[
https://issues.apache.org/jira/browse/SPARK-28913?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Qiang Wang updated SPARK-28913:
-------------------------------
Description:
The stack trace is below:
{quote}19/08/28 07:00:40 WARN Executor task launch worker for task 325074
BlockManager: Block rdd_10916_493 could not be removed as it was not found on
disk or in memory 19/08/28 07:00:41 ERROR Executor task launch worker for task
325074 Executor: Exception in task 3.0 in stage 347.1 (TID 325074)
java.lang.ArrayIndexOutOfBoundsException: 6741 at
org.apache.spark.dpshade.recommendation.ALS$$anonfun$org$apache$spark$ml$recommendation$ALS$$computeFactors$1.apply(ALS.scala:1460)
at
org.apache.spark.dpshade.recommendation.ALS$$anonfun$org$apache$spark$ml$recommendation$ALS$$computeFactors$1.apply(ALS.scala:1440)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$mapValues$1$$anonfun$apply$40$$anonfun$apply$41.apply(PairRDDFunctions.scala:760)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$mapValues$1$$anonfun$apply$40$$anonfun$apply$41.apply(PairRDDFunctions.scala:760)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409) at
org.apache.spark.storage.memory.MemoryStore.putIteratorAsValues(MemoryStore.scala:216)
at
org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1041)
at
org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1032)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:972) at
org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1032) at
org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:763)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:334) at
org.apache.spark.rdd.RDD.iterator(RDD.scala:285) at
org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:141)
at
org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:137)
at
scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
at scala.collection.immutable.List.foreach(List.scala:381) at
scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:137) at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at
org.apache.spark.scheduler.Task.run(Task.scala:108) at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:358) at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745){quote}
This happened after the dataset was sub-sampled.
Dataset properties: ~12B ratings
Setup: 55 r3.8xlarge ec2 instances
was:
The stack trace is below:
{quote}
java.lang.ArrayIndexOutOfBoundsException: 2716
org.apache.spark.mllib.recommendation.ALS$$anonfun$org$apache$spark$mllib$recommendation$ALS$$updateBlock$1.apply$mcVI$sp(ALS.scala:543)
scala.collection.immutable.Range.foreach$mVc$sp(Range.scala:141)
org.apache.spark.mllib.recommendation.ALS.org$apache$spark$mllib$recommendation$ALS$$updateBlock(ALS.scala:537)
org.apache.spark.mllib.recommendation.ALS$$anonfun$org$apache$spark$mllib$recommendation$ALS$$updateFeatures$2.apply(ALS.scala:505)
org.apache.spark.mllib.recommendation.ALS$$anonfun$org$apache$spark$mllib$recommendation$ALS$$updateFeatures$2.apply(ALS.scala:504)
org.apache.spark.rdd.MappedValuesRDD$$anonfun$compute$1.apply(MappedValuesRDD.scala:31)
org.apache.spark.rdd.MappedValuesRDD$$anonfun$compute$1.apply(MappedValuesRDD.scala:31)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
org.apache.spark.util.collection.ExternalAppendOnlyMap.insertAll(ExternalAppendOnlyMap.scala:138)
org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$5.apply(CoGroupedRDD.scala:159)
org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$5.apply(CoGroupedRDD.scala:158)
scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:158)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MappedValuesRDD.compute(MappedValuesRDD.scala:31)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.FlatMappedValuesRDD.compute(FlatMappedValuesRDD.scala:31)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.FlatMappedRDD.compute(FlatMappedRDD.scala:33)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
{quote}
This happened after the dataset was sub-sampled.
Dataset properties: ~12B ratings
Setup: 55 r3.8xlarge ec2 instances
> ArrayIndexOutOfBoundsException in ALS for Large datasets
> --------------------------------------------------------
>
> Key: SPARK-28913
> URL: https://issues.apache.org/jira/browse/SPARK-28913
> Project: Spark
> Issue Type: Bug
> Components: MLlib
> Affects Versions: 2.2.1
> Reporter: Qiang Wang
> Assignee: Xiangrui Meng
> Priority: Major
>
> The stack trace is below:
> {quote}19/08/28 07:00:40 WARN Executor task launch worker for task 325074
> BlockManager: Block rdd_10916_493 could not be removed as it was not found on
> disk or in memory 19/08/28 07:00:41 ERROR Executor task launch worker for
> task 325074 Executor: Exception in task 3.0 in stage 347.1 (TID 325074)
> java.lang.ArrayIndexOutOfBoundsException: 6741 at
> org.apache.spark.dpshade.recommendation.ALS$$anonfun$org$apache$spark$ml$recommendation$ALS$$computeFactors$1.apply(ALS.scala:1460)
> at
> org.apache.spark.dpshade.recommendation.ALS$$anonfun$org$apache$spark$ml$recommendation$ALS$$computeFactors$1.apply(ALS.scala:1440)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$mapValues$1$$anonfun$apply$40$$anonfun$apply$41.apply(PairRDDFunctions.scala:760)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$mapValues$1$$anonfun$apply$40$$anonfun$apply$41.apply(PairRDDFunctions.scala:760)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:409) at
> org.apache.spark.storage.memory.MemoryStore.putIteratorAsValues(MemoryStore.scala:216)
> at
> org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1041)
> at
> org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1032)
> at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:972) at
> org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1032)
> at
> org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:763)
> at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:334) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:285) at
> org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:141)
> at
> org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:137)
> at
> scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
> at scala.collection.immutable.List.foreach(List.scala:381) at
> scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
> at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:137) at
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at
> org.apache.spark.scheduler.Task.run(Task.scala:108) at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:358) at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745){quote}
> This happened after the dataset was sub-sampled.
> Dataset properties: ~12B ratings
> Setup: 55 r3.8xlarge ec2 instances
--
This message was sent by Atlassian Jira
(v8.3.2#803003)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
