agora inbox for pgsql-hackers@postgresql.org  

help / color / mirror / Atom feed

[PATCH v21 7/8] Row pattern recognition patch (tests).
319+ messages / 2 participants
[nested] [flat]

* [PATCH v21 7/8] Row pattern recognition patch (tests).
@ 2024-08-26 04:32 Tatsuo Ishii <ishii@postgresql.org>
  0 siblings, 0 replies; 319+ messages in thread

From: Tatsuo Ishii @ 2024-08-26 04:32 UTC (permalink / raw)

---
 src/test/regress/expected/rpr.out  | 836 +++++++++++++++++++++++++++++
 src/test/regress/parallel_schedule |   2 +-
 src/test/regress/sql/rpr.sql       | 405 ++++++++++++++
 3 files changed, 1242 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..0789e09435
--- /dev/null
+++ b/src/test/regress/expected/rpr.out
@@ -0,0 +1,836 @@
+--
+-- 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)
+
+-- basic test using PREV. UP appears twice
+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+ UP+)
+ 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 |        150 | 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 |        130 | 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 |       1500 | 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 |       1300 | 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)
+
+-- basic test using PREV. Use '*'
+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 |         150 |         90 | 07-06-2023
+ company1 | 07-06-2023 |    90 |             |            | 
+ company1 | 07-07-2023 |   110 |         110 |        120 | 07-08-2023
+ 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 |        1500 |         60 | 07-06-2023
+ company2 | 07-06-2023 |    60 |             |            | 
+ company2 | 07-07-2023 |  1100 |        1100 |       1200 | 07-08-2023
+ company2 | 07-08-2023 |  1300 |             |            | 
+ company2 | 07-09-2023 |  1200 |             |            | 
+ company2 | 07-10-2023 |  1300 |             |            | 
+(20 rows)
+
+-- basic test with none greedy pattern
+SELECT company, tdate, price, count(*) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (A A A)
+ DEFINE
+  A AS price >= 140 AND price <= 150
+);
+ company  |   tdate    | price | count 
+----------+------------+-------+-------
+ company1 | 07-01-2023 |   100 |     0
+ company1 | 07-02-2023 |   200 |     0
+ company1 | 07-03-2023 |   150 |     3
+ company1 | 07-04-2023 |   140 |     0
+ company1 | 07-05-2023 |   150 |     0
+ company1 | 07-06-2023 |    90 |     0
+ company1 | 07-07-2023 |   110 |     0
+ company1 | 07-08-2023 |   130 |     0
+ company1 | 07-09-2023 |   120 |     0
+ company1 | 07-10-2023 |   130 |     0
+ company2 | 07-01-2023 |    50 |     0
+ company2 | 07-02-2023 |  2000 |     0
+ company2 | 07-03-2023 |  1500 |     0
+ company2 | 07-04-2023 |  1400 |     0
+ company2 | 07-05-2023 |  1500 |     0
+ company2 | 07-06-2023 |    60 |     0
+ company2 | 07-07-2023 |  1100 |     0
+ company2 | 07-08-2023 |  1300 |     0
+ company2 | 07-09-2023 |  1200 |     0
+ company2 | 07-10-2023 |  1300 |     0
+(20 rows)
+
+-- last_value() should remain consistent
+SELECT company, tdate, price, 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+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | last_value 
+----------+------------+-------+------------
+ company1 | 07-01-2023 |   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 |        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 |       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 |       1200
+ 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)
+
+-- ROWS BETWEEN CURRENT ROW AND offset FOLLOWING
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w,
+ count(*) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND 2 FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ 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 | count 
+----------+------------+-------+-------------+------------+-------
+ company1 | 07-01-2023 |   100 | 07-01-2023  | 07-03-2023 |     3
+ company1 | 07-02-2023 |   200 |             |            |     0
+ company1 | 07-03-2023 |   150 |             |            |     0
+ company1 | 07-04-2023 |   140 | 07-04-2023  | 07-06-2023 |     3
+ company1 | 07-05-2023 |   150 |             |            |     0
+ company1 | 07-06-2023 |    90 |             |            |     0
