michele.artini
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

added spark.sql.shuffle.partitions=3840 to dedup scan wf

This commit is contained in:
Claudio Atzori 2020-04-16 14:41:28 +02:00
parent 3437383112
commit ec5dfc068d
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml
View File

@ -92,6 +92,7 @@
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts> </spark-opts>
<arg>-mt</arg><arg>yarn</arg> <arg>-mt</arg><arg>yarn</arg>
<arg>--i</arg><arg>${graphBasePath}</arg> <arg>--i</arg><arg>${graphBasePath}</arg>
@ -118,6 +119,7 @@
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts> </spark-opts>
<arg>-mt</arg><arg>yarn</arg> <arg>-mt</arg><arg>yarn</arg>
<arg>--i</arg><arg>${graphBasePath}</arg> <arg>--i</arg><arg>${graphBasePath}</arg>