From: | Melanie Plageman <melanieplageman(at)gmail(dot)com> |
---|---|
To: | pgsql-committers(at)lists(dot)postgresql(dot)org |
Subject: | pgsql: Increase default effective_io_concurrency to 16 |
Date: | 2025-03-12 20:00:03 |
Message-ID: | E1tsSFH-0029BG-38@gemulon.postgresql.org |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-committers |
Increase default effective_io_concurrency to 16
The default effective_io_concurrency has been 1 since it was introduced
in b7b8f0b6096d2ab6e. Referencing the associated discussion [1], it
seems 1 was chosen as a conservative value that seemed unlikely to cause
regressions.
Experimentation on high latency cloud storage as well as fast, local
nvme storage (see Discussion link) shows that even slightly higher
values improve query timings substantially. 1 actually performs worse
than 0 [2]. With effective_io_concurrency 1, we are not prefetching
enough to avoid I/O stalls, but we are issuing extra syscalls.
The new default is 16, which should be more appropriate for common
hardware while still avoiding flooding low IOPs devices with I/O
requests.
[1] https://www.postgresql.org/message-id/flat/FDDBA24E-FF4D-4654-BA75-692B3BA71B97%40enterprisedb.com
[2] https://www.postgresql.org/message-id/CAAKRu_Zv08Cic%3DqdCfzrQabpEXGrd9Z9UOW5svEVkCM6%3DFXA9g%40mail.gmail.com
Reviewed-by: Andres Freund <andres(at)anarazel(dot)de>
Discussion: https://postgr.es/m/CAAKRu_Z%2BJa-mwXebOoOERMMUMvJeRhzTjad4dSThxG0JLXESxw%40mail.gmail.com
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/ff79b5b2aba02d720f9b7fff644dd50ce07b8c6e
Modified Files
--------------
doc/src/sgml/config.sgml | 38 +++++++++++----------------
src/backend/utils/misc/postgresql.conf.sample | 2 +-
src/include/storage/bufmgr.h | 2 +-
3 files changed, 18 insertions(+), 24 deletions(-)
From | Date | Subject | |
---|---|---|---|
Next Message | Nathan Bossart | 2025-03-12 20:02:33 | pgsql: Remove count_one_bits() in acl.c. |
Previous Message | Heikki Linnakangas | 2025-03-12 19:15:21 | pgsql: Handle interrupts while waiting on Append's async subplans |