[
https://issues.apache.org/jira/browse/HADOOP-14204?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15932911#comment-15932911
]
Steve Loughran commented on HADOOP-14204:
-----------------------------------------
Stack. This is my github cloud examples running with Spark master built against
hadoop-2.8.0 RC3
{code}
org.apache.spark.SparkException: Job aborted.
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:196)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:161)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:161)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:161)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:137)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:442)
at
org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:478)
at
org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:93)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:606)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:509)
at
com.hortonworks.spark.cloud.examples.S3DataFrameExample.action(S3DataFrameExample.scala:160)
at
com.hortonworks.spark.cloud.ObjectStoreExample$class.action(ObjectStoreExample.scala:67)
at
com.hortonworks.spark.cloud.examples.S3DataFrameExample.action(S3DataFrameExample.scala:56)
at
com.hortonworks.spark.cloud.examples.S3DataFrameExampleSuite$$anonfun$2.apply$mcV$sp(S3DataFrameExampleSuite.scala:47)
at
com.hortonworks.spark.cloud.CloudSuite$$anonfun$ctest$1.apply$mcV$sp(CloudSuite.scala:133)
at
com.hortonworks.spark.cloud.CloudSuite$$anonfun$ctest$1.apply(CloudSuite.scala:131)
at
com.hortonworks.spark.cloud.CloudSuite$$anonfun$ctest$1.apply(CloudSuite.scala:131)
at
org.scalatest.Transformer$$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$$anon$1.apply(FunSuiteLike.scala:166)
at org.scalatest.Suite$class.withFixture(Suite.scala:1122)
at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555)
at
org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
at
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(CloudSuite.scala:40)
at
org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:255)
at
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfter$$super$runTest(CloudSuite.scala:40)
at org.scalatest.BeforeAndAfter$class.runTest(BeforeAndAfter.scala:200)
at com.hortonworks.spark.cloud.CloudSuite.runTest(CloudSuite.scala:40)
at
org.scalatest.FunSuiteLike$$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$$anonfun$run$1.apply(FunSuiteLike.scala:212)
at org.scalatest.SuperEngine.runImpl(Engine.scala:545)
at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212)
at
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfterAll$$super$run(CloudSuite.scala:40)
at
org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
at
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfter$$super$run(CloudSuite.scala:40)
at org.scalatest.BeforeAndAfter$class.run(BeforeAndAfter.scala:241)
at com.hortonworks.spark.cloud.CloudSuite.run(CloudSuite.scala:40)
at org.scalatest.Suite$class.callExecuteOnSuite$1(Suite.scala:1492)
at org.scalatest.Suite$$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$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1043)
at
org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:2722)
at
org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1043)
at org.scalatest.tools.Runner$.main(Runner.scala:860)
at org.scalatest.tools.Runner.main(Runner.scala)
Cause: org.apache.spark.SparkException: Job aborted due to stage failure:
Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage
1.0 (TID 1, localhost, executor driver): org.apache.spark.SparkException: Task
failed while writing rows
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:253)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$12.apply(FileFormatWriter.scala:178)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$12.apply(FileFormatWriter.scala:177)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:317)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.UnsupportedOperationException
at java.util.Collections$UnmodifiableList.sort(Collections.java:1331)
at java.util.Collections.sort(Collections.java:175)
at
com.amazonaws.services.s3.model.transform.RequestXmlFactory.convertToXmlByteArray(RequestXmlFactory.java:42)
at
com.amazonaws.services.s3.AmazonS3Client.completeMultipartUpload(AmazonS3Client.java:2692)
at
org.apache.hadoop.fs.s3a.S3AFileSystem$WriteOperationHelper.completeMultipartUpload(S3AFileSystem.java:2298)
at
org.apache.hadoop.fs.s3a.S3ABlockOutputStream$MultiPartUpload.complete(S3ABlockOutputStream.java:561)
at
org.apache.hadoop.fs.s3a.S3ABlockOutputStream$MultiPartUpload.access$200(S3ABlockOutputStream.java:454)
at
org.apache.hadoop.fs.s3a.S3ABlockOutputStream.close(S3ABlockOutputStream.java:352)
at
org.apache.hadoop.fs.FSDataOutputStream$PositionCache.close(FSDataOutputStream.java:72)
at
org.apache.hadoop.fs.FSDataOutputStream.close(FSDataOutputStream.java:106)
at
org.apache.parquet.hadoop.ParquetFileWriter.end(ParquetFileWriter.java:639)
at
org.apache.parquet.hadoop.InternalParquetRecordWriter.close(InternalParquetRecordWriter.java:117)
at
org.apache.parquet.hadoop.ParquetRecordWriter.close(ParquetRecordWriter.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.close(ParquetOutputWriter.scala:42)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.releaseResources(FileFormatWriter.scala:317)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:311)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:239)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:237)
at
org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1360)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:242)
... 8 more
Suppressed: java.lang.NullPointerException
at
org.apache.parquet.hadoop.InternalParquetRecordWriter.flushRowGroupToStore(InternalParquetRecordWriter.java:160)
at
org.apache.parquet.hadoop.InternalParquetRecordWriter.close(InternalParquetRecordWriter.java:109)
at
org.apache.parquet.hadoop.ParquetRecordWriter.close(ParquetRecordWriter.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.close(ParquetOutputWriter.scala:42)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.releaseResources(FileFormatWriter.scala:317)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$1.apply$mcV$sp(FileFormatWriter.scala:245)
at
org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1369)
... 9 more
