[SPARK-10197] Add null check in wrapperFor (inside HiveInspectors).

• Type: Bug
• Status: Resolved
• Priority: Blocker
• Resolution: Fixed
• Affects Version/s: 1.5.0
• Fix Version/s: 1.5.0
• Component/s: SQL
• Target Version/s: 1.5.0
• Sprint: Spark 1.5 doc/QA sprint
• Assignee: Yin Huai
• Reporter: Yin Huai
• Created: 24/Aug/15 23:19
• Updated: 26/Aug/15 21:35
• Resolved: 25/Aug/15 08:23

Description

I tried to save a table to ORC, but seems we need to add null check in wrapperFor method of HiveInspectors.

Driver stacktrace:
	at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1267)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1255)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1254)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
	at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1254)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:684)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:684)
	at scala.Option.foreach(Option.scala:236)
	at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:684)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1480)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1442)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1431)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:554)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1805)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1818)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1895)
	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$$anonfun$execute$5.apply(SparkPlan.scala:138)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
	at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
	at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927)
	at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927)
	at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
	at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
	at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
	at com.databricks.spark.sql.perf.tpcds.Tables$Table.genData(Tables.scala:125)
	at com.databricks.spark.sql.perf.tpcds.Tables$$anonfun$genData$2.apply(Tables.scala:169)
	at com.databricks.spark.sql.perf.tpcds.Tables$$anonfun$genData$2.apply(Tables.scala:167)
	at scala.collection.immutable.List.foreach(List.scala:318)
	at com.databricks.spark.sql.perf.tpcds.Tables.genData(Tables.scala:167)
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
	at org.apache.spark.sql.execution.datasources.DynamicPartitionWriterContainer.writeRows(WriterContainer.scala:391)
	at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
	at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
	at org.apache.spark.scheduler.Task.run(Task.scala:88)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
	at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.NullPointerException
	at org.apache.spark.sql.hive.HiveInspectors$$anonfun$wrapperFor$2.apply(HiveInspectors.scala:377)
	at org.apache.spark.sql.hive.HiveInspectors$$anonfun$wrapperFor$2.apply(HiveInspectors.scala:377)
	at org.apache.spark.sql.hive.orc.OrcOutputWriter.writeInternal(OrcRelation.scala:130)
	at org.apache.spark.sql.execution.datasources.DynamicPartitionWriterContainer.writeRows(WriterContainer.scala:346)
	at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$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)

Issue Links

• duplicates: SPARK-10302 NPE while save a DataFrame as ORC
• links to: [Github] Pull Request #8407 (yhuai)