55 lines
2.2 KiB
XML
55 lines
2.2 KiB
XML
<workflow-app name="Analyze_BASE_Records" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>baseInputPath</name>
|
|
<description>the path of the BASE dump</description>
|
|
</property>
|
|
<property>
|
|
<name>baseDataPath</name>
|
|
<description>the path where to store BASE records</description>
|
|
</property>
|
|
<property>
|
|
<name>baseReportsPath</name>
|
|
<description>path where to store the reports</description>
|
|
</property>
|
|
<property>
|
|
<name>baseReimportFlag</name>
|
|
<description>flag to re-import the records from dump</description>
|
|
</property>
|
|
</parameters>
|
|
|
|
<start to="analyzeBaseRecords"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="analyzeBaseRecords">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>AnalyzeBaseRecords</name>
|
|
<class>eu.dnetlib.dhp.collection.plugin.base.BaseAnalyzerJob</class>
|
|
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--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.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--inputPath</arg><arg>${baseInputPath}</arg>
|
|
<arg>--dataPath</arg><arg>${baseDataPath}</arg>
|
|
<arg>--outputPath</arg><arg>${baseReportsPath}</arg>
|
|
<arg>--reimport</arg><arg>${baseReimportFlag}</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<end name="End"/>
|
|
</workflow-app>
|