搭建hadoop高可用集群（二）

配置hadoop

解压完后，单独配置这6个文件

hadoop-env.sh

第54行

 export JAVA_HOME=/opt/soft/jdk180export HDFS_NAMENODE_USER=rootexport HDFS_DATANODE_USER=rootexport HDFS_SECONDARYNAMENODE_USER=rootexport HDFS_JOURNALNODE_USER=rootexport HDFS_ZKFC_USER=rootexport YARN_RESOURCEMANAGER_USER=rootexport YARN_NODEMANAGER_USER=root

workers

填入ip

hadoop151
hadoop152
hadoop153
hadoop154

core-site.xml

<configuration><property><name>fs.defaultFS</name><value>hdfs://gky</value><description>逻辑名称，必须与hdfs-site.xml中的dfs.nameservice值保持一致</description></property><property><name>hadoop.tmp.dir</name><value>/opt/soft/hadoop313/tmpdata</value><description>namenode上本地的hadoop临时文件夹</description></property><property><name>hadoop.http.staticuser.user</name><value>root</value><description>默认用户</description></property><property><name>hadoop.proxyuser.root.hosts</name><value>*</value><description></description></property><property><name>hadoop.proxyuser.root.groups</name><value>*</value><description></description></property><property><name>io.file.buffer.size</name><value>131072</value><description>读写文件的buffer大小为：128k</description></property><property><name>ha.zookeeper.quorum</name><value>hadoop151:2181,hadoop152:2181,hadoop153:2181</value>//改成自己的ip<description>zookeeper队列</description></property><property><name>ha.zookeeper.session-timeout.ms</name><value>10000</value><description>hadoop连接zookeeper的超时时长设置为10s</description></property>
</configuration>

hdfs-site.xml

<configuration><property><name>dfs.replication</name><value>3</value><description>hadoop中每一个block文件的备份数量</description></property><property><name>dfs.namenode.name.dir</name><value>/opt/soft/hadoop313/data/dfs/name</value><description>namenode上存储hdfs名字空间元数据的目录</description></property><property><name>dfs.datanode.data.dir</name><value>/opt/soft/hadoop313/data/dfs/data</value><description>datanode上数据块的物理存储位置目录</description></property><property><name>dfs.namenode.secondary.http-address</name><value>hadoop151:9869</value><description></description></property><property><name>dfs.nameservices</name><value>gky</value><description>指定hdfs的nameservice,需要和core-site.xml中保持一致</description></property><property><name>dfs.ha.namenodes.gky</name><value>nn1,nn2</value><description>gky为集群的逻辑名称，映射两个namenode逻辑</description></property><property><name>dfs.namenode.rpc-address.gky.nn1</name><value>hadoop151:9000</value><description>namenode1的RPC通信地址</description></property><property><name>dfs.namenode.http-address.gky.nn1</name><value>hadoop151:9870</value><description>namenode1的http通信地址</description></property><property><name>dfs.namenode.rpc-address.gky.nn2</name><value>hadoop152:9000</value><description>namenode2的RPC通信地址</description></property><property><name>dfs.namenode.http-address.gky.nn2</name><value>hadoop152:9870</value><description>namenode2的http通信地址</description></property><property><name>dfs.namenode.shared.edits.dir</name><value>qjournal://hadoop151:8485;hadoop152:8485;hadoop153:8485/gky</value><description>指定NameNode的edits元数据的共享存储位置(JournalNode列表)</description></property><property><name>dfs.journalnode.edits.dir</name><value>/opt/soft/hadoop313/data/journaldata</value><description>指定JournalNode在本地磁盘存放数据的位置</description></property><!-- 容错 --><property><name>dfs.ha.automatic-failover.enabled</name><value>true</value><description>开启NameNode故障自动切换</description></property><property><name>dfs.client.failover.proxy.provider.gky</name><value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value><description>失败后自动切换的实现方式</description></property><property><name>dfs.ha.fencing.methods</name><value>sshfence</value><description>防止脑裂的处理</description></property><property><name>dfs.ha.fencing.ssh.private-key-files</name><value>/root/.ssh/id_rsa</value><description>使用sshfence隔离机制，需要ssh免密登录</description></property><property><name>dfs.permissions.enabled</name><value>false</value><description>关闭HDFS操作权限验证</description></property><property><name>dfs.image.transfer.bandwidthPerSec</name><value>1048576</value><description></description></property><property><name>dfs.block.scanner.volume.bytes.per.second</name><value>1048576</value><description></description></property>
</configuration>

mapred-site.xml

<configuration><property><name>mapreduce.framework.name</name><value>yarn</value><description>job执行框架：local,classic or yarn</description><final>true</final></property><property><name>mapreduce.application.classpath</name><value>/opt/soft/hadoop313/etc/hadoop:/opt/soft/hadoop313/share/hadoop/common/lib/*:/opt/soft/hadoop313/share/hadoop/common/*:/opt/soft/hadoop313/share/hadoop/hdfs/*:/opt/soft/hadoop313/share/hadoop/hdfs/lib/*:/opt/soft/hadoop313/share/hadoop/mapreduce/*:/opt/soft/hadoop313/share/hadoop/mapreduce/lib/*:/opt/soft/hadoop313/share/hadoop/yarn/*:/opt/soft/hadoop313/share/hadoop/yarn/lib/*</value></property><property><name>mapreduce.jobhistory.address</name><value>hadoop151:10020</value></property><property><name>mapreduce.jobhistory.webapp.address</name><value>hadoop151:19888</value></property><property><name>mapreduce.map.memory.mb</name><value>1024</value><description>map阶段的task工作内存</description></property><property><name>mapreduce.reduce.memory.mb</name><value>2048</value><description>reduce阶段的task工作内存</description></property>
</configuration>

