dnet-hadoop/dhp-workflows/dhp-graph-provision-scholex.../src/main/resources/eu/dnetlib/dhp/sx/export/oozie_app/workflow.xml

49 lines
1.7 KiB
XML

<workflow-app name="Export Scholexplorer Graph to OpenAIRE" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>workingDirPath</name>
<description>the source path</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>memory for individual executor</description>
</property>
</parameters>
<start to="ExtractOAF"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ExtractOAF">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ExtractOAF</name>
<class>eu.dnetlib.dhp.export.SparkExportContentForOpenAire</class>
<jar>dhp-graph-provision-scholexplorer-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
${sparkExtraOPT}
</spark-opts>
<arg>--workingDirPath</arg><arg>${workingDirPath}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>