entitiesPath
the input entity path
workingPath
path for the working directory
numPartitions
number of partitions for the spark files
dedupConfPath
path for the dedup configuration file
sparkDriverMemory
memory for driver process
sparkExecutorMemory
memory for individual executor
sparkExecutorCores
number of cores used by single executor
oozieActionShareLibForSpark2
oozie action sharelib for spark 2.*
spark2ExtraListeners
com.cloudera.spark.lineage.NavigatorAppListener
spark 2.* extra listeners classname
spark2SqlQueryExecutionListeners
com.cloudera.spark.lineage.NavigatorQueryListener
spark 2.* sql query execution listeners classname
spark2YarnHistoryServerAddress
spark 2.* yarn history server address
spark2EventLogDir
spark 2.* event log dir location
${jobTracker}
${nameNode}
mapreduce.job.queuename
${queueName}
oozie.launcher.mapred.job.queue.name
${oozieLauncherQueueName}
oozie.action.sharelib.for.spark
${oozieActionShareLibForSpark2}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
yarn
cluster
Create Similarity Relations
eu.dnetlib.jobs.SparkCreateSimRels
dnet-dedup-test-${projectVersion}.jar
--num-executors=32
--executor-memory=12G
--executor-cores=4
--driver-memory=4G
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.dynamicAllocation.enabled=false
--entitiesPath${entitiesPath}
--workingPath${workingPath}
--numPartitions${numPartitions}
--dedupConfPath${dedupConfPath}
--useTree${useTree}
yarn
cluster
Create Merge Relations
eu.dnetlib.jobs.SparkCreateMergeRels
dnet-dedup-test-${projectVersion}.jar
--num-executors=32
--executor-memory=12G
--executor-cores=4
--driver-memory=4G
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.dynamicAllocation.enabled=true
--entitiesPath${entitiesPath}
--workingPath${workingPath}
--numPartitions${numPartitions}
--dedupConfPath${dedupConfPath}
yarn
cluster
Compute Statistics
eu.dnetlib.jobs.SparkComputeStatistics
dnet-dedup-test-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--entitiesPath${entitiesPath}
--workingPath${workingPath}
--numPartitions${numPartitions}