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1495)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1483)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1482)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1482)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:810)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:810)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:810)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1710)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1665)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1654)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:635)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2019)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2040)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2072)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:176)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:161)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:161)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:161)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:137)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:442)
at
org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:478)
at
org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:93)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:606)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:509)
at
com.hortonworks.spark.cloud.examples.S3DataFrameExample.action(S3DataFrameExample.scala:160)
at
com.hortonworks.spark.cloud.ObjectStoreExample$class.action(ObjectStoreExample.scala:67)
at
com.hortonworks.spark.cloud.examples.S3DataFrameExample.action(S3DataFrameExample.scala:56)
at
com.hortonworks.spark.cloud.examples.S3DataFrameExampleSuite$$anonfun$2.apply$mcV$sp(S3DataFrameExampleSuite.scala:47)
at
com.hortonworks.spark.cloud.CloudSuite$$anonfun$ctest$1.apply$mcV$sp(CloudSuite.scala:133)
at
com.hortonworks.spark.cloud.CloudSuite$$anonfun$ctest$1.apply(CloudSuite.scala:131)
at
com.hortonworks.spark.cloud.CloudSuite$$anonfun$ctest$1.apply(CloudSuite.scala:131)
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$1.apply(FunSuiteLike.scala:166)
at org.scalatest.Suite$class.withFixture(Suite.scala:1122)
at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555)
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
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(CloudSuite.scala:40)
at
org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:255)
at
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfter$$super$runTest(CloudSuite.scala:40)
at org.scalatest.BeforeAndAfter$class.runTest(BeforeAndAfter.scala:200)
at com.hortonworks.spark.cloud.CloudSuite.runTest(CloudSuite.scala:40)
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
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfterAll$$super$run(CloudSuite.scala:40)
at
org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
at
com.hortonworks.spark.cloud.CloudSuite.org$scalatest$BeforeAndAfter$$super$run(CloudSuite.scala:40)
at org.scalatest.BeforeAndAfter$class.run(BeforeAndAfter.scala:241)
at com.hortonworks.spark.cloud.CloudSuite.run(CloudSuite.scala:40)
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)
Cause: org.apache.spark.SparkException: Task failed while writing rows
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:253)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$12.apply(FileFormatWriter.scala:178)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$12.apply(FileFormatWriter.scala:177)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:317)
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)
Cause: java.lang.UnsupportedOperationException
at java.util.Collections$UnmodifiableList.sort(Collections.java:1331)
at java.util.Collections.sort(Collections.java:175)
at
com.amazonaws.services.s3.model.transform.RequestXmlFactory.convertToXmlByteArray(RequestXmlFactory.java:42)
at
com.amazonaws.services.s3.AmazonS3Client.completeMultipartUpload(AmazonS3Client.java:2692)
at
org.apache.hadoop.fs.s3a.S3AFileSystem$WriteOperationHelper.completeMultipartUpload(S3AFileSystem.java:2298)
at
org.apache.hadoop.fs.s3a.S3ABlockOutputStream$MultiPartUpload.complete(S3ABlockOutputStream.java:561)
at
org.apache.hadoop.fs.s3a.S3ABlockOutputStream$MultiPartUpload.access$200(S3ABlockOutputStream.java:454)
at
org.apache.hadoop.fs.s3a.S3ABlockOutputStream.close(S3ABlockOutputStream.java:352)
at
org.apache.hadoop.fs.FSDataOutputStream$PositionCache.close(FSDataOutputStream.java:72)
at
org.apache.hadoop.fs.FSDataOutputStream.close(FSDataOutputStream.java:106)
at
org.apache.parquet.hadoop.ParquetFileWriter.end(ParquetFileWriter.java:639)
at
org.apache.parquet.hadoop.InternalParquetRecordWriter.close(InternalParquetRecordWriter.java:117)
at
org.apache.parquet.hadoop.ParquetRecordWriter.close(ParquetRecordWriter.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.close(ParquetOutputWriter.scala:42)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.releaseResources(FileFormatWriter.scala:317)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:311)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:239)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:237)
at
org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1360)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:242)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$12.apply(FileFormatWriter.scala:178)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$12.apply(FileFormatWriter.scala:177)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:317)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
{code}
> S3A multipart commit failing, "UnsupportedOperationException at
> java.util.Collections$UnmodifiableList.sort"
> ------------------------------------------------------------------------------------------------------------
>
> Key: HADOOP-14204
> URL: https://issues.apache.org/jira/browse/HADOOP-14204
> Project: Hadoop Common
> Issue Type: Bug
> Components: fs/s3
> Affects Versions: 2.8.0
> Reporter: Steve Loughran
> Assignee: Steve Loughran
> Priority: Critical
>
> Stack trace seen trying to commit a multipart upload, as the EMR code (which
> takes a {{List<String> etags}} is trying to sort that list directly, which it
> can't do if the list doesn't want to be sorted.
> later versions of the SDK clone the list before sorting.
> We need to make sure that the list passed in can be sorted.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
