All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Peter-Jan Gootzen <pgootzen@nvidia.com>
Cc: virtualization@lists.linux.dev, vgoyal@redhat.com,
	stefanha@redhat.com, miklos@szeredi.hu, dgilbert@redhat.com,
	yorayz@nvidia.comm, gurtovoy@nvidia.com
Subject: Re: [PATCH 0/2] virtio-fs: introduce multi-queue support
Date: Fri, 10 May 2024 07:05:50 -0400	[thread overview]
Message-ID: <20240510070542-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <20240501153817.540855-1-pgootzen@nvidia.com>

On Wed, May 01, 2024 at 05:38:15PM +0200, Peter-Jan Gootzen wrote:
> In this patch set we are adding multi-queue support in the virtio-fs
> driver to enhance performance.
> While multi-queue functionality has been in the virtio-fs specification
> since its inception, the current implementation in the Linux kernel
> creates multiple queues, but only enqueues requests on the first request
> queue.
> 
> The first commit in this patch set limits the number of request queues
> to the number of CPUs in the system, to reduce unnecessary resource
> consumption on the device-side.
> The second commit adds a multi queue mapping to the virtio-fs device
> driver that is created using MSI-X affinity mappings or, in case of no
> existing mappings, by evenly grouping the CPUs and dividing the queues
> over these groups.


Acked-by: Michael S. Tsirkin <mst@redhat.com>

> Future work in this direction could include:
> - CPU hotplug support
> - In case of no MSI-X, using the created multi-queue mapping to set
>   interrupt affinities
> 
> See the commit message of the second patch for performance results.
> 
> Peter-Jan Gootzen (2):
>   virtio-fs: limit number of request queues
>   virtio-fs: add multi-queue support
> 
>  fs/fuse/virtio_fs.c | 73 ++++++++++++++++++++++++++++++++++++++++-----
>  1 file changed, 65 insertions(+), 8 deletions(-)
> 
> -- 
> 2.34.1


  parent reply	other threads:[~2024-05-10 11:05 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-01 15:38 [PATCH 0/2] virtio-fs: introduce multi-queue support Peter-Jan Gootzen
2024-05-01 15:38 ` [PATCH 1/2] virtio-fs: limit number of request queues Peter-Jan Gootzen
2024-05-06 19:10   ` Stefan Hajnoczi
2024-05-28  8:40   ` Jingbo Xu
2024-05-28  9:05     ` Peter-Jan Gootzen
2024-05-28  9:13       ` Jingbo Xu
2024-05-01 15:38 ` [PATCH 2/2] virtio-fs: add multi-queue support Peter-Jan Gootzen
2024-05-28  8:51   ` Jingbo Xu
2024-05-28 11:59     ` Miklos Szeredi
2024-05-28 12:39       ` Peter-Jan Gootzen
2024-05-28 13:22         ` Miklos Szeredi
2024-05-28 13:35       ` Jingbo Xu
2024-05-28 14:21         ` Peter-Jan Gootzen
2024-05-29  1:52           ` Jingbo Xu
2024-05-29  9:27             ` Peter-Jan Gootzen
2024-05-06 19:52 ` [PATCH 0/2] virtio-fs: introduce " Stefan Hajnoczi
2024-05-10 11:05 ` Michael S. Tsirkin [this message]
2024-05-10 11:41   ` Miklos Szeredi

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=20240510070542-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=gurtovoy@nvidia.com \
    --cc=miklos@szeredi.hu \
    --cc=pgootzen@nvidia.com \
    --cc=stefanha@redhat.com \
    --cc=vgoyal@redhat.com \
    --cc=virtualization@lists.linux.dev \
    --cc=yorayz@nvidia.comm \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.