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

[CORE] Add nativeFilters info for simpleString of scan #8169

Merged
merged 2 commits into from
Dec 9, 2024
Merged

[CORE] Add nativeFilters info for simpleString of scan #8169

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7f89544
[CORE] Add nativeFilters info for simpleString of scan
zml1206 Dec 6, 2024
162ecc3
update
zml1206 Dec 9, 2024
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: 10 additions & 0 deletions gluten-substrait/src/main/scala/org/apache/gluten/execution/BatchScanExecTransformer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ import org.apache.gluten.utils.FileIndexUtil
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.util.truncatedString
import org.apache.spark.sql.connector.catalog.Table
import org.apache.spark.sql.connector.read.{InputPartition, Scan}
import org.apache.spark.sql.execution.datasources.v2.{BatchScanExecShim, FileScan}
Expand Down Expand Up @@ -169,4 +170,13 @@ abstract class BatchScanExecTransformerBase(
case "ClickHouseScan" => ReadFileFormat.MergeTreeReadFormat
case _ => ReadFileFormat.UnknownFormat
}

override def simpleString(maxFields: Int): String = {
val truncatedOutputString = truncatedString(output, "[", ", ", "]", maxFields)
val runtimeFiltersString = s"RuntimeFilters: ${runtimeFilters.mkString("[", ",", "]")}"
val nativeFiltersString = s"nativeFilters: ${filterExprs().mkString("[", ",", "]")}"
Copy link
Member

Choose a reason for hiding this comment

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

Nit: Do we prefer NativeFilters than nativeFilters?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Good catch, thank you.

val result = s"$nodeName$truncatedOutputString ${scan.description()}" +
s" $runtimeFiltersString $nativeFiltersString"
redact(result)
}
}
15 changes: 15 additions & 0 deletions ...-substrait/src/main/scala/org/apache/gluten/execution/FileSourceScanExecTransformer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,13 +26,16 @@ import org.apache.gluten.utils.FileIndexUtil
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference, Expression, PlanExpression}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.util.truncatedString
import org.apache.spark.sql.connector.read.InputPartition
import org.apache.spark.sql.execution.FileSourceScanExecShim
import org.apache.spark.sql.execution.datasources.HadoopFsRelation
import org.apache.spark.sql.execution.metric.SQLMetric
import org.apache.spark.sql.types.StructType
import org.apache.spark.util.collection.BitSet

import org.apache.commons.lang3.StringUtils

case class FileSourceScanExecTransformer(
@transient override val relation: HadoopFsRelation,
override val output: Seq[Attribute],
Expand Down Expand Up @@ -190,6 +193,18 @@ abstract class FileSourceScanExecTransformerBase(
case "CSVFileFormat" => ReadFileFormat.TextReadFormat
case _ => ReadFileFormat.UnknownFormat
}

override def simpleString(maxFields: Int): String = {
val metadataEntries = metadata.toSeq.sorted.map {
case (key, value) =>
key + ": " + StringUtils.abbreviate(redact(value), maxMetadataValueLength)
}
val metadataStr = truncatedString(metadataEntries, " ", ", ", "", maxFields)
val nativeFiltersString = s"nativeFilters: ${filterExprs().mkString("[", ",", "]")}"
Copy link
Member

Choose a reason for hiding this comment

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

ditto

redact(
s"$nodeNamePrefix$nodeName${truncatedString(output, "[", ",", "]", maxFields)}$metadataStr" +
s" $nativeFiltersString")
}
}

object FileSourceScanExecTransformerBase {
Expand Down
9 changes: 1 addition & 8 deletions .../src/main/scala/org/apache/spark/sql/execution/datasources/v2/AbstractBatchScanExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.physical.{KeyGroupedPartitioning, Partitioning, SinglePartition}
import org.apache.spark.sql.catalyst.util.{truncatedString, InternalRowComparableWrapper}
import org.apache.spark.sql.catalyst.util.InternalRowComparableWrapper
import org.apache.spark.sql.connector.catalog.Table
import org.apache.spark.sql.connector.read._
import org.apache.spark.sql.internal.SQLConf
Expand Down Expand Up @@ -252,13 +252,6 @@ abstract class AbstractBatchScanExec(
rdd
}

override def simpleString(maxFields: Int): String = {
val truncatedOutputString = truncatedString(output, "[", ", ", "]", maxFields)
val runtimeFiltersString = s"RuntimeFilters: ${runtimeFilters.mkString("[", ",", "]")}"
val result = s"$nodeName$truncatedOutputString ${scan.description()} $runtimeFiltersString"
redact(result)
}

override def nodeName: String = {
s"BatchScanTransformer ${table.name()}".trim
}
Expand Down
Loading