集群搭建
因为服务器数量有限,这里服务器开启的进程有点多:
机器名 | 安装软件 | 运行进程 |
hadoop001 | Hadoop,Zookeeper |
NameNode, DFSZKFailoverController, ResourceManager DataNode, NodeManager QuorumPeerMain JournalNode |
hadoop002 | Hadoop,Zookeeper |
NameNode, DFSZKFailoverController, ResourceManager DataNode, NodeManager QuorumPeerMain JournalNode |
hadoop003 | Hadoop,Zookeeper |
DataNode, NodeManager QuorumPeerMain |
无密码登陆
ssh-keygen -t rsa
在~/.ssh/目录中生成两个文件id_rsa和id_rsa.pub
如果想从hadoop001免密码登录到hadoop002中要在hadoop001中执行
ssh-copy-id -i ~/.ssh/id_rsa.pub [用户名]@hadoop002
这里为了实现任何机器之间都可以免密码登陆,所以在hadoop001中再执行两遍上面的操作(把@后面的机器名分别改成hadoop001和hadoop003),最后把生成的authorized_keys复制所有的节点上
Hadoop配置
core-site.xml
<configuration>
<!-- -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://appcluster</value>
</property> <!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/data/hadoop/storage/tmp</value>
</property> <!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>hadoop001:2181,hadoop002:2181,hadoop003:2181</value>
</property> <property>
<name>ha.zookeeper.session-timeout.ms</name>
<value>2000</value>
</property>
</configuration>
hdfs-site.xml
<configuration>
<!--指定namenode名称空间的存储地址-->
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///data/hadoop/storage/hdfs/name</value>
</property> <!--指定datanode数据存储地址-->
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///data/hadoop/storage/hdfs/data</value>
</property> <!--指定数据冗余份数-->
<property>
<name>dfs.replication</name>
<value>2</value>
</property> <!--指定hdfs的nameservice为appcluster,需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>appcluster</value>
</property> <!-- appcluster下面有两个NameNode,分别是nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.appcluster</name>
<value>nn1,nn2</value>
</property> <!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.appcluster.nn1</name>
<value>hadoop001:8020</value>
</property> <!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.appcluster.nn2</name>
<value>hadoop002:8020</value>
</property> <!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.appcluster.nn1</name>
<value>hadoop001:50070</value>
</property> <!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.appcluster.nn2</name>
<value>hadoop002:50070</value>
</property> <!-- 指定NameNode的元数据在JournalNode上的存放位置 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hadoop001:8485;hadoop002:8485;hadoop003:8485/appcluster</value>
</property> <property>
<name>dfs.ha.automatic-failover.enabled.appcluster</name>
<value>true</value>
</property> <!-- 配置失败自动切换实现方式 -->
<property>
<name>dfs.client.failover.proxy.provider.appcluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property> <!-- 配置隔离机制 -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property> <!-- 使用隔离机制时需要ssh免密码登陆 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/[用户名]/.ssh/id_rsa</value>
</property> <!-- -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/data/hadoop/tmp/journal</value>
</property>
</configuration>
mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property> <!-- 配置 MapReduce JobHistory Server 地址 ,默认端口10020 -->
<property>
<name>mapreduce.jobhistory.address</name>
<value>0.0.0.0:10020</value>
</property> <!-- 配置 MapReduce JobHistory Server web ui 地址, 默认端口19888 -->
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>0.0.0.0:19888</value>
</property>
</configuration>
yarn-site.xml
<?xml version="1.0"?>
<configuration>
<!--rm失联后重新链接的时间-->
<property>
<name>yarn.resourcemanager.connect.retry-interval.ms</name>
<value>2000</value>
</property> <!--开启resourcemanagerHA,默认为false-->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property> <!--配置resourcemanager-->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property> <property>
<name>ha.zookeeper.quorum</name>
<value>hadoop001:2181,hadoop002:2181,hadoop003:2181</value>
</property> <!--开启故障自动切换-->
<property>
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
<value>true</value>
</property> <property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hadoop001</value>
</property> <property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hadoop002</value>
