forked from D-Net/dnet-hadoop
61 lines
2.3 KiB
XML
61 lines
2.3 KiB
XML
|
<workflow-app name="result_to_community_from_semrel_propagation" xmlns="uri:oozie:workflow:0.5">
|
||
|
<parameters>
|
||
|
<property>
|
||
|
<name>sourcePath</name>
|
||
|
<description>the source path</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>allowedsemrels</name>
|
||
|
<description>the semantic relationships allowed for propagation</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>isLookupUrl</name>
|
||
|
<description>the isLookup service endpoint</description>
|
||
|
</property>
|
||
|
</parameters>
|
||
|
|
||
|
<start to="ResultToCommunityFromSemRelPropagation"/>
|
||
|
|
||
|
<kill name="Kill">
|
||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||
|
</kill>
|
||
|
|
||
|
<action name="ResultToCommunityFromSemRelPropagation">
|
||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||
|
<job-tracker>${jobTracker}</job-tracker>
|
||
|
<name-node>${nameNode}</name-node>
|
||
|
<master>yarn-cluster</master>
|
||
|
<mode>cluster</mode>
|
||
|
<name>ResultToCommunitySemRelPropagation</name>
|
||
|
<class>eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob</class>
|
||
|
<jar>dhp-propagation-${projectVersion}.jar</jar>
|
||
|
<spark-opts>--executor-memory ${sparkExecutorMemory}
|
||
|
--executor-cores ${sparkExecutorCores}
|
||
|
--driver-memory=${sparkDriverMemory}
|
||
|
--conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
|
||
|
--conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
|
||
|
</spark-opts>
|
||
|
<arg>-mt</arg> <arg>yarn-cluster</arg>
|
||
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
||
|
<!-- <arg>-allowedsemrels</arg><arg>${allowedsemrels}</arg>-->
|
||
|
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
|
||
|
<!-- <arg>-isLookupUrl</arg><arg>${isLookupUrl}</arg>-->
|
||
|
</spark>
|
||
|
<ok to="End"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
<end name="End"/>
|
||
|
</workflow-app>
|