From: Stefan Hajnoczi <stefanha@redhat.com>
To: Sochin Jiang <jiangxiaoqing.sochin@bytedance.com>
Cc: mst@redhat.com, jasowang@redhat.com, pbonzini@redhat.com,
lizefan.x@bytedance.com, linux-kernel@vger.kernel.org,
Christoph Hellwig <hch@infradead.org>
Subject: Re: [PATCH] virtio_blk: make virtio blks as non-rotational devices
Date: Mon, 29 Mar 2021 17:23:20 +0100 [thread overview]
Message-ID: <YGH++CMejgUlvBy1@stefanha-x1.localdomain> (raw)
In-Reply-To: <20210326033914.65483-1-jiangxiaoqing.sochin@bytedance.com>
[-- Attachment #1: Type: text/plain, Size: 1583 bytes --]
On Fri, Mar 26, 2021 at 11:39:13AM +0800, Sochin Jiang wrote:
> This confuses some users seeing one rotational block device
> in the guest(/sys/block/vdx/queue/rotational), let's make
> virtio blks as virtual block devices, just like xen blks,
> and as we known, QUEUE_FLAG_VIRT is defined as QUEUE_FLAG_NONROT
> actually. See also rbd and nbd block devices.
>
> Signed-off-by: Sochin Jiang <jiangxiaoqing.sochin@bytedance.com>
> ---
> drivers/block/virtio_blk.c | 1 +
> 1 file changed, 1 insertion(+)
I would like to make this change because it seems consistent and often
the disk really is non-rotational. However, a justification and
performance results are needed especially since this has been reverted
previously. Please see commit f8b12e513b953aebf30f8ff7d2de9be7e024dbbe
("virtio_blk: revert QUEUE_FLAG_VIRT addition").
That was in 2009, so maybe things have changed now. Please explain what
has changed in the commit description.
This flag can affect performance. Please include performance data.
> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> index b9fa3ef5b57c..31a978a4dab5 100644
> --- a/drivers/block/virtio_blk.c
> +++ b/drivers/block/virtio_blk.c
> @@ -822,6 +822,7 @@ static int virtblk_probe(struct virtio_device *vdev)
> max_size = min(max_size, v);
>
> blk_queue_max_segment_size(q, max_size);
> + blk_queue_flag_set(QUEUE_FLAG_VIRT, q);
>
> /* Host can optionally specify the block size of the device */
> err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
> --
> 2.11.0
>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
parent reply other threads:[~2021-03-29 16:24 UTC|newest]
Thread overview: expand[flat|nested] mbox.gz Atom feed
[parent not found: <20210326033914.65483-1-jiangxiaoqing.sochin@bytedance.com>]
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=YGH++CMejgUlvBy1@stefanha-x1.localdomain \
--to=stefanha@redhat.com \
--cc=hch@infradead.org \
--cc=jasowang@redhat.com \
--cc=jiangxiaoqing.sochin@bytedance.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan.x@bytedance.com \
--cc=mst@redhat.com \
--cc=pbonzini@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
all inboxes | Powered by JetHome®