Skip to content

Apache DataFusion SQL Query Engine

doc: More comments on GroupedHashAggregateStream refactor (#23200)

Yongting Youd111dd037e73
diff --git a/datafusion/physical-plan/src/aggregates/mod.rs b/datafusion/physical-plan/src/aggregates/mod.rs
index 08468bffc0..4f5b893578 100644
--- a/datafusion/physical-plan/src/aggregates/mod.rs
+++ b/datafusion/physical-plan/src/aggregates/mod.rs
@@ -1009,6 +1009,13 @@ impl AggregateExec {
));
}
+ // `GroupedHashAggregateStream` is being incrementally refactored. See the
+ // tracking issue for details.
+ //
+ // New features and improvements should go directly into the new implementation.
+ // Please coordinate through the tracking issue.
+ //
+ // Issue: <https://github.com/apache/datafusion/issues/22710>
if context
.session_config()
.options()
@@ -1028,7 +1035,7 @@ impl AggregateExec {
}
}
- // grouping by something else and we need to just materialize all results
+ // Execution paths that have not been migrated use the fallback implementation
Ok(StreamType::GroupedHash(GroupedHashAggregateStream::new(
self, context, partition,
)?))
diff --git a/datafusion/physical-plan/src/aggregates/row_hash.rs b/datafusion/physical-plan/src/aggregates/row_hash.rs
index 5cd7f508af..a4d19b0f7d 100644
--- a/datafusion/physical-plan/src/aggregates/row_hash.rs
+++ b/datafusion/physical-plan/src/aggregates/row_hash.rs
@@ -132,6 +132,16 @@ enum OutOfMemoryMode {
/// HashTable based Grouping Aggregator
///
+/// # Development Note
+///
+/// This implementation is being incrementally refactored. See the tracking issue
+/// for details.
+///
+/// New features and improvements should go directly into the new implementation.
+/// Please coordinate through the tracking issue.
+///
+/// Issue: <https://github.com/apache/datafusion/issues/22710>
+///
/// # Design Goals
///
/// This structure is designed so that updating the aggregates can be