wangyum opened a new issue, #10992:
URL: https://github.com/apache/incubator-gluten/issues/10992
### Backend
VL (Velox)
### Bug description
Spark version is 4.0. How to reproduce this issue:
```scala
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark
import java.util.Collections
import org.apache.gluten.config.GlutenConfig
import org.apache.spark.sql.connector.DistributionAndOrderingSuiteBase
import
org.apache.spark.sql.connector.catalog.functions.{UnboundBucketFunction,
UnboundDaysFunction, UnboundTruncateFunction, UnboundYearsFunction}
import org.apache.spark.sql.connector.catalog.{Identifier,
InMemoryTableCatalog}
import org.apache.spark.sql.connector.distributions.Distributions
import org.apache.spark.sql.{GlutenSQLTestsBaseTrait, GlutenTestsBaseTrait,
Row}
import org.apache.spark.sql.connector.expressions.Expressions.identity
import org.apache.spark.sql.connector.expressions.Transform
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.internal.SQLConf.{AUTO_BROADCASTJOIN_THRESHOLD,
V2_BUCKETING_ENABLED}
import org.apache.spark.sql.types.{FloatType, LongType, StringType,
StructType, TimestampType}
class MyKeyGroupedPartitioningSuite extends DistributionAndOrderingSuiteBase
with GlutenTestsBaseTrait {
private val functions = Seq(
UnboundYearsFunction,
UnboundDaysFunction,
UnboundBucketFunction,
UnboundTruncateFunction)
private var originalV2BucketingEnabled: Boolean = false
private var originalAutoBroadcastJoinThreshold: Long = -1
override def sparkConf: SparkConf = {
// Native SQL configs
super.sparkConf
.set(GlutenConfig.COLUMNAR_FORCE_SHUFFLED_HASH_JOIN_ENABLED.key,
"false")
.set("spark.sql.adaptive.enabled", "false")
.set("spark.sql.shuffle.partitions", "5")
GlutenSQLTestsBaseTrait.nativeSparkConf(super.sparkConf, warehouse)
}
override def beforeAll(): Unit = {
super.beforeAll()
originalV2BucketingEnabled = conf.getConf(V2_BUCKETING_ENABLED)
conf.setConf(V2_BUCKETING_ENABLED, true)
originalAutoBroadcastJoinThreshold =
conf.getConf(AUTO_BROADCASTJOIN_THRESHOLD)
conf.setConf(AUTO_BROADCASTJOIN_THRESHOLD, -1L)
conf.setConfString("spark.shuffle.manager",
"org.apache.spark.shuffle.sort.ColumnarShuffleManager")
conf.setConfString(GlutenConfig.COLUMNAR_FORCE_SHUFFLED_HASH_JOIN_ENABLED.key,
"false")
conf.setConfString("spark.sql.adaptive.enabled", "false")
conf.setConfString("spark.sql.shuffle.partitions", "5")
}
override def afterAll(): Unit = {
try {
super.afterAll()
} finally {
conf.setConf(V2_BUCKETING_ENABLED, originalV2BucketingEnabled)
conf.setConf(AUTO_BROADCASTJOIN_THRESHOLD,
originalAutoBroadcastJoinThreshold)
}
}
before {
functions.foreach { f =>
catalog.createFunction(Identifier.of(Array.empty, f.name()), f)
}
}
after {
catalog.clearTables()
catalog.clearFunctions()
}
private val emptyProps: java.util.Map[String, String] = {
Collections.emptyMap[String, String]
}
private val items: String = "items"
private val items_schema: StructType = new StructType()
.add("id", LongType)
.add("name", StringType)
.add("price", FloatType)
.add("arrive_time", TimestampType)
private val purchases: String = "purchases"
private val purchases_schema: StructType = new StructType()
.add("item_id", LongType)
.add("price", FloatType)
.add("time", TimestampType)
private def createTable(
table: String,
schema: StructType,
partitions: Array[Transform],
catalog: InMemoryTableCatalog = catalog): Unit = {
catalog.createTable(Identifier.of(Array("ns"), table),
schema, partitions, emptyProps, Distributions.unspecified(),
Array.empty, None, None,
numRowsPerSplit = 1)
}
test("SPARK-41471: shuffle one side: only one side reports partitioning") {
val items_partitions = Array(identity("id"))
createTable(items, items_schema, items_partitions)
sql(s"INSERT INTO testcat.ns.$items VALUES " +
"(1, 'aa', 40.0, cast('2020-01-01' as timestamp)), " +
"(3, 'bb', 10.0, cast('2020-01-01' as timestamp)), " +
"(4, 'cc', 15.5, cast('2020-02-01' as timestamp))")
createTable(purchases, purchases_schema, Array.empty)
sql(s"INSERT INTO testcat.ns.$purchases VALUES " +
"(1, 42.0, cast('2020-01-01' as timestamp)), " +
"(3, 19.5, cast('2020-02-01' as timestamp))")
Seq(true).foreach { shuffle =>
withSQLConf(SQLConf.V2_BUCKETING_SHUFFLE_ENABLED.key ->
shuffle.toString) {
val df = sql("SELECT id, name, i.price as purchase_price, p.price as
sale_price " +
s"FROM testcat.ns.$items i JOIN testcat.ns.$purchases p " +
"ON i.id = p.item_id ORDER BY id, purchase_price, sale_price")
df.explain(true)
checkAnswer(df, Seq(Row(1, "aa", 40.0, 42.0), Row(3, "bb", 10.0,
19.5)))
}
}
}
}
```
Exception:
```
keygroupedpartitioning(item_id#27L, 3, [1], [3], [4]) (of class
org.apache.spark.sql.catalyst.plans.physical.KeyGroupedPartitioning)
scala.MatchError: keygroupedpartitioning(item_id#27L, 3, [1], [3], [4]) (of
class org.apache.spark.sql.catalyst.plans.physical.KeyGroupedPartitioning)
at
org.apache.spark.sql.execution.utils.ExecUtil$.genShuffleDependency(ExecUtil.scala:165)
at
org.apache.gluten.backendsapi.velox.VeloxSparkPlanExecApi.genShuffleDependency(VeloxSparkPlanExecApi.scala:550)
at
org.apache.spark.sql.execution.ColumnarShuffleExchangeExec.columnarShuffleDependency$lzycompute(ColumnarShuffleExchangeExec.scala:92)
at
org.apache.spark.sql.execution.ColumnarShuffleExchangeExec.columnarShuffleDependency(ColumnarShuffleExchangeExec.scala:83)
at
org.apache.spark.sql.execution.ColumnarShuffleExchangeExec.doExecuteColumnar(ColumnarShuffleExchangeExec.scala:146)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$executeColumnar$1(SparkPlan.scala:228)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:252)
...
```
### Gluten version
main branch
### Spark version
None
### 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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
