Add SQL test for TOAST value allocations on rewrite

michaelpq · michaelpq · commit 69f75d671475 · 2025-08-15T12:30:36.000+09:00
The SQL test added in this commit check a specific code path that had no coverage until now. When a TOAST datum is rewritten, toast_save_datum() has a dedicated path to make sure that a new value is allocated if it does not exist on the TOAST table yet. This test uses a trick with PLAIN and EXTERNAL storage, with a tuple large enough to be toasted and small enough to fit on a page. It is initially stored in plain more, and the rewrite forces the tuple to be stored externally. The key point is that there is no value allocated during the initial insert, and that there is one after the rewrite. A second pattern checked is the reuse of the same value across rewrites, using \gset. A set of patches under discussion is messing up with this area of the code, so this makes sure that such rewrite cases remain consistent across the board. Author: Nikhil Kumar Veldanda <veldanda.nikhilkumar17@gmail.com> Co-authored-by: Michael Paquier <michael@paquier.xyz> Discussion: https://postgr.es/m/CAFAfj_E+kw5P713S8_jZyVgQAGVFfzFiTUJPrgo-TTtJJoazQw@mail.gmail.com
diff --git a/src/test/regress/expected/vacuum.out b/src/test/regress/expected/vacuum.out
@@ -686,3 +686,49 @@ RESET ROLE;
 DROP TABLE vacowned;
 DROP TABLE vacowned_parted;
 DROP ROLE regress_vacuum;
+-- Test checking how new toast values are allocated on rewrite.
+-- Create table with plain storage (forces inline storage initially).
+CREATE TABLE vac_rewrite_toast (id int, f1 TEXT STORAGE plain);
+-- Insert tuple large enough to trigger toast storage on rewrite, still
+-- small enough to fit on a page.
+INSERT INTO vac_rewrite_toast values (1, repeat('a', 7000));
+-- Switch to external storage to force toast table usage.
+ALTER TABLE vac_rewrite_toast ALTER COLUMN f1 SET STORAGE EXTERNAL;
+-- This second tuple is toasted, its value should still be the
+-- same after rewrite.
+INSERT INTO vac_rewrite_toast values (2, repeat('a', 7000));
+SELECT pg_column_toast_chunk_id(f1) AS id_2_chunk FROM vac_rewrite_toast
+  WHERE id = 2 \gset
+-- Check initial state of the data.
+SELECT id, pg_column_toast_chunk_id(f1) IS NULL AS f1_chunk_null,
+  substr(f1, 5, 10) AS f1_data,
+  pg_column_compression(f1) AS f1_comp
+  FROM vac_rewrite_toast ORDER BY id;
+ id | f1_chunk_null |  f1_data   | f1_comp 
+----+---------------+------------+---------
+  1 | t             | aaaaaaaaaa | 
+  2 | f             | aaaaaaaaaa | 
+(2 rows)
+
+-- VACUUM FULL forces toast data rewrite.
+VACUUM FULL vac_rewrite_toast;
+-- Check after rewrite.
+SELECT id, pg_column_toast_chunk_id(f1) IS NULL AS f1_chunk_null,
+  substr(f1, 5, 10) AS f1_data,
+  pg_column_compression(f1) AS f1_comp
+  FROM vac_rewrite_toast ORDER BY id;
+ id | f1_chunk_null |  f1_data   | f1_comp 
+----+---------------+------------+---------
+  1 | f             | aaaaaaaaaa | 
+  2 | f             | aaaaaaaaaa | 
+(2 rows)
+
+-- The same value is reused for the tuple toasted before the rewrite.
+SELECT pg_column_toast_chunk_id(f1) = :'id_2_chunk' AS same_chunk
+  FROM vac_rewrite_toast WHERE id = 2;
+ same_chunk 
+------------
+ t
+(1 row)
+
+DROP TABLE vac_rewrite_toast;
diff --git a/src/test/regress/sql/vacuum.sql b/src/test/regress/sql/vacuum.sql
@@ -495,3 +495,33 @@ RESET ROLE;
 DROP TABLE vacowned;
 DROP TABLE vacowned_parted;
 DROP ROLE regress_vacuum;
+
+-- Test checking how new toast values are allocated on rewrite.
+-- Create table with plain storage (forces inline storage initially).
+CREATE TABLE vac_rewrite_toast (id int, f1 TEXT STORAGE plain);
+-- Insert tuple large enough to trigger toast storage on rewrite, still
+-- small enough to fit on a page.
+INSERT INTO vac_rewrite_toast values (1, repeat('a', 7000));
+-- Switch to external storage to force toast table usage.
+ALTER TABLE vac_rewrite_toast ALTER COLUMN f1 SET STORAGE EXTERNAL;
+-- This second tuple is toasted, its value should still be the
+-- same after rewrite.
+INSERT INTO vac_rewrite_toast values (2, repeat('a', 7000));
+SELECT pg_column_toast_chunk_id(f1) AS id_2_chunk FROM vac_rewrite_toast
+  WHERE id = 2 \gset
+-- Check initial state of the data.
+SELECT id, pg_column_toast_chunk_id(f1) IS NULL AS f1_chunk_null,
+  substr(f1, 5, 10) AS f1_data,
+  pg_column_compression(f1) AS f1_comp
+  FROM vac_rewrite_toast ORDER BY id;
+-- VACUUM FULL forces toast data rewrite.
+VACUUM FULL vac_rewrite_toast;
+-- Check after rewrite.
+SELECT id, pg_column_toast_chunk_id(f1) IS NULL AS f1_chunk_null,
+  substr(f1, 5, 10) AS f1_data,
+  pg_column_compression(f1) AS f1_comp
+  FROM vac_rewrite_toast ORDER BY id;
+-- The same value is reused for the tuple toasted before the rewrite.
+SELECT pg_column_toast_chunk_id(f1) = :'id_2_chunk' AS same_chunk
+  FROM vac_rewrite_toast WHERE id = 2;
+DROP TABLE vac_rewrite_toast;
