linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Damien Le Moal <dlemoal@kernel.org>
To: Yu Kuai <yukuai1@huaweicloud.com>, Yu Kuai <hailan@yukuai.org.cn>,
	axboe@kernel.dk, tj@kernel.org, josef@toxicpanda.com,
	song@kernel.org, neil@brown.name, akpm@linux-foundation.org,
	hch@infradead.org, colyli@kernel.org, hare@suse.de,
	tieren@fnnas.com
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	cgroups@vger.kernel.org, linux-raid@vger.kernel.org,
	yi.zhang@huawei.com, yangerkun@huawei.com,
	johnny.chenyi@huawei.com, "yukuai (C)" <yukuai3@huawei.com>
Subject: Re: [PATCH RFC v2 09/10] block: fix disordered IO in the case recursive split
Date: Mon, 1 Sep 2025 15:51:23 +0900	[thread overview]
Message-ID: <73ce25dd-ce6e-4482-8537-b4f2166bbc47@kernel.org> (raw)
In-Reply-To: <5417dfdd-f558-2d5e-43b1-043c6bd30041@huaweicloud.com>

On 9/1/25 11:40 AM, Yu Kuai wrote:
> Hi,
> 
> 在 2025/08/30 12:28, Yu Kuai 写道:
>>>> @@ -745,12 +745,16 @@ void submit_bio_noacct_nocheck(struct bio *bio)
>>>>        * to collect a list of requests submited by a ->submit_bio method while
>>>>        * it is active, and then process them after it returned.
>>>>        */
>>>> -    if (current->bio_list)
>>>> -        bio_list_add(&current->bio_list[0], bio);
>>>> -    else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO))
>>>> +    if (current->bio_list) {
>>>> +        if (split)
>>>> +            bio_list_add_head(&current->bio_list[0], bio);
>>>> +        else
>>>> +            bio_list_add(&current->bio_list[0], bio);
>>> This really needs a comment clarifying why we do an add at tail instead of
>>> keeping the original order with a add at head. I am also scared that this may
>>> break sequential write ordering for zoned devices.
>>
>> I think add at head is exactly what we do here to keep the orginal order for
>> the case bio split. Other than split, if caller do generate multiple sequential
>> bios, we should keep the order by add at tail.
>>
>> Not sure about zoned devices for now, I'll have a look in details.
> 
> For zoned devices, can we somehow trigger this recursive split? I
> suspect bio disordered will apear in this case but I don't know for
> now and I can't find a way to reporduce it.

dm-linear can be stacked on e.g. dm-crypt, or the reverse. So recursive
splitting may be possible. Though since for DM everything is zone aligned, it
may be hard to find a reproducer. Though dm-crypt will always split BIOs to
BIO_MAX_VECS << PAGE_SECTORS_SHIFT sectors, so it may be possible with very
large BIOs. Would need to try, but really overloaded with other things right now.

> 
> Perhaps I can bypass zoned devices for now, and if we really met the
> recursive split case and there is a problem, we can fix it later:
> 
> if (split && !bdev_is_zoned(bio->bi_bdev))
>     bio_list_add_head()
> 
> Thanks,
> Kuai
> 


-- 
Damien Le Moal
Western Digital Research

  reply	other threads:[~2025-09-01  6:54 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-28  6:57 [PATCH RFC v2 00/10] block: fix disordered IO in the case recursive split Yu Kuai
2025-08-28  6:57 ` [PATCH RFC v2 01/10] block: factor out a helper bio_submit_split_bioset() Yu Kuai
2025-08-30  0:37   ` Damien Le Moal
2025-08-30  4:03     ` Yu Kuai
2025-08-28  6:57 ` [PATCH RFC v2 02/10] md/raid0: convert raid0_handle_discard() to use bio_submit_split_bioset() Yu Kuai
2025-08-30  0:41   ` Damien Le Moal
2025-08-30  4:10     ` Yu Kuai
2025-08-30  4:38       ` Damien Le Moal
2025-08-28  6:57 ` [PATCH RFC v2 03/10] md/raid1: convert " Yu Kuai
2025-08-30  0:43   ` Damien Le Moal
2025-08-28  6:57 ` [PATCH RFC v2 04/10] md/raid10: convert read/write " Yu Kuai
2025-08-30  0:48   ` Damien Le Moal
2025-08-30  4:18     ` Yu Kuai
2025-08-28  6:57 ` [PATCH RFC v2 05/10] md/raid5: convert " Yu Kuai
2025-08-30  0:50   ` Damien Le Moal
2025-08-28  6:57 ` [PATCH RFC v2 06/10] md/md-linear: " Yu Kuai
2025-08-30  0:51   ` Damien Le Moal
2025-08-28  6:57 ` [PATCH RFC v2 07/10] blk-crypto: " Yu Kuai
2025-08-30  0:55   ` Damien Le Moal
2025-08-28  6:57 ` [PATCH RFC v2 08/10] block: skip unnecessary checks for split bio Yu Kuai
2025-08-30  0:58   ` Damien Le Moal
2025-08-30  4:22     ` Yu Kuai
2025-08-28  6:57 ` [PATCH RFC v2 09/10] block: fix disordered IO in the case recursive split Yu Kuai
2025-08-30  1:02   ` Damien Le Moal
2025-08-30  4:28     ` Yu Kuai
2025-09-01  2:40       ` Yu Kuai
2025-09-01  6:51         ` Damien Le Moal [this message]
2025-08-28  6:57 ` [PATCH RFC v2 10/10] md/raid0: convert raid0_make_request() to use bio_submit_split_bioset() Yu Kuai

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=73ce25dd-ce6e-4482-8537-b4f2166bbc47@kernel.org \
    --to=dlemoal@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=colyli@kernel.org \
    --cc=hailan@yukuai.org.cn \
    --cc=hare@suse.de \
    --cc=hch@infradead.org \
    --cc=johnny.chenyi@huawei.com \
    --cc=josef@toxicpanda.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=neil@brown.name \
    --cc=song@kernel.org \
    --cc=tieren@fnnas.com \
    --cc=tj@kernel.org \
    --cc=yangerkun@huawei.com \
    --cc=yi.zhang@huawei.com \
    --cc=yukuai1@huaweicloud.com \
    --cc=yukuai3@huawei.com \
    /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).