>

<name>dfs.blocksize</name>

</property>

<name>dfs.replication</name>

</property>

<name>dfs.webhdfs.enabled</name>

</property>

<name>dfs.permissions</name>

<value>false</value>

</property>

<name>dfs.permissions.enabled</name>

<value>false</value>

</property>

<name>dfs.nameservices</name>

</property>

<name>dfs.ha.namenodes.ns1</name>

</property>

<name>dfs.namenode.rpc-address.ns1.nn1</name>

<value>nn01.hadoop.com:8020</value>

</property>

<name>dfs.namenode.rpc-address.ns1.nn2</name>

<value>nn02.hadoop.com:8020</value>

</property>

<name>dfs.namenode.servicerpc-address.ns1.nn1</name>

<value>nn01.hadoop.com:53310</value>

</property>

<name>dfs.namenode.servicerpc-address.ns1.nn2</name>

<value>nn02.hadoop.com:53310</value>

</property>

<name>dfs.namenode.http-address.ns1.nn1</name>

<value>nn01.hadoop.com:50070</value>

</property>

<name>dfs.namenode.http-address.ns1.nn2</name>

<value>nn02.hadoop.com:50070</value>

</property>

<name>dfs.namenode.shared.edits.dir.ns1.nn1</name>

<value>qjournal://dn01.hadoop.com:8485;dn02.hadoop.com:8485;dn03.hadoop.com:8485/ns1</value>

</property>

<name>dfs.namenode.shared.edits.dir.ns1.nn2</name>

<value>qjournal://dn01.hadoop.com:8485;dn02.hadoop.com:8485;dn03.hadoop.com:8485/ns1</value>

