org.scalatest.exceptions.TestFailedException: Exception thrown while executing query: == Parsed Logical Plan == Sort [index#32327 ASC], true +- Relation[index#32327,col#32328] ParquetRelation == Analyzed Logical Plan == index: int, col: tinyint Sort [index#32327 ASC], true +- Relation[index#32327,col#32328] ParquetRelation == Optimized Logical Plan == Sort [index#32327 ASC], true +- Relation[index#32327,col#32328] ParquetRelation == Physical Plan == Sort [index#32327 ASC], true, 0 +- Exchange rangepartitioning(index#32327 ASC, 5), None +- WholeStageCodegen : +- Scan ParquetRelation[index#32327,col#32328] InputPaths: file:/home/jenkins/workspace/spark-master-test-sbt-hadoop-2.4/target/tmp/spark-6ba3af80-7a32-44f1-a3de-b30573e2005a == Exception == org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree: Exchange rangepartitioning(index#32327 ASC, 5), None +- WholeStageCodegen : +- Scan ParquetRelation[index#32327,col#32328] InputPaths: file:/home/jenkins/workspace/spark-master-test-sbt-hadoop-2.4/target/tmp/spark-6ba3af80-7a32-44f1-a3de-b30573e2005a org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree: Exchange rangepartitioning(index#32327 ASC, 5), None +- WholeStageCodegen : +- Scan ParquetRelation[index#32327,col#32328] InputPaths: file:/home/jenkins/workspace/spark-master-test-sbt-hadoop-2.4/target/tmp/spark-6ba3af80-7a32-44f1-a3de-b30573e2005a at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:47) at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:106) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:115) at org.apache.spark.sql.execution.Sort.doExecute(Sort.scala:60) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:223) at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:231) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:53) at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1748) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$collect$1.apply(DataFrame.scala:1503) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$collect$1.apply(DataFrame.scala:1503) at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:1761) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1503) at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1480) at org.apache.spark.sql.QueryTest$.checkAnswer(QueryTest.scala:315) at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:143) at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:154) at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1$$anonfun$apply$mcV$sp$19.apply(hadoopFsRelationSuites.scala:154) at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1$$anonfun$apply$mcV$sp$19.apply(hadoopFsRelationSuites.scala:121) at org.apache.spark.sql.test.SQLTestUtils$class.withTempPath(SQLTestUtils.scala:125) at org.apache.spark.sql.sources.HadoopFsRelationTest.withTempPath(hadoopFsRelationSuites.scala:38) at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply$mcV$sp(hadoopFsRelationSuites.scala:121) at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply(hadoopFsRelationSuites.scala:121) at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply(hadoopFsRelationSuites.scala:121) 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$1.apply(FunSuiteLike.scala:166) at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:54) at org.scalatest.FunSuiteLike$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$$super$run(SparkFunSuite.scala:26) at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257) at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256) at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:26) at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:357) at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:502) at sbt.ForkMain$Run$2.call(ForkMain.java:296) at sbt.ForkMain$Run$2.call(ForkMain.java:286) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 4477.0 failed 1 times, most recent failure: Lost task 0.0 in stage 4477.0 (TID 70197, localhost): java.lang.NullPointerException at org.apache.spark.sql.execution.vectorized.OnHeapColumnVector.putInt(OnHeapColumnVector.java:193) at org.apache.spark.sql.execution.datasources.parquet.VectorizedPlainValuesReader.readBytes(VectorizedPlainValuesReader.java:88) at org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readBytes(VectorizedRleValuesReader.java:283) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readIntBatch(UnsafeRowParquetRecordReader.java:763) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readBatch(UnsafeRowParquetRecordReader.java:640) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.access$000(UnsafeRowParquetRecordReader.java:461) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextBatch(UnsafeRowParquetRecordReader.java:224) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextKeyValue(UnsafeRowParquetRecordReader.java:174) at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:203) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(generated.java:32) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:40) at org.apache.spark.sql.execution.WholeStageCodegen$$anonfun$5$$anon$1.hasNext(WholeStageCodegen.scala:305) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369) at org.apache.spark.util.random.SamplingUtils$.reservoirSampleAndCount(SamplingUtils.scala:41) at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:261) at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:259) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313) at org.apache.spark.rdd.RDD.iterator(RDD.scala:277) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:69) at org.apache.spark.scheduler.Task.run(Task.scala:82) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1452) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1440) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1439) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1439) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1661) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1620) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1609) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:623) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1773) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1786) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1799) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:847) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) at org.apache.spark.rdd.RDD.withScope(RDD.scala:323) at org.apache.spark.rdd.RDD.collect(RDD.scala:846) at org.apache.spark.RangePartitioner$.sketch(Partitioner.scala:264) at org.apache.spark.RangePartitioner.