carbondata-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Kunal Kapoor (JIRA)" <j...@apache.org>
Subject [jira] [Created] (CARBONDATA-1705) NullPointerException is thrown while loading data into table
Date Mon, 13 Nov 2017 19:14:00 GMT
Kunal Kapoor created CARBONDATA-1705:
----------------------------------------

             Summary: NullPointerException is thrown while loading data into table
                 Key: CARBONDATA-1705
                 URL: https://issues.apache.org/jira/browse/CARBONDATA-1705
             Project: CarbonData
          Issue Type: Bug
            Reporter: Kunal Kapoor
            Assignee: Kunal Kapoor


*Steps:*
1. CREATE TABLE maintable(id int, name string, city string, age int) STORED BY 'org.apache.carbondata.format'
TBLPROPERTIES('dictionary_include'='id')
2. create tablemaintable_preagg_avg stored BY 'carbondata' tblproperties
('parent'='maintable') as select id,avg(age) from maintable group by id
3. LOAD DATA LOCAL INPATH 'sample.csv' into table maintable

*Exception:*
17/11/12 00:04:17 ERROR TaskContextImpl: Error in TaskCompletionListener
java.lang.NullPointerException
	at org.apache.spark.TaskContextImpl$$anonfun$markTaskCompleted$1.apply(TaskContextImpl.scala:97)
	at org.apache.spark.TaskContextImpl$$anonfun$markTaskCompleted$1.apply(TaskContextImpl.scala:95)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
	at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:95)
	at org.apache.spark.scheduler.Task.run(Task.scala:112)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)
17/11/12 00:04:17 ERROR Executor: Exception in task 0.0 in stage 5163.0 (TID 65678)
org.apache.spark.util.TaskCompletionListenerException
	at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
	at org.apache.spark.scheduler.Task.run(Task.scala:112)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)
17/11/12 00:04:17 ERROR TaskSetManager: Task 0 in stage 5163.0 failed 1 times; aborting job
17/11/12 00:04:17 ERROR CarbonDataRDDFactory$: ScalaTest-main-running-TestPreAggregateLoad
load data frame failed
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5163.0
failed 1 times, most recent failure: Lost task 0.0 in stage 5163.0 (TID 65678, localhost,
executor driver): org.apache.spark.util.TaskCompletionListenerException
	at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
	at org.apache.spark.scheduler.Task.run(Task.scala:112)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
	at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
	at scala.Option.foreach(Option.scala:257)
	at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:935)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
	at org.apache.spark.rdd.RDD.collect(RDD.scala:934)
	at org.apache.carbondata.spark.rdd.CarbonDataRDDFactory$.loadDataFrame(CarbonDataRDDFactory.scala:918)
	at org.apache.carbondata.spark.rdd.CarbonDataRDDFactory$.loadCarbonData(CarbonDataRDDFactory.scala:325)
	at org.apache.spark.sql.execution.command.management.LoadTableCommand.loadData(LoadTableCommand.scala:336)
	at org.apache.spark.sql.execution.command.management.LoadTableCommand.processData(LoadTableCommand.scala:177)
	at org.apache.spark.sql.execution.command.management.LoadTableCommand.run(LoadTableCommand.scala:60)
	at org.apache.spark.sql.execution.command.management.LoadTableByInsertCommand.processData(LoadTableByInsertCommand.scala:47)
	at org.apache.spark.sql.execution.command.management.LoadTableByInsertCommand.run(LoadTableByInsertCommand.scala:33)
	at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
	at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
	at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
	at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
	at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:87)
	at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:87)
	at org.apache.spark.sql.Dataset.<init>(Dataset.scala:185)
	at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
	at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
	at org.apache.spark.sql.execution.command.preaaggregate.LoadPostAggregateListener$$anonfun$onEvent$4.apply(PreAggregateListeners.scala:77)
	at org.apache.spark.sql.execution.command.preaaggregate.LoadPostAggregateListener$$anonfun$onEvent$4.apply(PreAggregateListeners.scala:65)
	at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
	at scala.collection.Iterator$class.foreach(Iterator.scala:893)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
	at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
	at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
	at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
	at org.apache.spark.sql.execution.command.preaaggregate.LoadPostAggregateListener$.onEvent(PreAggregateListeners.scala:65)
	at org.apache.carbondata.events.OperationListenerBus.fireEvent(OperationListenerBus.java:116)
	at org.apache.carbondata.spark.rdd.CarbonDataRDDFactory$.loadCarbonData(CarbonDataRDDFactory.scala:486)
	at org.apache.spark.sql.execution.command.management.LoadTableCommand.loadData(LoadTableCommand.scala:336)
	at org.apache.spark.sql.execution.command.management.LoadTableCommand.processData(LoadTableCommand.scala:177)
	at org.apache.spark.sql.execution.command.management.LoadTableCommand.run(LoadTableCommand.scala:60)
