Skip to content
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

Jump to bottom

fix: Fallback to Spark if scan has meta columns #997

Merged
merged 1 commit into from
Oct 7, 2024
Merged

fix: Fallback to Spark if scan has meta columns #997

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
15 changes: 14 additions & 1 deletion spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,11 +25,12 @@ import org.apache.spark.SparkConf
import org.apache.spark.internal.Logging
import org.apache.spark.network.util.ByteUnit
import org.apache.spark.sql.{SparkSession, SparkSessionExtensions}
import org.apache.spark.sql.catalyst.expressions.{Divide, DoubleLiteral, EqualNullSafe, EqualTo, Expression, FloatLiteral, GreaterThan, GreaterThanOrEqual, KnownFloatingPointNormalized, LessThan, LessThanOrEqual, NamedExpression, PlanExpression, Remainder}
import org.apache.spark.sql.catalyst.expressions.{Attribute, Divide, DoubleLiteral, EqualNullSafe, EqualTo, Expression, FloatLiteral, GreaterThan, GreaterThanOrEqual, KnownFloatingPointNormalized, LessThan, LessThanOrEqual, NamedExpression, PlanExpression, Remainder}
import org.apache.spark.sql.catalyst.expressions.aggregate.{Final, Partial}
import org.apache.spark.sql.catalyst.optimizer.NormalizeNaNAndZero
import org.apache.spark.sql.catalyst.rules.Rule
import org.apache.spark.sql.catalyst.trees.TreeNode
import org.apache.spark.sql.catalyst.util.MetadataColumnHelper
import org.apache.spark.sql.comet._
import org.apache.spark.sql.comet.execution.shuffle.{CometColumnarShuffle, CometNativeShuffle, CometShuffleExchangeExec, CometShuffleManager}
import org.apache.spark.sql.comet.util.Utils
Expand Down Expand Up @@ -101,7 +102,19 @@ class CometSparkSessionExtensions
def isDynamicPruningFilter(e: Expression): Boolean =
e.exists(_.isInstanceOf[PlanExpression[_]])

def hasMetadataCol(plan: SparkPlan): Boolean = {
plan.expressions.exists(_.exists {
case a: Attribute =>
a.isMetadataCol
case _ => false
})
}

plan.transform {
case scan if hasMetadataCol(scan) =>
withInfo(scan, "Metadata column is not supported")
scan

case scanExec: FileSourceScanExec
if COMET_DPP_FALLBACK_ENABLED.get() &&
scanExec.partitionFilters.exists(isDynamicPruningFilter) =>
Expand Down
Loading