Error while training the model when using com.github.jelmerk.spark.HnswLibKryoRegistrator

Question

Error while training the model when using com.github.jelmerk.spark.HnswLibKryoRegistrator

jfernandrezj opened this issue 4 months ago · comments

Stack trace:

Serialization trace:
classes (sun.misc.Launcher$AppClassLoader)
classLoader (scala.reflect.runtime.JavaMirrors$JavaMirror)
$outer (scala.reflect.runtime.JavaMirrors$JavaMirror$$anon$2)
currentOwner (scala.reflect.internal.Trees$TreeTypeSubstituter)
EmptyTreeTypeSubstituter (scala.reflect.runtime.JavaUniverse)
$outer (scala.reflect.api.TypeTags$TypeTagImpl)
evidence$5 (com.github.jelmerk.spark.knn.hnsw.HnswSimilarityModelImpl)
com.esotericsoftware.kryo.KryoException: java.util.ConcurrentModificationException
Serialization trace:
classes (sun.misc.Launcher$AppClassLoader)
classLoader (scala.reflect.runtime.JavaMirrors$JavaMirror)
$outer (scala.reflect.runtime.JavaMirrors$JavaMirror$$anon$2)
currentOwner (scala.reflect.internal.Trees$TreeTypeSubstituter)
EmptyTreeTypeSubstituter (scala.reflect.runtime.JavaUniverse)
$outer (scala.reflect.api.TypeTags$TypeTagImpl)
evidence$5 (com.github.jelmerk.spark.knn.hnsw.HnswSimilarityModelImpl)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:101)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	at com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:508)
	at com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:651)
	at org.apache.spark.serializer.KryoSerializationStream.writeObject(KryoSerializer.scala:269)
	at org.apache.spark.broadcast.TorrentBroadcast$.$anonfun$blockifyObject$4(TorrentBroadcast.scala:321)
	at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1462)
	at org.apache.spark.broadcast.TorrentBroadcast$.blockifyObject(TorrentBroadcast.scala:323)
	at org.apache.spark.broadcast.TorrentBroadcast.writeBlocks(TorrentBroadcast.scala:140)
	at org.apache.spark.broadcast.TorrentBroadcast.<init>(TorrentBroadcast.scala:95)
	at org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:34)
	at org.apache.spark.broadcast.BroadcastManager.newBroadcast(BroadcastManager.scala:74)
	at org.apache.spark.SparkContext.broadcast(SparkContext.scala:1515)
	at org.myproject.sub.serialization.Feature.$anonfun$setValue$1(Feature.scala:131)
	at scala.Option.map(Option.scala:230)
	at org.myproject.sub.serialization.Feature.setValue(Feature.scala:131)
	at org.myproject.sub.HasObjectParams.set(HasObjectParams.scala:40)
	at org.myproject.sub.HasObjectParams.set$(HasObjectParams.scala:39)
	at org.myproject.sub.CustomHNSWTransformer.set(CustomHNSWTransformer.scala:20)
	at org.myproject.sub.CustomHNSWTransformer.setSearchGraph(CustomHNSWTransformer.scala:38)
	at org.myproject.sub.CustomHNSWEstimator.train(CustomHNSWEstimator.scala:63)
	at org.myproject.sub.HierarchicalResolverTestSpec.$anonfun$new$1(HierarchicalResolverTestSpec.scala:41)
	at org.scalatest.OutcomeOf.outcomeOf(OutcomeOf.scala:85)
	at org.scalatest.OutcomeOf.outcomeOf$(OutcomeOf.scala:83)
	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.FlatSpecLike$$anon$1.apply(FlatSpecLike.scala:1682)
	at org.scalatest.TestSuite.withFixture(TestSuite.scala:196)
	at org.scalatest.TestSuite.withFixture$(TestSuite.scala:195)
	at org.scalatest.FlatSpec.withFixture(FlatSpec.scala:1685)
	at org.scalatest.FlatSpecLike.invokeWithFixture$1(FlatSpecLike.scala:1680)
	at org.scalatest.FlatSpecLike.$anonfun$runTest$1(FlatSpecLike.scala:1692)
	at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289)