<init>(Partitioner.scala:126) at org.apache.spark.sql.execution.exchange.ShuffleExchange$.prepareShuffleDependency(ShuffleExchange.scala:211) at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:83) at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:113) at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:107) at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:46) ... 77 more Caused by: java.lang.NullPointerException at org.apache.spark.sql.execution.vectorized.OnHeapColumnVector.putInt(OnHeapColumnVector.java:193) at org.apache.spark.sql.execution.datasources.parquet.VectorizedPlainValuesReader.readBytes(VectorizedPlainValuesReader.java:88) at org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readBytes(VectorizedRleValuesReader.java:283) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readIntBatch(UnsafeRowParquetRecordReader.java:763) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readBatch(UnsafeRowParquetRecordReader.java:640) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.access$000(UnsafeRowParquetRecordReader.java:461) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextBatch(UnsafeRowParquetRecordReader.java:224) at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextKeyValue(UnsafeRowParquetRecordReader.java:174) at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:203) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(generated.java:32) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:40) at org.apache.spark.sql.execution.WholeStageCodegen$$anonfun$5$$anon$1.hasNext(WholeStageCodegen.scala:305) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369) at org.apache.spark.util.random.SamplingUtils$.reservoirSampleAndCount(SamplingUtils.scala:41) at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:261) at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:259) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313) at org.apache.spark.rdd.RDD.iterator(RDD.scala:277) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:69) at org.apache.spark.scheduler.Task.run(Task.scala:82) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) ... 3 more
sbt.ForkMain$ForkError: org.scalatest.exceptions.TestFailedException:
Exception thrown while executing query:
== Parsed Logical Plan ==
Sort [index#32327 ASC], true
+- Relation[index#32327,col#32328] ParquetRelation
== Analyzed Logical Plan ==
index: int, col: tinyint
Sort [index#32327 ASC], true
+- Relation[index#32327,col#32328] ParquetRelation
== Optimized Logical Plan ==
Sort [index#32327 ASC], true
+- Relation[index#32327,col#32328] ParquetRelation
== Physical Plan ==
Sort [index#32327 ASC], true, 0
+- Exchange rangepartitioning(index#32327 ASC, 5), None
+- WholeStageCodegen
: +- Scan ParquetRelation[index#32327,col#32328] InputPaths: file:/home/jenkins/workspace/spark-master-test-sbt-hadoop-2.4/target/tmp/spark-6ba3af80-7a32-44f1-a3de-b30573e2005a
== Exception ==
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree:
Exchange rangepartitioning(index#32327 ASC, 5), None
+- WholeStageCodegen
: +- Scan ParquetRelation[index#32327,col#32328] InputPaths: file:/home/jenkins/workspace/spark-master-test-sbt-hadoop-2.4/target/tmp/spark-6ba3af80-7a32-44f1-a3de-b30573e2005a
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree:
Exchange rangepartitioning(index#32327 ASC, 5), None
+- WholeStageCodegen
: +- Scan ParquetRelation[index#32327,col#32328] InputPaths: file:/home/jenkins/workspace/spark-master-test-sbt-hadoop-2.4/target/tmp/spark-6ba3af80-7a32-44f1-a3de-b30573e2005a
at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:47)
at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:106)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:115)
at org.apache.spark.sql.execution.Sort.doExecute(Sort.scala:60)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:116)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:223)
at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:231)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:53)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1748)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$collect$1.apply(DataFrame.scala:1503)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$collect$1.apply(DataFrame.scala:1503)
at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:1761)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1503)
at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1480)
at org.apache.spark.sql.QueryTest$.checkAnswer(QueryTest.scala:315)
at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:143)
at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:154)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1$$anonfun$apply$mcV$sp$19.apply(hadoopFsRelationSuites.scala:154)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1$$anonfun$apply$mcV$sp$19.apply(hadoopFsRelationSuites.scala:121)
at org.apache.spark.sql.test.SQLTestUtils$class.withTempPath(SQLTestUtils.scala:125)
at org.apache.spark.sql.sources.HadoopFsRelationTest.withTempPath(hadoopFsRelationSuites.scala:38)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply$mcV$sp(hadoopFsRelationSuites.scala:121)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply(hadoopFsRelationSuites.scala:121)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply(hadoopFsRelationSuites.scala:121)
at org.scalatest.Transformer$$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$$anon$1.apply(FunSuiteLike.scala:166)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:54)
at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
at org.scalatest.FunSuiteLike$$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$run(SparkFunSuite.scala:26)
at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:26)
at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:357)
at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:502)
at sbt.ForkMain$Run$2.call(ForkMain.java:296)
at sbt.ForkMain$Run$2.call(ForkMain.java:286)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 4477.0 failed 1 times, most recent failure: Lost task 0.0 in stage 4477.0 (TID 70197, localhost): java.lang.NullPointerException
