agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v3 6/7] Row pattern recognition patch (tests).
135+ messages / 3 participants
[nested] [flat]

* [PATCH v3 6/7] Row pattern recognition patch (tests).
@ 2023-07-26 10:49 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Tatsuo Ishii @ 2023-07-26 10:49 UTC (permalink / raw)

---
 src/test/regress/expected/rpr.out  | 425 +++++++++++++++++++++++++++++
 src/test/regress/parallel_schedule |   2 +-
 src/test/regress/sql/rpr.sql       | 214 +++++++++++++++
 3 files changed, 640 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..19c054a0b8
--- /dev/null
+++ b/src/test/regress/expected/rpr.out
@@ -0,0 +1,425 @@
+--
+-- 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)
+
+-- the first row start with less than or equal to 100
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        140
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |             |           
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |          90 |        120
+ company1 | 07-07-2023 |   110 |             |           
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       1400
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |             |           
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |          60 |       1200
+ company2 | 07-07-2023 |  1100 |             |           
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- second row raises 120%
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price) * 1.2,
+  DOWN AS price < PREV(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        140
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |             |           
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |             |           
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       1400
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |             |           
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |             |           
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- using NEXT
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        200
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |         140 |        150
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |         110 |        130
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       2000
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |        1400 |       1500
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |        1100 |       1300
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        200
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |         140 |        150
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |         110 |        130
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       2000
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |        1400 |       1500
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |        1100 |       1300
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- match everything
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+)
+ DEFINE
+  A AS TRUE
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |         100 |        130
+ company1 | 07-02-2023 |   200 |             |           
+ company1 | 07-03-2023 |   150 |             |           
+ company1 | 07-04-2023 |   140 |             |           
+ company1 | 07-05-2023 |   150 |             |           
+ company1 | 07-06-2023 |    90 |             |           
+ company1 | 07-07-2023 |   110 |             |           
+ company1 | 07-08-2023 |   130 |             |           
+ company1 | 07-09-2023 |   120 |             |           
+ company1 | 07-10-2023 |   130 |             |           
+ company2 | 07-01-2023 |    50 |          50 |       1300
+ company2 | 07-02-2023 |  2000 |             |           
+ company2 | 07-03-2023 |  1500 |             |           
+ company2 | 07-04-2023 |  1400 |             |           
+ company2 | 07-05-2023 |  1500 |             |           
+ company2 | 07-06-2023 |    60 |             |           
+ company2 | 07-07-2023 |  1100 |             |           
+ company2 | 07-08-2023 |  1300 |             |           
+ company2 | 07-09-2023 |  1200 |             |           
+ company2 | 07-10-2023 |  1300 |             |           
+(20 rows)
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP PAST LAST ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |             | 
+ company1 | 07-02-2023 |   200 | 07-02-2023  | 07-05-2023
+ company1 | 07-03-2023 |   150 |             | 
+ company1 | 07-04-2023 |   140 |             | 
+ company1 | 07-05-2023 |   150 |             | 
+ company1 | 07-06-2023 |    90 |             | 
+ company1 | 07-07-2023 |   110 | 07-07-2023  | 07-10-2023
+ company1 | 07-08-2023 |   130 |             | 
+ company1 | 07-09-2023 |   120 |             | 
+ company1 | 07-10-2023 |   130 |             | 
+ company2 | 07-01-2023 |    50 |             | 
+ company2 | 07-02-2023 |  2000 | 07-02-2023  | 07-05-2023
+ company2 | 07-03-2023 |  1500 |             | 
+ company2 | 07-04-2023 |  1400 |             | 
+ company2 | 07-05-2023 |  1500 |             | 
+ company2 | 07-06-2023 |    60 |             | 
+ company2 | 07-07-2023 |  1100 | 07-07-2023  | 07-10-2023
+ company2 | 07-08-2023 |  1300 |             | 
+ company2 | 07-09-2023 |  1200 |             | 
+ company2 | 07-10-2023 |  1300 |             | 
+(20 rows)
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+ company  |   tdate    | price | first_value | last_value 
+----------+------------+-------+-------------+------------
+ company1 | 07-01-2023 |   100 |             | 
+ company1 | 07-02-2023 |   200 | 07-02-2023  | 07-05-2023
+ company1 | 07-03-2023 |   150 | 07-03-2023  | 07-05-2023
+ company1 | 07-04-2023 |   140 | 07-04-2023  | 07-05-2023
+ company1 | 07-05-2023 |   150 |             | 
+ company1 | 07-06-2023 |    90 |             | 
+ company1 | 07-07-2023 |   110 | 07-07-2023  | 07-10-2023
+ company1 | 07-08-2023 |   130 | 07-08-2023  | 07-10-2023
+ company1 | 07-09-2023 |   120 | 07-09-2023  | 07-10-2023
+ company1 | 07-10-2023 |   130 |             | 
+ company2 | 07-01-2023 |    50 |             | 
+ company2 | 07-02-2023 |  2000 | 07-02-2023  | 07-05-2023
+ company2 | 07-03-2023 |  1500 | 07-03-2023  | 07-05-2023
+ company2 | 07-04-2023 |  1400 | 07-04-2023  | 07-05-2023
+ company2 | 07-05-2023 |  1500 |             | 
+ company2 | 07-06-2023 |    60 |             | 
+ company2 | 07-07-2023 |  1100 | 07-07-2023  | 07-10-2023
+ company2 | 07-08-2023 |  1300 | 07-08-2023  | 07-10-2023
+ company2 | 07-09-2023 |  1200 | 07-09-2023  | 07-10-2023
+ company2 | 07-10-2023 |  1300 |             | 
+(20 rows)
+
+--
+-- Error cases
+--
+-- row pattern definition variable name must not appear more than once
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ ORDER BY tdate
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price),
+  UP AS price > PREV(price)
+);
+ERROR:  syntax error at or near "ORDER"
+LINE 6:  ORDER BY tdate
+         ^
+-- pattern variable name must appear in DEFINE
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+ END)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ERROR:  syntax error at or near "END"
+LINE 8:  PATTERN (START UP+ DOWN+ END)
+                                  ^
+-- FRAME must start at current row when row patttern recognition is used
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ERROR:  FRAME must start at current row when row patttern recognition is used
+-- SEEK is not supported
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ SEEK
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+ERROR:  SEEK is not supported
+LINE 8:  SEEK
+         ^
+HINT:  Use INITIAL.
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index 4df9d8503b..896531002b 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -98,7 +98,7 @@ test: publication subscription
 # Another group of parallel tests
 # select_views depends on create_view
 # ----------
-test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock indirect_toast equivclass
+test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock indirect_toast equivclass rpr
 