</property>

<name>dfs.ha.automatic-failover.enabled.ns1</name>

</property>

<name>dfs.client.failover.proxy.provider.ns1</name>

<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>

</property>

<name>dfs.ha.fencing.methods</name>

<value>sshfence</value>

</property>

<name>dfs.ha.fencing.ssh.private-key-files</name>

<value>/home/hadoop/.ssh/id_rsa</value>

</property>

<name>dfs.ha.fencing.ssh.connect-timeout</name>

</property>

<name>dfs.journalnode.edits.dir</name>

<value>/home/hadoop/hadoop-2.9.0/journal</value>

</property>

<name>ha.failover-controller.cli-check.rpc-timeout.ms</name>

</property>

<name>ipc.client.connect.timeout</name>

</property>

<name>dfs.image.transfer.bandwidthPerSec</name>

</property>

</configuration>

[hadoop@nn01 hadoop]$ vi mapred-site.xml

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

</property>

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

<value>rm01.hadoop.com:10020</value>

</property>

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

<value>rm01.hadoop.com:19888</value>

</property>

</configuration>

[hadoop@nn01 hadoop]$ vi yarn-site.xml

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

<value>mapreduce_shuffle</value>

</property>

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

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

</property>

<name>yarn.resourcemanager.connect.retry-interval.ms</name>

</property>

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

<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler</value>

</property>

<name>yarn.app.mapreduce.am.scheduler.connection.wait.interval-ms</name>

</property>

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

</property>

<name>yarn.resourcemanager.store.class</name>

<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>

</property>

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

<value>dn01.hadoop.com:2181,dn02.hadoop.com:2181,dn03.hadoop.com:2181</value>

</property>

<name>yarn.resourcemanager.zk-state-store.parent-path</name>

<value>/rmstore</value>

</property>

<name>yarn.resourcemanager.zk-num-retries</name>

</property>

<name>yarn.resourcemanager.zk-retry-interval-ms</name>

</property>

<name>yarn.resourcemanager.zk-timeout-ms</name>

</property>

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

<value>world:anyone:rwcda</value>

</property>

<name>yarn.resourcemanager.am.max-attempts</name>

</property>

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

<value>yarn-cluster</value>

</property>

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

</property>

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

</property>

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

<value>rm01.hadoop.com</value>

</property>

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

<value>rm02.hadoop.com</value>

</property>

<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>

</property>

<name>yarn.resourcemanager.ha.automatic-failover.embedded</name>

</property>

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

<value>rm01.hadoop.com:8032</value>

</property>

<name>yarn.resourcemanager.scheduler.address.rm1</name>

<value>rm01.hadoop.com:8030</value>

</property>

<name>yarn.resourcemanager.admin.address.rm1</name>

<value>rm01.hadoop.com:8033</value>

</property>

<name>yarn.resourcemanager.resource-tracker.address.rm1</name>

<value>rm01.hadoop.com:8031</value>

</property>

<name>yarn.resourcemanager.webapp.address.rm1</name>

<value>rm01.hadoop.com:8088</value>

</property>

<name>yarn.resourcemanager.webapp.https.address.rm1</name>

<value>rm01.hadoop.com:8090</value>

</property>

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

<value>rm02.hadoop.com:8032</value>

</property>

<name>yarn.resourcemanager.scheduler.address.rm2</name>

<value>rm02.hadoop.com:8030</value>

</property>

<name>yarn.resourcemanager.admin.address.rm2</name>

<value>rm02.hadoop.com:8033</value>

</property>

<name>yarn.resourcemanager.resource-tracker.address.rm2</name>

<value>rm02.hadoop.com:8031</value>

</property>

<name>yarn.resourcemanager.webapp.address.rm2</name>

<value>rm02.hadoop.com:8088</value>

</property>

<name>yarn.resourcemanager.webapp.https.address.rm2</name>

<value>rm02.hadoop.com:8090</value>

</property>

</configuration>

[hadoop@nn01 hadoop]$ vi slaves

dn01.hadoop.com

dn02.hadoop.com

dn03.hadoop.com

[hadoop@nn01 ~]$ hdfs zkfc -formatZK

启动journalnode节点用于namenode主备数据同步

[hadoop@dn01 ~]$ hadoop-daemon.sh start journalnode

[hadoop@dn02 ~]$ hadoop-daemon.sh start journalnode

[hadoop@dn03 ~]$ hadoop-daemon.sh start journalnode

启动主namenode

[hadoop@nn01 ~]$ hdfs namenode -format -clusterId c1

[hadoop@nn01 ~]$ hadoop-daemon.sh start namenode

启动备用namenode

[hadoop@nn02 ~]$ hdfs namenode -bootstrapStandby

[hadoop@nn02 ~]$ hadoop-daemon.sh start namenode

启动namenode故障转移程序

[hadoop@nn01 ~]$ hadoop-daemon.sh start zkfc

[hadoop@nn02 ~]$ hadoop-daemon.sh start zkfc

启动datanode

[hadoop@dn01 ~]$ hadoop-daemon.sh start datanode

[hadoop@dn02 ~]$ hadoop-daemon.sh start datanode

[hadoop@dn03 ~]$ hadoop-daemon.sh start datanode

启动主resoucemanager

[hadoop@rm01 ~]$ start-yarn.sh

启动备用resoucemanager

[hadoop@rm02 ~]$ yarn-daemon.sh start resourcemanager

http://nn01.hadoop.com:50070/dfshealth.html#tab-overview

http://nn02.hadoop.com:50070/dfshealth.html#tab-overview

http://rm01.hadoop.com:8088/cluster/cluster

http://rm02.hadoop.com:8088/cluster/cluster

HDFS HA 检验实验

[hadoop@nn01 ~]$ jps

2352 DFSZKFailoverController

2188 NameNode

3105 Jps

执行命令

[hadoop@nn01 ~]$ kill -9 2188

刷新页面，看到

说明切换成功。

ResourceManager HA 检验实验

[hadoop@rm01 ~]$ jps

1599 ResourceManager

1927 Jps

启动wordcount程序

kill掉主ResourceManager进程

[hadoop@rm01 ~]$ kill -9 1599

看控制台输出，可以看到备的ResourceManager被启用

说明切换成功。

阅读全文

0 0