Skip to content

[AURON #1656] Support to disable the scan timestamp for Parquet and ORC formats #1657

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
richox merged 8 commits into from
Nov 27, 2025
+34 −1
Merged

[AURON #1656] Support to disable the scan timestamp for Parquet and ORC formats #1657

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
fa1d2d1
Support to disable the scan timestamp for Parquet and ORC formats
cxzl25 Nov 23, 2025
d00fcb3
nested type
cxzl25 Nov 24, 2025
3284580
Update spark-extension/src/main/scala/org/apache/spark/sql/auron/Nati…
cxzl25 Nov 24, 2025
98b1464
Update spark-extension/src/main/scala/org/apache/spark/sql/auron/Nati…
cxzl25 Nov 24, 2025
a631ca4
use requiredSchema
cxzl25 Nov 24, 2025
bb6d54e
Update spark-extension/src/main/scala/org/apache/spark/sql/auron/Auro…
cxzl25 Nov 27, 2025
c88e7f8
Update spark-extension/src/main/scala/org/apache/spark/sql/auron/Auro…
cxzl25 Nov 27, 2025
f8d381c
table
cxzl25 Nov 27, 2025
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
22 changes: 21 additions & 1 deletion spark-extension/src/main/scala/org/apache/spark/sql/auron/AuronConverters.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ import org.apache.spark.Partition
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.internal.{config, Logging}
import org.apache.spark.sql.auron.AuronConvertStrategy.{childOrderingRequiredTag, convertibleTag, convertStrategyTag, convertToNonNativeTag, isNeverConvert, joinSmallerSideTag, neverConvertReasonTag}
import org.apache.spark.sql.auron.NativeConverters.{roundRobinTypeSupported, scalarTypeSupported, StubExpr}
import org.apache.spark.sql.auron.NativeConverters.{existTimestampType, roundRobinTypeSupported, scalarTypeSupported, StubExpr}
import org.apache.spark.sql.auron.util.AuronLogUtils.logDebugPlanConversion
import org.apache.spark.sql.catalyst.expressions.AggregateWindowFunction
import org.apache.spark.sql.catalyst.expressions.Alias
Expand Down Expand Up @@ -135,8 +135,12 @@ object AuronConverters extends Logging {
getBooleanConf("spark.auron.enable.data.writing", defaultValue = false)
def enableScanParquet: Boolean =
getBooleanConf("spark.auron.enable.scan.parquet", defaultValue = true)
def enableScanParquetTimestamp: Boolean =
getBooleanConf("spark.auron.enable.scan.parquet.timestamp", defaultValue = true)
def enableScanOrc: Boolean =
getBooleanConf("spark.auron.enable.scan.orc", defaultValue = true)
def enableScanOrcTimestamp: Boolean =
getBooleanConf("spark.auron.enable.scan.orc.timestamp", defaultValue = true)
def enableBroadcastExchange: Boolean =
getBooleanConf("spark.auron.enable.broadcastExchange", defaultValue = true)
def enableShuffleExechange: Boolean =
Expand Down Expand Up @@ -467,9 +471,25 @@ object AuronConverters extends Logging {
relation.fileFormat match {
case p if p.getClass.getName.endsWith("ParquetFileFormat") =>
assert(enableScanParquet)
if (!enableScanParquetTimestamp) {
assert(
!exec.requiredSchema.exists(e => existTimestampType(e.dataType)),
s"Parquet scan with timestamp type is not supported for table: ${tableIdentifier
Copy link
Copy Markdown
Contributor Author

@cxzl25 cxzl25 Nov 27, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

spark-sql (default)> set spark.auron.enable.scan.parquet.timestamp=false;
spark.auron.enable.scan.parquet.timestamp	false
Time taken: 0.054 seconds, Fetched 1 row(s)
spark-sql (default)> select * from t3_parquet ;
25/11/27 16:34:36 WARN AuronConverters: Falling back exec: FileSourceScanExec: assertion failed: Parquet scan with timestamp type is not supported for table: `spark_catalog`.`default`.`t3_parquet`. Set spark.auron.enable.scan.parquet.timestamp=true to enable timestamp support or remove timestamp columns from the query.

.getOrElse("unknown")}. " +
"Set spark.auron.enable.scan.parquet.timestamp=true to enable timestamp support " +
"or remove timestamp columns from the query.")
}
addRenameColumnsExec(Shims.get.createNativeParquetScanExec(exec))
case p if p.getClass.getName.endsWith("OrcFileFormat") =>
assert(enableScanOrc)
if (!enableScanOrcTimestamp) {
assert(
!exec.requiredSchema.exists(e => existTimestampType(e.dataType)),
s"ORC scan with timestamp type is not supported for tableIdentifier: ${tableIdentifier
.getOrElse("unknown")}. " +
"Set spark.auron.enable.scan.orc.timestamp=true to enable timestamp support " +
"or remove timestamp columns from the query.")
}
addRenameColumnsExec(Shims.get.createNativeOrcScanExec(exec))
case p =>
throw new NotImplementedError(
Expand Down
13 changes: 13 additions & 0 deletions spark-extension/src/main/scala/org/apache/spark/sql/auron/NativeConverters.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,19 @@ object NativeConverters extends Logging {
}
}

def existTimestampType(dataType: DataType): Boolean = {
dataType match {
case TimestampType =>
true
case at: ArrayType => existTimestampType(at.elementType)
case m: MapType =>
existTimestampType(m.keyType) || existTimestampType(m.valueType)
case s: StructType =>
s.fields.exists(e => existTimestampType(e.dataType))
case _ => false
}
}

def roundRobinTypeSupported(dataType: DataType): Boolean = dataType match {
case MapType(_, _, _) => false
case ArrayType(elementType, _) => roundRobinTypeSupported(elementType)
Expand Down
Loading