	at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
	at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
	at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
	at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
	at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:87)
	at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:87)
	at org.apache.spark.sql.Dataset.<init>(Dataset.scala:185)
	at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
	at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
	at org.apache.spark.sql.test.Spark2TestQueryExecutor.sql(Spark2TestQueryExecutor.scala:35)
	at org.apache.spark.sql.test.util.QueryTest.sql(QueryTest.scala:87)
	at org.apache.carbondata.integration.spark.testsuite.preaggregate.TestPreAggregateLoad$$anonfun$4.apply$mcV$sp(TestPreAggregateLoad.scala:129)
	at org.apache.carbondata.integration.spark.testsuite.preaggregate.TestPreAggregateLoad$$anonfun$4.apply(TestPreAggregateLoad.scala:121)
	at org.apache.carbondata.integration.spark.testsuite.preaggregate.TestPreAggregateLoad$$anonfun$4.apply(TestPreAggregateLoad.scala:121)
	at org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
	at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
	at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
	at org.scalatest.Transformer.apply(Transformer.scala:22)
	at org.scalatest.Transformer.apply(Transformer.scala:20)
	at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
	at org.apache.spark.sql.test.util.CarbonFunSuite.withFixture(CarbonFunSuite.scala:41)
	at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
	at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
	at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
	at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
	at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
	at org.scalatest.FunSuite.runTest(FunSuite.scala:1555)
	at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
	at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
	at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413)
	at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401)
	at scala.collection.immutable.List.foreach(List.scala:381)
	at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
	at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396)
	at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483)
	at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:208)
	at org.scalatest.FunSuite.runTests(FunSuite.scala:1555)
	at org.scalatest.Suite$class.run(Suite.scala:1424)
	at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1555)
	at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
	at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
	at org.scalatest.SuperEngine.runImpl(Engine.scala:545)
	at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212)
	at org.apache.carbondata.integration.spark.testsuite.preaggregate.TestPreAggregateLoad.org$scalatest$BeforeAndAfterAll$$super$run(TestPreAggregateLoad.scala:24)
	at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
	at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
	at org.apache.carbondata.integration.spark.testsuite.preaggregate.TestPreAggregateLoad.run(TestPreAggregateLoad.scala:24)
	at org.scalatest.Suite$class.callExecuteOnSuite$1(Suite.scala:1492)
	at org.scalatest.Suite$$anonfun$runNestedSuites$1.apply(Suite.scala:1528)
	at org.scalatest.Suite$$anonfun$runNestedSuites$1.apply(Suite.scala:1526)
	at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
	at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
	at org.scalatest.Suite$class.runNestedSuites(Suite.scala:1526)
	at org.scalatest.tools.DiscoverySuite.runNestedSuites(DiscoverySuite.scala:29)
	at org.scalatest.Suite$class.run(Suite.scala:1421)
	at org.scalatest.tools.DiscoverySuite.run(DiscoverySuite.scala:29)
	at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:55)
	at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$3.apply(Runner.scala:2563)
	at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$3.apply(Runner.scala:2557)
	at scala.collection.immutable.List.foreach(List.scala:381)
	at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:2557)
	at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1044)
	at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1043)
	at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:2722)
	at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1043)
	at org.scalatest.tools.Runner$.main(Runner.scala:860)
	at org.scalatest.tools.Runner.main(Runner.scala)
Caused by: org.apache.spark.util.TaskCompletionListenerException
	at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
	at org.apache.spark.scheduler.Task.run(Task.scala:112)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)
17/11/12 00:04:17 ERROR CarbonDataRDDFactory$: ScalaTest-main-running-TestPreAggregateLoad

org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5163.0
failed 1 times, most recent failure: Lost task 0.0 in stage 5163.0 (TID 65678, localhost,
executor driver): org.apache.spark.util.TaskCompletionListenerException
	at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
	at org.apache.spark.scheduler.Task.run(Task.scala:112)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

Mime
View raw message