graphInputPath
the path where the graph is stored
outputDir
the path where the the generated data will be stored
datasourceIdWhitelist
-
a white list (comma separeted, - for empty list) of datasource ids
datasourceTypeWhitelist
-
a white list (comma separeted, - for empty list) of datasource types
datasourceIdBlacklist
-
a black list (comma separeted, - for empty list) of datasource ids
topicWhitelist
*
a white list (comma separeted, * for all) of topics
esEventIndexName
the elasticsearch index name for events
esNotificationsIndexName
the elasticsearch index name for notifications
esIndexHost
the elasticsearch host
esBatchWriteRetryCount
8
an ES configuration property
esBatchWriteRetryWait
60s
an ES configuration property
esBatchSizeEntries
200
an ES configuration property
esNodesWanOnly
true
an ES configuration property
maxIndexedEventsForDsAndTopic
the max number of events for each couple (ds/topic)
brokerApiBaseUrl
the url of the broker service api
brokerDbUrl
the url of the broker database
brokerDbUser
the user of the broker database
brokerDbPassword
the password of the broker database
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
PrepareSimpleEntititiesJob
eu.dnetlib.dhp.broker.oa.PrepareSimpleEntititiesJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
PrepareRelatedDatasourcesJob
eu.dnetlib.dhp.broker.oa.PrepareRelatedDatasourcesJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
PrepareRelatedDatasetsJob
eu.dnetlib.dhp.broker.oa.PrepareRelatedDatasetsJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
PrepareRelatedProjectsJob
eu.dnetlib.dhp.broker.oa.PrepareRelatedProjectsJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
PrepareRelatedPublicationsJob
eu.dnetlib.dhp.broker.oa.PrepareRelatedPublicationsJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
PrepareRelatedSoftwaresJob
eu.dnetlib.dhp.broker.oa.PrepareRelatedSoftwaresJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
JoinStep0
eu.dnetlib.dhp.broker.oa.JoinStep0Job
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
JoinStep1
eu.dnetlib.dhp.broker.oa.JoinStep1Job
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
JoinStep2
eu.dnetlib.dhp.broker.oa.JoinStep2Job
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
JoinStep3
eu.dnetlib.dhp.broker.oa.JoinStep3Job
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
JoinStep4
eu.dnetlib.dhp.broker.oa.JoinStep4Job
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
PrepareGroupsJob
eu.dnetlib.dhp.broker.oa.PrepareGroupsJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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
--graphPath${graphInputPath}
--workingDir${workingDir}
yarn
cluster
GenerateEventsJob
eu.dnetlib.dhp.broker.oa.GenerateEventsJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--workingDir${workingDir}
--outputDir${outputDir}
--datasourceIdWhitelist${datasourceIdWhitelist}
--datasourceTypeWhitelist${datasourceTypeWhitelist}
--datasourceIdBlacklist${datasourceIdBlacklist}
--topicWhitelist${topicWhitelist}
yarn
cluster
IndexEventSubsetOnESJob
eu.dnetlib.dhp.broker.oa.IndexEventSubsetJob
dhp-broker-events-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.dynamicAllocation.maxExecutors="8"
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--outputDir${outputDir}
--index${esEventIndexName}
--esHost${esIndexHost}
--esBatchWriteRetryCount${esBatchWriteRetryCount}
--esBatchWriteRetryWait${esBatchWriteRetryWait}
--esBatchSizeEntries${esBatchSizeEntries}
--esNodesWanOnly${esNodesWanOnly}
--maxEventsForTopic${maxIndexedEventsForDsAndTopic}
--brokerApiBaseUrl${brokerApiBaseUrl}
yarn
cluster
IndexNotificationsOnESJob
eu.dnetlib.dhp.broker.oa.IndexNotificationsJob
dhp-broker-events-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.dynamicAllocation.maxExecutors="8"
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--outputDir${outputDir}
--index${esNotificationsIndexName}
--esHost${esIndexHost}
--esBatchWriteRetryCount${esBatchWriteRetryCount}
--esBatchWriteRetryWait${esBatchWriteRetryWait}
--esBatchSizeEntries${esBatchSizeEntries}
--esNodesWanOnly${esNodesWanOnly}
--brokerApiBaseUrl${brokerApiBaseUrl}
yarn
cluster
GenerateStatsJob
eu.dnetlib.dhp.broker.oa.GenerateStatsJob
dhp-broker-events-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--outputDir${outputDir}
--dbUrl${brokerDbUrl}
--dbUser${brokerDbUser}
--dbPassword${brokerDbPassword}
--brokerApiBaseUrl${brokerApiBaseUrl}