<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://mycluster</value></property><property><name>hadoop.tmp.dir</name><value>/opt/module/hadoop-2.6.5/data/tmp</value></property><property><name>fs.trash.interval</name><value>2</value></property><property><name>fs.trash.checkpoint.interval</name><value>1</value></property><property><name>hadoop.http.staticuser.user</name><value>root</value></property><property><name>ha.zookeeper.quorum</name><value>hadoop001:2181,hadoop002:2181,hadoop003:2181</value></property></configuration>
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><!-- 完全分布式集群名称 --><property><name>dfs.nameservices</name><value>mycluster</value></property><!-- 集群中NameNode节点都有哪些 --><property><name>dfs.ha.namenodes.mycluster</name><value>nn1,nn2</value></property><!-- nn1的RPC通信地址 --><property><name>dfs.namenode.rpc-address.mycluster.nn1</name><value>hadoop001:8020</value></property><!-- nn2的RPC通信地址 --><property><name>dfs.namenode.rpc-address.mycluster.nn2</name><value>hadoop003:8020</value></property><!-- nn1的http通信地址 --><property><name>dfs.namenode.http-address.mycluster.nn1</name><value>hadoop001:50070</value></property><!-- nn2的http通信地址 --><property><name>dfs.namenode.http-address.mycluster.nn2</name><value>hadoop003:50070</value></property><!-- 指定NameNode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/mycluster</value></property><!-- 配置隔离机制，即同一时刻只能有一台服务器对外响应 --><property><name>dfs.ha.fencing.methods</name><value>sshfence</value></property><!-- 使用隔离机制时需要ssh无秘钥登录--><property><name>dfs.ha.fencing.ssh.private-key-files</name><value>/root/.ssh/id_rsa</value></property><!-- 声明journalnode服务器存储目录--><property><name>dfs.journalnode.edits.dir</name><value>/opt/module/hadoop-2.6.5/data/jn</value></property><!-- 关闭权限检查--><property><name>dfs.permissions.enable</name><value>false</value></property><!-- 访问代理类：client，mycluster，active配置失败自动切换实现方式--><property><name>dfs.client.failover.proxy.provider.mycluster</name><value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value></property><!-- automatic failover--><property><name>dfs.ha.automatic-failover.enabled</name><value>true</value></property></configuration>
[root@hadoop001 hadoop-2.6.5]# bin/hdfs haadmin -transitionToActive nn1
Automatic failover is enabled for NameNode at hadoop003/192.168.170.133:8020
Refusing to manually manage HA state, sinceit may cause
a split-brain scenario or other incorrect state.
If you are very sure you know what you are doing, please
specify the forcemanual flag.
# 这里需要强制切换
[root@hadoop001 hadoop-2.6.5]# bin/hdfs haadmin -transitionToActive --forcemanual nn1
You have specified the forcemanual flag. This flag is dangerous, asit can induce a split-brain scenario that WILL CORRUPT your HDFS namespace, possibly irrecoverably.
It is recommended notto use this flag, but instead to shut down the cluster and disable automatic failover if you prefer to manually manage your HA state.
You may abort safely by answering 'n' or hitting ^C now.
Are you sure you want tocontinue (Y or N) y
18/08/2116:12:59 WARN ha.HAAdmin: Proceeding with manual HA state management even though
automatic failover is enabled for NameNode at hadoop003/192.168.170.133:802018/08/2116:13:00 WARN ha.HAAdmin: Proceeding with manual HA state management even though
automatic failover is enabled for NameNode at hadoop001/192.168.170.131:8020# 可以看到nn2已经激活，nn1在standby状态
[root@hadoop001 hadoop-2.6.5]# bin/hdfs haadmin -getServiceState nn1
standby
[root@hadoop001 hadoop-2.6.5]# bin/hdfs haadmin -getServiceState nn2
active
<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><property><name>yarn.nodemanager.aux-services</name><value>mapreduce_shuffle</value></property><!--日志聚合--><property><name>yarn.log-aggregation-enable</name><value>true</value></property><!--任务历史服务--><property><name>yarn.log.server.url</name><value>http://hadoop001:19888/jobhistory/logs/</value></property><property><name>yarn.log-aggregation.retain-seconds</name><value>86400</value></property><!--启用resourcemanager ha--><property><name>yarn.resourcemanager.ha.enabled</name><value>true</value></property><!--声明两台resourcemanager的地址--><property><name>yarn.resourcemanager.cluster-id</name><value>cluster-yarn1</value></property><property><name>yarn.resourcemanager.ha.rm-ids</name><value>rm1,rm2</value></property><property><name>yarn.resourcemanager.hostname.rm1</name><value>hadoop002</value></property><property><name>yarn.resourcemanager.hostname.rm2</name><value>hadoop003</value></property><!--指定zookeeper集群的地址--><property><name>yarn.resourcemanager.zk-address</name><value>hadoop001:2181,hadoop002:2181,hadoop003:2181</value></property><!--启用自动恢复--><property><name>yarn.resourcemanager.recovery.enabled</name><value>true</value></property><!--指定resourcemanager的状态信息存储在zookeeper集群--><property><name>yarn.resourcemanager.store.class</name><value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value></property></configuration>
