2010YOUY01 commented on code in PR #23657:
URL: https://github.com/apache/datafusion/pull/23657#discussion_r3637263902
##########
datafusion/physical-plan/src/aggregates/ordered_final_stream.rs:
##########
@@ -23,22 +23,44 @@ use std::task::{Context, Poll};
use arrow::datatypes::SchemaRef;
use arrow::record_batch::RecordBatch;
-use datafusion_common::Result;
+use datafusion_common::{DataFusionError, Result, internal_err};
use datafusion_execution::TaskContext;
use datafusion_execution::memory_pool::{MemoryConsumer, MemoryReservation};
+use datafusion_physical_expr::PhysicalSortExpr;
+use datafusion_physical_expr::expressions::Column;
+use datafusion_physical_expr_common::sort_expr::LexOrdering;
use futures::stream::{Stream, StreamExt};
use super::AggregateExec;
use super::aggregate_hash_table::{FinalMarker, OrderedAggregateTable};
+use super::group_values::GroupByMetrics;
use crate::aggregates::AggregateMode;
use crate::metrics::{BaselineMetrics, RecordOutput, SpillMetrics};
+use crate::sorts::IncrementalSortIterator;
+use crate::sorts::streaming_merge::{SortedSpillFile, StreamingMergeBuilder};
+use crate::spill::spill_manager::SpillManager;
use crate::stream::EmptyRecordBatchStream;
use crate::{InputOrderMode, RecordBatchStream, SendableRecordBatchStream};
/// Final aggregate stream for `InputOrderMode::Sorted` and
/// `InputOrderMode::PartiallySorted`.
///
/// See comments at [`super::ordered_partial_stream`] for details.
+///
+/// # Spilling
+///
+/// This section is only for implementation notes, for background, see
[`super::ordered_partial_stream`]
Review Comment:
[ae022e6](https://github.com/apache/datafusion/pull/23657/commits/ae022e6f613be0760f1426b36319749adf80cb7b)
##########
datafusion/physical-plan/src/aggregates/ordered_final_stream.rs:
##########
@@ -47,13 +69,46 @@ pub(crate) struct OrderedFinalAggregateStream {
state: Option<OrderedFinalAggregateState>,
}
+/// Spill configuration and accumulated runs for partially ordered final
+/// aggregation. Each file is one fully group-key-sorted intermediate-state
run;
Review Comment:
[d8fc050](https://github.com/apache/datafusion/pull/23657/commits/d8fc0509f9e215ffcc9d58e84fa4cd24ed0a979e)
--
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]
