refactor: merge CoalesceAsyncExecInput into CoalesceBatches (#18540)

## Which issue does this PR close?

<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->

- Closes #18155.

## Rationale for this change

<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->

## What changes are included in this PR?

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

Merges the functionality of `CoalesceAsyncExecInput` into
`CoalesceBatches` to remove redundant optimizer logic and simplify batch
coalescing behavior.


## Are these changes tested?

<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
Behavior is covered by existing ``CoalesceBatches and optimizer tests.
## Are there any user-facing changes?
No
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

Author: Tim-53

datafusion/physical-optimizer/src/coalesce_async_exec_input.rs

@@ -22,12 +22,12 @@ use crate::PhysicalOptimizerRule;
 
 use std::sync::Arc;
 
-use datafusion_common::config::ConfigOptions;
 use datafusion_common::error::Result;
+use datafusion_common::{config::ConfigOptions, internal_err};
 use datafusion_physical_expr::Partitioning;
 use datafusion_physical_plan::{
-    coalesce_batches::CoalesceBatchesExec, filter::FilterExec, joins::HashJoinExec,
-    repartition::RepartitionExec, ExecutionPlan,
+    async_func::AsyncFuncExec, coalesce_batches::CoalesceBatchesExec, filter::FilterExec,
+    joins::HashJoinExec, repartition::RepartitionExec, ExecutionPlan,
 };
 
 use datafusion_common::tree_node::{Transformed, TransformedResult, TreeNode};
@@ -72,11 +72,27 @@ impl PhysicalOptimizerRule for CoalesceBatches {
                         )
                     })
                     .unwrap_or(false);
+
             if wrap_in_coalesce {
                 Ok(Transformed::yes(Arc::new(CoalesceBatchesExec::new(
                     plan,
                     target_batch_size,
                 ))))
+            } else if let Some(async_exec) = plan_any.downcast_ref::<AsyncFuncExec>() {
+                // Coalesce inputs to async functions to reduce number of async function invocations
+                let children = async_exec.children();
+                if children.len() != 1 {
+                    return internal_err!(
+                        "Expected AsyncFuncExec to have exactly one child"
+                    );
+                }
+
+                let coalesce_exec = Arc::new(CoalesceBatchesExec::new(
+                    Arc::clone(children[0]),
+                    target_batch_size,
+                ));
+                let new_plan = plan.with_new_children(vec![coalesce_exec])?;
+                Ok(Transformed::yes(new_plan))
             } else {
                 Ok(Transformed::no(plan))
             }

datafusion/physical-optimizer/src/coalesce_batches.rs

@@ -28,7 +28,6 @@
 #![cfg_attr(test, allow(clippy::needless_pass_by_value))]
 
 pub mod aggregate_statistics;
-pub mod coalesce_async_exec_input;
 pub mod coalesce_batches;
 pub mod combine_partial_final_agg;
 pub mod enforce_distribution;

datafusion/physical-optimizer/src/lib.rs

@@ -36,7 +36,6 @@ use crate::sanity_checker::SanityCheckPlan;
 use crate::topk_aggregation::TopKAggregation;
 use crate::update_aggr_exprs::OptimizeAggregateOrder;
 
-use crate::coalesce_async_exec_input::CoalesceAsyncExecInput;
 use crate::limit_pushdown_past_window::LimitPushPastWindows;
 use datafusion_common::config::ConfigOptions;
 use datafusion_common::Result;
@@ -123,7 +122,6 @@ impl PhysicalOptimizer {
             // The CoalesceBatches rule will not influence the distribution and ordering of the
             // whole plan tree. Therefore, to avoid influencing other rules, it should run last.
             Arc::new(CoalesceBatches::new()),
-            Arc::new(CoalesceAsyncExecInput::new()),
             // Remove the ancillary output requirement operator since we are done with the planning
             // phase.
             Arc::new(OutputRequirements::new_remove_mode()),

datafusion/physical-optimizer/src/optimizer.rs

@@ -238,7 +238,6 @@ physical_plan after EnforceSorting SAME TEXT AS ABOVE
 physical_plan after OptimizeAggregateOrder SAME TEXT AS ABOVE
 physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
 physical_plan after coalesce_batches SAME TEXT AS ABOVE
-physical_plan after coalesce_async_exec_input SAME TEXT AS ABOVE
 physical_plan after OutputRequirements DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/example.csv]]}, projection=[a, b, c], file_type=csv, has_header=true
 physical_plan after LimitAggregation SAME TEXT AS ABOVE
 physical_plan after LimitPushPastWindows SAME TEXT AS ABOVE
@@ -317,7 +316,6 @@ physical_plan after EnforceSorting SAME TEXT AS ABOVE
 physical_plan after OptimizeAggregateOrder SAME TEXT AS ABOVE
 physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
 physical_plan after coalesce_batches SAME TEXT AS ABOVE
-physical_plan after coalesce_async_exec_input SAME TEXT AS ABOVE
 physical_plan after OutputRequirements
 01)GlobalLimitExec: skip=0, fetch=10, statistics=[Rows=Exact(8), Bytes=Exact(671), [(Col[0]:),(Col[1]:),(Col[2]:),(Col[3]:),(Col[4]:),(Col[5]:),(Col[6]:),(Col[7]:),(Col[8]:),(Col[9]:),(Col[10]:)]]
 02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/parquet-testing/data/alltypes_plain.parquet]]}, projection=[id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col, double_col, date_string_col, string_col, timestamp_col], limit=10, file_type=parquet, statistics=[Rows=Exact(8), Bytes=Exact(671), [(Col[0]:),(Col[1]:),(Col[2]:),(Col[3]:),(Col[4]:),(Col[5]:),(Col[6]:),(Col[7]:),(Col[8]:),(Col[9]:),(Col[10]:)]]
@@ -362,7 +360,6 @@ physical_plan after EnforceSorting SAME TEXT AS ABOVE
 physical_plan after OptimizeAggregateOrder SAME TEXT AS ABOVE
 physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
 physical_plan after coalesce_batches SAME TEXT AS ABOVE
-physical_plan after coalesce_async_exec_input SAME TEXT AS ABOVE
 physical_plan after OutputRequirements
 01)GlobalLimitExec: skip=0, fetch=10
 02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/parquet-testing/data/alltypes_plain.parquet]]}, projection=[id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col, double_col, date_string_col, string_col, timestamp_col], limit=10, file_type=parquet
@@ -602,7 +599,6 @@ physical_plan after EnforceSorting SAME TEXT AS ABOVE
 physical_plan after OptimizeAggregateOrder SAME TEXT AS ABOVE
 physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
 physical_plan after coalesce_batches SAME TEXT AS ABOVE
-physical_plan after coalesce_async_exec_input SAME TEXT AS ABOVE
 physical_plan after OutputRequirements DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/example.csv]]}, projection=[a, b, c], file_type=csv, has_header=true
 physical_plan after LimitAggregation SAME TEXT AS ABOVE
 physical_plan after LimitPushPastWindows SAME TEXT AS ABOVE