[SPARK-3349] Incorrect partitioning after LIMIT operator

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 1.2.0
• Component/s: SQL
• Assignee: Eric Liang
• Reporter: Eric Liang
• Created: 02/Sep/14 18:21
• Updated: 09/Sep/14 02:29
• Resolved: 08/Sep/14 23:15

Description

Reproduced by the following example:

import org.apache.spark.sql.catalyst.plans.Inner
import org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute
import org.apache.spark.sql.catalyst.expressions._

val series = sql("select distinct year from sales order by year asc limit 10")
val results = sql("select * from sales")
series.registerTempTable("series")
results.registerTempTable("results")

sql("select * from results inner join series where results.year = series.year").count

-----------

java.lang.IllegalArgumentException: Can't zip RDDs with unequal numbers of partitions
	at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:56)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
	at org.apache.spark.ShuffleDependency.<init>(Dependency.scala:79)
	at org.apache.spark.rdd.ShuffledRDD.getDependencies(ShuffledRDD.scala:80)
	at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:191)
	at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:189)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.dependencies(RDD.scala:189)
	at org.apache.spark.scheduler.DAGScheduler.visit$1(DAGScheduler.scala:298)
	at org.apache.spark.scheduler.DAGScheduler.getParentStages(DAGScheduler.scala:310)
	at org.apache.spark.scheduler.DAGScheduler.newStage(DAGScheduler.scala:246)
	at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:723)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1333)
	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
	at akka.actor.ActorCell.invoke(ActorCell.scala:456)
	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
	at akka.dispatch.Mailbox.run(Mailbox.scala:219)
	at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
	at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
	at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
	at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
	at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)

Issue Links

• links to: [Github] Pull Request #2262 (ericl)