aboutsummaryrefslogtreecommitdiff
path: root/src/backend/access/transam/parallel.c
diff options
context:
space:
mode:
authorMichael Paquier <michael@paquier.xyz>2024-11-11 09:02:30 +0900
committerMichael Paquier <michael@paquier.xyz>2024-11-11 09:02:30 +0900
commit5d4298e75f252b162008ad0475f29349023573cb (patch)
treef878fbd8ff87b3e264139e85daf171f9c298cb79 /src/backend/access/transam/parallel.c
parent29d66b2d2f80dba0ac7fa5453d4da2dfbdd5ed2b (diff)
downloadpostgresql-5d4298e75f252b162008ad0475f29349023573cb.tar.gz
postgresql-5d4298e75f252b162008ad0475f29349023573cb.zip
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
Diffstat (limited to 'src/backend/access/transam/parallel.c')
0 files changed, 0 insertions, 0 deletions