alamb commented on code in PR #23657:
URL: https://github.com/apache/datafusion/pull/23657#discussion_r3626976863
##########
datafusion/physical-plan/src/aggregates/ordered_final_stream.rs:
##########
@@ -180,36 +497,183 @@ impl OrderedFinalAggregateStream {
next_state,
))
}
+ // Can't do early emit, continue aggregating.
Ok(None) => {
- // Ordered variant doesn't support memory-limited
- // execution, so it errors when memory reservation
fails.
- if let Err(e) =
self.reservation.try_resize(table.memory_size()) {
- return ControlFlow::Break((
- Poll::Ready(Some(Err(e))),
- OrderedFinalAggregateState::ReadingInput {
table },
- ));
- }
-
- // Can't do early emit, continue aggregating.
ControlFlow::Continue(OrderedFinalAggregateState::ReadingInput {
table,
+ spill_context,
})
}
Err(e) => ControlFlow::Break((
Poll::Ready(Some(Err(e))),
- OrderedFinalAggregateState::ReadingInput { table },
+ OrderedFinalAggregateState::ReadingInput {
+ table,
+ spill_context,
+ },
)),
}
}
Poll::Ready(Some(Err(e))) => ControlFlow::Break((
Poll::Ready(Some(Err(e))),
- OrderedFinalAggregateState::ReadingInput { table },
+ OrderedFinalAggregateState::ReadingInput {
+ table,
+ spill_context,
+ },
)),
Poll::Ready(None) => {
self.close_input();
- table.input_done();
-
ControlFlow::Continue(OrderedFinalAggregateState::DrainingFinal { table })
+ match spill_context {
+ Some(spill_context) if spill_context.has_spills() => {
+ ControlFlow::Continue(
+ OrderedFinalAggregateState::PreparingMergeInput {
+ table,
+ spill_context,
+ },
+ )
+ }
+ _ => {
+ table.input_done();
+ ControlFlow::Continue(
+ OrderedFinalAggregateState::ProducingOutput {
table },
+ )
+ }
+ }
+ }
+ }
+ }
+
+ /// Sorts and spills one complete in-memory state run, then resumes input.
+ ///
+ /// See comments at `poll_next()` for details.
+ ///
+ /// Returns the next operator state with control flow decision.
+ fn handle_spilling(
+ &mut self,
+ original_state: OrderedFinalAggregateState,
+ ) -> OrderedFinalAggregateStateTransition {
+ let OrderedFinalAggregateState::Spilling {
+ mut table,
+ mut spill_context,
+ } = original_state
+ else {
+ unreachable!("expected spilling state")
+ };
+
+ let elapsed_compute = self.baseline_metrics.elapsed_compute().clone();
+ let timer = elapsed_compute.timer();
+ let mut result = spill_context.spill_table(&mut table);
+
+ // Spilling shrinks the aggregate table and releases its accumulated
+ // memory. Update the reservation accordingly.
+ if self.reservation.try_resize(table.memory_size()).is_err() {
+ // Fold spill error and reservation error into one
+ result = internal_err!("Reservation after spilling should succeed")
Review Comment:
I was confused for a while as I thought this could be a normal error (e,g,
happen if other plans are allocating from the memory manager at the same time).
In other words, I think we should just propagte the "resources exhausted" error
here
However, i see now this is trying to *shrink* the size of the reservation,
which will only fail on underflow (bad accounting)
Maybe we could clarify the message here from `"Reservation after spilling
should succeed"` to `"Decreasing allocation after spilling should succeed"`"
and also icnlude the errir itself (for debugging) rather than just swalliowing
the error
--
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]
