pg_stat_statements: Avoid some locking during PGSS entry scans
Michael Paquier <michael@paquier.xyz>
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
Files
| Path | Change | +/− |
|---|---|---|
| contrib/pg_stat_statements/pg_stat_statements.c | modified | +6 −1 |
Discussion
- pg_stat_statements: Avoid holding excessive lock 6 messages · 2024-11-05 → 2024-11-11