+ company1 | 07-07-2023 |   110 | 07-07-2023  | 07-09-2023 |     3
+ company1 | 07-08-2023 |   130 |             |            |     0
+ company1 | 07-09-2023 |   120 |             |            |     0
+ company1 | 07-10-2023 |   130 |             |            |     0
+ company2 | 07-01-2023 |    50 | 07-01-2023  | 07-03-2023 |     3
+ company2 | 07-02-2023 |  2000 |             |            |     0
+ company2 | 07-03-2023 |  1500 |             |            |     0
+ company2 | 07-04-2023 |  1400 | 07-04-2023  | 07-06-2023 |     3
+ company2 | 07-05-2023 |  1500 |             |            |     0
+ company2 | 07-06-2023 |    60 |             |            |     0
+ company2 | 07-07-2023 |  1100 | 07-07-2023  | 07-09-2023 |     3
+ company2 | 07-08-2023 |  1300 |             |            |     0
+ company2 | 07-09-2023 |  1200 |             |            |     0
+ company2 | 07-10-2023 |  1300 |             |            |     0
+(20 rows)
+
+--
+-- Aggregates
+--
+-- using AFTER MATCH SKIP PAST LAST ROW
+SELECT company, tdate, price,
+ first_value(price) OVER w,
+ last_value(price) OVER w,
+ max(price) OVER w,
+ min(price) OVER w,
+ sum(price) OVER w,
+ avg(price) OVER w,
+ count(price) OVER w
+FROM stock
+WINDOW w AS (
+PARTITION BY company
+ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+AFTER MATCH SKIP PAST LAST ROW
+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 | max  | min | sum  |          avg          | count 
+----------+------------+-------+-------------+------------+------+-----+------+-----------------------+-------
+ company1 | 07-01-2023 |   100 |         100 |        140 |  200 | 100 |  590 |  147.5000000000000000 |     4
+ company1 | 07-02-2023 |   200 |             |            |      |     |      |                       |     0
+ company1 | 07-03-2023 |   150 |             |            |      |     |      |                       |     0
+ company1 | 07-04-2023 |   140 |             |            |      |     |      |                       |     0
+ company1 | 07-05-2023 |   150 |             |            |      |     |      |                       |     0
+ company1 | 07-06-2023 |    90 |          90 |        120 |  130 |  90 |  450 |  112.5000000000000000 |     4
+ company1 | 07-07-2023 |   110 |             |            |      |     |      |                       |     0
+ company1 | 07-08-2023 |   130 |             |            |      |     |      |                       |     0
+ company1 | 07-09-2023 |   120 |             |            |      |     |      |                       |     0
+ company1 | 07-10-2023 |   130 |             |            |      |     |      |                       |     0
+ company2 | 07-01-2023 |    50 |          50 |       1400 | 2000 |  50 | 4950 | 1237.5000000000000000 |     4
+ company2 | 07-02-2023 |  2000 |             |            |      |     |      |                       |     0
+ company2 | 07-03-2023 |  1500 |             |            |      |     |      |                       |     0
+ company2 | 07-04-2023 |  1400 |             |            |      |     |      |                       |     0
+ company2 | 07-05-2023 |  1500 |             |            |      |     |      |                       |     0
+ company2 | 07-06-2023 |    60 |          60 |       1200 | 1300 |  60 | 3660 |  915.0000000000000000 |     4
+ company2 | 07-07-2023 |  1100 |             |            |      |     |      |                       |     0
+ company2 | 07-08-2023 |  1300 |             |            |      |     |      |                       |     0
+ company2 | 07-09-2023 |  1200 |             |            |      |     |      |                       |     0
+ company2 | 07-10-2023 |  1300 |             |            |      |     |      |                       |     0
+(20 rows)
+
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price,
+ first_value(price) OVER w,
+ last_value(price) OVER w,
+ max(price) OVER w,
+ min(price) OVER w,
+ sum(price) OVER w,
+ avg(price) OVER w,
+ count(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 UP+ DOWN+)
+DEFINE
+START AS TRUE,
+UP AS price > PREV(price),
+DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value | max  | min  | sum  |          avg          | count 
+----------+------------+-------+-------------+------------+------+------+------+-----------------------+-------