at org.apache.spark.sql.execution.vectorized.OnHeapColumnVector.putInt(OnHeapColumnVector.java:193)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedPlainValuesReader.readBytes(VectorizedPlainValuesReader.java:88)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readBytes(VectorizedRleValuesReader.java:283)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readIntBatch(UnsafeRowParquetRecordReader.java:763)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readBatch(UnsafeRowParquetRecordReader.java:640)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.access$000(UnsafeRowParquetRecordReader.java:461)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextBatch(UnsafeRowParquetRecordReader.java:224)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextKeyValue(UnsafeRowParquetRecordReader.java:174)
at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:203)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(generated.java:32)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:40)
at org.apache.spark.sql.execution.WholeStageCodegen$$anonfun$5$$anon$1.hasNext(WholeStageCodegen.scala:305)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369)
at org.apache.spark.util.random.SamplingUtils$.reservoirSampleAndCount(SamplingUtils.scala:41)
at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:261)
at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:259)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:69)
at org.apache.spark.scheduler.Task.run(Task.scala:82)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1452)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1440)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1439)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1439)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1661)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1620)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1609)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:623)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1773)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1786)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1799)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:847)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:323)
at org.apache.spark.rdd.RDD.collect(RDD.scala:846)
at org.apache.spark.RangePartitioner$.sketch(Partitioner.scala:264)
at org.apache.spark.RangePartitioner.<init>(Partitioner.scala:126)
at org.apache.spark.sql.execution.exchange.ShuffleExchange$.prepareShuffleDependency(ShuffleExchange.scala:211)
at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:83)
at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:113)
at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:107)
at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:46)
... 77 more
Caused by: java.lang.NullPointerException
at org.apache.spark.sql.execution.vectorized.OnHeapColumnVector.putInt(OnHeapColumnVector.java:193)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedPlainValuesReader.readBytes(VectorizedPlainValuesReader.java:88)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readBytes(VectorizedRleValuesReader.java:283)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readIntBatch(UnsafeRowParquetRecordReader.java:763)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.readBatch(UnsafeRowParquetRecordReader.java:640)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader$ColumnReader.access$000(UnsafeRowParquetRecordReader.java:461)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextBatch(UnsafeRowParquetRecordReader.java:224)
at org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader.nextKeyValue(UnsafeRowParquetRecordReader.java:174)
at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:203)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(generated.java:32)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:40)
at org.apache.spark.sql.execution.WholeStageCodegen$$anonfun$5$$anon$1.hasNext(WholeStageCodegen.scala:305)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:369)
at org.apache.spark.util.random.SamplingUtils$.reservoirSampleAndCount(SamplingUtils.scala:41)
at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:261)
at org.apache.spark.RangePartitioner$$anonfun$9.apply(Partitioner.scala:259)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$24.apply(RDD.scala:755)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:69)
at org.apache.spark.scheduler.Task.run(Task.scala:82)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
... 3 more
at org.scalatest.Assertions$class.newAssertionFailedException(Assertions.scala:495)
at org.scalatest.FunSuite.newAssertionFailedException(FunSuite.scala:1555)
at org.scalatest.Assertions$class.fail(Assertions.scala:1328)
at org.scalatest.FunSuite.fail(FunSuite.scala:1555)
at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:144)
at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:154)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1$$anonfun$apply$mcV$sp$19.apply(hadoopFsRelationSuites.scala:154)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1$$anonfun$apply$mcV$sp$19.apply(hadoopFsRelationSuites.scala:121)
at org.apache.spark.sql.test.SQLTestUtils$class.withTempPath(SQLTestUtils.scala:125)
at org.apache.spark.sql.sources.HadoopFsRelationTest.withTempPath(hadoopFsRelationSuites.scala:38)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply$mcV$sp(hadoopFsRelationSuites.scala:121)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply(hadoopFsRelationSuites.scala:121)
at org.apache.spark.sql.sources.HadoopFsRelationTest$$anonfun$32$$anonfun$apply$1.apply(hadoopFsRelationSuites.scala:121)
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$1.apply(FunSuiteLike.scala:166)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:54)
at org.scalatest.FunSuiteLike$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$$super$run(SparkFunSuite.scala:26)
at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:26)
at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:357)
at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:502)
at sbt.ForkMain$Run$2.call(ForkMain.java:296)
at sbt.ForkMain$Run$2.call(ForkMain.java:286)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)