 # ----------
 # Another group of parallel tests (JSON related)
diff --git a/src/test/regress/sql/rpr.sql b/src/test/regress/sql/rpr.sql
new file mode 100644
index 0000000000..01459e619b
--- /dev/null
+++ b/src/test/regress/sql/rpr.sql
@@ -0,0 +1,214 @@
+--
+-- 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)
+);
+
+-- the first row start with less than or equal to 100
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- second row raises 120%
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (LOWPRICE UP+ DOWN+)
+ DEFINE
+  LOWPRICE AS price <= 100,
+  UP AS price > PREV(price) * 1.2,
+  DOWN AS price < PREV(price)
+);
+
+-- using NEXT
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (START UPDOWN)
+ DEFINE
+  START AS TRUE,
+  UPDOWN AS price > PREV(price) AND price > NEXT(price)
+);
+
+-- match everything
+
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+)
+ DEFINE
+  A AS TRUE
+);
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP PAST LAST ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP PAST LAST ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+
+-- backtracking with reclassification of rows
+-- using AFTER MATCH SKIP TO NEXT ROW
+SELECT company, tdate, price, first_value(tdate) OVER w, last_value(tdate) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ INITIAL
+ PATTERN (A+ B+)
+ DEFINE
+  A AS price > 100,
+  B AS price > 100
+);
+
+--
+-- Error cases
+--
+
+-- row pattern definition variable name must not appear more than once
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ ORDER BY tdate
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price),
+  UP AS price > PREV(price)
+);
+
+-- pattern variable name must appear in DEFINE
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+ END)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- FRAME must start at current row when row patttern recognition is used
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
+ INITIAL
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
+
+-- SEEK is not supported
+SELECT company, tdate, price, first_value(price) OVER w, last_value(price) OVER w
+ FROM stock
+ WINDOW w AS (
+ PARTITION BY company
+ ORDER BY tdate
+ ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
+ AFTER MATCH SKIP TO NEXT ROW
+ SEEK
+ PATTERN (START UP+ DOWN+)
+ DEFINE
+  START AS TRUE,
+  UP AS price > PREV(price),
+  DOWN AS price < PREV(price)
+);
-- 
2.25.1


----Next_Part(Wed_Jul_26_21_21_34_2023_317)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v3-0007-Allow-to-print-raw-parse-tree.patch"



^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread