You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Joao (JIRA)" <ji...@apache.org> on 2015/09/16 11:22:46 UTC
[jira] [Updated] (SPARK-10632) Cannot save DataFrame with User
Defined Types
[ https://issues.apache.org/jira/browse/SPARK-10632?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Joao updated SPARK-10632:
-------------------------
Description:
Cannot save DataFrames that contain user-defined types.
At first I thought it was a problem with my udt class, then tried the Vector class from mlib and the error was the same.
The code below should reproduce the error.
{noformat}
val df = sc.parallelize(Seq((1,Vectors.dense(1,1,1)), (2,Vectors.dense(2,2,2)))).toDF()
df.write.format("json").mode(SaveMode.Overwrite).save(path)
{noformat}
The error log is below
{noformat}
15/09/16 09:58:27 ERROR DefaultWriterContainer: Aborting task.
scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
15/09/16 09:58:27 INFO NativeS3FileSystem: OutputStream for key 'adad/_temporary/0/_temporary/attempt_201509160958_0000_m_000000_0/part-r-00000-2a262ed4-be5a-4190-92a1-a5326cc76ed6' closed. Now beginning upload
15/09/16 09:58:27 INFO NativeS3FileSystem: OutputStream for key 'adad/_temporary/0/_temporary/attempt_201509160958_0000_m_000000_0/part-r-00000-2a262ed4-be5a-4190-92a1-a5326cc76ed6' upload complete
15/09/16 09:58:28 ERROR DefaultWriterContainer: Task attempt attempt_201509160958_0000_m_000000_0 aborted.
15/09/16 09:58:28 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
15/09/16 09:58:28 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
15/09/16 09:58:28 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
15/09/16 09:58:28 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool
15/09/16 09:58:28 INFO TaskSchedulerImpl: Cancelling stage 0
15/09/16 09:58:28 INFO DAGScheduler: ResultStage 0 (save at DataFrameSave.scala:32) failed in 1.409 s
15/09/16 09:58:28 INFO DAGScheduler: Job 0 failed: save at DataFrameSave.scala:32, took 1.618305 s
15/09/16 09:58:28 ERROR InsertIntoHadoopFsRelation: Aborting job.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
at com.sessioncam.app.DataFrameSave$.main(DataFrameSave.scala:32)
at com.sessioncam.app.DataFrameSave.main(DataFrameSave.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
15/09/16 09:58:29 ERROR DefaultWriterContainer: Job job_201509160958_0000 aborted.
Exception in thread "main" org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:156)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
at com.sessioncam.app.DataFrameSave$.main(DataFrameSave.scala:32)
at com.sessioncam.app.DataFrameSave.main(DataFrameSave.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150)
... 23 more
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
{noformat}
was:
Cannot save DataFrames that contain user-defined types.
At first I thought it was a problem with my udt class, then tried the Vector class from mlib and the error was the same.
Te code below should reproduce the error.
{noformat}
val df = sc.parallelize(Seq((1,Vectors.dense(1,1,1)), (2,Vectors.dense(2,2,2)))).toDF()
df.write.format("json").mode(SaveMode.Overwrite).save(path)
{noformat}
The error log is below
{noformat}
15/09/16 09:58:27 ERROR DefaultWriterContainer: Aborting task.
scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
15/09/16 09:58:27 INFO NativeS3FileSystem: OutputStream for key 'adad/_temporary/0/_temporary/attempt_201509160958_0000_m_000000_0/part-r-00000-2a262ed4-be5a-4190-92a1-a5326cc76ed6' closed. Now beginning upload
15/09/16 09:58:27 INFO NativeS3FileSystem: OutputStream for key 'adad/_temporary/0/_temporary/attempt_201509160958_0000_m_000000_0/part-r-00000-2a262ed4-be5a-4190-92a1-a5326cc76ed6' upload complete
15/09/16 09:58:28 ERROR DefaultWriterContainer: Task attempt attempt_201509160958_0000_m_000000_0 aborted.
15/09/16 09:58:28 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
15/09/16 09:58:28 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
15/09/16 09:58:28 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
15/09/16 09:58:28 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool
15/09/16 09:58:28 INFO TaskSchedulerImpl: Cancelling stage 0
15/09/16 09:58:28 INFO DAGScheduler: ResultStage 0 (save at DataFrameSave.scala:32) failed in 1.409 s
15/09/16 09:58:28 INFO DAGScheduler: Job 0 failed: save at DataFrameSave.scala:32, took 1.618305 s
15/09/16 09:58:28 ERROR InsertIntoHadoopFsRelation: Aborting job.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
at com.sessioncam.app.DataFrameSave$.main(DataFrameSave.scala:32)
at com.sessioncam.app.DataFrameSave.main(DataFrameSave.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
15/09/16 09:58:29 ERROR DefaultWriterContainer: Job job_201509160958_0000 aborted.
