Thread: pgsql: pg_stat_statements: Avoid some locking during PGSS entry scans

pgsql: pg_stat_statements: Avoid some locking during PGSS entry scans

From
Michael Paquier
Date:
pg_stat_statements: Avoid some locking during PGSS entry scans

A single PGSS entry's spinlock is used to be able to modify "counters"
without holding pgss->lock exclusively, as mentioned at the top of
pg_stat_statements.c and within pgssEntry.

Within a single pgssEntry, stats_since and minmax_stats_since are never
modified without holding pgss->lock exclusively, so there is no need to
hold an entry's spinlock when reading stats_since and
minmax_stats_since, as done when scanning all the PGSS entries for
function calls of pg_stat_statements().

This also restores the consistency between the code and the comments
about the entry's spinlock usage.  This change is a performance
improvement (it can be argued that this is a logic bug), so there is no
need for a backpatch.  This saves two instructions from being read while
holding an entry's spinlock.

Author: Karina Litskevich
Reviewed-by: Michael Paquier, wenhui qiu
Discussion: https://postgr.es/m/CACiT8ibhCmzbcOxM0v4pRLH3abk-95LPkt7_uC2JMP+miPjxsg@mail.gmail.com

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/5d4298e75f252b162008ad0475f29349023573cb

Modified Files
--------------
contrib/pg_stat_statements/pg_stat_statements.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)