	at org.scalatest.FlatSpecLike.runTest(FlatSpecLike.scala:1692)
	at org.scalatest.FlatSpecLike.runTest$(FlatSpecLike.scala:1674)
	at org.scalatest.FlatSpec.runTest(FlatSpec.scala:1685)
	at org.scalatest.FlatSpecLike.$anonfun$runTests$1(FlatSpecLike.scala:1750)
	at org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:396)
	at scala.collection.immutable.List.foreach(List.scala:431)
	at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
	at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:373)
	at org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:410)
	at scala.collection.immutable.List.foreach(List.scala:431)
	at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
	at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:379)
	at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461)
	at org.scalatest.FlatSpecLike.runTests(FlatSpecLike.scala:1750)
	at org.scalatest.FlatSpecLike.runTests$(FlatSpecLike.scala:1749)
	at org.scalatest.FlatSpec.runTests(FlatSpec.scala:1685)
	at org.scalatest.Suite.run(Suite.scala:1147)
	at org.scalatest.Suite.run$(Suite.scala:1129)
	at org.scalatest.FlatSpec.org$scalatest$FlatSpecLike$$super$run(FlatSpec.scala:1685)
	at org.scalatest.FlatSpecLike.$anonfun$run$1(FlatSpecLike.scala:1795)
	at org.scalatest.SuperEngine.runImpl(Engine.scala:521)
	at org.scalatest.FlatSpecLike.run(FlatSpecLike.scala:1795)
	at org.scalatest.FlatSpecLike.run$(FlatSpecLike.scala:1793)
	at org.scalatest.FlatSpec.run(FlatSpec.scala:1685)
	at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45)
	at org.scalatest.tools.Runner$.$anonfun$doRunRunRunDaDoRunRun$13(Runner.scala:1340)
	at org.scalatest.tools.Runner$.$anonfun$doRunRunRunDaDoRunRun$13$adapted(Runner.scala:1334)
	at scala.collection.immutable.List.foreach(List.scala:431)
	at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1334)
	at org.scalatest.tools.Runner$.$anonfun$runOptionallyWithPassFailReporter$24(Runner.scala:1031)
	at org.scalatest.tools.Runner$.$anonfun$runOptionallyWithPassFailReporter$24$adapted(Runner.scala:1010)
	at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1500)
	at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010)
	at org.scalatest.tools.Runner$.run(Runner.scala:850)
	at org.scalatest.tools.Runner.run(Runner.scala)
	at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2or3(ScalaTestRunner.java:43)
	at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:26)
Caused by: java.util.ConcurrentModificationException
	at java.util.Vector$Itr.checkForComodification(Vector.java:1212)
	at java.util.Vector$Itr.next(Vector.java:1165)
	at com.esotericsoftware.kryo.serializers.CollectionSerializer.write(CollectionSerializer.java:99)
	at com.esotericsoftware.kryo.serializers.CollectionSerializer.write(CollectionSerializer.java:40)
	at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:575)
	at com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:79)
	... 87 more

Jelmer Kuperus · Answer 1 · Tue Mar 12 2024 00:18:47 GMT+0800 (China Standard Time)

Looks like you are running this from scalatest, can you show me what your test looks like ?

Jelmer Kuperus · Answer 2 · Fri Mar 22 2024 18:08:28 GMT+0800 (China Standard Time)

Closing because of inactivity

Andres Fernandez · Answer 3 · Fri Apr 05 2024 19:21:32 GMT+0800 (China Standard Time)

Hello @jelmerk, just came back from holidays; you are right, I am running it in a test, I will share the test details later today. Would you kindly reopen this issue please.