linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Gao Xiang <hsiangkao@linux.alibaba.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <dgc@kernel.org>, Tal Zussman <tz2294@columbia.edu>,
	Jens Axboe <axboe@kernel.dk>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Christian Brauner <brauner@kernel.org>,
	"Darrick J. Wong" <djwong@kernel.org>,
	Carlos Maiolino <cem@kernel.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>, Jan Kara <jack@suse.cz>,
	linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org
Subject: Re: [PATCH RFC v4 2/3] iomap: use BIO_COMPLETE_IN_TASK for dropbehind writeback
Date: Fri, 27 Mar 2026 14:45:12 +0800	[thread overview]
Message-ID: <9e83a4b5-ac4f-46d1-9510-a24e7ef54b87@linux.alibaba.com> (raw)
In-Reply-To: <acYjSMkz9MdWQKoJ@infradead.org>



On 2026/3/27 14:27, Christoph Hellwig wrote:
> On Fri, Mar 27, 2026 at 02:24:02PM +0800, Gao Xiang wrote:
>>   - use EROFS directly, in that case, we still need process
>>     contexts to decompress, but due to Android latency
>>     requirements, they really need per-cpu RT threads instead,
>>     otherwise it will cause serious regression too; but I'm not
>>     sure that case can be replaced by this work since workqueues
>>     don't support RT threads and I guess generic block layer
>>     won't be bothered with that too.
> 
> All of the I/O completions should be latency sensitive.  So I think it
> would be great if you could help out here with the requirements and
> implementation.

Yes, especially for sync read completion. Our requirement can
be outlined as:

   - a mark to make the whole bio completion in task, so that
     we ensure that the bio completion is in the task context
     so that we don't need to worry about that;

   - another per-CPU RT thread flag (or similiar) relates to
     a bio or some other things, so that bio completion can be
     handled by per-cpu RT threads instead of workqueues
     instead.

If they meet, I think that would be very helpful to clean
up our internal codebase at least.

Thanks,
Gao Xiang


  reply	other threads:[~2026-03-27  6:45 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-25 18:42 [PATCH RFC v4 0/3] block: enable RWF_DONTCACHE for block devices Tal Zussman
2026-03-25 18:43 ` [PATCH RFC v4 1/3] block: add BIO_COMPLETE_IN_TASK for task-context completion Tal Zussman
2026-03-25 19:54   ` Matthew Wilcox
2026-03-25 20:14   ` Jens Axboe
2026-04-08 18:48     ` Tal Zussman
2026-04-08 19:51       ` Jens Axboe
2026-04-08 22:51         ` Tal Zussman
2026-04-08 23:36           ` Jens Axboe
2026-03-25 20:26   ` Dave Chinner
2026-03-25 20:39     ` Matthew Wilcox
2026-03-26  2:44       ` Dave Chinner
2026-04-08 18:50     ` Tal Zussman
2026-03-25 21:03   ` Bart Van Assche
2026-03-26  3:18     ` Dave Chinner
2026-03-27  6:01   ` Christoph Hellwig
2026-04-08 19:35     ` Tal Zussman
2026-03-25 18:43 ` [PATCH RFC v4 2/3] iomap: use BIO_COMPLETE_IN_TASK for dropbehind writeback Tal Zussman
2026-03-25 20:21   ` Matthew Wilcox
2026-03-27  6:03     ` Christoph Hellwig
2026-04-08 19:36     ` Tal Zussman
2026-04-08 19:44     ` Tal Zussman
2026-04-08 20:01       ` Matthew Wilcox
2026-04-08 20:10         ` Tal Zussman
2026-03-25 20:34   ` Dave Chinner
2026-03-27  6:08     ` Christoph Hellwig
2026-03-27  6:24       ` Gao Xiang
2026-03-27  6:27         ` Christoph Hellwig
2026-03-27  6:45           ` Gao Xiang [this message]
2026-03-25 18:43 ` [PATCH RFC v4 3/3] block: enable RWF_DONTCACHE for block devices Tal Zussman

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=9e83a4b5-ac4f-46d1-9510-a24e7ef54b87@linux.alibaba.com \
    --to=hsiangkao@linux.alibaba.com \
    --cc=axboe@kernel.dk \
    --cc=brauner@kernel.org \
    --cc=cem@kernel.org \
    --cc=dgc@kernel.org \
    --cc=djwong@kernel.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=tz2294@columbia.edu \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.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