+ company1 | 07-01-2023 |   100 |         100 |        140 |  200 |  100 |  590 |  147.5000000000000000 |     4
+ company1 | 07-02-2023 |   200 |             |            |      |      |      |                       |     0
+ company1 | 07-03-2023 |   150 |             |            |      |      |      |                       |     0
+ company1 | 07-04-2023 |   140 |         140 |         90 |  150 |   90 |  380 |  126.6666666666666667 |     3
+ company1 | 07-05-2023 |   150 |             |            |      |      |      |                       |     0
+ company1 | 07-06-2023 |    90 |          90 |        120 |  130 |   90 |  450 |  112.5000000000000000 |     4
+ company1 | 07-07-2023 |   110 |         110 |        120 |  130 |  110 |  360 |  120.0000000000000000 |     3
+ company1 | 07-08-2023 |   130 |             |            |      |      |      |                       |     0
+ company1 | 07-09-2023 |   120 |             |            |      |      |      |                       |     0
+ company1 | 07-10-2023 |   130 |             |            |      |      |      |                       |     0
+ company2 | 07-01-2023 |    50 |          50 |       1400 | 2000 |   50 | 4950 | 1237.5000000000000000 |     4
+ company2 | 07-02-2023 |  2000 |             |            |      |      |      |                       |     0
+ company2 | 07-03-2023 |  1500 |             |            |      |      |      |                       |     0
+ company2 | 07-04-2023 |  1400 |        1400 |         60 | 1500 |   60 | 2960 |  986.6666666666666667 |     3
+ company2 | 07-05-2023 |  1500 |             |            |      |      |      |                       |     0
+ company2 | 07-06-2023 |    60 |          60 |       1200 | 1300 |   60 | 3660 |  915.0000000000000000 |     4
+ company2 | 07-07-2023 |  1100 |        1100 |       1200 | 1300 | 1100 | 3600 | 1200.0000000000000000 |     3
+ company2 | 07-08-2023 |  1300 |             |            |      |      |      |                       |     0
+ company2 | 07-09-2023 |  1200 |             |            |      |      |      |                       |     0
+ company2 | 07-10-2023 |  1300 |             |            |      |      |      |                       |     0
+(20 rows)
+
+-- JOIN case
+CREATE TEMP TABLE t1 (i int, v1 int);
+CREATE TEMP TABLE t2 (j int, v2 int);
+INSERT INTO t1 VALUES(1,10);
+INSERT INTO t1 VALUES(1,11);
+INSERT INTO t1 VALUES(1,12);
+INSERT INTO t2 VALUES(2,10);
+INSERT INTO t2 VALUES(2,11);
+INSERT INTO t2 VALUES(2,12);
+SELECT * FROM t1, t2 WHERE t1.v1 <= 11 AND t2.v2 <= 11;
+ i | v1 | j | v2 
+---+----+---+----
+ 1 | 10 | 2 | 10
+ 1 | 10 | 2 | 11
+ 1 | 11 | 2 | 10
+ 1 | 11 | 2 | 11
+(4 rows)
+
+SELECT *, count(*) OVER w FROM t1, t2
+WINDOW w AS (
+ PARTITION BY t1.i
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (A)
+ DEFINE
+ A AS v1 <= 11 AND v2 <= 11
+);
+ i | v1 | j | v2 | count 
+---+----+---+----+-------
+ 1 | 10 | 2 | 10 |     1
+ 1 | 10 | 2 | 11 |     1
+ 1 | 10 | 2 | 12 |     0
+ 1 | 11 | 2 | 10 |     1
+ 1 | 11 | 2 | 11 |     1
+ 1 | 11 | 2 | 12 |     0
+ 1 | 12 | 2 | 10 |     0
+ 1 | 12 | 2 | 11 |     0
+ 1 | 12 | 2 | 12 |     0
+(9 rows)
+
+-- WITH case
+WITH wstock AS (
+  SELECT * FROM stock WHERE tdate < '2023-07-08'
+)
+SELECT tdate, price,
+first_value(tdate) OVER w,
+count(*) OVER w
+ FROM wstock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ 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)
+);
+   tdate    | price | first_value | count 
+------------+-------+-------------+-------
+ 07-01-2023 |   100 | 07-01-2023  |     4
+ 07-02-2023 |   200 |             |     0
+ 07-03-2023 |   150 |             |     0
+ 07-04-2023 |   140 |             |     0
+ 07-05-2023 |   150 |             |     0
+ 07-06-2023 |    90 |             |     0
+ 07-07-2023 |   110 |             |     0
+ 07-01-2023 |    50 | 07-01-2023  |     4
+ 07-02-2023 |  2000 |             |     0
+ 07-03-2023 |  1500 |             |     0
+ 07-04-2023 |  1400 |             |     0
+ 07-05-2023 |  1500 |             |     0
+ 07-06-2023 |    60 |             |     0
+ 07-07-2023 |  1100 |             |     0
+(14 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
+ ORDER BY tdate
+ 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),
+  UP AS price > PREV(price)
+);
