Feedback-ID: id4a34324:Fastmail
Date: Thu, 28 Aug 2025 19:27:32 -0400
From: Andres Freund <andres@anarazel.de>
To: Tomas Vondra <tomas@vondra.me>
Cc: Thomas Munro <thomas.munro@gmail.com>, Peter Geoghegan <pg@bowt.ie>,
	Nazir Bilal Yavuz <byavuz81@gmail.com>, Robert Haas <robertmhaas@gmail.com>,
	Melanie Plageman <melanieplageman@gmail.com>,
 PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>,
	Georgios <gkokolatos@protonmail.com>,
 Konstantin Knizhnik <knizhnik@garret.ru>,
	Dilip Kumar <dilipbalaut@gmail.com>
Subject: Re: index prefetching
Message-ID: <e33gafg4p7iwvo24ytrxuw43nafm5xm3jefpdspnarcbkfurs7@3jbgdiinxem5>
References: <6butbqln6ewi5kuxz3kfv2mwomnlgtate4mb4lpa7gb2l63j4t@stlwbi2dvvev>
 <ce485718-f49e-4cbc-99de-5b935fe98926@vondra.me>
 <y32ow7vfdrrcchxrwgfr5tbwg3ncm4f3rlp65svcbqorbm3tmn@cwvipbplnqyt>
 <0dd33755-cab8-49c8-b1ed-698732577fbb@vondra.me>
 <1c9302da-c834-4773-a527-1c1a7029c5a3@vondra.me>
 <onbn3rx35x6k7mfnsmejnebt4nahnii3qnjrac2jzdh3puwo6t@dzjzsx5ppaj7>
 <6d59c277-c440-4d1f-a46e-157958c06a5f@vondra.me>
 <5pltwb73d7cynsxo2yb54ygjk7haviatkrx43mnzihc6kkield@ahnstpgof46i>
 <CA+hUKGKL3MRvEftAE+kwBuL2PLg2CwUoHEMr=-KSvsWN8pHq9w@mail.gmail.com>
 <ffcc1472-604e-48cf-afd1-25a245d3df4a@vondra.me>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <ffcc1472-604e-48cf-afd1-25a245d3df4a@vondra.me>
Archived-At: 
 <https://www.postgresql.org/message-id/e33gafg4p7iwvo24ytrxuw43nafm5xm3jefpdspnarcbkfurs7%403jbgdiinxem5>
Precedence: bulk

Hi,

On 2025-08-29 01:00:58 +0200, Tomas Vondra wrote:
> I'm not sure how to determine what concurrency it "wants". All I know is
> that for "warm" runs [1], the basic index prefetch patch uses distance
> ~2.0 on average, and is ~2x slower than master. And with the patches the
> distance is ~270, and it's 30% slower than master. (IIRC there's about
> 30% misses, so 270 is fairly high. Can't check now, the machine is
> running other tests.)

There got to be something wrong here, I don't see a reason why at any
meaningful distance it'd be slower.

What set of patches do I need to repro the issue?

And what are the complete set of pieces to load the data?
https://postgr.es/m/293a4735-79a4-499c-9a36-870ee9286281%40vondra.me
has the query, but afaict not enough information to infer init.sql


> Not sure about wait events, but I don't think any backends are doing
> sychnronous I/O. There's only that one query running, and it's using AIO
> (except for the index, which is still read synchronously).
> 
> Likewise, I don't think there's insufficient number of workers. I've
> tried with 3 and 12 workers, and there's virtually no difference between
> those. IIRC when watching "top", I've never seen more than 1 or maybe 2
> workers active (using CPU).

That doesn't say much - if the they are doing IO, they're not on CPU...

Greetings,

Andres Freund