geoffreyclaude commented on code in PR #26242:
URL: https://github.com/apache/datafusion/pull/26242#discussion_r4347999719
##########
datafusion/physical-plan/src/sorts/sort.rs:
##########
@@ -728,6 +784,87 @@ impl ExternalSorter {
.build()
}
+ /// Sort runs concurrently, preserving their order for the merge's
equal-key ties.
+ async fn prepare_sort_runs(
+ &mut self,
+ runs: Vec<RecordBatch>,
+ concurrency: &SortConcurrency,
+ ) -> Result<Vec<SendableRecordBatchStream>> {
+ let run_count = runs.len();
+ let (sizes, shared_input_size) = self.sort_run_sizes(&runs)?;
+ let shared_input =
+ shared_input_size.map(|size|
Arc::new(self.reservation.split(size)));
+ let jobs =
+ runs.into_iter()
+ .zip(sizes)
+ .enumerate()
+ .map(move |(index, (batch, size))| {
+ let reservation = self.reservation.split(size);
+ let sort = self.sort_run(batch, reservation,
shared_input.clone())?;
+ let permits = Arc::clone(&concurrency.permits);
+ Ok::<_, DataFusionError>(async move {
+ let stream = Self::prepare_sort_run(sort,
permits).await?;
+ Ok((index, stream))
+ })
+ });
+ // Ordered buffering would keep completed runs behind a slow earlier
run,
+ // filling the window and preventing new jobs from starting.
+ let jobs = futures::stream::iter(jobs)
+ .try_buffer_unordered(concurrency.per_partition_limit);
+ Self::collect_prepared_runs(run_count, jobs).await
+ }
+
+ /// Restore input order because the merge uses it to break equal-key ties.
Review Comment:
Agreed: I've updated the relevant comments in a new commit.
--
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]