+ERROR:  row pattern definition variable name "up" appears more than once in DEFINE clause
+LINE 11:   UP AS price > PREV(price),
+           ^
+-- subqueries in DEFINE clause are 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
+ INITIAL
+ PATTERN (START LOWPRICE)
+ DEFINE
+  START AS TRUE,
+  LOWPRICE AS price < (SELECT 100)
+);
+ERROR:  cannot use subquery in DEFINE expression
+LINE 11:   LOWPRICE AS price < (SELECT 100)
+                               ^
+-- aggregates in DEFINE clause are 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
+ INITIAL
+ PATTERN (START LOWPRICE)
+ DEFINE
+  START AS TRUE,
+  LOWPRICE AS price < count(*)
+);
+ERROR:  aggregate functions are not allowed in DEFINE
+LINE 11:   LOWPRICE AS price < count(*)
+                               ^
+-- 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 f53a526f7c..299354c9ae 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..302e2b86a5
--- /dev/null
+++ b/src/test/regress/sql/rpr.sql
@@ -0,0 +1,405 @@
+--
+-- 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)
+);
+
+-- basic test using PREV. UP appears twice
+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+ UP+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- basic test using PREV. Use '*'
+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)
+);
+
+-- basic test with none greedy pattern
+SELECT company, tdate, price, count(*) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (A A A)
+ DEFINE
+  A AS price >= 140 AND price <= 150
+);
+
+-- last_value() should remain consistent
+SELECT company, tdate, price, 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+)
+ 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
+);
+
+-- ROWS BETWEEN CURRENT ROW AND offset FOLLOWING
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w,
+ count(*) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND 2 FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+--
+-- Aggregates
+--
+
+-- using AFTER MATCH SKIP PAST LAST ROW
+SELECT company, tdate, price,
+ first_value(price) OVER w,
+ last_value(price) OVER w,
+ max(price) OVER w,
+ min(price) OVER w,
+ sum(price) OVER w,
+ avg(price) OVER w,
+ count(price) OVER w
+FROM stock
+WINDOW w AS (
+PARTITION BY company
+ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+AFTER MATCH SKIP PAST LAST ROW
+INITIAL
+PATTERN (START UP+ DOWN+)
+DEFINE
+START AS TRUE,
+UP AS price > PREV(price),
+DOWN AS price < PREV(price)
+);
+
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price,
+ first_value(price) OVER w,
+ last_value(price) OVER w,
+ max(price) OVER w,
+ min(price) OVER w,
+ sum(price) OVER w,
+ avg(price) OVER w,
+ count(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 UP+ DOWN+)
+DEFINE
+START AS TRUE,
+UP AS price > PREV(price),
+DOWN AS price < PREV(price)
+);
+
+-- JOIN case
+CREATE TEMP TABLE t1 (i int, v1 int);
+CREATE TEMP TABLE t2 (j int, v2 int);
+INSERT INTO t1 VALUES(1,10);
+INSERT INTO t1 VALUES(1,11);
+INSERT INTO t1 VALUES(1,12);
+INSERT INTO t2 VALUES(2,10);
+INSERT INTO t2 VALUES(2,11);
+INSERT INTO t2 VALUES(2,12);
+
+SELECT * FROM t1, t2 WHERE t1.v1 <= 11 AND t2.v2 <= 11;
+
+SELECT *, count(*) OVER w FROM t1, t2
+WINDOW w AS (
+ PARTITION BY t1.i
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (A)
+ DEFINE
+ A AS v1 <= 11 AND v2 <= 11
+);
+
+-- WITH case
+WITH wstock AS (
+  SELECT * FROM stock WHERE tdate < '2023-07-08'
+)
+SELECT tdate, price,
+first_value(tdate) OVER w,
+count(*) OVER w
+ FROM wstock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ 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)
+);
+
+--
+-- 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
+ ORDER BY tdate
+ 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),
+  UP AS price > PREV(price)
+);
+
+-- subqueries in DEFINE clause are 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
+ INITIAL
+ PATTERN (START LOWPRICE)
+ DEFINE
+  START AS TRUE,
+  LOWPRICE AS price < (SELECT 100)
+);
+
+-- aggregates in DEFINE clause are 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
+ INITIAL
+ PATTERN (START LOWPRICE)
+ DEFINE
+  START AS TRUE,
+  LOWPRICE AS price < count(*)
+);
+
+-- 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(Mon_Aug_26_13_39_47_2024_878)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v21-0008-Allow-to-print-raw-parse-tree.patch"



