You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Dongjoon Hyun (JIRA)" <ji...@apache.org> on 2019/06/02 17:28:00 UTC
[jira] [Updated] (SPARK-27907) HiveUDAF with 0 rows throw NPE
[ https://issues.apache.org/jira/browse/SPARK-27907?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Dongjoon Hyun updated SPARK-27907:
----------------------------------
Affects Version/s: (was: 3.1.0)
> HiveUDAF with 0 rows throw NPE
> ------------------------------
>
> Key: SPARK-27907
> URL: https://issues.apache.org/jira/browse/SPARK-27907
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.3.3, 3.0.0, 2.4.3
> Reporter: Ajith S
> Priority: Major
>
> When query returns zero rows, the HiveUDAFFunction throws NPE
> CASE 1:
> create table abc(a int)
> select histogram_numeric(a,2) from abc // NPE
> Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 0, localhost, executor driver): java.lang.NullPointerException
> at org.apache.spark.sql.hive.HiveUDAFFunction.eval(hiveUDFs.scala:471)
> at org.apache.spark.sql.hive.HiveUDAFFunction.eval(hiveUDFs.scala:315)
> at org.apache.spark.sql.catalyst.expressions.aggregate.TypedImperativeAggregate.eval(interfaces.scala:543)
> at org.apache.spark.sql.execution.aggregate.AggregationIterator.$anonfun$generateResultProjection$5(AggregationIterator.scala:231)
> at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.outputForEmptyGroupingKeyWithoutInput(ObjectAggregationIterator.scala:97)
> at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec.$anonfun$doExecute$2(ObjectHashAggregateExec.scala:132)
> at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec.$anonfun$doExecute$2$adapted(ObjectHashAggregateExec.scala:107)
> at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndexInternal$2(RDD.scala:839)
> at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndexInternal$2$adapted(RDD.scala:839)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:327)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:291)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:327)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:291)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:327)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:291)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
> at org.apache.spark.scheduler.Task.run(Task.scala:122)
> at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:425)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1350)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:428)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> CASE 2:
> create table abc(a int)
> insert into abc values (1)
> select histogram_numeric(a,2) from abc where a=3 //NPE
> Job aborted due to stage failure: Task 0 in stage 4.0 failed 1 times, most recent failure: Lost task 0.0 in stage 4.0 (TID 5, localhost, executor driver): java.lang.NullPointerException
> at org.apache.spark.sql.hive.HiveUDAFFunction.serialize(hiveUDFs.scala:477)
> at org.apache.spark.sql.hive.HiveUDAFFunction.serialize(hiveUDFs.scala:315)
> at org.apache.spark.sql.catalyst.expressions.aggregate.TypedImperativeAggregate.serializeAggregateBufferInPlace(interfaces.scala:570)
> at org.apache.spark.sql.execution.aggregate.AggregationIterator.$anonfun$generateResultProjection$6(AggregationIterator.scala:254)
> at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.outputForEmptyGroupingKeyWithoutInput(ObjectAggregationIterator.scala:97)
> at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec.$anonfun$doExecute$2(ObjectHashAggregateExec.scala:132)
> at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec.$anonfun$doExecute$2$adapted(ObjectHashAggregateExec.scala:107)
> at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndexInternal$2(RDD.scala:839)
> at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndexInternal$2$adapted(RDD.scala:839)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:327)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:291)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:327)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:291)
> at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:94)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
> at org.apache.spark.scheduler.Task.run(Task.scala:122)
> at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:425)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1350)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:428)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org