dnet-hadoop/dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/scan/oozie_app/workflow.xml

92 lines
3.2 KiB
XML

<workflow-app name="Create Similarity Relations" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>graphBasePath</name>
<description>the raw graph base path</description>
</property>
<property>
<name>rawSet</name>
<description>the output directory in the targetPath</description>
</property>
<property>
<name>isLookUpUrl</name>
<description>the address of the lookUp service</description>
</property>
<property>
<name>actionSetId</name>
<description>id of the actionSet</description>
</property>
<property>
<name>workingPath</name>
<description>path for the working directory</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>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
</configuration>
</global>
<start to="DeleteWorkingPath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DeleteWorkingPath">
<fs>
<delete path='${workingPath}/${actionSetId}/*_simrel'/>
</fs>
<ok to="DuplicateScan"/>
<error to="Kill"/>
</action>
<action name="DuplicateScan">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Create Similarity Relations</name>
<class>eu.dnetlib.dhp.dedup.SparkCreateSimRels</class>
<jar>dhp-dedup-${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</arg>
<arg>--i</arg><arg>${graphBasePath}</arg>
<arg>--o</arg><arg>${rawSet}</arg>
<arg>--la</arg><arg>${isLookUpUrl}</arg>
<arg>--asi</arg><arg>${actionSetId}</arg>
<arg>--w</arg><arg>${workingPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>