agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v5 6/7] Row pattern recognition patch (tests).
9657+ messages / 2 participants
[nested] [flat]

* [PATCH v5 6/7] Row pattern recognition patch (tests).
@ 2023-09-02 06:32  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Tatsuo Ishii @ 2023-09-02 06:32 UTC (permalink / raw)

---
 src/test/regress/expected/rpr.out  | 463 +++++++++++++++++++++++++++++
 src/test/regress/parallel_schedule |   2 +-
 src/test/regress/sql/rpr.sql       | 229 ++++++++++++++
 3 files changed, 693 insertions(+), 1 deletion(-)
 create mode 100644 src/test/regress/expected/rpr.out
 create mode 100644 src/test/regress/sql/rpr.sql

diff --git a/src/test/regress/expected/rpr.out b/src/test/regress/expected/rpr.out
new file mode 100644
index 0000000000..340ccf242c
--- /dev/null
+++ b/src/test/regress/expected/rpr.out
@@ -0,0 +1,463 @@
+--
+-- Test for row pattern definition clause
+--
+CREATE TEMP TABLE stock (
+       company TEXT,
+       tdate DATE,
+       price INTEGER
+       	       );
+INSERT INTO stock VALUES ('company1', '2023-07-01', 100);
+INSERT INTO stock VALUES ('company1', '2023-07-02', 200);
+INSERT INTO stock VALUES ('company1', '2023-07-03', 150);
+INSERT INTO stock VALUES ('company1', '2023-07-04', 140);
+INSERT INTO stock VALUES ('company1', '2023-07-05', 150);
+INSERT INTO stock VALUES ('company1', '2023-07-06', 90);
+INSERT INTO stock VALUES ('company1', '2023-07-07', 110);
+INSERT INTO stock VALUES ('company1', '2023-07-08', 130);
+INSERT INTO stock VALUES ('company1', '2023-07-09', 120);
+INSERT INTO stock VALUES ('company1', '2023-07-10', 130);
+INSERT INTO stock VALUES ('company2', '2023-07-01', 50);
+INSERT INTO stock VALUES ('company2', '2023-07-02', 2000);
+INSERT INTO stock VALUES ('company2', '2023-07-03', 1500);
+INSERT INTO stock VALUES ('company2', '2023-07-04', 1400);
+INSERT INTO stock VALUES ('company2', '2023-07-05', 1500);
+INSERT INTO stock VALUES ('company2', '2023-07-06', 60);
+INSERT INTO stock VALUES ('company2', '2023-07-07', 1100);
+INSERT INTO stock VALUES ('company2', '2023-07-08', 1300);
+INSERT INTO stock VALUES ('company2', '2023-07-09', 1200);
+INSERT INTO stock VALUES ('company2', '2023-07-10', 1300);
+SELECT * FROM stock;
+ company  |   tdate    | price 
+----------+------------+-------
+ company1 | 07-01-2023 |   100
+ company1 | 07-02-2023 |   200
+ company1 | 07-03-2023 |   150
+ company1 | 07-04-2023 |   140
+ company1 | 07-05-2023 |   150
+ company1 | 07-06-2023 |    90
+ company1 | 07-07-2023 |   110
+ company1 | 07-08-2023 |   130
+ company1 | 07-09-2023 |   120
+ company1 | 07-10-2023 |   130
+ company2 | 07-01-2023 |    50
+ company2 | 07-02-2023 |  2000
+ company2 | 07-03-2023 |  1500
+ company2 | 07-04-2023 |  1400
+ company2 | 07-05-2023 |  1500
+ company2 | 07-06-2023 |    60
+ company2 | 07-07-2023 |  1100
+ company2 | 07-08-2023 |  1300
+ company2 | 07-09-2023 |  1200
+ company2 | 07-10-2023 |  1300
+(20 rows)
+
+-- basic test using PREV
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w,
+ nth_value(tdate, 2) OVER w AS nth_second
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value | nth_second 
+----------+------------+-------+-------------+------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        140 | 07-02-2023
+ company1 | 07-02-2023 |   200 |             |            | 
+ company1 | 07-03-2023 |   150 |             |            | 
+ company1 | 07-04-2023 |   140 |             |            | 
+ company1 | 07-05-2023 |   150 |             |            | 
+ company1 | 07-06-2023 |    90 |          90 |        120 | 07-07-2023
+ company1 | 07-07-2023 |   110 |             |            | 
+ company1 | 07-08-2023 |   130 |             |            | 
+ company1 | 07-09-2023 |   120 |             |            | 
+ company1 | 07-10-2023 |   130 |             |            | 
+ company2 | 07-01-2023 |    50 |          50 |       1400 | 07-02-2023
+ company2 | 07-02-2023 |  2000 |             |            | 
+ company2 | 07-03-2023 |  1500 |             |            | 
+ company2 | 07-04-2023 |  1400 |             |            | 
+ company2 | 07-05-2023 |  1500 |             |            | 
+ company2 | 07-06-2023 |    60 |          60 |       1200 | 07-07-2023
+ company2 | 07-07-2023 |  1100 |             |            | 
+ company2 | 07-08-2023 |  1300 |             |            | 
+ company2 | 07-09-2023 |  1200 |             |            | 
+ company2 | 07-10-2023 |  1300 |             |            | 
+(20 rows)
+
+-- omit "START" in DEFINE but it is ok because "START AS TRUE" is
+-- implicitly defined. per spec.
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w,
+ nth_value(tdate, 2) OVER w AS nth_second
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value | nth_second 
+----------+------------+-------+-------------+------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        140 | 07-02-2023
+ company1 | 07-02-2023 |   200 |             |            | 
+ company1 | 07-03-2023 |   150 |             |            | 
+ company1 | 07-04-2023 |   140 |             |            | 
+ company1 | 07-05-2023 |   150 |             |            | 
+ company1 | 07-06-2023 |    90 |          90 |        120 | 07-07-2023
+ company1 | 07-07-2023 |   110 |             |            | 
+ company1 | 07-08-2023 |   130 |             |            | 
+ company1 | 07-09-2023 |   120 |             |            | 
+ company1 | 07-10-2023 |   130 |             |            | 
+ company2 | 07-01-2023 |    50 |          50 |       1400 | 07-02-2023
+ company2 | 07-02-2023 |  2000 |             |            | 
+ company2 | 07-03-2023 |  1500 |             |            | 
+ company2 | 07-04-2023 |  1400 |             |            | 
+ company2 | 07-05-2023 |  1500 |             |            | 
+ company2 | 07-06-2023 |    60 |          60 |       1200 | 07-07-2023
+ company2 | 07-07-2023 |  1100 |             |            | 
+ company2 | 07-08-2023 |  1300 |             |            | 
+ company2 | 07-09-2023 |  1200 |             |            | 
+ company2 | 07-10-2023 |  1300 |             |            | 
+(20 rows)
+
+-- the first row start with less than or equal to 100
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        140
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |             |           
