From ccb32e7c0a26eda65c73049a467313fcb4d87431 Mon Sep 17 00:00:00 2001
From: zhuqi-lucas <821684824@qq.com>
Date: Fri, 1 Aug 2025 17:28:52 +0800
Subject: [PATCH 1/2] Port arrow-rs optimization for get_buffer_memory_size for
 gc string view

---
 datafusion/physical-plan/src/coalesce/mod.rs | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/datafusion/physical-plan/src/coalesce/mod.rs b/datafusion/physical-plan/src/coalesce/mod.rs
index 0eca27f8e40e0..b4c55d58bec1b 100644
--- a/datafusion/physical-plan/src/coalesce/mod.rs
+++ b/datafusion/physical-plan/src/coalesce/mod.rs
@@ -240,7 +240,8 @@ fn gc_string_view_batch(batch: &RecordBatch) -> RecordBatch {
                     }
                 })
                 .sum();
-            let actual_buffer_size = s.get_buffer_memory_size();
+            let actual_buffer_size =
+                s.data_buffers().iter().map(|b| b.capacity()).sum::<usize>();
 
             // Re-creating the array copies data and can be time consuming.
             // We only do it if the array is sparse

From cddce851ea13369f69398ec9dc871dff2545a481 Mon Sep 17 00:00:00 2001
From: zhuqi-lucas <821684824@qq.com>
Date: Fri, 1 Aug 2025 17:32:41 +0800
Subject: [PATCH 2/2] add comments and fast path

---
 datafusion/physical-plan/src/coalesce/mod.rs | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/datafusion/physical-plan/src/coalesce/mod.rs b/datafusion/physical-plan/src/coalesce/mod.rs
index b4c55d58bec1b..8e0ba072b7467 100644
--- a/datafusion/physical-plan/src/coalesce/mod.rs
+++ b/datafusion/physical-plan/src/coalesce/mod.rs
@@ -228,6 +228,12 @@ fn gc_string_view_batch(batch: &RecordBatch) -> RecordBatch {
             let Some(s) = c.as_string_view_opt() else {
                 return Arc::clone(c);
             };
+
+            // Fast path: if the data buffers are empty, we can return the original array
+            if s.data_buffers().is_empty() {
+                return Arc::clone(c);
+            }
+
             let ideal_buffer_size: usize = s
                 .views()
                 .iter()
@@ -240,6 +246,9 @@ fn gc_string_view_batch(batch: &RecordBatch) -> RecordBatch {
                     }
                 })
                 .sum();
+
+            // We don't use get_buffer_memory_size here, because gc is for the contents of the
+            // data buffers, not views and nulls.
             let actual_buffer_size =
                 s.data_buffers().iter().map(|b| b.capacity()).sum::<usize>();