|
|
|
@ -1,11 +1,56 @@
|
|
|
|
|
<workflow-app name="Gen Enriched Orcid Works" xmlns="uri:oozie:workflow:0.5">
|
|
|
|
|
<workflow-app name="gen_orcid_no_doi_dataset" xmlns="uri:oozie:workflow:0.5">
|
|
|
|
|
<parameters>
|
|
|
|
|
<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>oozieActionShareLibForSpark2</name>
|
|
|
|
|
<description>oozie action sharelib for spark 2.*</description>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<name>spark2ExtraListeners</name>
|
|
|
|
|
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
|
|
|
|
<description>spark 2.* extra listeners classname</description>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<name>spark2SqlQueryExecutionListeners</name>
|
|
|
|
|
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
|
|
|
|
<description>spark 2.* sql query execution listeners classname</description>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<name>spark2YarnHistoryServerAddress</name>
|
|
|
|
|
<description>spark 2.* yarn history server address</description>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<name>spark2EventLogDir</name>
|
|
|
|
|
<description>spark 2.* event log dir location</description>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<name>workingPath</name>
|
|
|
|
|
<description>the working dir base path</description>
|
|
|
|
|
</property>
|
|
|
|
|
</parameters>
|
|
|
|
|
|
|
|
|
|
<global>
|
|
|
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
|
|
|
<name-node>${nameNode}</name-node>
|
|
|
|
|
<configuration>
|
|
|
|
|
<property>
|
|
|
|
|
<name>oozie.action.sharelib.for.spark</name>
|
|
|
|
|
<value>${oozieActionShareLibForSpark2}</value>
|
|
|
|
|
</property>
|
|
|
|
|
</configuration>
|
|
|
|
|
</global>
|
|
|
|
|
|
|
|
|
|
<start to="ResetWorkingPath"/>
|
|
|
|
|
|
|
|
|
|
<kill name="Kill">
|
|
|
|
@ -16,20 +61,25 @@
|
|
|
|
|
<fs>
|
|
|
|
|
<delete path='${workingPath}/no_doi_enriched_works/output'/>
|
|
|
|
|
</fs>
|
|
|
|
|
<ok to="Gen_Enriched_Orcid_Works"/>
|
|
|
|
|
<ok to="GenOrcidNoDoiDataset"/>
|
|
|
|
|
<error to="Kill"/>
|
|
|
|
|
</action>
|
|
|
|
|
|
|
|
|
|
<action name="Gen_Enriched_Orcid_Works">
|
|
|
|
|
<action name="GenOrcidNoDoiDataset">
|
|
|
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
|
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
|
|
|
<name-node>${nameNode}</name-node>
|
|
|
|
|
<master>yarn</master>
|
|
|
|
|
<master>yarn-cluster</master>
|
|
|
|
|
<mode>cluster</mode>
|
|
|
|
|
<name>Gen_Enriched_Orcid_Works</name>
|
|
|
|
|
<name>GenOrcidNoDoiDataset</name>
|
|
|
|
|
<class>eu.dnetlib.doiboost.orcidnodoi.SparkGenEnrichedOrcidWorks</class>
|
|
|
|
|
<jar>dhp-doiboost-1.2.4-SNAPSHOT.jar</jar>
|
|
|
|
|
<spark-opts>--num-executors 10 --conf spark.yarn.jars="hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2" --executor-memory=${sparkExecutorMemory} --executor-cores=${sparkExecutorCores} --driver-memory=${sparkDriverMemory}
|
|
|
|
|
<jar>dhp-doiboost-${projectVersion}.jar</jar>
|
|
|
|
|
<spark-opts>
|
|
|
|
|
--executor-memory=${sparkExecutorMemory}
|
|
|
|
|
--executor-cores=${sparkExecutorCores}
|
|
|
|
|
--driver-memory=${sparkDriverMemory}
|
|
|
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
|
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
|
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
|
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
|
|
|
</spark-opts>
|
|
|
|
|
<arg>-w</arg><arg>${workingPath}/</arg>
|
|
|
|
|
<arg>-n</arg><arg>${nameNode}</arg>
|
|
|
|
|