Hello! >> Variant B is not acceptable IMO as it adds a whole bunch of >> null-terminators unnecessarily. For example, in a simple "select 1", >> (expr == NULL) is true 19 times, so that is an extra 19 bytes.
> Variant B is not acceptable here.
Could we improve Variant B?
I was thinking about adding a count of NULL pointers encountered by the query
jumble walker since the last scalar or non-null field visited.
This way, we can traverse the query as follows:
====
QueryA->subNodeOne = &(Value X);
/* JumbleState->Count = 0;
QueryA_ID = hash_any_extended(&(Value X), sizeof(Value X), QueryA_ID) */
QueryA->subNodeTwo = NULL;
/* JumbleState->Count = 1; */
QueryA->subNodeThee = NULL;
/* JumbleState->Count = 2; */
QueryA->subNodeFour = NULL;
/* JumbleState->Count = 3; */
QueryA->scalar = Value Z;
/* QueryA_ID = hash_any_extended(&(JumbleState->Count),
sizeof(JumbleState->Count), QueryA_ID)
JumbleState->Count = 0;
QueryA_ID = hash_any_extended(&(Value Y), sizeof(Value Y), QueryA_ID) */
====
Variant A improvement
---------------------
I have attached the updated Variant A patch with the following changes:
- Implemented a pg_stat_statements regression test (see similar test results
on REL_17_3 in Query-ID-collision-at_pg_stat_statements-1ea6e890b22.txt).
- Added extra description about the Query ID collision
in src/include/nodes/parsenodes.h.
-- End of contrib/pg_stat_statements/expected/select.out for REL_17_3
CREATE TABLE pgss_c AS
SELECT id FROM generate_series(1,2) AS id;
SELECT pg_stat_statements_reset() IS NOT NULL AS t;
t
---
t
(1 row)
SELECT DISTINCT id FROM pgss_c;
id
----
2
1
(2 rows)
SELECT id FROM pgss_c ORDER BY id;
id
----
1
2
(2 rows)
SELECT id FROM pgss_c LIMIT 1;
id
----
1
(1 row)
SELECT id FROM pgss_c OFFSET 1;
id
----
2
(1 row)
SELECT query FROM pg_stat_statements
WHERE query LIKE '%pgss_c%'
ORDER BY query COLLATE "C";
query
--------------------------------
SELECT DISTINCT id FROM pgss_c
SELECT id FROM pgss_c LIMIT $1
(2 rows)
SELECT pg_stat_statements_reset() IS NOT NULL AS t;
t
---
t
(1 row)
SELECT id FROM pgss_c ORDER BY id;
id
----
1
2
(2 rows)
SELECT DISTINCT id FROM pgss_c;
id
----
2
1
(2 rows)
SELECT id FROM pgss_c OFFSET 1;
id
----
2
(1 row)
SELECT id FROM pgss_c LIMIT 1;
id
----
1
(1 row)
SELECT query FROM pg_stat_statements
WHERE query LIKE '%pgss_c%'
ORDER BY query COLLATE "C";
query
-----------------------------------
SELECT id FROM pgss_c OFFSET $1
SELECT id FROM pgss_c ORDER BY id
(2 rows)
SELECT pg_stat_statements_reset() IS NOT NULL AS t;
t
---
t
(1 row)
DROP TABLE pgss_c;
v2-0001-Query-ID-Calculation-Fix-Variant-A.patch
Description: v2-0001-Query-ID-Calculation-Fix-Variant-A.patch