^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread

* [PATCH v1 5/5] Use anonymous files to back shared memory segments
@ 2024-10-15 14:18 Dmitrii Dolgov <9erthalion6@gmail.com>
  0 siblings, 0 replies; 319+ messages in thread

From: Dmitrii Dolgov @ 2024-10-15 14:18 UTC (permalink / raw)

Allow to use anonymous files for shared memory, instead of plain
anonymous memory. Such an anonymous file is created via memfd_create, it
lives in memory, behaves like a regular file and semantically equivalent
to an anonymous memory allocated via mmap with MAP_ANONYMOUS.

Advantages of using anon files are following:

* We've got a file descriptor, which could be used for regular file
  operations (modification, truncation, you name it).

* The file could be given a name, which improves readability when it
  comes to process maps. Here is how it looks like

7f5a2bd04000-7f5a32e52000 rw-s 00000000 00:01 1845 /memfd:strategy (deleted)
7f5a39252000-7f5a4030e000 rw-s 00000000 00:01 1842 /memfd:checkpoint (deleted)
7f5a4670e000-7f5a4d7ba000 rw-s 00000000 00:01 1839 /memfd:iocv (deleted)
7f5a53bba000-7f5a5ad26000 rw-s 00000000 00:01 1836 /memfd:descriptors (deleted)
7f5a9ad26000-7f5aa9d94000 rw-s 00000000 00:01 1833 /memfd:buffers (deleted)
7f5d29d94000-7f5d30e00000 rw-s 00000000 00:01 1830 /memfd:main (deleted)

* By default, Linux will not add file-backed shared mappings into a core dump,
  making it more convenient to work with them in PostgreSQL: no more huge dumps
  to process.

The downside is that memfd_create is Linux specific.
---
 src/backend/port/sysv_shmem.c | 47 +++++++++++++++++++++++++++++------
 src/include/portability/mem.h |  2 +-
 2 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 4bdadbb0e2..a01c3e4789 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -103,6 +103,7 @@ typedef struct AnonymousMapping
 	void *shmem; 				/* Pointer to the start of the mapped memory */
 	void *seg_addr; 			/* SysV shared memory for the header */
 	unsigned long seg_id; 		/* IPC key */
+	int segment_fd; 			/* fd for the backing anon file */
 } AnonymousMapping;
 
 static AnonymousMapping Mappings[ANON_MAPPINGS];
@@ -116,7 +117,7 @@ static int next_free_slot = 0;
  * 00400000-00490000         /path/bin/postgres
  * ...
  * 012d9000-0133e000         [heap]
- * 7f443a800000-7f470a800000 /dev/zero (deleted)
+ * 7f443a800000-7f470a800000 /memfd:main (deleted)
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
  * ...
@@ -143,9 +144,9 @@ static int next_free_slot = 0;
  * The result would look like this:
  *
  * 012d9000-0133e000         [heap]
- * 7f4426f54000-7f442e010000 /dev/zero (deleted)
+ * 7f4426f54000-7f442e010000 /memfd:main (deleted)
  * [...free space...]
- * 7f443a800000-7f444196c000 /dev/zero (deleted)
+ * 7f443a800000-7f444196c000 /memfd:buffers (deleted)
  * [...free space...]
  * 7f470a800000-7f471831d000 /usr/lib/locale/locale-archive
  * 7f4718400000-7f4718401000 /usr/lib64/libicudata.so.74.2
@@ -708,6 +709,18 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
+	/*
+	 * Prepare an anonymous file backing the segment. Its size will be
+	 * specified later via ftruncate.
+	 *
+	 * The file behaves like a regular file, but lives in memory. Once all
+	 * references to the file are dropped,  it is automatically released.
+	 * Anonymous memory is used for all backing pages of the file, thus it has
+	 * the same semantics as anonymous memory allocations using mmap with the
+	 * MAP_ANONYMOUS flag.
+	 */
+	mapping->segment_fd = memfd_create(MappingName(mapping->shmem_slot), 0);
+
 #ifndef MAP_HUGETLB
 	/* PGSharedMemoryCreate should have dealt with this case */
 	Assert(huge_pages != HUGE_PAGES_ON);
@@ -725,8 +738,13 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		if (allocsize % hugepagesize != 0)
 			allocsize += hugepagesize - (allocsize % hugepagesize);
 
