forked from D-Net/dnet-hadoop
145 lines
5.2 KiB
XML
145 lines
5.2 KiB
XML
|
<workflow-app name="sub_dump_community_products" xmlns="uri:oozie:workflow:0.5">
|
||
|
|
||
|
<parameters>
|
||
|
<property>
|
||
|
<name>sourcePath</name>
|
||
|
<description>the source path</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>outputPath</name>
|
||
|
<description>the output path</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>hiveDbName</name>
|
||
|
<description>the target hive database name</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>hiveJdbcUrl</name>
|
||
|
<description>hive server jdbc url</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>hiveMetastoreUris</name>
|
||
|
<description>hive server metastore URIs</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>sparkDriverMemory</name>
|
||
|
<description>memory for driver process</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>sparkExecutorMemory</name>
|
||
|
<description>memory for individual executor</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>sparkExecutorCores</name>
|
||
|
<description>number of cores used by single executor</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>oozieActionShareLibForSpark2</name>
|
||
|
<description>oozie action sharelib for spark 2.*</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>spark2ExtraListeners</name>
|
||
|
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
||
|
<description>spark 2.* extra listeners classname</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>spark2SqlQueryExecutionListeners</name>
|
||
|
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
||
|
<description>spark 2.* sql query execution listeners classname</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>spark2YarnHistoryServerAddress</name>
|
||
|
<description>spark 2.* yarn history server address</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>spark2EventLogDir</name>
|
||
|
<description>spark 2.* event log dir location</description>
|
||
|
</property>
|
||
|
</parameters>
|
||
|
|
||
|
<global>
|
||
|
<job-tracker>${jobTracker}</job-tracker>
|
||
|
<name-node>${nameNode}</name-node>
|
||
|
<configuration>
|
||
|
<property>
|
||
|
<name>mapreduce.job.queuename</name>
|
||
|
<value>${queueName}</value>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>oozie.launcher.mapred.job.queue.name</name>
|
||
|
<value>${oozieLauncherQueueName}</value>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>oozie.action.sharelib.for.spark</name>
|
||
|
<value>${oozieActionShareLibForSpark2}</value>
|
||
|
</property>
|
||
|
|
||
|
</configuration>
|
||
|
</global>
|
||
|
|
||
|
<start to="common_action_community_funder"/>
|
||
|
|
||
|
<kill name="Kill">
|
||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||
|
</kill>
|
||
|
|
||
|
<action name="common_action_community_funder">
|
||
|
<sub-workflow>
|
||
|
<app-path>${wf:appPath()}/dump_common
|
||
|
</app-path>
|
||
|
<propagate-configuration/>
|
||
|
<configuration>
|
||
|
<property>
|
||
|
<name>sourcePath</name>
|
||
|
<value>${sourcePath}</value>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>selectedResults</name>
|
||
|
<value>${sourcePath}</value>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>communityMapPath</name>
|
||
|
<value>${workingDir}/communityMap</value>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>outputPath</name>
|
||
|
<value>${workingDir}</value>
|
||
|
</property>
|
||
|
</configuration>
|
||
|
</sub-workflow>
|
||
|
<ok to="splitForCommunities" />
|
||
|
<error to="Kill" />
|
||
|
</action>
|
||
|
|
||
|
|
||
|
|
||
|
<action name="splitForCommunities">
|
||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||
|
<master>yarn</master>
|
||
|
<mode>cluster</mode>
|
||
|
<name>Split dumped result for community</name>
|
||
|
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkSplitForCommunity</class>
|
||
|
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||
|
<spark-opts>
|
||
|
--executor-memory=${sparkExecutorMemory}
|
||
|
--executor-cores=${sparkExecutorCores}
|
||
|
--driver-memory=${sparkDriverMemory}
|
||
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||
|
</spark-opts>
|
||
|
<arg>--sourcePath</arg><arg>${workingDir}/ext</arg>
|
||
|
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||
|
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||
|
</spark>
|
||
|
<ok to="End"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
|
||
|
|
||
|
<end name="End"/>
|
||
|
|
||
|
</workflow-app>
|