Skip to content

[SPARK-45386][SQL]: Fix correctness issue with persist using StorageLevel.NONE on Dataset #43188

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

Merged
WeichenXu123 merged 3 commits into from
Oct 2, 2023
Merged

[SPARK-45386][SQL]: Fix correctness issue with persist using StorageLevel.NONE on Dataset #43188

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
08fd200
SPARK-45386: Fix correctness issue with StorageLevel.NONE
Sep 29, 2023
4434ebc
Move to CacheManager
Oct 1, 2023
e228dfd
Add comment
Oct 2, 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
4 changes: 3 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3833,7 +3833,9 @@ class Dataset[T] private[sql](
* @since 1.6.0
*/
def persist(newLevel: StorageLevel): this.type = {
sparkSession.sharedState.cacheManager.cacheQuery(this, None, newLevel)
if (newLevel != StorageLevel.NONE) {
sparkSession.sharedState.cacheManager.cacheQuery(this, None, newLevel)
}
this
}

Expand Down
6 changes: 6 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ import org.apache.spark.sql.functions._
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SharedSparkSession
import org.apache.spark.sql.types._
import org.apache.spark.storage.StorageLevel

case class TestDataPoint(x: Int, y: Double, s: String, t: TestDataPoint2)
case class TestDataPoint2(x: Int, s: String)
Expand Down Expand Up @@ -2597,6 +2598,11 @@ class DatasetSuite extends QueryTest
parameters = Map("cls" -> classOf[Array[Int]].getName))
}
}

test("SPARK-45386: persist with StorageLevel.NONE should give correct count") {
val ds = Seq(1, 2).toDS().persist(StorageLevel.NONE)
assert(ds.count() == 2)
}
}

class DatasetLargeResultCollectingSuite extends QueryTest
Expand Down