yarn-site.xml

<configuration><property><name>yarn.resourcemanager.ha.enabled</name><value>true</value><description>开启resourcemanager高可用</description></property><property><name>yarn.resourcemanager.cluster-id</name><value>yrcabc</value><description>指定yarn的集群中的id</description></property><property><name>yarn.resourcemanager.ha.rm-ids</name><value>rm1,rm2</value><description>指定resourcemanager的名字</description></property><property><name>yarn.resourcemanager.hostname.rm1</name><value>hadoop153</value><description>设置rm1的名字</description></property><property><name>yarn.resourcemanager.hostname.rm2</name><value>hadoop154</value><description>设置rm2的名字</description></property><property><name>yarn.resourcemanager.webapp.address.rm1</name><value>hadoop153:8088</value><description></description></property><property><name>yarn.resourcemanager.webapp.address.rm2</name><value>hadoop154:8088</value><description></description></property><property><name>yarn.resourcemanager.zk-address</name><value>hadoop151:2181,hadoop152:2181,hadoop153:2181</value><description>指定zk集群地址</description></property><property><name>yarn.nodemanager.aux-services</name><value>mapreduce_shuffle</value><description>运行mapreduce程序必须配置的附属服务</description></property><property><name>yarn.nodemanager.local-dirs</name><value>/opt/soft/hadoop313/tmpdata/yarn/local</value><description>nodemanager本地存储目录</description></property><property><name>yarn.nodemanager.log-dirs</name><value>/opt/soft/hadoop313/tmpdata/yarn/log</value><description>nodemanager本地日志目录</description></property><property><name>yarn.nodemanager.resource.memory-mb</name><value>2048</value><description>resource进程的内存</description></property><property><name>yarn.nodemanager.resource.cpu-vcores</name><value>2</value><description>resource工作中所能使用机器的内核数</description></property><property><name>yarn.scheduler.minimum-allocation-mb</name><value>256</value><description></description></property><property><name>yarn.log-aggregation-enable</name><value>true</value><description>yarn的日志能不能合并</description></property><property><name>yarn.log-aggregation.retain-seconds</name><value>86400</value><description>yarn的合并日志保存的时间（多少秒）</description></property><property><name>yarn.nodemanager.vmem-check-enabled</name><value>false</value><description></description></property><property><name>yarn.application.classpath</name><value>/opt/soft/hadoop313/etc/hadoop:/opt/soft/hadoop313/share/hadoop/common/lib/*:/opt/soft/hadoop313/share/hadoop/common/*:/opt/soft/hadoop313/share/hadoop/hdfs/*:/opt/soft/hadoop313/share/hadoop/hdfs/lib/*:/opt/soft/hadoop313/share/hadoop/mapreduce/*:/opt/soft/hadoop313/share/hadoop/mapreduce/lib/*:/opt/soft/hadoop313/share/hadoop/yarn/*:/opt/soft/hadoop313/share/hadoop/yarn/lib/*</value><description></description></property><property><name>yarn.nodemanager.env-whitelist</name><value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_MAPRED_HOME</value><description></description></property>
</configuration>

/etc/profile

#HADOOP_HOME
export HADOOP_HOME=/opt/soft/hadoop313
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/lib

拷贝

将配置好的文件拷贝到另外三台机器中

   scp -r ./hadoop313/ root@hadoop151:/opt/softscp -r ./hadoop313/ root@hadoop152:/opt/softscp -r ./hadoop313/ root@hadoop153:/opt/softscp -r ./hadoop313/ root@hadoop154:/opt/soft

scp -r /etc/profile root@hadoop151:/etc
scp -r /etc/profile root@hadoop152:/etc
scp -r /etc/profile root@hadoop153:/etc
scp -r /etc/profile root@hadoop154:/etc

集群首次启动

1、先启动zk集群（自动化脚本）

2、在hadoop151,hadoop152,hadoop153启动JournalNode

hdfs --daemon start journalnode

可以用脚本查看三台机器的启动状态

3、在hadoop151格式化

hdfs namenode -format

4、在hadoop151启动namenode服务

hdfs --daemon start namenode

5、在hadoop152机器上同步namenode信息

hdfs namenode -bootstrapStandby

6、在hadoop152上启动namenode服务

hdfs --daemon start namenode

没启动之前的jps

启动之后

查看namenode节点状态

hdfs haadmin -getServiceState nn2

7、关闭所有dfs有关的服务

stop-dfs.sh

8、格式化zk

hdfs zkfc -formatZK

格式化完可以进工作空间

zkCli.sh

9、启动dfs

start-dfs.sh

查看namenode节点状态



151挂掉后，152会变成active,如果151又上线，它不会变成active,会变成standby

10、启动yarn

start-yarn.sh

查看状态

查看resourcemanager节点状态

yarn rmadmin -getServiceState rm1

如图153是active
当输入 hadoop153:8088或hadoop154:8088时，页面地址都会转到hadoop153:8088

安装成功

上传一个文件，测试wordcount,运行成功，即安装成功

后面hadoop可直接用start-all.sh开启，stop-all.sh关闭；zookeeper可以用脚本一键开启关闭（要注意开启时，要先开启zookeeper）