dnet-hadoop/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorgani.../oozie_app/workflow.xml

97 lines
4.1 KiB
XML

<workflow-app name="community_to_result_propagation" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>baseURL</name>
<description>the baseURL from where to reach the community APIs</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="reset_outputpath">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="prepare_result_communitylist"/>
<error to="Kill"/>
</action>
<action name="prepare_result_communitylist">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Prepare-Community-Result-Organization</name>
<class>eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--outputPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
<ok to="exec-propagation"/>
<error to="Kill"/>
</action>
<action name="exec-propagation">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>community2resultfromorganization-Publication</name>
<class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/communityorganization/resulttocommunityfromorganization/</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>