HadoopHA集群搭建
2017-03-15 09:19
405 查看
三台主机:
192.168.143.111 hdp1
192.168.143.112 hdp2
192.168.143.113 hdp3
tickTime=2000
dataDir=.../zookeeper/data
dataLogDir=.../zookeeper/dataLog
clientPort=2181
initLimit=5
syncLimit=2
server.1=hdp1:2888:3888
server.2=hdp2:2888:3888
server.3=hdp3:2888:3888
(2)在ZooKeeper目录下创建myid,hdp1的内容为1,hdp2的内容为2,hdp3的内容为3。
(3)分别启动ZooKeeper:zkServer.sh start
core-site.xml
<configuration>
<!-- 指定hdfs的nameservice为ns1 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://ns1/</value>
</property>
<!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/home/hadoop/app/hadoop-2.4.1/tmp</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>hdp1:2181,hdp2:2181,hdp3:2181</value>
</property>
</configuration>
hdfs-site.xml
<configuration>
<!--指定hdfs的nameservice为ns1,需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>ns1</value>
</property>
<!-- ns1下面有两个NameNode,分别是nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.ns1</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns1.nn1</name>
<value>hdp1:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.ns1.nn1</name>
<value>hdp1:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns1.nn2</name>
<value>hdp2:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.ns1.nn2</name>
<value>hdp2:50070</value>
</property>
<!-- 指定NameNode的元数据在JournalNode上的存放位置,与ZooKeeper位置相同 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hdp1:8485;hdp2:8485;hdp3:8485/ns1</value>
</property>
<!-- 指定JournalNode在本地磁盘存放数据的位置 -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/home/hadoop/app/hadoop-2.4.1/journaldata</value>
</property>
<!-- 开启NameNode失败自动切换 -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- 配置失败自动切换实现方式 -->
<property>
<name>dfs.client.failover.proxy.provider.ns1</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 配置隔离机制方法,多个机制用换行分割,即每个机制暂用一行-->
<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>
<!-- 使用sshfence隔离机制时需要ssh免登陆 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<
4000
;value>/home/hadoop/.ssh/id_rsa</value>
</property>
<!-- 配置sshfence隔离机制超时时间 -->
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
</configuration>
yarn-site.xml
<configuration>
<!-- 开启RM高可用 -->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<!-- 指定RM的cluster id -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yrc</value>
</property>
<!-- 指定RM的名字 -->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!-- 分别指定RM的地址 -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hdp1</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hdp2</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>hdp1:2181,hdp2:2181,hdp3:2181</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>
slaves
hdp3
再启动journalnode:hadoop-daemon.sh start journalnode
hdp1上格式化HDFS:hdfs namenode -format
启动hdp1的NameNode:hadoop-daemon.sh start namenode
在hdp2上执行命令:hdfs namenode -bootstrapStandby
在hdp1上执行:hdfs zkfc -formatZK
在hdp1上执行:start-dfs.sh
在hdp1上执行:start-yarn.sh
在hdp1上执行:start-dfs.sh start-yarn.sh
在hdp2上执行:yarn-daemon.sh start resourcemanager
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.defaultFS", "hdfs://ns1");
conf.set("dfs.nameservices", "ns1");
conf.set("dfs.ha.namenodes.ns1", "nn1,nn2");
conf.set("dfs.namenode.rpc-address.ns1.nn1", "hdp11:9000");
conf.set("dfs.namenode.rpc-address.ns1.nn2", "hdp2:9000");
//conf.setBoolean(name, value);
conf.set("dfs.client.failover.proxy.provider.ns1", "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider");
FileSystem fs = FileSystem.get(new URI("hdfs://ns1"), conf, "hadoop");
InputStream in =new FileInputStream("c://eclipse.rar");
OutputStream out = fs.create(new Path("/eclipse"));
IOUtils.copyBytes(in, out, 4096, true);
}
}
192.168.143.111 hdp1
192.168.143.112 hdp2
192.168.143.113 hdp3
1、安装配置ZooKeeper;
(1)在conf目录下创建配置文件zoo.cfgtickTime=2000
dataDir=.../zookeeper/data
dataLogDir=.../zookeeper/dataLog
clientPort=2181
initLimit=5
syncLimit=2
server.1=hdp1:2888:3888
server.2=hdp2:2888:3888
server.3=hdp3:2888:3888
(2)在ZooKeeper目录下创建myid,hdp1的内容为1,hdp2的内容为2,hdp3的内容为3。
(3)分别启动ZooKeeper:zkServer.sh start
2、修改hadoop配置文件;
hadoo-env.sh与mapred-site.xml的配置与非ha机制相同。core-site.xml
