Feedback-ID: id4a34324:Fastmail
Date: Tue, 18 Mar 2025 17:04:46 -0400
From: Andres Freund <andres@anarazel.de>
To: Bruce Momjian <bruce@momjian.us>
Cc: Melanie Plageman <melanieplageman@gmail.com>,
	PostgreSQL-development <pgsql-hackers@lists.postgresql.org>,
 Greg Smith <greg.smith@crunchydata.com>
Subject: Re: Increase default maintenance_io_concurrency to 16
Message-ID: <4p7gtb2nfr3njhgq7bmpe24unsbyoerlom7zrcu5sl2vyyutlp@ol5ywrm7j5ok>
References: <E1tuWgZ-0035xZ-0x@gemulon.postgresql.org>
 <Z9nStg5TJssYfg_b@momjian.us>
 <fycuaxeisofdyv4265ejiluixuklmoaaoywa7nhz3heytf4na6@3vd6owgwvadc>
 <Z9nWFVBx3OJSwqg6@momjian.us>
 <rdd4m4fze6zt4fjmp2p2ez5smokglno7pqefloyiql36kkudw6@pwpmabadygqz>
 <Z9nZET_03i2CQ1tP@momjian.us>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <Z9nZET_03i2CQ1tP@momjian.us>
Archived-At: 
 <https://www.postgresql.org/message-id/4p7gtb2nfr3njhgq7bmpe24unsbyoerlom7zrcu5sl2vyyutlp%40ol5ywrm7j5ok>
Precedence: bulk

Hi,

On 2025-03-18 16:35:29 -0400, Bruce Momjian wrote:
> Uh, the random_page_cost = 4 assumes caching, so it is assuming actual
> random I/O to be 40x slower, which I doubt is true for SSDs:

Uh, huh:

> 	https://www.postgresql.org/docs/current/runtime-config-query.html#RUNTIME-CONFIG-QUERY-CONSTANTS
>
> 	Random access to mechanical disk storage is normally much more expensive
> 	than four times sequential access. However, a lower default is used
> 	(4.0) because the majority of random accesses to disk, such as indexed
> 	reads, are assumed to be in cache. The default value can be thought of
> 	as modeling random access as 40 times slower than sequential, while
> 	expecting 90% of random reads to be cached.

Is that actually a good description of what we assume? I don't know where that
90% is coming from? Briefly skimming through selfuncs.c and costsize.c I don't
see anything.

The relevant change:

commit c1d9df4fa227781b31be44a5a3024865a7f48049
Author: Bruce Momjian <bruce@momjian.us>
Date:   2012-02-14 16:54:54 -0500

    Document random page cost is only 4x seqeuntial, and not 40x.

The relevant discussion seems to be:
https://postgr.es/m/4F31A05A.1060506%402ndQuadrant.com

But I don't see any origin of that number in that thread.

I am not sure if I found the correct email for Greg Smith?

Greetings,

Andres Freund