You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by do...@apache.org on 2019/06/02 17:54:57 UTC
[spark] branch master updated: [SPARK-27907][SQL] HiveUDAF should
return NULL in case of 0 rows
This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 3806887 [SPARK-27907][SQL] HiveUDAF should return NULL in case of 0 rows
3806887 is described below
commit 3806887afb36266aee8749ac95ea0e9016fbf6ff
Author: Ajith <aj...@gmail.com>
AuthorDate: Sun Jun 2 10:54:21 2019 -0700
[SPARK-27907][SQL] HiveUDAF should return NULL in case of 0 rows
## What changes were proposed in this pull request?
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)
```
Hence add a check not avoid NPE
## How was this patch tested?
Added new UT case
Closes #24762 from ajithme/hiveudaf.
Authored-by: Ajith <aj...@gmail.com>
Signed-off-by: Dongjoon Hyun <dh...@apple.com>
---
.../src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala | 10 ++++++++--
.../org/apache/spark/sql/hive/execution/HiveUDAFSuite.scala | 10 ++++++++++
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
index 76e4085..d78fc9d 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
@@ -468,13 +468,19 @@ private[hive] case class HiveUDAFFunction(
}
override def eval(buffer: HiveUDAFBuffer): Any = {
- resultUnwrapper(finalHiveEvaluator.evaluator.terminate(buffer.buf))
+ resultUnwrapper(finalHiveEvaluator.evaluator.terminate(
+ if (buffer == null) {
+ finalHiveEvaluator.evaluator.getNewAggregationBuffer
+ } else {
+ buffer.buf
+ }
+ ))
}
override def serialize(buffer: HiveUDAFBuffer): Array[Byte] = {
// Serializes an `AggregationBuffer` that holds partial aggregation results so that we can
// shuffle it for global aggregation later.
- aggBufferSerDe.serialize(buffer.buf)
+ aggBufferSerDe.serialize(if (buffer == null) null else buffer.buf)
}
override def deserialize(bytes: Array[Byte]): HiveUDAFBuffer = {
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDAFSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDAFSuite.scala
index 3252cda..b0d615c 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDAFSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDAFSuite.scala
@@ -149,6 +149,16 @@ class HiveUDAFSuite extends QueryTest with TestHiveSingleton with SQLTestUtils {
}
}
}
+
+ test("SPARK-27907 HiveUDAF with 0 rows throws NPE") {
+ withTable("abc") {
+ sql("create table abc(a int)")
+ checkAnswer(sql("select histogram_numeric(a,2) from abc"), Row(null))
+ sql("insert into abc values (1)")
+ checkAnswer(sql("select histogram_numeric(a,2) from abc"), Row(Row(1.0, 1.0) :: Nil))
+ checkAnswer(sql("select histogram_numeric(a,2) from abc where a=3"), Row(null))
+ }
+ }
}
/**
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org