forked from D-Net/dnet-hadoop
47 lines
2.1 KiB
XML
47 lines
2.1 KiB
XML
<workflow-app name="index_infospace_graph" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<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>
|
|
|
|
<start to="GraphJoinEntities"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="GraphJoinEntities">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
<master>yarn-cluster</master>
|
|
<mode>cluster</mode>
|
|
<name>GraphIndexing</name>
|
|
<class>eu.dnetlib.dhp.graph.SparkGraphIndexingJob</class>
|
|
<jar>dhp-graph-provision-${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" --conf spark.yarn.executor.memoryOverhead=${sparkExecutorMemoryOverhead}</spark-opts>
|
|
<arg>-mt</arg> <arg>yarn-cluster</arg>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--hive_db_name</arg><arg>${hive_db_name}</arg>
|
|
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<end name="End"/>
|
|
</workflow-app> |