Skip to content

[SPARK-43087][SQL] Support coalesce buckets in join in AQE #40731

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wangyum wants to merge 2 commits into from
Closed

[SPARK-43087][SQL] Support coalesce buckets in join in AQE #40731

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4bbf7e3
Bucketed read in AQE
wangyum Apr 10, 2023
854b30f
Update BucketedReadSuite.scala
wangyum Apr 11, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ import org.apache.spark.sql.catalyst.util.sideBySide
import org.apache.spark.sql.errors.QueryExecutionErrors
import org.apache.spark.sql.execution._
import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec._
import org.apache.spark.sql.execution.bucketing.DisableUnnecessaryBucketedScan
import org.apache.spark.sql.execution.bucketing.{CoalesceBucketsInJoin, DisableUnnecessaryBucketedScan}
import org.apache.spark.sql.execution.columnar.InMemoryTableScanExec
import org.apache.spark.sql.execution.exchange._
import org.apache.spark.sql.execution.ui.{SparkListenerSQLAdaptiveExecutionUpdate, SparkListenerSQLAdaptiveSQLMetricUpdates, SQLPlanMetric}
Expand Down Expand Up @@ -118,6 +118,7 @@ case class AdaptiveSparkPlanExec(
val ensureRequirements =
EnsureRequirements(requiredDistribution.isDefined, requiredDistribution)
Seq(
CoalesceBucketsInJoin,
RemoveRedundantProjects,
ensureRequirements,
AdjustShuffleExchangePosition,
Expand Down
9 changes: 4 additions & 5 deletions sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ import org.apache.spark.sql.catalyst.expressions
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.physical.HashPartitioning
import org.apache.spark.sql.execution.{FileSourceScanExec, SortExec, SparkPlan}
import org.apache.spark.sql.execution.adaptive.{AdaptiveSparkPlanExec, AdaptiveSparkPlanHelper, DisableAdaptiveExecution}
import org.apache.spark.sql.execution.adaptive.{AdaptiveSparkPlanExec, AdaptiveSparkPlanHelper}
import org.apache.spark.sql.execution.datasources.BucketingUtils
import org.apache.spark.sql.execution.exchange.ShuffleExchangeExec
import org.apache.spark.sql.execution.joins.SortMergeJoinExec
Expand Down Expand Up @@ -1010,8 +1010,7 @@ abstract class BucketedReadSuite extends QueryTest with SQLTestUtils with Adapti
}
}

test("bucket coalescing is applied when join expressions match with partitioning expressions",
DisableAdaptiveExecution("Expected shuffle num mismatched")) {
test("bucket coalescing is applied when join expressions match with partitioning expressions") {
withTable("t1", "t2") {
df1.write.format("parquet").bucketBy(8, "i", "j").saveAsTable("t1")
df2.write.format("parquet").bucketBy(4, "i", "j").saveAsTable("t2")
Expand All @@ -1024,10 +1023,10 @@ abstract class BucketedReadSuite extends QueryTest with SQLTestUtils with Adapti
expectedNumShuffles: Int,
expectedCoalescedNumBuckets: Option[Int]): Unit = {
val plan = sql(query).queryExecution.executedPlan
val shuffles = plan.collect { case s: ShuffleExchangeExec => s }
val shuffles = collect(plan) { case s: ShuffleExchangeExec => s }
assert(shuffles.length == expectedNumShuffles)

val scans = plan.collect {
val scans = collect(plan) {
case f: FileSourceScanExec if f.optionalNumCoalescedBuckets.isDefined => f
}
if (expectedCoalescedNumBuckets.isDefined) {
Expand Down