[
https://issues.apache.org/jira/browse/SPARK-45972?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17787111#comment-17787111
]
Yang Jie commented on SPARK-45972:
----------------------------------
cc [~dongjoon] I haven't found the root cause yet. Do you have any ideas?
Thanks ~
> `ParquetFileFormatV1Suite/ParquetFileFormatV2Suite` often fails in the daily
> tests of Java 21
> ---------------------------------------------------------------------------------------------
>
> Key: SPARK-45972
> URL: https://issues.apache.org/jira/browse/SPARK-45972
> Project: Spark
> Issue Type: Improvement
> Components: SQL, Tests
> Affects Versions: 4.0.0
> Reporter: Yang Jie
> Priority: Major
>
> There are two test cases, ParquetFileFormatV1Suite and
> ParquetFileFormatV2Suite, that often fail in the daily tests of Java 21. The
> reason for the failure is 'There are ${n} possibly leaked file streams..'.
> [https://github.com/apache/spark/actions/runs/6899686304/job/18771676570]
> [https://github.com/apache/spark/actions/runs/6886143740/job/18731379673]
> [https://github.com/apache/spark/actions/runs/6872747886/job/18691717269]
> [https://github.com/apache/spark/actions/runs/6859020738/job/18650698085]
> https://github.com/apache/spark/actions/runs/6845491908/job/18610786715
>
> {code:java}
> ===== POSSIBLE THREAD LEAK IN SUITE
> o.a.s.sql.execution.datasources.parquet.ParquetFileFormatV1Suite, threads:
> readingParquetFooters-ForkJoinPool-7045-worker-3 (daemon=true),
> readingParquetFooters-ForkJoinPool-7045-worker-4 (daemon=true),
> shuffle-boss-2239-1 (daemon=true), rpc-boss-2236-1 (daemon=true) =====
> 30295
> 30296
> 30297[info]
> org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV1Suite
> *** ABORTED *** (11 seconds, 836 milliseconds)
> 30298[info] The code passed to eventually never returned normally.
> Attempted 15 times over 10.009598219999999 seconds. Last failure message:
> There are 2 possibly leaked file streams.. (SharedSparkSession.scala:164)
> 30299[info] org.scalatest.exceptions.TestFailedDueToTimeoutException:
> 30300[info] at
> org.scalatest.enablers.Retrying$$anon$4.tryTryAgain$2(Retrying.scala:219)
> 30301[info] at
> org.scalatest.enablers.Retrying$$anon$4.retry(Retrying.scala:226)
> 30302[info] at
> org.scalatest.concurrent.Eventually.eventually(Eventually.scala:313)
> 30303[info] at
> org.scalatest.concurrent.Eventually.eventually$(Eventually.scala:312)
> 30304[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatSuite.eventually(ParquetFileFormatSuite.scala:31)
> 30305[info] at
> org.apache.spark.sql.test.SharedSparkSessionBase.afterEach(SharedSparkSession.scala:164)
> 30306[info] at
> org.apache.spark.sql.test.SharedSparkSessionBase.afterEach$(SharedSparkSession.scala:158)
> 30307[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatSuite.afterEach(ParquetFileFormatSuite.scala:31)
> 30308[info] at
> org.scalatest.BeforeAndAfterEach.$anonfun$runTest$1(BeforeAndAfterEach.scala:247)
> 30309[info] at
> org.scalatest.Status.$anonfun$withAfterEffect$1(Status.scala:377)
> 30310[info] at
> org.scalatest.Status.$anonfun$withAfterEffect$1$adapted(Status.scala:373)
> 30311[info] at
> org.scalatest.SucceededStatus$.whenCompleted(Status.scala:462)
> 30312[info] at org.scalatest.Status.withAfterEffect(Status.scala:373)
> 30313[info] at org.scalatest.Status.withAfterEffect$(Status.scala:371)
> 30314[info] at
> org.scalatest.SucceededStatus$.withAfterEffect(Status.scala:434)
> 30315[info] at
> org.scalatest.BeforeAndAfterEach.runTest(BeforeAndAfterEach.scala:246)
> 30316[info] at
> org.scalatest.BeforeAndAfterEach.runTest$(BeforeAndAfterEach.scala:227)
> 30317[info] at
> org.apache.spark.SparkFunSuite.runTest(SparkFunSuite.scala:69)
> 30318[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.$anonfun$runTests$1(AnyFunSuiteLike.scala:269)
> 30319[info] at
> org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:413)
> 30320[info] at scala.collection.immutable.List.foreach(List.scala:333)
> 30321[info] at
> org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
> 30322[info] at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:396)
