[ 
https://issues.apache.org/jira/browse/SPARK-27406?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Dongjoon Hyun updated SPARK-27406:
----------------------------------
    Affects Version/s: 2.4.0

> UnsafeArrayData serialization breaks when two machines have different Oops 
> size
> -------------------------------------------------------------------------------
>
>                 Key: SPARK-27406
>                 URL: https://issues.apache.org/jira/browse/SPARK-27406
>             Project: Spark
>          Issue Type: Bug
>          Components: SQL
>    Affects Versions: 2.4.0, 2.4.1
>            Reporter: peng bo
>            Assignee: peng bo
>            Priority: Major
>              Labels: correctness
>             Fix For: 2.4.2, 3.0.0
>
>
> ApproxCountDistinctForIntervals holds the UnsafeArrayData data to initialize 
> endpoints. When the UnsafeArrayData is serialized with Java serialization, 
> the BYTE_ARRAY_OFFSET in memory can change if two machines have different 
> pointer width (Oops in JVM).
> It's similar to SPARK-10914.
> {code:java}
> java.lang.NullPointerException
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals$$anonfun$endpoints$1.apply(ApproxCountDistinctForIntervals.scala:69)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals$$anonfun$endpoints$1.apply(ApproxCountDistinctForIntervals.scala:69)
>       at 
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
>       at 
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
>       at 
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
>       at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
>       at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
>       at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.endpoints$lzycompute(ApproxCountDistinctForIntervals.scala:69)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.endpoints(ApproxCountDistinctForIntervals.scala:66)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.org$apache$spark$sql$catalyst$expressions$aggregate$ApproxCountDistinctForIntervals$$hllppArray$lzycompute(ApproxCountDistinctForIntervals.scala:94)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.org$apache$spark$sql$catalyst$expressions$aggregate$ApproxCountDistinctForIntervals$$hllppArray(ApproxCountDistinctForIntervals.scala:93)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.org$apache$spark$sql$catalyst$expressions$aggregate$ApproxCountDistinctForIntervals$$numWordsPerHllpp$lzycompute(ApproxCountDistinctForIntervals.scala:104)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.org$apache$spark$sql$catalyst$expressions$aggregate$ApproxCountDistinctForIntervals$$numWordsPerHllpp(ApproxCountDistinctForIntervals.scala:104)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.totalNumWords$lzycompute(ApproxCountDistinctForIntervals.scala:106)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.totalNumWords(ApproxCountDistinctForIntervals.scala:106)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.createAggregationBuffer(ApproxCountDistinctForIntervals.scala:110)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.ApproxCountDistinctForIntervals.createAggregationBuffer(ApproxCountDistinctForIntervals.scala:44)
>       at 
> org.apache.spark.sql.catalyst.expressions.aggregate.TypedImperativeAggregate.initialize(interfaces.scala:528)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator$$anonfun$initAggregationBuffer$2.apply(ObjectAggregationIterator.scala:120)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator$$anonfun$initAggregationBuffer$2.apply(ObjectAggregationIterator.scala:120)
>       at 
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
>       at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.initAggregationBuffer(ObjectAggregationIterator.scala:120)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.org$apache$spark$sql$execution$aggregate$ObjectAggregationIterator$$createNewAggregationBuffer(ObjectAggregationIterator.scala:112)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.getAggregationBufferByKey(ObjectAggregationIterator.scala:128)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.processInputs(ObjectAggregationIterator.scala:150)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.<init>(ObjectAggregationIterator.scala:78)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:114)
>       at 
> org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:105)
>       at 
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$12.apply(RDD.scala:823)
>       at 
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$12.apply(RDD.scala:823)
>       at 
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
>       at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
>       at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
>       at 
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
>       at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
>       at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
>       at 
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
>       at 
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:55)
>       at org.apache.spark.scheduler.Task.run(Task.scala:121)
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org

Reply via email to