public inbox for linux-raid@vger.kernel.org
 help / color / mirror / Atom feed
From: "Yu Kuai" <yukuai@fnnas.com>
To: <song@kernel.org>
Cc: <linux-raid@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	 <linan122@huawei.com>, <xni@redhat.com>,
	"Yu Kuai" <yukuai@fnnas.com>
Subject: Re: [PATCH] md: support to align bio to limits
Date: Fri, 21 Nov 2025 13:19:40 +0800	[thread overview]
Message-ID: <8140d7a2-e152-4f6b-a16d-5fd1dcc2fe20@fnnas.com> (raw)
In-Reply-To: <20251121051406.1316884-3-yukuai@fnnas.com>

Hi,

I forgot to remove this patch, that is patch 3 in this set, before sending
to mail list, please ignore this one.

在 2025/11/21 13:14, Yu Kuai 写道:
> For personalities that report optimal IO size, it's indicate that users
> can get the best IO bandwidth if they issue IO with this size. However
> there is also an implicit condition that IO should also be aligned to the
> optimal IO size.
>
> Currently, bio will only be split by limits, if bio offset is not aligned
> to limits, then all split bio will not be aligned. This patch add a new
> feature to align bio to limits first, and following patches will support
> this for each personality if necessary.
>
> Signed-off-by: Yu Kuai <yukuai@fnnas.com>
> ---
>   drivers/md/md.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
>   drivers/md/md.h |  1 +
>   2 files changed, 47 insertions(+)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 7b5c5967568f..b09f87b27807 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -427,6 +427,48 @@ bool md_handle_request(struct mddev *mddev, struct bio *bio)
>   }
>   EXPORT_SYMBOL(md_handle_request);
>   
> +static struct bio *__md_bio_align_to_limits(struct mddev *mddev,
> +					    struct bio *bio)
> +{
> +	unsigned int max_sectors = mddev->gendisk->queue->limits.max_sectors;
> +	sector_t start = bio->bi_iter.bi_sector;
> +	sector_t align_start = roundup(start, max_sectors);
> +	sector_t end;
> +	sector_t align_end;
> +
> +	/* already aligned */
> +	if (align_start == start)
> +		return bio;
> +
> +	end = start + bio_sectors(bio);
> +	align_end = rounddown(end, max_sectors);
> +
> +	/* bio is too small to split */
> +	if (align_end <= align_start)
> +		return bio;
> +
> +	return bio_submit_split_bioset(bio, align_start - start,
> +				       &mddev->gendisk->bio_split);
> +}
> +
> +static struct bio *md_bio_align_to_limits(struct mddev *mddev, struct bio *bio)
> +{
> +	if (!mddev->bio_align_to_limits)
> +		return bio;
> +
> +	/* atomic write can't split */
> +	if (bio->bi_opf & REQ_ATOMIC)
> +		return bio;
> +
> +	switch (bio_op(bio)) {
> +	case REQ_OP_READ:
> +	case REQ_OP_WRITE:
> +		return __md_bio_align_to_limits(mddev, bio);
> +	default:
> +		return bio;
> +	}
> +}
> +
>   static void md_submit_bio(struct bio *bio)
>   {
>   	const int rw = bio_data_dir(bio);
> @@ -442,6 +484,10 @@ static void md_submit_bio(struct bio *bio)
>   		return;
>   	}
>   
> +	bio = md_bio_align_to_limits(mddev, bio);
> +	if (!bio)
> +		return;
> +
>   	bio = bio_split_to_limits(bio);
>   	if (!bio)
>   		return;
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index 75fd8c873b6f..1ed90fd85ac4 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -630,6 +630,7 @@ struct mddev {
>   	bool	has_superblocks:1;
>   	bool	fail_last_dev:1;
>   	bool	serialize_policy:1;
> +	bool	bio_align_to_limits:1;
>   };
>   
>   enum recovery_flags {

-- 
Thanks,
Kuai

  reply	other threads:[~2025-11-21  5:21 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-21  5:13 [PATCH 0/7] md: raid5,raid0,raid10: align bio to io_opt Yu Kuai
2025-11-21  5:13 ` [PATCH 1/7] md/raid5: use mempool to allocate stripe_request_ctx Yu Kuai
2025-11-21  5:14 ` [PATCH] md: support to align bio to limits Yu Kuai
2025-11-21  5:19   ` Yu Kuai [this message]
2025-11-25  1:37   ` kernel test robot
2025-11-25  8:23   ` kernel test robot
2025-11-21  5:14 ` [PATCH 2/7] md/raid5: make sure max_sectors is not less than io_opt Yu Kuai
2025-11-21  5:14 ` [PATCH 3/7] md: support to align bio to limits Yu Kuai
2025-11-22 21:20   ` kernel test robot
2025-11-21  5:14 ` [PATCH 4/7] md: add a helper md_config_align_limits() Yu Kuai
2025-11-21  5:14 ` [PATCH 5/7] md/raid5: align bio to io_opt Yu Kuai
2025-11-21  5:14 ` [PATCH 6/7] md/raid10: " Yu Kuai
2025-11-21  5:14 ` [PATCH 7/7] md/raid0: " Yu Kuai
2025-11-21  8:59   ` Paul Menzel

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=8140d7a2-e152-4f6b-a16d-5fd1dcc2fe20@fnnas.com \
    --to=yukuai@fnnas.com \
    --cc=linan122@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=song@kernel.org \
    --cc=xni@redhat.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