Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11514#discussion_r55117715
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala ---
@@ -101,15 +101,69 @@ private[sql] case class LogicalRDD(
private[sql] case class PhysicalRDD(
output: Seq[Attribute],
rdd: RDD[InternalRow],
- override val nodeName: String,
- override val metadata: Map[String, String] = Map.empty,
- isUnsafeRow: Boolean = false,
- override val outputPartitioning: Partitioning = UnknownPartitioning(0))
+ override val nodeName: String) extends LeafNode {
+
+ private[sql] override lazy val metrics = Map(
+ "numOutputRows" -> SQLMetrics.createLongMetric(sparkContext, "number
of output rows"))
+
+ protected override def doExecute(): RDD[InternalRow] = {
+ val numOutputRows = longMetric("numOutputRows")
+ rdd.mapPartitionsInternal { iter =>
+ val proj = UnsafeProjection.create(schema)
+ iter.map { r =>
+ numOutputRows += 1
+ proj(r)
+ }
+ }
+ }
+
+ override def simpleString: String = {
+ s"RDD $nodeName${output.mkString("[", ",", "]")}"
+ }
+}
--- End diff --
If a partitioning is UnknownPartitioning, the number is meaningless, I
think.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