> 30323[info] at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:475)
> 30324[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.runTests(AnyFunSuiteLike.scala:269)
> 30325[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.runTests$(AnyFunSuiteLike.scala:268)
> 30326[info] at
> org.scalatest.funsuite.AnyFunSuite.runTests(AnyFunSuite.scala:1564)
> 30327[info] at org.scalatest.Suite.run(Suite.scala:1114)
> 30328[info] at org.scalatest.Suite.run$(Suite.scala:1096)
> 30329[info] at
> org.scalatest.funsuite.AnyFunSuite.org$scalatest$funsuite$AnyFunSuiteLike$$super$run(AnyFunSuite.scala:1564)
> 30330[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.$anonfun$run$1(AnyFunSuiteLike.scala:273)
> 30331[info] at org.scalatest.SuperEngine.runImpl(Engine.scala:535)
> 30332[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.run(AnyFunSuiteLike.scala:273)
> 30333[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.run$(AnyFunSuiteLike.scala:272)
> 30334[info] at
> org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:69)
> 30335[info] at
> org.scalatest.BeforeAndAfterAll.liftedTree1$1(BeforeAndAfterAll.scala:213)
> 30336[info] at
> org.scalatest.BeforeAndAfterAll.run(BeforeAndAfterAll.scala:210)
> 30337[info] at
> org.scalatest.BeforeAndAfterAll.run$(BeforeAndAfterAll.scala:208)
> 30338[info] at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:69)
> 30339[info] at
> org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:321)
> 30340[info] at
> org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:517)
> 30341[info] at sbt.ForkMain$Run.lambda$runTest$1(ForkMain.java:414)
> 30342[info] at
> java.base/java.util.concurrent.FutureTask.run(FutureTask.java:317)
> 30343[info] at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1144)
> 30344[info] at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
> 30345[info] at java.base/java.lang.Thread.run(Thread.java:1583)
> 30346[info] Cause: java.lang.IllegalStateException: There are 2 possibly
> leaked file streams.
> 30347[info] at
> org.apache.spark.DebugFilesystem$.assertNoOpenStreams(DebugFilesystem.scala:54)
> 30348[info] at
> org.apache.spark.sql.test.SharedSparkSessionBase.$anonfun$afterEach$1(SharedSparkSession.scala:165)
> 30349[info] at
> scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.scala:18)
> 30350[info] at
> org.scalatest.enablers.Retrying$$anon$4.makeAValiantAttempt$1(Retrying.scala:184)
> 30351[info] at
> org.scalatest.enablers.Retrying$$anon$4.tryTryAgain$2(Retrying.scala:196)
> 30352[info] at
> org.scalatest.enablers.Retrying$$anon$4.retry(Retrying.scala:226)
> 30353[info] at
> org.scalatest.concurrent.Eventually.eventually(Eventually.scala:313)
> 30354[info] at
> org.scalatest.concurrent.Eventually.eventually$(Eventually.scala:312)
> 30355[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatSuite.eventually(ParquetFileFormatSuite.scala:31)
> 30356[info] at
> org.apache.spark.sql.test.SharedSparkSessionBase.afterEach(SharedSparkSession.scala:164)
> 30357[info] at
> org.apache.spark.sql.test.SharedSparkSessionBase.afterEach$(SharedSparkSession.scala:158)
> 30358[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatSuite.afterEach(ParquetFileFormatSuite.scala:31)
> 30359[info] at
> org.scalatest.BeforeAndAfterEach.$anonfun$runTest$1(BeforeAndAfterEach.scala:247)
> 30360[info] at
> org.scalatest.Status.$anonfun$withAfterEffect$1(Status.scala:377)
> 30361[info] at
> org.scalatest.Status.$anonfun$withAfterEffect$1$adapted(Status.scala:373)
> 30362[info] at
> org.scalatest.SucceededStatus$.whenCompleted(Status.scala:462)
> 30363[info] at org.scalatest.Status.withAfterEffect(Status.scala:373)
> 30364[info] at org.scalatest.Status.withAfterEffect$(Status.scala:371)
> 30365[info] at
> org.scalatest.SucceededStatus$.withAfterEffect(Status.scala:434)
> 30366[info] at
> org.scalatest.BeforeAndAfterEach.runTest(BeforeAndAfterEach.scala:246)
> 30367[info] at
> org.scalatest.BeforeAndAfterEach.runTest$(BeforeAndAfterEach.scala:227)
> 30368[info] at
> org.apache.spark.SparkFunSuite.runTest(SparkFunSuite.scala:69)
