From 2c06a48bd848f400a690b6abc15c3fec662a1418 Mon Sep 17 00:00:00 2001
From: "lancedb-gatefixer[bot]"
 <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
Date: Thu, 6 Aug 2026 16:45:10 +0800
Subject: [PATCH] test(python): cover Arrow buffer release after add (#3860)

## Summary

- add deterministic regression coverage that `Table.add()` releases
backing Arrow buffers without cyclic garbage collection
- track the foreign buffer owner rather than RSS, separating live input
retention from allocator high-water behavior
- preserve the bounded-lifetime behavior of the Scannable writer that
superseded the historical preprocessing path

## Root cause

The historical Python preprocessing/write path produced a high allocator
RSS while ingesting very wide IPC batches. The current Scannable writer
releases each input buffer when `Table.add()` completes; remaining RSS
is allocator high-water rather than a live Arrow reference. The resolved
behavior had no regression coverage, so a future native lifetime
regression could silently reintroduce the original failure mode.

## Validation

- `uv run --extra tests --extra dev maturin develop`
- `uv run --project python --extra tests pytest
python/python/tests/test_table.py::test_add
python/python/tests/test_table.py::test_add_releases_arrow_buffers_without_gc
-q`
- `uv run --project python --extra dev ruff format --check
python/python/tests/test_table.py`
- `uv run --project python --extra dev ruff check .`

Fixes #2512

<!-- lance-gatekeeper-fix:v1 agent=29226408a8d07da592daf341d5384e37
generation=1 -->

Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
---
 python/python/tests/test_table.py | 35 +++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/python/python/tests/test_table.py b/python/python/tests/test_table.py
index d7748095e..70a52b100 100644
--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -2,10 +2,13 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 
+import ctypes
+import gc
 import os
 import sys
 import threading
 import warnings
+import weakref
 from concurrent.futures import ThreadPoolExecutor
 from datetime import date, datetime, timedelta
 from time import sleep
@@ -459,6 +462,38 @@ def test_add(mem_db: DBConnection):
     _add(table, schema)
 
 
+def test_add_releases_arrow_buffers_without_gc(mem_db: DBConnection):
+    """Regression test for https://github.com/lancedb/lancedb/issues/2512."""
+    schema = pa.schema([pa.field("x", pa.int64())])
+    table = mem_db.create_table("test_add_releases_arrow_buffers", schema=schema)
+
+    class BufferOwner:
+        def __init__(self, size: int):
+            self.memory = ctypes.create_string_buffer(size)
+
+    owner_refs = []
+    gc_was_enabled = gc.isenabled()
+    gc.disable()
+    try:
+        for _ in range(3):
+            size = 8 * 1024
+            owner = BufferOwner(size)
+            arrow_buffer = pa.foreign_buffer(
+                ctypes.addressof(owner.memory), size, owner
+            )
+            array = pa.Array.from_buffers(pa.int64(), 1024, [None, arrow_buffer])
+            batch = pa.RecordBatch.from_arrays([array], schema=schema)
+            owner_refs.append(weakref.ref(owner))
+
+            table.add(batch)
+            del batch, array, arrow_buffer, owner
+
+        assert all(owner_ref() is None for owner_ref in owner_refs)
+    finally:
+        if gc_was_enabled:
+            gc.enable()
+
+
 def test_add_write_parallelism(mem_db: DBConnection):
     schema = pa.schema([pa.field("id", pa.int64())])
     table = mem_db.create_table("test", schema=schema)