<configuration>
<!-- 指定hdfs的nameservice为ns1 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://ns1/</value>
</property>
<!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/home/hadoop/app/hadoop-2.4.1/tmp</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>hdp1:2181,hdp2:2181,hdp3:2181</value>
</property>
</configuration>
hdfs-site.xml
<configuration>
<!--指定hdfs的nameservice为ns1,需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>ns1</value>
</property>
<!-- ns1下面有两个NameNode,分别是nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.ns1</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns1.nn1</name>
<value>hdp1:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.ns1.nn1</name>
<value>hdp1:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns1.nn2</name>
<value>hdp2:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.ns1.nn2</name>
<value>hdp2:50070</value>
</property>
<!-- 指定NameNode的元数据在JournalNode上的存放位置,与ZooKeeper位置相同 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hdp1:8485;hdp2:8485;hdp3:8485/ns1</value>
</property>
<!-- 指定JournalNode在本地磁盘存放数据的位置 -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/home/hadoop/app/hadoop-2.4.1/journaldata</value>
</property>
<!-- 开启NameNode失败自动切换 -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- 配置失败自动切换实现方式 -->
<property>
<name>dfs.client.failover.proxy.provider.ns1</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 配置隔离机制方法,多个机制用换行分割,即每个机制暂用一行-->
<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>
<!-- 使用sshfence隔离机制时需要ssh免登陆 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<
4000
;value>/home/hadoop/.ssh/id_rsa</value>
</property>
<!-- 配置sshfence隔离机制超时时间 -->
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
</configuration>
yarn-site.xml
<configuration>
<!-- 开启RM高可用 -->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<!-- 指定RM的cluster id -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yrc</value>
</property>
<!-- 指定RM的名字 -->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!-- 分别指定RM的地址 -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hdp1</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hdp2</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>hdp1:2181,hdp2:2181,hdp3:2181</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>
slaves
hdp3
3、初次启动顺序
先启动ZooKeeper集群:zkServer.sh start再启动journalnode:hadoop-daemon.sh start journalnode
hdp1上格式化HDFS:hdfs namenode -format
启动hdp1的NameNode:hadoop-daemon.sh start namenode
在hdp2上执行命令:hdfs namenode -bootstrapStandby
在hdp1上执行:hdfs zkfc -formatZK
在hdp1上执行:start-dfs.sh
在hdp1上执行:start-yarn.sh
4、平常启动顺序
先启动ZooKeeper集群在hdp1上执行:start-dfs.sh start-yarn.sh
在hdp2上执行:yarn-daemon.sh start resourcemanager
5、HA机制下hdfs的Java编程
public class HDFS_HA {public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.defaultFS", "hdfs://ns1");
conf.set("dfs.nameservices", "ns1");
conf.set("dfs.ha.namenodes.ns1", "nn1,nn2");
conf.set("dfs.namenode.rpc-address.ns1.nn1", "hdp11:9000");
conf.set("dfs.namenode.rpc-address.ns1.nn2", "hdp2:9000");
//conf.setBoolean(name, value);
conf.set("dfs.client.failover.proxy.provider.ns1", "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider");
FileSystem fs = FileSystem.get(new URI("hdfs://ns1"), conf, "hadoop");
InputStream in =new FileInputStream("c://eclipse.rar");
OutputStream out = fs.create(new Path("/eclipse"));
IOUtils.copyBytes(in, out, 4096, true);
}
}
相关文章推荐
- Hadoop2.2.0 HA + Jdk1.8.0 + Zookeeper3.4.5 + Hbase0.98 集群搭建详细过程(服务器集群)
- Hadoop2.6集群环境搭建(HDFS HA+YARN)原来4G内存也能任性一次.
- Hadoop2.5.2 HA高可靠性集群搭建(Hadoop+Zookeeper)
- Hadoop2.5.2 HA高可靠性集群搭建(Hadoop+Zookeeper)
- Hadoop2.5+HA+zk3.4.6集群搭建
- Hadoop2.5.2 HA高可靠性集群搭建(Hadoop+Zookeeper)
- hadoop2.2.0的ha分布式集群搭建
- 第二章:hadoop2+HA+Zookeeper QJM集群搭建实验
- Hadoop2.2.0 HA高可用分布式集群搭建(hbase,hive,sqoop,spark)
- Hadoop 2.3.0-cdh5.0.0 HA集群搭建(yum 安装)
- hadoop2.2+HA 集群搭建
- 搭建 hadoop2 自动切换HA 集群
- Hadoop-2.6.0集群HA搭建
- 关于hadoop的HA集群配置和搭建
- hadoop集群搭建-Namenode HA和ResourceManager HA
- Hadoop2.6集群环境搭建(HDFS HA+YARN)
- Hadoop2.6集群环境搭建(HDFS HA+YARN)
- Hadoop2.2.0集群搭建(HA,联邦,yarn)
- Hadoop2.5.2 HA高可靠性集群搭建(Hadoop+Zookeeper)
- Hadoop2学习记录(1) |HA完全分布式集群搭建