+		/*
+		 * Do not use an anonymous file here yet. When adding it, do not forget
+		 * to use ftruncate and flags MFD_HUGETLB & MFD_HUGE_2MB/MFD_HUGE_1GB
+		 * in memfd_create.
+		 */
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
 		{
@@ -762,7 +780,8 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 * - First create the temporary probe mapping of a fixed size and let
 		 *   kernel to place it at address of its choice. By the virtue of the
 		 *   probe mapping size we expect it to be located at the lowest
-		 *   possible address, expecting some non mapped space above.
+		 *   possible address, expecting some non mapped space above. The probe
+		 *   is does not need to be  backed by an anonymous file.
 		 *
 		 * - Unmap the probe mapping, remember the address.
 		 *
@@ -777,7 +796,7 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 *   without a restart.
 		 */
 		probe = mmap(NULL, PROBE_MAPPING_SIZE, PROT_READ | PROT_WRITE,
-				   PG_MMAP_FLAGS, -1, 0);
+				   PG_MMAP_FLAGS | MAP_ANONYMOUS, -1, 0);
 
 		if (probe == MAP_FAILED)
 		{
@@ -793,8 +812,14 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 
 			munmap(probe, PROBE_MAPPING_SIZE);
 
+			/*
+			 * Specify the segment file size using allocsize, which contains
+			 * potentially modified size.
+			 */
+			ftruncate(mapping->segment_fd, allocsize);
+
 			ptr = mmap(probe - offset, allocsize, PROT_READ | PROT_WRITE,
-					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, -1, 0);
+					   PG_MMAP_FLAGS | MAP_FIXED_NOREPLACE, mapping->segment_fd, 0);
 			mmap_errno = errno;
 			if (ptr == MAP_FAILED)
 			{
@@ -813,8 +838,11 @@ CreateAnonymousSegment(AnonymousMapping *mapping)
 		 */
 		allocsize = mapping->shmem_size;
 
+		/* Specify the segment file size using allocsize. */
+		ftruncate(mapping->segment_fd, allocsize);
+
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
-						   PG_MMAP_FLAGS, -1, 0);
+						   PG_MMAP_FLAGS, mapping->segment_fd, 0);
 		mmap_errno = errno;
 	}
 
@@ -903,6 +931,9 @@ AnonymousShmemResize(int newval, void *extra)
 		if (m->shmem_size == new_size)
 			continue;
 
+		/* Resize the backing anon file. */
+		ftruncate(m->segment_fd, new_size);
+
 		if (mremap(m->shmem, m->shmem_size, new_size, 0) < 0)
 			elog(LOG, "mremap(%p, %zu) failed: %m",
 				 m->shmem, m->shmem_size);
diff --git a/src/include/portability/mem.h b/src/include/portability/mem.h
index 2cd05313b8..50db0da28d 100644
--- a/src/include/portability/mem.h
+++ b/src/include/portability/mem.h
@@ -38,7 +38,7 @@
 #define MAP_NOSYNC			0
 #endif
 
-#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_ANONYMOUS|MAP_HASSEMAPHORE)
+#define PG_MMAP_FLAGS			(MAP_SHARED|MAP_HASSEMAPHORE)
 
 /* Some really old systems don't define MAP_FAILED. */
 #ifndef MAP_FAILED
-- 
2.45.1


--ers4zrhjqnhlajas--





^ permalink  raw  reply  [nested|flat] 319+ messages in thread