</property> <!--
在hadoop001上配置rm1,在hadoop002上配置rm2,
注意:一般都喜欢把配置好的文件远程复制到其它机器上,但这个在YARN的另一个机器上一定要修改
-->
<property>
<name>yarn.resourcemanager.ha.id</name>
<value>rm1</value>
<description>If we want to launch more than one RM in single node,we need this configuration</description>
</property> <!--开启自动恢复功能-->
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property> <!--配置与zookeeper的连接地址-->
<property>
<name>yarn.resourcemanager.zk-state-store.address</name>
<value>hadoop001:2181,hadoop002:2181,hadoop003:2181</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>hadoop001:2181,hadoop002:2181,hadoop003:2181</value>
</property> <property>
<name>yarn.resourcemanager.cluster-id</name>
<value>appcluster-yarn</value>
</property> <!--schelduler失联等待连接时间-->
<property>
<name>yarn.app.mapreduce.am.scheduler.connection.wait.interval-ms</name>
<value>5000</value>
</property> <!--配置rm1-->
<property>
<name>yarn.resourcemanager.address.rm1</name>
<value>hadoop001:8032</value>
</property> <property>
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>hadoop001:8030</value>
</property> <property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>hadoop001:8088</value>
</property> <property>
<name>yarn.resourcemanager.resource-tracker.address.rm1</name>
<value>hadoop001:8031</value>
</property> <property>
<name>yarn.resourcemanager.admin.address.rm1</name>
<value>hadoop001:8033</value>
</property> <property>
<name>yarn.resourcemanager.ha.admin.address.rm1</name>
<value>hadoop001:23142</value>
</property> <!--配置rm2-->
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>hadoop002:8032</value>
</property> <property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>hadoop002:8030</value>
</property> <property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>hadoop002:8088</value>
</property> <property>
<name>yarn.resourcemanager.resource-tracker.address.rm2</name>
<value>hadoop002:8031</value>
</property> <property>
<name>yarn.resourcemanager.admin.address.rm2</name>
<value>hadoop002:8033</value>
</property> <property>
<name>yarn.resourcemanager.ha.admin.address.rm2</name>
<value>hadoop002:23142</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.nodemanager.local-dirs</name>
<value>/data/hadoop/yarn/local</value>
</property> <property>
<name>yarn.nodemanager.log-dirs</name>
<value>/data/hadoop/yarn/log</value>
</property> <property>
<name>mapreduce.shuffle.port</name>
<value>23080</value>
</property> <!--故障处理类-->
<property>
<name>yarn.client.failover-proxy-provider</name>
<value>org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider</value>
</property> <property>
<name>yarn.resourcemanager.ha.automatic-failover.zk-base-path</name>
<value>/yarn-leader-election</value>
<description>Optionalsetting.Thedefaultvalueis/yarn-leader-election</description>
</property>
</configuration>
hadoop-env.sh & mapred-env.sh & yarn-env.sh
export JAVA_HOME=/usr/java/jdk1.7.0_60
export CLASS_PATH=$JAVA_HOME/lib:$JAVA_HOME/jre/lib export HADOOP_HOME=/data/hadoop-2.6.0
export HADOOP_PID_DIR=/data/hadoop/pids
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_OPTS="$HADOOP_OPTS-Djava.library.path=$HADOOP_HOME/lib/native" export HADOOP_PREFIX=$HADOOP_HOME export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export HDFS_CONF_DIR=$HADOOP_HOME/etc/hadoop
export YARN_CONF_DIR=$HADOOP_HOME/etc/hadoop export JAVA_LIBRARY_PATH=$HADOOP_HOME/lib/native export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
参考文献
[1] hdfs-site.xml:http://www.21ops.com/front-tech/10744.html
[2] yarn-site.xml: http://www.aboutyun.com/thread-10572-1-1.html 评论也值得参考
仅参考这两篇配置后报错:
15/07/17 13:58:55 FATAL ha.ZKFailoverController: Automatic failover is not enabled for NameNode at hadoop001/**.**.**.**:8020. Please ensure that automatic failover is enabled in the configuration before running the ZK failover controller.
再参考
[3]http://www.cnblogs.com/meiyuanbao/p/3545929.html (没有做到Yarn的HA)
发现需要在hdfs-site.xml添加配置:
<property>
<name>dfs.ha.automatic-failover.enabled.appcluster</name>
<value>true</value>
</property>