[
https://issues.apache.org/jira/browse/SPARK-15154?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15273885#comment-15273885
]
Pete Robbins commented on SPARK-15154:
--------------------------------------
[~davies] as you are the author of this code can you comment on my findings?
So the issue here is that the keyGenerator returns an UnsafeRow containing Int
values but the code below from LongHashedRelation.apply retrieves the key from
this as a Long. The bytes in the row are
on Little Endian: 01 00 00 00 00 00 00 00
on Big Endian: 00 00 00 01 00 00 00 00
By chance getInt and getLong will both return "1" on Little Endian whereas on
Big Endian getInt returns "1" but get Long will return "268435456"
val keyGenerator = UnsafeProjection.create(key)
// Create a mapping of key -> rows
var numFields = 0
while (input.hasNext) {
val unsafeRow = input.next().asInstanceOf[UnsafeRow]
numFields = unsafeRow.numFields()
val rowKey = keyGenerator(unsafeRow)
if (!rowKey.isNullAt(0)) {
val key = rowKey.getLong(0) // <<<---- Values in rowKey are Int not Long
map.append(key, unsafeRow)
}
}
> LongHashedRelation fails on Big Endian platform
> -----------------------------------------------
>
> Key: SPARK-15154
> URL: https://issues.apache.org/jira/browse/SPARK-15154
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.0.0
> Reporter: Pete Robbins
> Labels: big-endian
>
> NPE in
> org.apache.spark.sql.execution.joins.HashedRelationSuite.LongToUnsafeRowMap
> Error Message
> java.lang.NullPointerException was thrown.
> Stacktrace
> java.lang.NullPointerException
> at
> org.apache.spark.sql.execution.joins.HashedRelationSuite$$anonfun$3$$anonfun$apply$mcV$sp$1.apply$mcVI$sp(HashedRelationSuite.scala:121)
> at scala.collection.immutable.Range.foreach$mVc$sp(Range.scala:160)
> at
> org.apache.spark.sql.execution.joins.HashedRelationSuite$$anonfun$3.apply$mcV$sp(HashedRelationSuite.scala:119)
> at
> org.apache.spark.sql.execution.joins.HashedRelationSuite$$anonfun$3.apply(HashedRelationSuite.scala:112)
> at
> org.apache.spark.sql.execution.joins.HashedRelationSuite$$anonfun$3.apply(HashedRelationSuite.scala:112)
> at
> org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
> at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
> at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
> at org.scalatest.Transformer.apply(Transformer.scala:22)
> at org.scalatest.Transformer.apply(Transformer.scala:20)
> at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
> at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:57)
> at
> org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
> at
> org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
> at
> org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
> at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
> at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
> at org.scalatest.FunSuite.runTest(FunSuite.scala:1555)
> at
> org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
> at
> org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
> at
> org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413)
> at
> org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
> at
> org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396)
> at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483)
> at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:208)
> at org.scalatest.FunSuite.runTests(FunSuite.scala:1555)
> at org.scalatest.Suite$class.run(Suite.scala:1424)
> at
> org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1555)
> at
> org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
> at
> org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
> at org.scalatest.SuperEngine.runImpl(Engine.scala:545)
> at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212)
> at
> org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:29)
> at
> org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
> at
> org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
> at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:29)
> at org.scalatest.Suite$class.callExecuteOnSuite$1(Suite.scala:1492)
> at
> org.scalatest.Suite$$anonfun$runNestedSuites$1.apply(Suite.scala:1528)
> at
> org.scalatest.Suite$$anonfun$runNestedSuites$1.apply(Suite.scala:1526)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at org.scalatest.Suite$class.runNestedSuites(Suite.scala:1526)
> at
> org.scalatest.tools.DiscoverySuite.runNestedSuites(DiscoverySuite.scala:29)
> at org.scalatest.Suite$class.run(Suite.scala:1421)
> at org.scalatest.tools.DiscoverySuite.run(DiscoverySuite.scala:29)
> at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:55)
> at
> org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$3.apply(Runner.scala:2563)
> at
> org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$3.apply(Runner.scala:2557)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:2557)
> at
> org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1044)
> at
> org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1043)
> at
> org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:2722)
> at
> org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1043)
> at org.scalatest.tools.Runner$.main(Runner.scala:860)
> at org.scalatest.tools.Runner.main(Runner.scala)
> Most likely this will be caused by endianness of the bye arrays etc.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
