Я пытаюсь записать искровой DF в один CSV-файл. Обычно я использую этот вызов, который работает:
df.coalesce(1).write.mode("overwrite").csv(file_path, sep=",", header=True)
НО я столкнулся с случаем, когда появляются эти ошибки, и я получаю сообщение «файл уже существует». Из копания я сделал это повторная попытка pyspark и фактический сбой в журналах. Однако, просматривая журналы контейнера, я не вижу ничего, что указывало бы на причину сбоя. Я решил эту проблему, но я ищу объяснение , почему это решает проблему. Выполнение этой команды:
df.repartition(1).write.mode("overwrite").csv(file_path, sep=",", header=True)
успешно сохранит один CSV-файл по указанному пути.
Я смотрел на разницу между coalesce и repartition (это связано с добавлением к существующим разделам по сравнению с полным перемешиванием), но я не понимаю, как это решает вышеуказанную проблему.
РЕДАКТИРОВАТЬ, добавив полное сообщение об ошибке:
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:196)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:668)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:668)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:668)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:276)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:270)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:228)
at org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:656)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 148.0 failed 4 times, most recent failure: Lost task 0.3 in stage 148.0 (TID 10599, ip-172-31-42-50.ec2.internal, executor 140): org.apache.hadoop.fs.FileAlreadyExistsException: File already exists:s3://<PATH>/part-00000-a7dc7464-838c-4fd6-962c-899bb58548dc-c000.csv
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.checkExistenceIfNotOverwriting(RegularUploadPlanner.java:36)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.plan(RegularUploadPlanner.java:30)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.UploadPlannerChain.plan(UploadPlannerChain.java:37)
at com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.create(S3NativeFileSystem.java:601)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:932)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:913)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:810)
at com.amazon.ws.emr.hadoop.fs.EmrFileSystem.create(EmrFileSystem.java:212)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStream(CodecStreams.scala:81)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStreamWriter(CodecStreams.scala:92)
at org.apache.spark.sql.execution.datasources.csv.CsvOutputWriter.<init>(CSVFileFormat.scala:177)
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat$$anon$1.newInstance(CSVFileFormat.scala:85)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:120)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:108)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:233)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:169)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:168)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:2039)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2027)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2026)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2026)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:966)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:966)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:966)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2260)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2209)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2198)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:777)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:166)
... 33 more
Caused by: org.apache.hadoop.fs.FileAlreadyExistsException: File already exists:s3://<PATH>/part-00000-a7dc7464-838c-4fd6-962c-899bb58548dc-c000.csv
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.checkExistenceIfNotOverwriting(RegularUploadPlanner.java:36)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.plan(RegularUploadPlanner.java:30)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.UploadPlannerChain.plan(UploadPlannerChain.java:37)
at com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.create(S3NativeFileSystem.java:601)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:932)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:913)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:810)
at com.amazon.ws.emr.hadoop.fs.EmrFileSystem.create(EmrFileSystem.java:212)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStream(CodecStreams.scala:81)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStreamWriter(CodecStreams.scala:92)
at org.apache.spark.sql.execution.datasources.csv.CsvOutputWriter.<init>(CSVFileFormat.scala:177)
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat$$anon$1.newInstance(CSVFileFormat.scala:85)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:120)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:108)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:233)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:169)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:168)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Traceback (most recent call last):
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 929, in csv
self._jwrite.csv(path)
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o815.csv.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:196)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:668)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:668)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:668)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:276)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:270)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:228)
at org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:656)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 148.0 failed 4 times, most recent failure: Lost task 0.3 in stage 148.0 (TID 10599, ip-172-31-42-50.ec2.internal, executor 140): org.apache.hadoop.fs.FileAlreadyExistsException: File already exists:s3://<PATH>part-00000-a7dc7464-838c-4fd6-962c-899bb58548dc-c000.csv
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.checkExistenceIfNotOverwriting(RegularUploadPlanner.java:36)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.plan(RegularUploadPlanner.java:30)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.UploadPlannerChain.plan(UploadPlannerChain.java:37)
at com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.create(S3NativeFileSystem.java:601)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:932)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:913)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:810)
at com.amazon.ws.emr.hadoop.fs.EmrFileSystem.create(EmrFileSystem.java:212)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStream(CodecStreams.scala:81)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStreamWriter(CodecStreams.scala:92)
at org.apache.spark.sql.execution.datasources.csv.CsvOutputWriter.<init>(CSVFileFormat.scala:177)
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat$$anon$1.newInstance(CSVFileFormat.scala:85)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:120)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:108)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:233)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:169)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:168)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:2039)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2027)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2026)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2026)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:966)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:966)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:966)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2260)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2209)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2198)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:777)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:166)
... 33 more
Caused by: org.apache.hadoop.fs.FileAlreadyExistsException: File already exists:s3://<PATH>/part-00000-a7dc7464-838c-4fd6-962c-899bb58548dc-c000.csv
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.checkExistenceIfNotOverwriting(RegularUploadPlanner.java:36)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.RegularUploadPlanner.plan(RegularUploadPlanner.java:30)
at com.amazon.ws.emr.hadoop.fs.s3.upload.plan.UploadPlannerChain.plan(UploadPlannerChain.java:37)
at com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.create(S3NativeFileSystem.java:601)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:932)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:913)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:810)
at com.amazon.ws.emr.hadoop.fs.EmrFileSystem.create(EmrFileSystem.java:212)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStream(CodecStreams.scala:81)
at org.apache.spark.sql.execution.datasources.CodecStreams$.createOutputStreamWriter(CodecStreams.scala:92)
at org.apache.spark.sql.execution.datasources.csv.CsvOutputWriter.<init>(CSVFileFormat.scala:177)
at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat$$anon$1.newInstance(CSVFileFormat.scala:85)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:120)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:108)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:233)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:169)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:168)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more```