1、集群规划
1.1 规划说明
hadoop1 cluster1 nameNode
hadoop2 cluster1 nameNodeStandby ZooKeeper ResourceManager
hadoop3 cluster2 nameNode ZooKeeper
hadoop4 cluster2 nameNodeStandby ZooKeeper ResourceManagerStandBy
hadoop5 DataNode
hadoop6 DataNode
hadoop7 DataNode
1.2 集群 拓扑图
2、hadoop配置
2.1 core-site.xml
<?xml version="1.0" encoding="UTF-8"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <!-- Put site-specific property overrides in this file. --> <configuration> <property> <name>fs.defaultFS</name> <value>hdfs://cluster1</value> </property> <property> <name>hadoop.tmp.dir</name> <value>/home/hadoop/hadoop/tmp</value> </property> <property> <name>ha.zookeeper.quorum</name> <value>hadoop2:2181,hadoop3:2181,hadoop4:2181</value> </property> </configuration>
2.2 hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <!-- Put site-specific property overrides in this file. --> <configuration> <property> <name>dfs.replication</name> <value>3</value> </property> <!--指定DataNode存储block的副本数量。默认值是3个，我们现在有4个DataNode，该值不大于4即可。--> <property> <name>dfs.nameservices</name> <value>cluster1,cluster2</value> </property> <!--使用federation时，使用了2个HDFS集群。这里抽象出两个NameService实际上就是给这2个HDFS集群起了个别名。名字可以随便起，相互不重复即可 --> <!-- 以下是集群cluster1的配置信息--> <property> <name>dfs.ha.namenodes.cluster1</name> <value>nn1,nn2</value> </property> <!-- 指定NameService是cluster1时的namenode有哪些，这里的值也是逻辑名称，名字随便起，相互不重复即可 --> <property> <name>dfs.namenode.rpc-address.cluster1.nn1</name> <value>hadoop1:9000</value> </property> <!-- 指定hadoop1的RPC地址 --> <property> <name>dfs.namenode.http-address.cluster1.nn1</name> <value>hadoop1:50070</value> </property> <!-- 指定hadoop1的http地址 --> <property> <name>dfs.namenode.rpc-address.cluster1.nn2</name> <value>hadoop2:9000</value> </property> <!-- 指定hadoop2的RPC地址 --> <property> <name>dfs.namenode.http-address.cluster1.nn2</name> <value>hadoop2:50070</value> </property> <!-- 指定hadoop2的http地址 --> <property> <name>dfs.namenode.shared.edits.dir</name> <value>qjournal://hadoop2:8485;hadoop3:8485;hadoop4:8485/cluster1</value> </property> <!-- 指定cluster1的两个NameNode共享edits文件目录时，使用的JournalNode集群信息，在cluster1中配置此信息 --> <property> <name>dfs.ha.automatic-failover.enabled.cluster1</name> <value>true</value> </property> <!-- 指定cluster1是否启动自动故障恢复，即当NameNode出故障时，是否自动切换到另一台NameNode --> <property> <name>dfs.client.failover.proxy.provider.cluster1</name> <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value> </property> <!-- 指定cluster1出故障时，哪个实现类负责执行故障切换 --> <!-- 以下是集群cluster2的配置信息--> <property> <name>dfs.ha.namenodes.cluster2</name> <value>nn3,nn4</value> </property> <!-- 指定NameService是cluster2时的namenode有哪些，这里的值也是逻辑名称，名字随便起，相互不重复即可 --> <property> <name>dfs.namenode.rpc-address.cluster2.nn3</name> <value>hadoop3:9000</value> </property> <!-- 指定hadoop3的RPC地址 --> <property> <name>dfs.namenode.http-address.cluster2.nn3</name> <value>hadoop3:50070</value> </property> <!-- 指定hadoop3的http地址 --> <property> <name>dfs.namenode.rpc-address.cluster2.nn4</name> <value>hadoop4:9000</value> </property> <!-- 指定hadoop4的RPC地址 --> <property> <name>dfs.namenode.http-address.cluster2.nn4</name> <value>hadoop4:50070</value> </property> <!-- 指定hadoop4的http地址 --> <!-- <property> <name>dfs.namenode.shared.edits.dir</name> <value>qjournal://hadoop2:8485;hadoop3:8485;hadoop4:8485/cluster2</value> </property> --> <!-- 指定cluster2的两个NameNode共享edits文件目录时，使用的JournalNode集群信息，在cluster2中配置此信息 --> <property> <name>dfs.ha.automatic-failover.enabled.cluster2</name> <value>true</value> </property> <!-- 指定cluster2是否启动自动故障恢复，即当NameNode出故障时，是否自动切换到另一台NameNode --> <property> <name>dfs.client.failover.proxy.provider.cluster2</name> <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value> </property> <!-- 指定cluster2出故障时，哪个实现类负责执行故障切换 --> <property> <name>dfs.journalnode.edits.dir</name> <value>/home/hadoop/hadoop/jndir</value> </property> <!-- 指定JournalNode集群在对NameNode的目录进行共享时，自己存储数据的磁盘路径 --> <property> <name>dfs.datanode.data.dir</name> <value>/home/hadoop/hadoop/datadir</value> </property> <property> <name>dfs.namenode.name.dir</name> <value>/home/hadoop/hadoop/namedir</value> </property> <property> <name>dfs.ha.fencing.methods</name> <value>sshfence</value> </property> <!-- 一旦需要NameNode切换，使用ssh方式进行操作 --> <property> <name>dfs.ha.fencing.ssh.private-key-files</name> <value>/home/hadoop/.ssh/id_rsa</value> </property> <!-- 一旦需要NameNode切换，使用ssh方式进行操作 --> </configuration>
2.3 mapred-site.xml
<?xml version="1.0"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <!-- Put site-specific property overrides in this file. --> <configuration> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> </configuration>
