forked from D-Net/dnet-hadoop
46 lines
1.8 KiB
XML
46 lines
1.8 KiB
XML
|
<workflow-app name="Datacite_to_ActionSet_Workflow" xmlns="uri:oozie:workflow:0.5">
|
||
|
<parameters>
|
||
|
<property>
|
||
|
<name>sourcePath</name>
|
||
|
<description>the working path of Datacite stores</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>outputPath</name>
|
||
|
<description>the path of Datacite ActionSet</description>
|
||
|
</property>
|
||
|
</parameters>
|
||
|
|
||
|
<start to="ExportDataset"/>
|
||
|
|
||
|
<kill name="Kill">
|
||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||
|
</kill>
|
||
|
|
||
|
|
||
|
<action name="ExportDataset">
|
||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||
|
<master>yarn-cluster</master>
|
||
|
<mode>cluster</mode>
|
||
|
<name>ExportDataset</name>
|
||
|
<class>eu.dnetlib.dhp.actionmanager.datacite.ExportActionSetJobNode</class>
|
||
|
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||
|
<spark-opts>
|
||
|
--executor-memory=${sparkExecutorMemory}
|
||
|
--executor-cores=${sparkExecutorCores}
|
||
|
--driver-memory=${sparkDriverMemory}
|
||
|
--conf spark.sql.shuffle.partitions=3840
|
||
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||
|
</spark-opts>
|
||
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
||
|
<arg>--targetPath</arg><arg>${outputPath}</arg>
|
||
|
<arg>--master</arg><arg>yarn-cluster</arg>
|
||
|
</spark>
|
||
|
<ok to="End"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
<end name="End"/>
|
||
|
</workflow-app>
|