Exception in thread "main" org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:156)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
at com.sessioncam.app.DataFrameSave$.main(DataFrameSave.scala:32)
at com.sessioncam.app.DataFrameSave.main(DataFrameSave.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150)
... 23 more
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)
Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
... 8 more
{noformat}
> Cannot save DataFrame with User Defined Types
> ---------------------------------------------
>
> Key: SPARK-10632
> URL: https://issues.apache.org/jira/browse/SPARK-10632
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.0
> Reporter: Joao
>
> Cannot save DataFrames that contain user-defined types.
> At first I thought it was a problem with my udt class, then tried the Vector class from mlib and the error was the same.
> The code below should reproduce the error.
> {noformat}
> val df = sc.parallelize(Seq((1,Vectors.dense(1,1,1)), (2,Vectors.dense(2,2,2)))).toDF()
> df.write.format("json").mode(SaveMode.Overwrite).save(path)
> {noformat}
> The error log is below
> {noformat}
> 15/09/16 09:58:27 ERROR DefaultWriterContainer: Aborting task.
> scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$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)
> 15/09/16 09:58:27 INFO NativeS3FileSystem: OutputStream for key 'adad/_temporary/0/_temporary/attempt_201509160958_0000_m_000000_0/part-r-00000-2a262ed4-be5a-4190-92a1-a5326cc76ed6' closed. Now beginning upload
> 15/09/16 09:58:27 INFO NativeS3FileSystem: OutputStream for key 'adad/_temporary/0/_temporary/attempt_201509160958_0000_m_000000_0/part-r-00000-2a262ed4-be5a-4190-92a1-a5326cc76ed6' upload complete
> 15/09/16 09:58:28 ERROR DefaultWriterContainer: Task attempt attempt_201509160958_0000_m_000000_0 aborted.
> 15/09/16 09:58:28 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
> org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$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)
> Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> ... 8 more
> 15/09/16 09:58:28 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$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)
> Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> ... 8 more
> 15/09/16 09:58:28 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
> 15/09/16 09:58:28 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool
> 15/09/16 09:58:28 INFO TaskSchedulerImpl: Cancelling stage 0
> 15/09/16 09:58:28 INFO DAGScheduler: ResultStage 0 (save at DataFrameSave.scala:32) failed in 1.409 s
> 15/09/16 09:58:28 INFO DAGScheduler: Job 0 failed: save at DataFrameSave.scala:32, took 1.618305 s
> 15/09/16 09:58:28 ERROR InsertIntoHadoopFsRelation: Aborting job.
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$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)
> Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> ... 8 more
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
> at scala.Option.foreach(Option.scala:236)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108)
> at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
> at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
> at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
> at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
> at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
> at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
> at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
> at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
> at com.sessioncam.app.DataFrameSave$.main(DataFrameSave.scala:32)
> at com.sessioncam.app.DataFrameSave.main(DataFrameSave.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
> Caused by: org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> ... 8 more
> 15/09/16 09:58:29 ERROR DefaultWriterContainer: Job job_201509160958_0000 aborted.
> Exception in thread "main" org.apache.spark.SparkException: Job aborted.
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:156)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108)
> at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
> at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
> at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
> at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
> at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
> at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
> at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
> at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
> at com.sessioncam.app.DataFrameSave$.main(DataFrameSave.scala:32)
> at com.sessioncam.app.DataFrameSave.main(DataFrameSave.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
> Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$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)
> Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> ... 8 more
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
> at scala.Option.foreach(Option.scala:236)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150)
> ... 23 more
> Caused by: org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:251)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: scala.MatchError: [1,null,null,[1.0,1.0,1.0]] (of class org.apache.spark.sql.catalyst.expressions.GenericMutableRow)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:194)
> at org.apache.spark.mllib.linalg.VectorUDT.serialize(Vectors.scala:179)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:103)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:126)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$$anonfun$org$apache$spark$sql$execution$datasources$json$JacksonGenerator$$valWriter$2$1.apply(JacksonGenerator.scala:89)
> at org.apache.spark.sql.execution.datasources.json.JacksonGenerator$.apply(JacksonGenerator.scala:133)
> at org.apache.spark.sql.execution.datasources.json.JsonOutputWriter.writeInternal(JSONRelation.scala:185)
> at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:243)
> ... 8 more
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org