Skip to content

[AURON #1834] Support DataSourceScan metrics #1835

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 1 commit into from
Jan 7, 2026
Merged

[AURON #1834] Support DataSourceScan metrics #1835

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
21 changes: 17 additions & 4 deletions ...n/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeFileSourceScanBase.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,11 +32,11 @@ import org.apache.spark.sql.auron.Shims
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.expressions.Literal
import org.apache.spark.sql.catalyst.plans.physical.Partitioning
import org.apache.spark.sql.execution.{FileSourceScanExec, LeafExecNode, SparkPlan}
import org.apache.spark.sql.execution.{FileSourceScanExec, LeafExecNode, SparkPlan, SQLExecution}
import org.apache.spark.sql.execution.datasources.FilePartition
import org.apache.spark.sql.execution.datasources.FileScanRDD
import org.apache.spark.sql.execution.datasources.PartitionedFile
import org.apache.spark.sql.execution.metric.SQLMetric
import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics}
import org.apache.spark.sql.types.{DecimalType, NullType, StructField, StructType}
import org.apache.spark.util.SerializableConfiguration

Expand All @@ -48,18 +48,31 @@ abstract class NativeFileSourceScanBase(basedFileScan: FileSourceScanExec)
with NativeSupports {

override lazy val metrics: Map[String, SQLMetric] =
NativeHelper.getNativeFileScanMetrics(sparkContext)
NativeHelper.getNativeFileScanMetrics(sparkContext) ++ Seq(
"numPartitions" -> SQLMetrics.createMetric(sparkContext, "Native.partitions_read"),
"numFiles" -> SQLMetrics.createMetric(sparkContext, "Native.files_read"))

override val output: Seq[Attribute] = basedFileScan.output
override val outputPartitioning: Partitioning = basedFileScan.outputPartitioning

protected val inputFileScanRDD: FileScanRDD = {
MethodUtils.invokeMethod(basedFileScan, true, "prepare")
MethodUtils.invokeMethod(basedFileScan, true, "waitForSubqueries")
basedFileScan.inputRDDs().head match {
val fileScanRDD = basedFileScan.inputRDDs().head match {
case rdd: FileScanRDD => rdd
case rdd: MapPartitionsRDD[_, _] => rdd.prev.asInstanceOf[FileScanRDD]
}
val numPartitions = fileScanRDD.filePartitions.length
metrics("numPartitions").add(numPartitions)
val numFiles = fileScanRDD.filePartitions.foldLeft(0L)(_ + _.files.length)
metrics("numFiles").add(numFiles)
val executionId = sparkContext.getLocalProperty(SQLExecution.EXECUTION_ID_KEY)
SQLMetrics.postDriverMetricUpdates(
sparkContext,
executionId,
Seq(metrics("numPartitions"), metrics("numFiles")))

fileScanRDD
}

private val partitionSchema = basedFileScan.relation.partitionSchema
Expand Down
Loading