forked from D-Net/dnet-hadoop
126 lines
5.3 KiB
XML
126 lines
5.3 KiB
XML
|
<workflow-app name="promote_action_payload_for_relation_table" xmlns="uri:oozie:workflow:0.5">
|
||
|
<parameters>
|
||
|
<property>
|
||
|
<name>activePromoteRelationActionPayload</name>
|
||
|
<description>TODO</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>inputGraphPath</name>
|
||
|
<description>TODO</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>inputActionPayloadRootPath</name>
|
||
|
<description>TODO</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>outputGraphPath</name>
|
||
|
<description>TODO</description>
|
||
|
</property>
|
||
|
<property>
|
||
|
<name>mergeAndGetStrategy</name>
|
||
|
<description>TODO</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>oozie.action.sharelib.for.spark</name>
|
||
|
<value>${oozieActionShareLibForSpark2}</value>
|
||
|
</property>
|
||
|
</configuration>
|
||
|
</global>
|
||
|
|
||
|
<start to="DecisionPromoteRelationActionPayload"/>
|
||
|
|
||
|
<kill name="Kill">
|
||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||
|
</kill>
|
||
|
|
||
|
<decision name="DecisionPromoteRelationActionPayload">
|
||
|
<switch>
|
||
|
<case to="PromoteRelationActionPayloadForRelationTable">
|
||
|
${(activePromoteRelationActionPayload eq "true") and
|
||
|
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputGraphPath')),'/'),'relation')) eq "true") and
|
||
|
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputActionPayloadRootPath')),'/'),'clazz=eu.dnetlib.dhp.schema.oaf.Relation')) eq "true")}
|
||
|
</case>
|
||
|
<default to="SkipPromoteRelationActionPayloadForRelationTable"/>
|
||
|
</switch>
|
||
|
</decision>
|
||
|
|
||
|
<action name="PromoteRelationActionPayloadForRelationTable">
|
||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||
|
<master>yarn-cluster</master>
|
||
|
<mode>cluster</mode>
|
||
|
<name>PromoteRelationActionPayloadForRelationTable</name>
|
||
|
<class>eu.dnetlib.dhp.actionmanager.promote.PromoteActionPayloadForGraphTableJob</class>
|
||
|
<jar>dhp-actionmanager-${projectVersion}.jar</jar>
|
||
|
<spark-opts>
|
||
|
--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=2560
|
||
|
</spark-opts>
|
||
|
<arg>--inputGraphTablePath</arg><arg>${inputGraphPath}/relation</arg>
|
||
|
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
||
|
<arg>--inputActionPayloadPath</arg><arg>${inputActionPayloadRootPath}/clazz=eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
||
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
||
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphPath}/relation</arg>
|
||
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||
|
</spark>
|
||
|
<ok to="End"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
<action name="SkipPromoteRelationActionPayloadForRelationTable">
|
||
|
<distcp xmlns="uri:oozie:distcp-action:0.2">
|
||
|
<arg>-pb</arg>
|
||
|
<arg>${inputGraphPath}/relation</arg>
|
||
|
<arg>${outputGraphPath}/relation</arg>
|
||
|
</distcp>
|
||
|
<ok to="End"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
<end name="End"/>
|
||
|
</workflow-app>
|