pgsql: Increase default effective_io_concurrency to 16

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(-)

Browse pgsql-committers by date

  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