[ https://issues.apache.org/jira/browse/SPARK-10294?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Yin Huai updated SPARK-10294: ----------------------------- Summary: When saving a file larger than S3 size limit to S3, Parquet writer's close method is called twice and then NPE is thrown. (was: NPE when save data to parquet table) > When saving a file larger than S3 size limit to S3, Parquet writer's close > method is called twice and then NPE is thrown. > ------------------------------------------------------------------------------------------------------------------------- > > Key: SPARK-10294 > URL: https://issues.apache.org/jira/browse/SPARK-10294 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 1.5.0 > Reporter: Yin Huai > Attachments: screenshot-1.png > > > When a task saves a large parquet file (larger than the S3 file size limit) > to S3, looks like we still call parquet writer's close twice and triggers NPE > reported in SPARK-7837. Eventually, job failed and I got NPE as the > exception. Actually, the real problem was that the file was too large for S3. > {code} > 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:1818) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1831) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:1908) > 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$$anonfun$execute$5.apply(SparkPlan.scala:138) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) > at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138) > at > org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927) > at > org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927) > at > org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197) > at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146) > at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137) > at > com.databricks.spark.sql.perf.tpcds.Tables$Table.genData(Tables.scala:147) > at > com.databricks.spark.sql.perf.tpcds.Tables$$anonfun$genData$2.apply(Tables.scala:192) > at > com.databricks.spark.sql.perf.tpcds.Tables$$anonfun$genData$2.apply(Tables.scala:190) > at scala.collection.immutable.List.foreach(List.scala:318) > at com.databricks.spark.sql.perf.tpcds.Tables.genData(Tables.scala:190) > at Notebook$$anonfun$1$$anonfun$apply$1.apply(<console>:40) > at Notebook$$anonfun$1$$anonfun$apply$1.apply(<console>:39) > at scala.collection.immutable.List.foreach(List.scala:318) > at Notebook$$anonfun$1.apply(<console>:39) > at Notebook$$anonfun$1.apply(<console>:38) > at scala.collection.immutable.List.foreach(List.scala:318) > Caused by: org.apache.spark.SparkException: Task failed while writing rows. > at > org.apache.spark.sql.execution.datasources.DynamicPartitionWriterContainer.writeRows(WriterContainer.scala:391) > at > org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) > at > org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) > at org.apache.spark.scheduler.Task.run(Task.scala:88) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.lang.NullPointerException > at > org.apache.parquet.hadoop.InternalParquetRecordWriter.flushRowGroupToStore(InternalParquetRecordWriter.java:147) > at > org.apache.parquet.hadoop.InternalParquetRecordWriter.close(InternalParquetRecordWriter.java:113) > at > org.apache.parquet.hadoop.ParquetRecordWriter.close(ParquetRecordWriter.java:112) > at > org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.close(ParquetRelation.scala:98) > at > org.apache.spark.sql.execution.datasources.DynamicPartitionWriterContainer.writeRows(WriterContainer.scala:382) > at > org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$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) > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org