1. 配置 /opt/hadoop-2.7.4/etc/hadoop/core-site.xml
代码语言：javascript复制<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://bigdata:9000</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/home/bigdata/hadoopdata</value>
</property>
<property>
<name>hadoop.proxyuser.bigdata.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.bigdata.groups</name>
<value>*</value>
</property>
</configuration>2. 配置 /opt/hadoop-2.7.4/etc/hadoop/yarn-site.xml
代码语言：javascript复制<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.resourcemanager.address</name>
<value>bigdata:18040</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>bigdata:18030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>bigdata:18025</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>bigdata:18141</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>bigdata:18088</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<name>yarn.nodemanager.pmem-check-enabled</name>
<value>false</value>
</property>
<property>
<name>yarn.nodemanager.vmem-check-enabled</name>
<value>false</value>
</property>
</configuration>3. 配置 /opt/hadoop-2.7.4/etc/hadoop/mapred-site.xml
代码语言：javascript复制<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.done-dir</name>
<value>/user/history/done</value>
</property>
<property>
<name>mapreduce.jobhistory.intermediate-done-dir</name>
<value>/user/history/done_intermediate</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>bigdata:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>bigdata:19888</value>
</property>
</configuration>4. 配置 /opt/hadoop-2.7.4/etc/hadoop/capacity-scheduler.xml (使用以下内容直接替换文件内容)
代码语言：javascript复制<!--
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.scheduler.capacity.maximum-applications</name>
<value>10000</value>
<description>
Maximum number of applications that can be pending and running.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.maximum-am-resource-percent</name>
<value>0.5</value>
<description>
Maximum percent of resources in the cluster which can be used to run
application masters i.e. controls number of concurrent running
applications.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.resource-calculator</name>
<value>org.apache.hadoop.yarn.util.resource.DefaultResourceCalculator</value>
<description>
The ResourceCalculator implementation to be used to compare
Resources in the scheduler.
The default i.e. DefaultResourceCalculator only uses Memory while
DominantResourceCalculator uses dominant-resource to compare
multi-dimensional resources such as Memory, CPU etc.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.queues</name>
<value>etl,report,default</value>
<description>
The queues at the this level (root is the root queue).
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.default.capacity</name>
<value>40</value>
<description>Default queue target capacity.</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.etl.capacity</name>
<value>30</value>
<description>etl queue target capacity.</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.report.capacity</name>
<value>30</value>
<description>report queue target capacity.</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.default.user-limit-factor</name>
<value>1</value>
<description>
Default queue user limit a percentage from 0.0 to 1.0.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.etl.user-limit-factor</name>
<value>1</value>
<description>
etl queue user limit a percentage from 0.0 to 1.0.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.report.user-limit-factor</name>
<value>1</value>
<description>
report queue user limit a percentage from 0.0 to 1.0.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.default.maximum-capacity</name>
<value>100</value>
<description>
The maximum capacity of the default queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.etl.maximum-capacity</name>
<value>100</value>
<description>
The maximum capacity of the etl queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.report.maximum-capacity</name>
<value>100</value>
<description>
The maximum capacity of the report queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.default.state</name>
<value>RUNNING</value>
<description>
The state of the default queue. State can be one of RUNNING or STOPPED.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.etl.state</name>
<value>RUNNING</value>
<description>
The state of the etl queue. State can be one of RUNNING or STOPPED.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.report.state</name>
<value>RUNNING</value>
<description>
The state of the report queue. State can be one of RUNNING or STOPPED.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.default.acl_submit_applications</name>
<value>*</value>
<description>
The ACL of who can submit jobs to the default queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.etl.acl_submit_applications</name>
<value>*</value>
<description>
The ACL of who can submit jobs to the etl queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.report.acl_submit_applications</name>
<value>*</value>
<description>
The ACL of who can submit jobs to the report queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.default.acl_administer_queue</name>
<value>*</value>
<description>
The ACL of who can administer jobs on the default queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.etl.acl_administer_queue</name>
<value>*</value>
<description>
The ACL of who can administer jobs on the etl queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.root.report.acl_administer_queue</name>
<value>*</value>
<description>
The ACL of who can administer jobs on the report queue.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.node-locality-delay</name>
<value>40</value>
<description>
Number of missed scheduling opportunities after which the CapacityScheduler
attempts to schedule rack-local containers.
Typically this should be set to number of nodes in the cluster, By default is setting
approximately number of nodes in one rack which is 40.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.queue-mappings</name>
<value></value>
<description>
A list of mappings that will be used to assign jobs to queues
The syntax for this list is [u|g]:[name]:[queue_name][,next mapping]*
Typically this list will be used to map users to queues,
for example, u:%user:%user maps all users to queues with the same name
as the user.
</description>
</property>
<property>
<name>yarn.scheduler.capacity.queue-mappings-override.enable</name>
<value>false</value>
<description>
If a queue mapping is present, will it override the value specified
by the user? This can be used by administrators to place jobs in queues
that are different than the one specified by the user.
The default is false.
</description>
</property>
</configuration>最后启动 yarn
1. 先启动 hdfs
代码语言：javascript复制/opt/hadoop-2.7.4/sbin/start-dfs.sh2. 然后启动 yarn
代码语言：javascript复制/opt/hadoop-2.7.4/sbin/start-yarn.sh访问 http://bigdata:18088 验证 yarn 是否启动成功
3. 最后启动 historyserver
代码语言：javascript复制/opt/hadoop-2.7.4/sbin/mr-jobhistory-daemon.sh start historyserver访问 http://bigdata:19888 验证 historyserver 是否启动成功