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |          90 |        120
+ company1 | 07-07-2023 |   110 |             |           
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       1400
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |             |           
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |          60 |       1200
+ company2 | 07-07-2023 |  1100 |             |           
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- second row raises 120%
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price) * 1.2,
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        140
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |             |           
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |             |           
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       1400
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |             |           
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |             |           
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- using NEXT
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        200
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |         140 |        150
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |         110 |        130
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       2000
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |        1400 |       1500
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |        1100 |       1300
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        200
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |         140 |        150
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |         110 |        130
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       2000
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |        1400 |       1500
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |        1100 |       1300
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- match everything
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+)
+ DEFINE
+  A AS TRUE
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        130
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |             |           
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |             |           
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       1300
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |             |           
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |             |           
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP PAST LAST ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |             | 
+ company1 | 07-02-2023 |   200 | 07-02-2023  | 07-05-2023
+ company1 | 07-03-2023 |   150 |             | 
+ company1 | 07-04-2023 |   140 |             | 
+ company1 | 07-05-2023 |   150 |             | 
+ company1 | 07-06-2023 |    90 |             | 
+ company1 | 07-07-2023 |   110 | 07-07-2023  | 07-10-2023
+ company1 | 07-08-2023 |   130 |             | 
+ company1 | 07-09-2023 |   120 |             | 
+ company1 | 07-10-2023 |   130 |             | 
+ company2 | 07-01-2023 |    50 |             | 
+ company2 | 07-02-2023 |  2000 | 07-02-2023  | 07-05-2023
+ company2 | 07-03-2023 |  1500 |             | 
+ company2 | 07-04-2023 |  1400 |             | 
+ company2 | 07-05-2023 |  1500 |             | 
+ company2 | 07-06-2023 |    60 |             | 
+ company2 | 07-07-2023 |  1100 | 07-07-2023  | 07-10-2023
+ company2 | 07-08-2023 |  1300 |             | 
+ company2 | 07-09-2023 |  1200 |             | 
+ company2 | 07-10-2023 |  1300 |             | 
+(20 rows)
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |             | 
+ company1 | 07-02-2023 |   200 | 07-02-2023  | 07-05-2023
+ company1 | 07-03-2023 |   150 | 07-03-2023  | 07-05-2023
+ company1 | 07-04-2023 |   140 | 07-04-2023  | 07-05-2023
+ company1 | 07-05-2023 |   150 |             | 
+ company1 | 07-06-2023 |    90 |             | 
+ company1 | 07-07-2023 |   110 | 07-07-2023  | 07-10-2023
+ company1 | 07-08-2023 |   130 | 07-08-2023  | 07-10-2023
+ company1 | 07-09-2023 |   120 | 07-09-2023  | 07-10-2023
+ company1 | 07-10-2023 |   130 |             | 
+ company2 | 07-01-2023 |    50 |             | 
+ company2 | 07-02-2023 |  2000 | 07-02-2023  | 07-05-2023
+ company2 | 07-03-2023 |  1500 | 07-03-2023  | 07-05-2023
+ company2 | 07-04-2023 |  1400 | 07-04-2023  | 07-05-2023
+ company2 | 07-05-2023 |  1500 |             | 
+ company2 | 07-06-2023 |    60 |             | 
+ company2 | 07-07-2023 |  1100 | 07-07-2023  | 07-10-2023
+ company2 | 07-08-2023 |  1300 | 07-08-2023  | 07-10-2023
+ company2 | 07-09-2023 |  1200 | 07-09-2023  | 07-10-2023
+ company2 | 07-10-2023 |  1300 |             | 
+(20 rows)
+
+--
+-- Error cases
+--
+-- row pattern definition variable name must not appear more than once
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ ORDER BY tdate
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price),
+  UP AS price > PREV(price)
+);
+ERROR:  syntax error at or near "ORDER"
+LINE 6:  ORDER BY tdate
+         ^
+-- pattern variable name must appear in DEFINE
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+ END)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ERROR:  syntax error at or near "END"
+LINE 8:  PATTERN (START UP+ DOWN+ END)
+                                  ^
+-- FRAME must start at current row when row patttern recognition is used
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ERROR:  FRAME must start at current row when row patttern recognition is used
+-- SEEK is not supported
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ SEEK
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ERROR:  SEEK is not supported
+LINE 8:  SEEK
+         ^
+HINT:  Use INITIAL.
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index 4df9d8503b..896531002b 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -98,7 +98,7 @@ test: publication subscription
 # Another group of parallel tests
 # select_views depends on create_view
 # ----------
-test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock indirect_toast equivclass
+test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock indirect_toast equivclass rpr
 