> 30369[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.$anonfun$runTests$1(AnyFunSuiteLike.scala:269)
> 30370[info] at
> org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:413)
> 30371[info] at scala.collection.immutable.List.foreach(List.scala:333)
> 30372[info] at
> org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
> 30373[info] at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:396)
> 30374[info] at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:475)
> 30375[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.runTests(AnyFunSuiteLike.scala:269)
> 30376[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.runTests$(AnyFunSuiteLike.scala:268)
> 30377[info] at
> org.scalatest.funsuite.AnyFunSuite.runTests(AnyFunSuite.scala:1564)
> 30378[info] at org.scalatest.Suite.run(Suite.scala:1114)
> 30379[info] at org.scalatest.Suite.run$(Suite.scala:1096)
> 30380[info] at
> org.scalatest.funsuite.AnyFunSuite.org$scalatest$funsuite$AnyFunSuiteLike$$super$run(AnyFunSuite.scala:1564)
> 30381[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.$anonfun$run$1(AnyFunSuiteLike.scala:273)
> 30382[info] at org.scalatest.SuperEngine.runImpl(Engine.scala:535)
> 30383[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.run(AnyFunSuiteLike.scala:273)
> 30384[info] at
> org.scalatest.funsuite.AnyFunSuiteLike.run$(AnyFunSuiteLike.scala:272)
> 30385[info] at
> org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:69)
> 30386[info] at
> org.scalatest.BeforeAndAfterAll.liftedTree1$1(BeforeAndAfterAll.scala:213)
> 30387[info] at
> org.scalatest.BeforeAndAfterAll.run(BeforeAndAfterAll.scala:210)
> 30388[info] at
> org.scalatest.BeforeAndAfterAll.run$(BeforeAndAfterAll.scala:208)
> 30389[info] at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:69)
> 30390[info] at
> org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:321)
> 30391[info] at
> org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:517)
> 30392[info] at sbt.ForkMain$Run.lambda$runTest$1(ForkMain.java:414)
> 30393[info] at
> java.base/java.util.concurrent.FutureTask.run(FutureTask.java:317)
> 30394[info] at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1144)
> 30395[info] at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
> 30396[info] at java.base/java.lang.Thread.run(Thread.java:1583)
> 30397[info] Cause: java.lang.Throwable:
> 30398[info] at
> org.apache.spark.DebugFilesystem$.addOpenStream(DebugFilesystem.scala:35)
> 30399[info] at
> org.apache.spark.DebugFilesystem.open(DebugFilesystem.scala:75)
> 30400[info] at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:997)
> 30401[info] at
> org.apache.parquet.hadoop.util.HadoopInputFile.newStream(HadoopInputFile.java:69)
> 30402[info] at
> org.apache.parquet.hadoop.ParquetFileReader.<init>(ParquetFileReader.java:796)
> 30403[info] at
> org.apache.parquet.hadoop.ParquetFileReader.open(ParquetFileReader.java:666)
> 30404[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFooterReader.readFooter(ParquetFooterReader.java:85)
> 30405[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFooterReader.readFooter(ParquetFooterReader.java:76)
> 30406[info] at
> org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$.$anonfun$readParquetFootersInParallel$1(ParquetFileFormat.scala:450)
> 30407[info] at
> org.apache.spark.util.ThreadUtils$.$anonfun$parmap$2(ThreadUtils.scala:384)
> 30408[info] at scala.concurrent.Future$.$anonfun$apply$1(Future.scala:687)
> 30409[info] at
> scala.concurrent.impl.Promise$Transformation.run(Promise.scala:467)
> 30410[info] at
> java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1423)
> 30411[info] at
> java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:387)
> 30412[info] at
> java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1312)
> 30413[info] at
> java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1843)
> 30414[info] at
> java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1808)
> 30415[info] at
> java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:188)
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
