forked from D-Net/dnet-hadoop
90 lines
3.3 KiB
XML
90 lines
3.3 KiB
XML
<workflow-app name="import_infospace_graph" xmlns="uri:oozie:workflow:0.5">
|
|
|
|
<parameters>
|
|
<property>
|
|
<name>sourcePath</name>
|
|
<description>the source path</description>
|
|
</property>
|
|
<property>
|
|
<name>hive_db_name</name>
|
|
<description>the target hive database name</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>
|
|
</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>
|
|
</configuration>
|
|
</global>
|
|
|
|
<start to="MapGraphAsHiveDB"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="MapGraphAsHiveDB">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>MapGraphAsHiveDB</name>
|
|
<class>eu.dnetlib.dhp.oa.graph.SparkGraphImporterJob</class>
|
|
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory ${sparkExecutorMemory}
|
|
--executor-cores ${sparkExecutorCores}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
|
|
--conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
|
|
--conf spark.sql.warehouse.dir="/user/hive/warehouse"
|
|
</spark-opts>
|
|
<arg>-mt</arg> <arg>yarn</arg>
|
|
<arg>-s</arg><arg>${sourcePath}</arg>
|
|
<arg>-db</arg><arg>${hive_db_name}</arg>
|
|
<arg>-h</arg><arg>${hive_metastore_uris}</arg>
|
|
</spark>
|
|
<ok to="PostProcessing"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="PostProcessing">
|
|
<hive2 xmlns="uri:oozie:hive2-action:0.1">
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
<configuration>
|
|
<property>
|
|
<name>hive.metastore.uris</name>
|
|
<value>${hive_metastore_uris}</value>
|
|
</property>
|
|
</configuration>
|
|
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
|
|
<script>lib/scripts/postprocessing.sql</script>
|
|
<param>hive_db_name=${hive_db_name}</param>
|
|
</hive2>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<end name="End"/>
|
|
</workflow-app> |