spark on yarn 集群部署

概述

hadoop2.7.1

spark 1.5.1

192.168.31.62 resourcemanager, namenode, master

192.168.31.63 nodemanager, datanode, worker

192.168.31.64 nodemanager, datanode, worker

Hadoop配置

hadoop-env.sh mapred-env.sh yarn-env.sh至少配置JAVA_HOME

core-site.xml

<property>
<name>fs.defaultFS</name>
<value>hdfs://192.168.31.62:9000</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/opt/local/hadoop/tmp</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>hadoop.native.lib</name>
<value>true</value>
</property>

hdfs-site.xml

<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/opt/local/hadoop/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/opt/local/hadoop/dfs/data</value>
</property>
<property>
<name>dfs.permissions.enabled</name>
<value>false</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>192.168.31.62:50090</value>
</property>

mapred-site.xml

<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>

yarn-site.xml

<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>
<!--
<property>
<name>yarn.resourcemanager.hostname</name>
<value>192.168.31.62</value>
</property>
-->
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>192.168.31.62:8031</value>
</property>
<property>
<name>yarn.resourcemanager.address</name>
<value>192.168.31.62:8032</value>
</property>

<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>192.168.31.62:8030</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>

slaves

slave1
slave2

Spark配置

spark-env.sh

export JAVA_HOME=/opt/local/java/jdk
export SCALA_HOME=/opt/local/scala
export SPARK_WORKER_MEMORY=1g
export SPARK_MASTER_IP=192.168.31.62
export SPARK_DRIVER_MEORY=1G
export SPARK_LOCAL_DIRS=/opt/local/spark
export HADOOP_CONF_DIR=/opt/local/hadoop/etc/hadoop
export HADOOP_HOME=/opt/local/hadoop

slaves

slave1
slave2

http://hadoop.apache.org/docs/r2.7.1/hadoop-project-dist/hadoop-common/ClusterSetup.html