forked from D-Net/dnet-hadoop
50 lines
1.8 KiB
XML
50 lines
1.8 KiB
XML
<workflow-app name="import_infospace_graph" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>sourcePath</name>
|
|
<description>the source path</description>
|
|
</property>
|
|
<property>
|
|
<name>targetPath</name>
|
|
<description>the target 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>number of cores used by single executor</description>
|
|
</property>
|
|
</parameters>
|
|
|
|
<start to="MapGraphIntoDataFrame"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="MapGraphIntoDataFrame">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
<master>yarn-cluster</master>
|
|
<mode>cluster</mode>
|
|
<name>MapGraphIntoDataFrame</name>
|
|
<class>eu.dnetlib.dhp.graph.SparkGraphImporterJob</class>
|
|
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
|
<spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory=${sparkDriverMemory}</spark-opts>
|
|
<arg>-mt</arg> <arg>yarn-cluster</arg>
|
|
<arg>--input</arg><arg>${sourcePath}</arg>
|
|
<arg>--outputDir</arg><arg>${targetPath}</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<end name="End"/>
|
|
</workflow-app> |