Message-ID: <f1e19d97086cef964485dbb3ba3d7d8904709bb7.camel@j-davis.com>
Subject: Re: Should io_method=worker remain the default?
From: Jeff Davis <pgsql@j-davis.com>
To: Andres Freund <andres@anarazel.de>
Cc: Thomas Munro <thomas.munro@gmail.com>, pgsql-hackers@postgresql.org
Date: Mon, 08 Sep 2025 14:34:30 -0700
In-Reply-To: <g47verzfgnilmrestdb6o6echny4543fxmohkzqzcgasxvl7yl@752bn66qespk>
References: <d68e2a4f8c356107e5167408ad80eaa2fac0f57d.camel@j-davis.com>
	 <adywrhdn5zcfeldzug2pkzbdxizactr46goh4doiztvexrqomy@lgvl26gui63a>
	 <a81f2f7ef34afc24a89c613671ea017e3651329c.camel@j-davis.com>
	 <CA+hUKG+wCagh6mogKS_VL-SVABomho9beg7pLpntHRK2P6QrWA@mail.gmail.com>
	 <d2018eee32e211bdfc505862e9ae24b55cec5af0.camel@j-davis.com>
	 <g47verzfgnilmrestdb6o6echny4543fxmohkzqzcgasxvl7yl@752bn66qespk>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.52.3-0ubuntu1 
MIME-Version: 1.0
Archived-At: 
 <https://www.postgresql.org/message-id/f1e19d97086cef964485dbb3ba3d7d8904709bb7.camel%40j-davis.com>
Precedence: bulk

On Mon, 2025-09-08 at 16:45 -0400, Andres Freund wrote:
> I don't think accelerating copying from the pagecache into postgres
> shared
> buffers really is a goal of AIO. It can be a nice side-effect, but
> not more.

Interesting. I thought that was part of the design.

> Afaict you've not explained in what even remotely plausible scenario
> you'd
> have where > 30GB/s of reads from the page cache. I continue to
> maintain that
> the workload presented does not exist in the real world.

For now, let's just consider it a test case that stressed a couple
subsystems and found some interesting effects. I think it will be
helpful context for potential improvements in 19. If I find other
interesting cases, I'll post them.

Regards,
	Jeff Davis