sparkDriverMemory
memory for driver process
sparkExecutorMemory
memory for individual executor
sparkExecutorCores
number of cores used by single executor
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
${jobTracker}
${nameNode}
eu.dnetlib.doiboost.crossref.ExtractCrossrefRecords
--hdfsServerUri${nameNode}
--workingPath/data/doiboost/crossref/
--crossrefFileNameTarGzcrossref.tar.gz
yarn-cluster
cluster
SparkCreateCrossredDataset
eu.dnetlib.doiboost.crossref.GenerateCrossrefDatasetSpark
dhp-doiboost-${projectVersion}.jar
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=20
--executor-memory=6G
--driver-memory=7G
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--masteryarn-cluster
--sourcePath/data/doiboost/crossref/filess
--targetPath/tmp/miriam/crossref/crossrefDataset