Skip to content

[SPARK-32509][SQL] Ignore unused DPP True Filter in Canonicalization #29318

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
prakharjain09 wants to merge 4 commits into from
Closed

[SPARK-32509][SQL] Ignore unused DPP True Filter in Canonicalization #29318

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
dbcb450
Ignore unused DPP True Filter in Canonicalization
prakharjain09 Jul 31, 2020
6cb0703
remove unnecessary imports
prakharjain09 Jul 31, 2020
b1f8ba8
address review comments
prakharjain09 Aug 1, 2020
9947c35
Merge remote-tracking branch 'oss/master' into SPARK-32509_df_reuse
prakharjain09 Aug 1, 2020
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
10 changes: 9 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -608,12 +608,20 @@ case class FileSourceScanExec(
new FileScanRDD(fsRelation.sparkSession, readFile, partitions)
}

// Filters unused DynamicPruningExpression expressions - one which has been replaced
// with DynamicPruningExpression(Literal.TrueLiteral) during Physical Planning
private def filterUnusedDynamicPruningExpressions(
predicates: Seq[Expression]): Seq[Expression] = {
predicates.filterNot(_ == DynamicPruningExpression(Literal.TrueLiteral))
}

override def doCanonicalize(): FileSourceScanExec = {
FileSourceScanExec(
relation,
output.map(QueryPlan.normalizeExpressions(_, output)),
requiredSchema,
QueryPlan.normalizePredicates(partitionFilters, output),
QueryPlan.normalizePredicates(
filterUnusedDynamicPruningExpressions(partitionFilters), output),
optionalBucketSet,
optionalNumCoalescedBuckets,
QueryPlan.normalizePredicates(dataFilters, output),
Expand Down
24 changes: 24 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1240,6 +1240,30 @@ abstract class DynamicPartitionPruningSuiteBase
}
}

test("SPARK-32509: Unused Dynamic Pruning filter shouldn't affect " +
"canonicalization and exchange reuse") {
withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_REUSE_BROADCAST_ONLY.key -> "true") {
withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") {
val df = sql(
""" WITH view1 as (
| SELECT f.store_id FROM fact_stats f WHERE f.units_sold = 70
| )
|
| SELECT * FROM view1 v1 join view1 v2 WHERE v1.store_id = v2.store_id
""".stripMargin)

checkPartitionPruningPredicate(df, false, false)
val reuseExchangeNodes = df.queryExecution.executedPlan.collect {
case se: ReusedExchangeExec => se
}
assert(reuseExchangeNodes.size == 1, "Expected plan to contain 1 ReusedExchangeExec " +
s"nodes. Found ${reuseExchangeNodes.size}")

checkAnswer(df, Row(15, 15) :: Nil)
}
}
}

test("Plan broadcast pruning only when the broadcast can be reused") {
Given("dynamic pruning filter on the build side")
withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_REUSE_BROADCAST_ONLY.key -> "true") {
Expand Down