parthchandra commented on code in PR #3349:
URL: https://github.com/apache/datafusion-comet/pull/3349#discussion_r2771797648
##########
spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergNativeScanExec.scala:
##########
@@ -95,17 +216,26 @@ case class CometIcebergNativeScanExec(
}
}
- private val capturedMetricValues: Seq[MetricValue] = {
- originalPlan.metrics
- .filterNot { case (name, _) =>
- // Filter out metrics that are now runtime metrics incremented on the
native side
- name == "numOutputRows" || name == "numDeletes" || name == "numSplits"
- }
- .map { case (name, metric) =>
- val mappedType = mapMetricType(name, metric.metricType)
- MetricValue(name, metric.value, mappedType)
- }
- .toSeq
+ @transient private lazy val capturedMetricValues: Seq[MetricValue] = {
+ // Guard against null originalPlan (from doCanonicalize)
+ if (originalPlan == null) {
+ Seq.empty
+ } else {
+ // Force serializedPartitionData evaluation first - this triggers
serializePartitions which
+ // accesses inputRDD, which triggers Iceberg planning and populates
metrics
+ val _ = serializedPartitionData
Review Comment:
Is this the best place for this? should this be in `doExecuteColumnar`
instead?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
