From: Matthew Wilcox <willy@infradead.org>
To: "Darrick J. Wong" <djwong@kernel.org>
Cc: Fengnan Chang <changfengnan@bytedance.com>,
brauner@kernel.org, linux-xfs@vger.kernel.org,
linux-fsdevel@vger.kernel.org, Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org
Subject: Re: [PATCH] iomap: allow iomap using the per-cpu bio cache
Date: Fri, 22 Aug 2025 16:42:47 +0100 [thread overview]
Message-ID: <aKiP966iRv5gEBwm@casper.infradead.org> (raw)
In-Reply-To: <20250822150550.GP7942@frogsfrogsfrogs>
On Fri, Aug 22, 2025 at 08:05:50AM -0700, Darrick J. Wong wrote:
> On Fri, Aug 22, 2025 at 04:26:06PM +0800, Fengnan Chang wrote:
> > When use io_uring with direct IO, we could use per-cpu bio cache
> > from bio_alloc_bioset, So pass IOCB_ALLOC_CACHE flag to alloc
> > bio helper.
> >
> > + if (iter->flags & IOMAP_ALLOC_CACHE)
> > + bio_opf |= REQ_ALLOC_CACHE;
>
> Is there a reason /not/ to use the per-cpu bio cache unconditionally?
AIUI it's not safe because completions might happen on a different CPU
from the submission. At least, there's nowhere that sets REQ_ALLOC_CACHE
unconditionally.
This could do with some better documentation ..
next prev parent reply other threads:[~2025-08-22 15:42 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-22 8:26 [PATCH] iomap: allow iomap using the per-cpu bio cache Fengnan Chang
2025-08-22 15:05 ` Darrick J. Wong
2025-08-22 15:42 ` Matthew Wilcox [this message]
2025-08-22 16:07 ` Ritesh Harjani
2025-08-22 16:51 ` Matthew Wilcox
2025-08-23 4:15 ` Ritesh Harjani
2025-08-25 8:51 ` Fengnan Chang
2025-08-25 9:21 ` Christoph Hellwig
2025-08-25 9:41 ` Fengnan Chang
2025-08-25 10:47 ` Christoph Hellwig
2025-08-26 9:46 ` Fengnan Chang
2025-08-26 13:15 ` Christoph Hellwig
2025-08-26 16:53 ` Ritesh Harjani
2025-08-29 4:26 ` [External] " Fengnan Chang
2025-09-03 8:28 ` Fengnan Chang
2025-09-03 9:53 ` Pavel Begunkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aKiP966iRv5gEBwm@casper.infradead.org \
--to=willy@infradead.org \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=changfengnan@bytedance.com \
--cc=djwong@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).