From: Christoph Hellwig <hch@lst.de>
To: Christian Brauner <brauner@kernel.org>
Cc: Stefan Metzmacher <metze@samba.org>,
Christoph Hellwig <hch@lst.de>,
linux-fsdevel@vger.kernel.org,
Alexander Viro <viro@zeniv.linux.org.uk>, Jan Kara <jack@suse.cz>,
io-uring@vger.kernel.org, linux-api@vger.kernel.org
Subject: Re: [PATCH] fs: add RWF_DIRECT for preadv2/pwritev2/io_uring to set IOCB_DIRECT per io
Date: Fri, 20 Nov 2026 17:42:34 +0100 [thread overview]
Message-ID: <20261120164234.GA32683@lst.de> (raw)
In-Reply-To: <20261118-leihwagen-bauaufsicht-tritt-5fc43d456a16@brauner>
On Wed, Nov 18, 2026 at 03:53:56PM +0100, Christian Brauner wrote:
> On Tue, Nov 03, 2026 at 02:06:25PM +0100, Stefan Metzmacher wrote:
> > So what about making it opt-in as a start, like RWF_DONTCACHE with
> > FOP_DONTCACHE? A new FOP_DIRECT_PER_IO would be set by file systems
> > that base their I/O decisions on IOCB_DIRECT, all others return
> > -EOPNOTSUPP for RWF_DIRECT.
>
> Sounds kinda ok to me. So xfs, ext4 and btrfs would set it, I guess.
> Everything else returns -EOPNOTSUPP they're converted. That's the same
> thing we did for RWF_DONTCACHE.
>
> Christoph, how do you feel about that?
Not a fan, at least not without tightening up the coherency first.
next prev parent reply other threads:[~2026-11-20 16:42 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-12 18:46 [PATCH] fs: add RWF_DIRECT for preadv2/pwritev2/io_uring to set IOCB_DIRECT per io Stefan Metzmacher
2026-10-21 11:04 ` Christian Brauner
2026-11-03 8:07 ` Christoph Hellwig
2026-11-03 13:06 ` Stefan Metzmacher
2026-11-18 14:53 ` Christian Brauner
2026-11-20 16:42 ` Christoph Hellwig [this message]
2026-11-03 13:51 ` Paulo Alcantara
2026-11-03 19:13 ` Andy Lutomirski
2026-11-04 7:30 ` direct I/O vs buffered I/O coherency, was: " Christoph Hellwig
2026-11-04 17:48 ` Andy Lutomirski
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=20261120164234.GA32683@lst.de \
--to=hch@lst.de \
--cc=brauner@kernel.org \
--cc=io-uring@vger.kernel.org \
--cc=jack@suse.cz \
--cc=linux-api@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=metze@samba.org \
--cc=viro@zeniv.linux.org.uk \
/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