only stats

This commit is contained in:
Michele Artini 2021-02-11 10:57:23 +01:00
parent 8c836bf930
commit 83d815d0bc
2 changed files with 132 additions and 0 deletions

View File

@ -0,0 +1,18 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
</configuration>

View File

@ -0,0 +1,114 @@
<workflow-app name="create broker events" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>outputDir</name>
<description>the path where the the generated data will be stored</description>
</property>
<property>
<name>brokerApiBaseUrl</name>
<description>the url of the broker service api</description>
</property>
<property>
<name>brokerDbUrl</name>
<description>the url of the broker database</description>
</property>
<property>
<name>brokerDbUser</name>
<description>the user of the broker database</description>
</property>
<property>
<name>brokerDbPassword</name>
<description>the password of the broker database</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
</property>
<property>
<name>oozieActionShareLibForSpark2</name>
<description>oozie action sharelib for spark 2.*</description>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
<description>spark 2.* extra listeners classname</description>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
<description>spark 2.* sql query execution listeners classname</description>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<description>spark 2.* yarn history server address</description>
</property>
<property>
<name>spark2EventLogDir</name>
<description>spark 2.* event log dir location</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="stats"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="stats">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>GenerateStatsJob</name>
<class>eu.dnetlib.dhp.broker.oa.GenerateStatsJob</class>
<jar>dhp-broker-events-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--outputDir</arg><arg>${outputDir}</arg>
<arg>--dbUrl</arg><arg>${brokerDbUrl}</arg>
<arg>--dbUser</arg><arg>${brokerDbUser}</arg>
<arg>--dbPassword</arg><arg>${brokerDbPassword}</arg>
<arg>--brokerApiBaseUrl</arg><arg>${brokerApiBaseUrl}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>