mskapilks opened a new issue, #9245:
URL: https://github.com/apache/incubator-gluten/issues/9245
### Backend
VL (Velox)
### Bug description
Repro:
```scala
import org.apache.spark.sql.functions.udf
val plusOne = udf((x: Int) => x + 1)
spark.udf.register("plusOne", plusOne)
val df = sql("select plusOne((select plusOne(count(*)) from (values (1))
t0(inner_c))) as col from (values (2),(3)) t1(outer_c)")
df.collect()
```
Running this query with Spark 3.5 and Gluten 1.3 bundle
give below error
```scala
Caused by: org.apache.gluten.exception.GlutenException: Exception:
VeloxRuntimeError
Error Source: RUNTIME
Error Code: INVALID_STATE
Reason: Operator::getOutput failed for [operator: ValueStream, plan node ID:
0]: Error during calling Java code from native code:
java.lang.IllegalArgumentException: requirement failed: Subquery subquery#42,
[id=#645] has not finished
at scala.Predef$.require(Predef.scala:281)
at
org.apache.spark.sql.execution.ScalarSubquery.eval(subquery.scala:98)
at
org.apache.spark.sql.catalyst.expressions.IsNull.eval(nullExpressions.scala:354)
at
org.apache.spark.sql.catalyst.expressions.If.eval(conditionalExpressions.scala:89)
at
org.apache.spark.sql.catalyst.expressions.Alias.eval(namedExpressions.scala:158)
at
org.apache.gluten.expression.InterpretedArrowProjection.apply(InterpretedArrowProjection.scala:94)
at
org.apache.gluten.expression.InterpretedArrowProjection.apply(InterpretedArrowProjection.scala:35)
at
org.apache.gluten.execution.ColumnarPartialProjectExec.$anonfun$getProjectedBatchArrow$3(ColumnarPartialProjectExec.scala:248)
at
org.apache.gluten.execution.ColumnarPartialProjectExec.$anonfun$getProjectedBatchArrow$3$adapted(ColumnarPartialProjectExec.scala:246)
at scala.collection.immutable.Range.foreach(Range.scala:158)
at
org.apache.gluten.execution.ColumnarPartialProjectExec.org$apache$gluten$execution$ColumnarPartialProjectExec$$getProjectedBatchArrow(ColumnarPartialProjectExec.scala:246)
at
org.apache.gluten.execution.ColumnarPartialProjectExec$$anon$1.next(ColumnarPartialProjectExec.scala:191)
at
org.apache.gluten.execution.ColumnarPartialProjectExec$$anon$1.next(ColumnarPartialProjectExec.scala:180)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:461)
at
scala.collection.TraversableOnce$FlattenOps$$anon$2.hasNext(TraversableOnce.scala:521)
at
org.apache.gluten.iterator.IteratorsV1$InvocationFlowProtection.hasNext(IteratorsV1.scala:159)
at
org.apache.gluten.iterator.IteratorsV1$PayloadCloser.hasNext(IteratorsV1.scala:37)
at
scala.collection.convert.Wrappers$IteratorWrapper.hasNext(Wrappers.scala:32)
at
org.apache.gluten.vectorized.ColumnarBatchInIterator.hasNext(ColumnarBatchInIterator.java:36)
at
org.apache.gluten.vectorized.ColumnarBatchOutIterator.nativeHasNext(Native
Method)
at
org.apache.gluten.vectorized.ColumnarBatchOutIterator.hasNext0(ColumnarBatchOutIterator.java:57)
at
org.apache.gluten.iterator.ClosableIterator.hasNext(ClosableIterator.java:39)
at
scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:45)
at
org.apache.gluten.iterator.IteratorsV1$InvocationFlowProtection.hasNext(IteratorsV1.scala:159)
at
org.apache.gluten.iterator.IteratorsV1$IteratorCompleter.hasNext(IteratorsV1.scala:71)
at
org.apache.gluten.iterator.IteratorsV1$PayloadCloser.hasNext(IteratorsV1.scala:37)
at
org.apache.gluten.iterator.IteratorsV1$LifeTimeAccumulator.hasNext(IteratorsV1.scala:100)
at scala.collection.Iterator.isEmpty(Iterator.scala:387)
at scala.collection.Iterator.isEmpty$(Iterator.scala:387)
at
org.apache.gluten.iterator.IteratorsV1$LifeTimeAccumulator.isEmpty(IteratorsV1.scala:90)
at
org.apache.gluten.execution.VeloxColumnarToRowExec$.toRowIterator(VeloxColumnarToRowExec.scala:122)
at
org.apache.gluten.execution.VeloxColumnarToRowExec.$anonfun$doExecuteInternal$1(VeloxColumnarToRowExec.scala:78)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitions$2(RDD.scala:858)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitions$2$adapted(RDD.scala:858)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at
org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:623)
at
java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at
java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:829)
```
It works after disabling partial project with
`spark.gluten.sql.columnar.partial.project=false`.
### Spark version
Spark-3.5.x
### Spark configurations
_No response_
### System information
_No response_
### Relevant logs
```bash
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@gluten.apache.org.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@gluten.apache.org
For additional commands, e-mail: commits-h...@gluten.apache.org
