From 18e3113443bf4b35e220d4cd0e1ea6813719c01e Mon Sep 17 00:00:00 2001
From: ShiKaiWi <xykwei@gmail.com>
Date: Fri, 20 Sep 2024 23:48:13 +0800
Subject: [PATCH 1/2] Use `Arc<[Buffer]>` instead of raw `Vec<Buffer>` in
 `GenericByteViewArray` for faster `slice`

---
 arrow-array/src/array/byte_view_array.rs | 28 +++++++++++++++---------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/arrow-array/src/array/byte_view_array.rs b/arrow-array/src/array/byte_view_array.rs
index a155b6ab22e2..f9ce4d0d8772 100644
--- a/arrow-array/src/array/byte_view_array.rs
+++ b/arrow-array/src/array/byte_view_array.rs
@@ -114,7 +114,7 @@ use super::ByteArrayType;
 pub struct GenericByteViewArray<T: ByteViewType + ?Sized> {
     data_type: DataType,
     views: ScalarBuffer<u128>,
-    buffers: Vec<Buffer>,
+    buffers: Arc<[Buffer]>,
     phantom: PhantomData<T>,
     nulls: Option<NullBuffer>,
 }
@@ -178,7 +178,7 @@ impl<T: ByteViewType + ?Sized> GenericByteViewArray<T> {
         Ok(Self {
             data_type: T::DATA_TYPE,
             views,
-            buffers,
+            buffers: buffers.into(),
             nulls,
             phantom: Default::default(),
         })
@@ -191,14 +191,14 @@ impl<T: ByteViewType + ?Sized> GenericByteViewArray<T> {
     /// Safe if [`Self::try_new`] would not error
     pub unsafe fn new_unchecked(
         views: ScalarBuffer<u128>,
-        buffers: Vec<Buffer>,
+        buffers: impl Into<Arc<[Buffer]>>,
         nulls: Option<NullBuffer>,
     ) -> Self {
         Self {
             data_type: T::DATA_TYPE,
             phantom: Default::default(),
             views,
-            buffers,
+            buffers: buffers.into(),
             nulls,
         }
     }
@@ -208,7 +208,7 @@ impl<T: ByteViewType + ?Sized> GenericByteViewArray<T> {
         Self {
             data_type: T::DATA_TYPE,
             views: vec![0; len].into(),
-            buffers: vec![],
+            buffers: vec![].into(),
             nulls: Some(NullBuffer::new_null(len)),
             phantom: Default::default(),
         }
@@ -234,7 +234,7 @@ impl<T: ByteViewType + ?Sized> GenericByteViewArray<T> {
     }
 
     /// Deconstruct this array into its constituent parts
-    pub fn into_parts(self) -> (ScalarBuffer<u128>, Vec<Buffer>, Option<NullBuffer>) {
+    pub fn into_parts(self) -> (ScalarBuffer<u128>, Arc<[Buffer]>, Option<NullBuffer>) {
         (self.views, self.buffers, self.nulls)
     }
 
@@ -516,7 +516,7 @@ impl<T: ByteViewType + ?Sized> From<ArrayData> for GenericByteViewArray<T> {
         Self {
             data_type: T::DATA_TYPE,
             views,
-            buffers,
+            buffers: buffers.into(),
             nulls: value.nulls().cloned(),
             phantom: Default::default(),
         }
@@ -569,12 +569,20 @@ where
 }
 
 impl<T: ByteViewType + ?Sized> From<GenericByteViewArray<T>> for ArrayData {
-    fn from(mut array: GenericByteViewArray<T>) -> Self {
+    fn from(array: GenericByteViewArray<T>) -> Self {
         let len = array.len();
-        array.buffers.insert(0, array.views.into_inner());
+        let new_buffers = {
+            let mut buffers = Vec::with_capacity(array.buffers.len() + 1);
+            buffers.push(array.views.into_inner());
+            for buffer in array.buffers.iter() {
+                buffers.push(buffer.clone());
+            }
+            buffers
+        };
+
         let builder = ArrayDataBuilder::new(T::DATA_TYPE)
             .len(len)
-            .buffers(array.buffers)
+            .buffers(new_buffers)
             .nulls(array.nulls);
 
         unsafe { builder.build_unchecked() }

From 33eae4bb0b4ee83530eeec5a5e14adf376fc936f Mon Sep 17 00:00:00 2001
From: ShiKaiWi <xykwei@gmail.com>
Date: Sat, 21 Sep 2024 00:30:04 +0800
Subject: [PATCH 2/2] add benchmark case about view array slice

---
 arrow-array/Cargo.toml                                  | 2 +-
 arrow-array/benches/{gc_view_types.rs => view_types.rs} | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)
 rename arrow-array/benches/{gc_view_types.rs => view_types.rs} (91%)

diff --git a/arrow-array/Cargo.toml b/arrow-array/Cargo.toml
index 6170db85dc66..c6c9dfb967cd 100644
--- a/arrow-array/Cargo.toml
+++ b/arrow-array/Cargo.toml
@@ -65,7 +65,7 @@ name = "occupancy"
 harness = false
 
 [[bench]]
-name = "gc_view_types"
+name = "view_types"
 harness = false
 
 [[bench]]
diff --git a/arrow-array/benches/gc_view_types.rs b/arrow-array/benches/view_types.rs
similarity index 91%
rename from arrow-array/benches/gc_view_types.rs
rename to arrow-array/benches/view_types.rs
index 4b74a8f60b06..929a97551632 100644
--- a/arrow-array/benches/gc_view_types.rs
+++ b/arrow-array/benches/view_types.rs
@@ -42,6 +42,12 @@ fn criterion_benchmark(c: &mut Criterion) {
             black_box(sliced.gc());
         });
     });
+
+    c.bench_function("view types slice", |b| {
+        b.iter(|| {
+            black_box(array.slice(0, 100_000 / 2));
+        });
+    });
 }
 
 criterion_group!(benches, criterion_benchmark);