D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

[enrichment] use sparkExecutorMemory to define also the memoryOverhead

This commit is contained in:
Claudio Atzori 2024-05-01 08:32:59 +02:00
parent e96c2c1606
commit 11bd89e132
1 changed files with 15 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml
View File

@ -100,16 +100,12 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true --conf spark.sql.shuffle.partitions=8000
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg> <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -132,12 +128,11 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg> <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -160,12 +155,11 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg> <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -188,12 +182,11 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg> <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -218,12 +211,11 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg> <arg>--sourcePath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg> <arg>--outputPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
@ -247,19 +239,14 @@
<class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob</class> <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar> <jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts> <spark-opts>
--executor-cores=4 --executor-cores=${sparkExecutorCores}
--executor-memory=4G --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=5G --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=15000 --conf spark.sql.shuffle.partitions=15000
</spark-opts> </spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg> <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
@ -282,15 +269,12 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true --conf spark.sql.shuffle.partitions=8000
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts> </spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg> <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg> <arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
@ -312,15 +296,12 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true --conf spark.sql.shuffle.partitions=8000
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts> </spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg> <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg> <arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
@ -342,15 +323,12 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true --conf spark.sql.shuffle.partitions=4000
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts> </spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg> <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg> <arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
@ -363,15 +341,6 @@
<join name="wait2" to="End"/> <join name="wait2" to="End"/>
<!-- <action name="reset_workingDir">-->
<!-- <fs>-->
<!-- <delete path="${workingDir}"/>-->
<!-- <mkdir path="${workingDir}"/>-->
<!-- </fs>-->
<!-- <ok to="End"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<end name="End"/> <end name="End"/>
</workflow-app> </workflow-app>