workingPath
the Working Path
sparkDriverMemory
memory for driver process
sparkExecutorMemory
memory for individual executor
sparkExecutorCores
number of cores used by single executor
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
yarn-cluster
cluster
Create Baselnie DataSet
eu.dnetlib.dhp.sx.ebi.SparkCreateBaselineDataFrame
dhp-graph-mapper-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=1
--driver-memory=${sparkDriverMemory}
--executor-cores=${sparkExecutorCores}
${sparkExtraOPT}
--workingPath${workingPath}
--masteryarn
--hdfsServerUri${nameNode}
yarn-cluster
cluster
Create EBI DataSet
eu.dnetlib.dhp.sx.ebi.SparkEBILinksToOaf
dhp-graph-mapper-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=1000
${sparkExtraOPT}
--workingPath${workingPath}
--masteryarn
yarn-cluster
cluster
Create Baseline DataSet
eu.dnetlib.dhp.sx.ebi.SparkAddLinkUpdates
dhp-graph-mapper-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=1
--driver-memory=${sparkDriverMemory}
--executor-cores=${sparkExecutorCores}
${sparkExtraOPT}
--workingPath${workingPath}
--masteryarn