 # ----------
 # Another group of parallel tests (JSON related)
diff --git a/src/test/regress/sql/rpr.sql b/src/test/regress/sql/rpr.sql
new file mode 100644
index 0000000000..c4f704cdc4
--- /dev/null
+++ b/src/test/regress/sql/rpr.sql
@@ -0,0 +1,229 @@
+--
+-- Test for row pattern definition clause
+--
+
+CREATE TEMP TABLE stock (
+       company TEXT,
+       tdate DATE,
+       price INTEGER
+       	       );
+INSERT INTO stock VALUES ('company1', '2023-07-01', 100);
+INSERT INTO stock VALUES ('company1', '2023-07-02', 200);
+INSERT INTO stock VALUES ('company1', '2023-07-03', 150);
+INSERT INTO stock VALUES ('company1', '2023-07-04', 140);
+INSERT INTO stock VALUES ('company1', '2023-07-05', 150);
+INSERT INTO stock VALUES ('company1', '2023-07-06', 90);
+INSERT INTO stock VALUES ('company1', '2023-07-07', 110);
+INSERT INTO stock VALUES ('company1', '2023-07-08', 130);
+INSERT INTO stock VALUES ('company1', '2023-07-09', 120);
+INSERT INTO stock VALUES ('company1', '2023-07-10', 130);
+INSERT INTO stock VALUES ('company2', '2023-07-01', 50);
+INSERT INTO stock VALUES ('company2', '2023-07-02', 2000);
+INSERT INTO stock VALUES ('company2', '2023-07-03', 1500);
+INSERT INTO stock VALUES ('company2', '2023-07-04', 1400);
+INSERT INTO stock VALUES ('company2', '2023-07-05', 1500);
+INSERT INTO stock VALUES ('company2', '2023-07-06', 60);
+INSERT INTO stock VALUES ('company2', '2023-07-07', 1100);
+INSERT INTO stock VALUES ('company2', '2023-07-08', 1300);
+INSERT INTO stock VALUES ('company2', '2023-07-09', 1200);
+INSERT INTO stock VALUES ('company2', '2023-07-10', 1300);
+
+SELECT * FROM stock;
+
+-- basic test using PREV
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w,
+ nth_value(tdate, 2) OVER w AS nth_second
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- omit "START" in DEFINE but it is ok because "START AS TRUE" is
+-- implicitly defined. per spec.
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w,
+ nth_value(tdate, 2) OVER w AS nth_second
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- the first row start with less than or equal to 100
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- second row raises 120%
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price) * 1.2,
+  DOWN AS price < PREV(price)
+);
+
+-- using NEXT
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+
+-- match everything
+
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+)
+ DEFINE
+  A AS TRUE
+);
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP PAST LAST ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+
+--
+-- Error cases
+--
+
+-- row pattern definition variable name must not appear more than once
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ ORDER BY tdate
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price),
+  UP AS price > PREV(price)
+);
+
+-- pattern variable name must appear in DEFINE
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+ END)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- FRAME must start at current row when row patttern recognition is used
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- SEEK is not supported
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ SEEK
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
-- 
2.25.1


----Next_Part(Sat_Sep__2_15_52_35_2023_273)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v5-0007-Allow-to-print-raw-parse-tree.patch"



^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread