Josh Rosen created SPARK-17142:
----------------------------------
Summary: Complex query triggers binding error in HashAggregateExec
Key: SPARK-17142
URL: https://issues.apache.org/jira/browse/SPARK-17142
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.1.0
Reporter: Josh Rosen
Priority: Blocker
The following example runs successfully on Spark 2.0.0 but fails in the current
master (as of b72bb62d421840f82d663c6b8e3922bd14383fbb, if not earlier):
{code}
spark.sql("set spark.sql.crossJoin.enabled=true")
sc.parallelize(Seq(0)).toDF("int_col_1").createOrReplaceTempView("table_4")
sc.parallelize(Seq(0)).toDF("bigint_col_2").createOrReplaceTempView("table_2")
val query = """
SELECT
((t2.int_col) + (t1.bigint_col_2)) + ((t2.int_col) + (t1.bigint_col_2)) AS
int_col_1
FROM table_2 t1
INNER JOIN (
SELECT
LEAST(IF(False, LAG(0) OVER (ORDER BY t2.int_col_1 DESC), -230), -991)
AS int_col,
(t2.int_col_1) + (t1.int_col_1) AS int_col_2,
(t1.int_col_1) + (t2.int_col_1) AS int_col_3,
t2.int_col_1
FROM
table_4 t1,
table_4 t2
GROUP BY
(t1.int_col_1) + (t2.int_col_1),
t2.int_col_1
) t2
WHERE (t2.int_col_3) NOT IN (t2.int_col, t2.int_col_1)
GROUP BY (t2.int_col) + (t1.bigint_col_2)
"""
sql(query).collect()
{code}
This fails with the following exception:
{code}
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: bigint_col_2#65
at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:88)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:87)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:278)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:322)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:320)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:322)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:320)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:322)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:320)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:268)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:87)
at
org.apache.spark.sql.execution.aggregate.HashAggregateExec$$anonfun$32.apply(HashAggregateExec.scala:455)
at
org.apache.spark.sql.execution.aggregate.HashAggregateExec$$anonfun$32.apply(HashAggregateExec.scala:454)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.immutable.List.map(List.scala:285)
at
org.apache.spark.sql.execution.aggregate.HashAggregateExec.generateResultCode(HashAggregateExec.scala:454)
at
org.apache.spark.sql.execution.aggregate.HashAggregateExec.doProduceWithKeys(HashAggregateExec.scala:538)
at
org.apache.spark.sql.execution.aggregate.HashAggregateExec.doProduce(HashAggregateExec.scala:145)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at
org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.aggregate.HashAggregateExec.produce(HashAggregateExec.scala:37)
at
org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309)
at
org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:226)
at
org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:273)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2226)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2576)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2225)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$collect$1.apply(Dataset.scala:2230)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$collect$1.apply(Dataset.scala:2230)
at org.apache.spark.sql.Dataset.withCallback(Dataset.scala:2589)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2230)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2206)
... 48 elided
Caused by: java.lang.RuntimeException: Couldn't find bigint_col_2#65 in [(-991
+ bigint_col_2#65)#84]
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:94)
at
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1$$anonfun$applyOrElse$1.apply(BoundAttribute.scala:88)
at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
... 110 more
{code}
Note that this error occurs during query execution, not during analysis or
physical planning.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
