Davies Liu created SPARK-14870:
----------------------------------
Summary: NPE in generate aggregate
Key: SPARK-14870
URL: https://issues.apache.org/jira/browse/SPARK-14870
Project: Spark
Issue Type: Bug
Components: SQL
Reporter: Davies Liu
Assignee: Sameer Agarwal
When ran TPCDS Q14a
{code}
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
stage 126.0 failed 1 times, most recent failure: Lost task 0.0 in stage 126.0
(TID 234, localhost): java.lang.NullPointerException
at
org.apache.spark.sql.execution.vectorized.ColumnVector.putDecimal(ColumnVector.java:576)
at
org.apache.spark.sql.execution.vectorized.ColumnarBatch$Row.setDecimal(ColumnarBatch.java:325)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$7$$anon$1.hasNext(WholeStageCodegenExec.scala:361)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at
org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:254)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1450)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1438)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1437)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1437)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:809)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:809)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:809)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1659)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1607)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1780)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1793)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1806)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1820)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:880)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:357)
at org.apache.spark.rdd.RDD.collect(RDD.scala:879)
at
org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
at
org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply$mcI$sp(Dataset.scala:2367)
at
org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:2367)
at
org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:2367)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:53)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2386)
at org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:2366)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:290)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.NullPointerException
at
org.apache.spark.sql.execution.vectorized.ColumnVector.putDecimal(ColumnVector.java:576)
at
org.apache.spark.sql.execution.vectorized.ColumnarBatch$Row.setDecimal(ColumnarBatch.java:325)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$7$$anon$1.hasNext(WholeStageCodegenExec.scala:361)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at
org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:254)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
{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
