2010YOUY01 commented on code in PR #23657:
URL: https://github.com/apache/datafusion/pull/23657#discussion_r3638086781
##########
datafusion/physical-plan/src/aggregates/ordered_final_stream.rs:
##########
@@ -64,6 +119,135 @@ type OrderedFinalAggregateStateTransition = ControlFlow<
OrderedFinalAggregateState,
>;
+impl OrderedFinalSpillContext {
+ fn new(
+ agg: &AggregateExec,
+ context: &Arc<TaskContext>,
+ partition: usize,
+ batch_size: usize,
+ input_order_mode: &InputOrderMode,
+ spill_schema: &SchemaRef,
+ spill_metrics: SpillMetrics,
+ ) -> Result<Self> {
+ let group_schema = agg.group_by.group_schema(spill_schema)?;
+ let output_ordering = agg.cache.output_ordering();
+ let InputOrderMode::PartiallySorted(order_indices) = input_order_mode
else {
+ return internal_err!("Ordered final spill requires partially
ordered input");
+ };
+ let spill_indices = order_indices.iter().copied().chain(
+ (0..group_schema.fields().len()).filter(|idx|
!order_indices.contains(idx)),
+ );
+ let spill_sort_exprs = spill_indices.map(|idx| {
+ let field = group_schema.field(idx);
+ let output_expr = Column::new(field.name(), idx);
+ let sort_options = output_ordering
+ .and_then(|ordering| ordering.get_sort_options(&output_expr))
+ .unwrap_or_default();
+ PhysicalSortExpr::new(Arc::new(output_expr), sort_options)
+ });
+ let Some(spill_expr) = LexOrdering::new(spill_sort_exprs) else {
+ return internal_err!("Ordered final spill expression is empty");
+ };
+
+ let spill_manager = SpillManager::new(
+ context.runtime_env(),
+ spill_metrics,
+ Arc::clone(spill_schema),
+ )
+ .with_compression_type(context.session_config().spill_compression());
+
+ Ok(Self {
+ agg: agg.clone(),
+ context: Arc::clone(context),
+ partition,
+ batch_size,
+ spill_expr,
+ spill_manager,
+ spills: vec![],
+ })
+ }
+
+ fn has_spills(&self) -> bool {
+ !self.spills.is_empty()
+ }
+
+ /// Sort and spill the aggregated groups. Memory reservation should be
cleared
Review Comment:
added
--
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]
