Dream Spark ------spark on yarn ，yarn的配置

Posted 2020-08-26 拼命@三郎

<?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.resourcemanager.hostname</name>
<value>sdb-ali-hangzhou-dp1</value>
</property>
<property>
   <name>yarn.resourcemanager.webapp.address</name>
   <value>sdb-ali-hangzhou-dp1:21188</value>
 </property>
<property>
<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>
<!-- 这个配置是将生成的日志文件上传到hdfs，但是本地的会删除，也就是说在yarn的监控界面会看不到，所以并没有采用-->
<!--<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<name>yarn.nodemanager.remote-app-log-dir</name>
<value>/user/yarnlogs</value>
</property>
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>-1</value>
</property>
<property>
<name>yarn.log-aggregation.retain-check-interval-seconds</name>
<value>-1</value>
</property>-->
<!-- 72小时候yarn的日志会清除掉-->
<property>
<name>yarn.nodemanager.log.retain-seconds</name>
<value>604800</value>
</property>
<!--<property>
<name>yarn.application.classpath</name>
<value>/data/kefu3/application/easemobbigdata_jar/libs/*,$HADOOP_CONF_DIR,$HADOOP_COMMON_HOME/share/hadoop/common/*,$HADOOP_COMMON_HOME/share/hadoop/common/lib/*,$HADOOP_HDFS_HOME/share/hadoop/hdfs/*,$HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*,$HADOOP_YARN_HOME/share/hadoop/yarn/*,$HADOOP_YARN_HOME/share/hadoop/yarn/lib/*</value>
</property>-->
<!-- 以下是yarn的HA的配置，暂时没有使用-->
<!-- Site specific YARN configuration properties -->
<!--<property>
  <name>yarn.resourcemanager.ha.enabled</name>
  <value>true</value>
 </property>
 <property>
  <name>yarn.resourcemanager.ha.rm-ids</name>
  <value>nn1,nn2</value>
 </property>
 <property>
  <name>yarn.resourcemanager.hostname.nn1</name>
  <value>sdb-ali-hangzhou-dp1</value>
 </property>
 <property>
  <name>yarn.resourcemanager.hostname.nn2</name>
  <value>sdb-ali-hangzhou-dp2</value>
 </property>
 <property>
  <name>yarn.resourcemanager.recovery.enabled</name>
  <value>true</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>sdb-ali-hangzhou-dp1:2181,sdb-ali-hangzhou-dp2:2181</value>
  <description>For multiple zk services, separate them with comma</description>
 </property>
 <property>
  <name>yarn.resourcemanager.cluster-id</name>
  <value>yarn-ha</value>
 </property>
 <property>
  <name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
  <value>true</value>
  <description>Enable automatic failover; By default, it is enabled only when HA is enabled.</description>
 </property>
 <property>
    <name>yarn.resourcemanager.ha.automatic-failover.zk-base-path</name>
    <value>/yarn-leader-election</value>
  <description>Optional setting. The default value is /yarn-leader-election</description>
 </property>
 <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>
 <property>
  <name>yarn.resourcemanager.address.nn1</name>
  <value>sdb-ali-hangzhou-dp1:21132</value>
 </property>
 <property>
  <name>yarn.resourcemanager.address.nn2</name>
  <value>sdb-ali-hangzhou-dp2:21132</value>
 </property>
 <property>
  <name>yarn.resourcemanager.scheduler.address.nn1</name>
  <value>sdb-ali-hangzhou-dp1:21130</value>
 </property>
 <property>
  <name>yarn.resourcemanager.scheduler.address.nn2</name>
  <value>sdb-ali-hangzhou-dp2:21130</value>
 </property>
 <property>
  <name>yarn.resourcemanager.resource-tracker.address.nn1</name>
  <value>sdb-ali-hangzhou-dp1:21131</value>
 </property>
 <property>
  <name>yarn.resourcemanager.resource-tracker.address.nn2</name>
  <value>sdb-ali-hangzhou-dp2:21131</value>
 </property>
 <property>
  <name>yarn.resourcemanager.webapp.address.nn1</name>
  <value>sdb-ali-hangzhou-dp1:21188</value>
 </property>
 <property>
  <name>yarn.resourcemanager.webapp.address.nn2</name>
  <value>sdb-ali-hangzhou-dp2:21188</value>
 </property>
 <property>
 <name>yarn.nodemanager.resource.memory-mb</name>
 <value>10240</value>
 </property>
 <property>
 <name>yarn.scheduler.minimum-allocation-mb</name>
 <value>2048</value>
 </property>
 <property>
 <name>yarn.scheduler.maximum-allocation-mb</name>
 <value>10240</value>
 </property>
 <property>
 <name>yarn.app.mapreduce.am.resource.mb</name>
 <value>4096</value>
 </property>
 <property>
 <name>yarn.app.mapreduce.am.command-opts</name>
 <value>-Xmx1024m</value>
 </property>-->
</configuration>