<?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>
<!-- rm失联后重新链接的时间 -->
<property>
<name>yarn.resourcemanager.connect.retry-interval.ms</name>
<value>2000</value>
</property>
<property>
<!-- 启用RM高可用 -->
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
<description>启动Yran HA模式</description>
</property>
<property>
<!-- 指定两台RM主机名标识符 -->
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
<description>resourcemanager id</description>
</property>
<property>
<!--Ha功能，需要一组zk地址，用逗号分隔。被ZKFailoverController使用于自动失效备援failover。 -->
<name>ha.zookeeper.quorum</name>
<value>hdp01:2181,hdp02:2181,hdp03:2181,hdp04:2181</value>
<description>Zookeeper 队列</description>
</property>
<property>
<!--开启失效转移 -->
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
<value>true</value>
<description>开启 ResourceManager 故障自动切换</description>
</property>
<property>
<!-- 指定rm1的主机名-->
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hdp01</value>
<description>rm1 的hostname</description>
</property>
<property>
<!-- 指定rm2的主机名-->
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hdp02</value>
<description>rm2 的hostname</description>
</property>
<property>
<name>yarn.resourcemanager.ha.id</name>
<value>rm1</value>
<description>本机的rmid</description>
</property>
<property>
<!-- RM故障自动恢复 -->
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property>
<!-- 被RM用于状态存储的ZooKeeper服务器的主机:端口号,多个ZooKeeper的话使用逗号分隔。 -->
<name>yarn.resourcemanager.zk-state-store.address</name>
<value>hdp01:2181,hdp02:2181,hdp03:2181,hdp04:2181</value>
</property>
<property>
<!-- 配置RM状态信息存储方式,有MemStore和ZKStore。 -->
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<property>
<!--使用ZK集群保存状态信息,指定zookeeper队列 -->
<name>yarn.resourcemanager.zk-address</name>
<value>hdp01:2181,hdp02:2181,hdp03:2181,hdp04:2181</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>LN-rslog</value>
<description>集群ID</description>
</property>
<property>
<!-- schelduler失联等待连接时间,以毫秒为单位-->
<name>yarn.app.mapreduce.am.scheduler.connection.wait.interval-ms</name>
<value>5000</value>
</property>
<description>以下开始对 rm1 进行配置，rm2 改成对应的值！！！</description>
<property>
<!-- 客户端通过该地址向RM提交对应用程序操作 -->
<name>yarn.resourcemanager.address.rm1</name>
<value>hdp01:8032</value>
</property>
<property>
<!--ResourceManager 对ApplicationMaster暴露的访问地址。ApplicationMaster通过该地址向RM申请资源、释放资源等。 -->
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>hdp01:8030</value>
</property>
<property>
<!-- RM HTTP访问地址,查看集群信息-->
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>hdp01:8088</value>
</property>
<property>
<!-- NodeManager通过该地址交换信息 -->
<name>yarn.resourcemanager.resource-tracker.address.rm1</name>
<value>hdp01:8031</value>
</property>
<property>
<!--管理员通过该地址向RM发送管理命令 -->
<name>yarn.resourcemanager.admin.address.rm1</name>
<value>hdp01:8033</value>
</property>
<property>
<name>yarn.resourcemanager.ha.admin.address.rm1</name>
<value>hdp01:23142</value>
</property>
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>hdp02:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>hdp02:8030</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>hdp02:8088</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm2</name>
<value>hdp02:8031</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address.rm2</name>
<value>hdp02:8033</value>
</property>
<property>
<name>yarn.resourcemanager.ha.admin.address.rm2</name>
<value>hdp02:23142</value>
</property>
<property>
<!-- 为了能够运行MapReduce程序，需要让各个NodeManager在启动时加载shuffle server，shuffle server实际上是Jetty/Netty Server，Reduce Task通过该server从各个NodeManager上远程拷贝Map Task产生的中间结果。下面增加的两个配置均用于指定shuffle serve。 -->
<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>
<!--中间结果存放位置，类似于1.0中的mapred.local.dir。注意，这个参数通常会配置多个目录，已分摊磁盘IO负载 -->
<name>yarn.nodemanager.local-dirs</name>
<value>/data/hadoop/yarn/tmp</value>
</property>
<property>
<!-- yarn node 运行时日志存放地址，记录container日志，并非nodemanager日志存放地址 -->
<name>yarn.nodemanager.log-dirs</name>
<value>/data/hadoop/yarn/log</value>
</property>
<property>
<name>mapreduce.shuffle.port</name>
<value>23080</value>
</property>
<property>
<!-- 以轮训方式寻找活动的RM所使用的类-->
<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>
</property>
<property>
<!-- 每使用一个物理cpu，可以使用的虚拟cpu的比例，默认为2-->
<name>yarn.nodemanager.vcores-pcores-ratio</name>
<value>1</value>
</property>
<property>
<!-- 每单位的物理内存总量对应的虚拟内存量，默认是2.1，表示每使用1MB的物理内存，最多可以使用2.1MB的虚拟内存总量。-->
<name>yarn.nodemanager.vmem-pmem-ratio</name>
<value>5.2</value>
</property>
<!--
(2)yarn.nodemanager.vmem-pmem-ratio
任务每使用1MB物理内存，最多可使用虚拟内存量，默认是2.1
(3） yarn.nodemanager.pmem-check-enabled
是否启动一个线程检查每个任务正使用的物理
评论0