2.4 yarn-site.xml
<?xml version="1.0"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <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>hadoop5</value> </property> <!-- 分别指定RM的地址 --> <property> <name>yarn.resourcemanager.hostname.rm2</name> <value>hadoop6</value> </property> <!--开启故障自动切换--> <property> <name>yarn.resourcemanager.ha.automatic-failover.enabled</name> <value>true</value> </property> <!--在RM1上配置rm1,在MR2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> <!-- <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> --> <!--配置与zookeeper的连接地址--> <property> <name>yarn.resourcemanager.zk-state-store.address</name> <value>hadoop2:2181,hadoop3:2181,hadoop4:2181</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>hadoop2:2181,hadoop3:2181,hadoop4:2181</value> </property> <!--开启自动恢复功能--> <property> <name>yarn.resourcemanager.recovery.enabled</name> <value>true</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>hadoop2:8132</value> </property> <property> <name>yarn.resourcemanager.scheduler.address.rm1</name> <value>hadoop2:8130</value> </property> <property> <name>yarn.resourcemanager.webapp.address.rm1</name> <value>hadoop2:8188</value> </property> <property> <name>yarn.resourcemanager.resource-tracker.address.rm1</name> <value>hadoop2:8131</value> </property> <property> <name>yarn.resourcemanager.admin.address.rm1</name> <value>hadoop2:8033</value> </property> <property> <name>yarn.resourcemanager.ha.admin.address.rm1</name> <value>hadoop2:23142</value> </property> <!--配置rm2--> <property> <name>yarn.resourcemanager.address.rm2</name> <value>hadoop4:8132</value> </property> <property> <name>yarn.resourcemanager.scheduler.address.rm2</name> <value>hadoop4:8130</value> </property> <property> <name>yarn.resourcemanager.webapp.address.rm2</name> <value>hadoop4:8188</value> </property> <property> <name>yarn.resourcemanager.resource-tracker.address.rm2</name> <value>hadoop4:8131</value> </property> <property> <name>yarn.resourcemanager.admin.address.rm2</name> <value>hadoop4:8033</value> </property> <property> <name>yarn.resourcemanager.ha.admin.address.rm2</name> <value>hadoop4:23142</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>/home/hadoop/hadoop/yarn/local</value> </property> <property> <name>yarn.nodemanager.log-dirs</name> <value>/home/hadoop/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.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> </configuration>
2.5 slaves文件
hadoop5
hadoop6
hadoop7
3 zookeeper 配置
3.1 zoo.cfg
# The number of milliseconds of each tick
tickTime=2000
# The number of ticks that the initial
# synchronization phase can take
initLimit=10
# The number of ticks that can pass between
# sending a request and getting an acknowledgement
syncLimit=5
# the directory where the snapshot is stored.
# do not use /tmp for storage, /tmp here is just
# example sakes.
#dataDir=/tmp/zookeeper
# the port at which the clients will connect
clientPort=2181
#
# Be sure to read the maintenance section of the
# administrator guide before turning on autopurge.
#
# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#
# The number of snapshots to retain in dataDir
#autopurge.snapRetainCount=3
# Purge task interval in hours
# Set to "0" to disable auto purge feature
#autopurge.purgeInterval=1
dataDir=/home/hadoop/zookeeper/data
dataLogDir=/home/hadoop/zookeeper/log
server.1=hadoop2:2888:3888
server.2=hadoop3:2888:3888
server.3=hadoop4:2888:3888
3.2 配置myid
在zookeeper data目录中分别执行
echo 1 > myid echo 2 > myid echo 3 > myid
4 集群初始化及启动
4.1 在 hadoop2,hadoop3,hadoop4启动zookeeper
cd apps/zookeeper-3.4.5/ bin/zkServer.sh start
4.2 格式化zookeeper集群,在hadoop1、hadoop3 执行
hdfs zkfc -formatZK
4.3 启动JournalNode集群,在hadoop2,hadoop3,hadoop4 上执行
hadoop-daemon.sh start journalnode
4.4 格式化cluster1的namenode 在hadoop1上执行
hdfs namenode -format -clusterId c1
4.5 启动cluster1格式化后的namenode,在hadoop1上执行
hadoop-daemon.sh start namenode
4.6 把NameNode的数据从hadoop1同步到hadoop2中
hdfs namenode -bootstrapStandby
4.7 启动hadoop2即cluster1 nameNodeStandby
hadoop-daemon.sh start namenode
4.8 格式化cluster2的namenode 在hadoop3上执行
hdfs namenode -format -clusterId c2
4.9 启动cluster2格式化后的namenode,在hadoop3上执行
hadoop-daemon.sh start namenode
4.10 把NameNode的数据从hadoop3同步到hadoop4中在hadoop4上执行
hdfs namenode -bootstrapStandby
4.11 启动hadoop4即cluster2 namenode的standby
hadoop-daemon.sh start namenode
4.12 启动所有 datanode,在任何一个namenode上执行
hadoop-daemons.sh start datanode
4.13 启动yarn 在hadoop2上执行
start-yarn.sh
4.14 启动yarn 在hadoop4上执行
yarn-daemon.sh start resourcemanager
4.15 启动ZooKeeperFailoverController在每个namenode上执行
hadoop-daemon.sh start zkfc