[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230116111207.yxlwh4jlejtn4ple@sgarzare-redhat>
Date: Mon, 16 Jan 2023 12:12:07 +0100
From: Stefano Garzarella <sgarzare@...hat.com>
To: Bobby Eshleman <bobby.eshleman@...edance.com>
Cc: Bobby Eshleman <bobbyeshleman@...il.com>,
Cong Wang <cong.wang@...edance.com>,
Arseniy Krasnov <AVKrasnov@...rdevices.ru>,
Stefan Hajnoczi <stefanha@...hat.com>,
"Michael S. Tsirkin" <mst@...hat.com>,
Jason Wang <jasowang@...hat.com>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, kvm@...r.kernel.org,
virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH net-next v10] virtio/vsock: replace virtio_vsock_pkt with
sk_buff
On Fri, Jan 13, 2023 at 10:21:37PM +0000, Bobby Eshleman wrote:
>This commit changes virtio/vsock to use sk_buff instead of
>virtio_vsock_pkt. Beyond better conforming to other net code, using
>sk_buff allows vsock to use sk_buff-dependent features in the future
>(such as sockmap) and improves throughput.
>
>This patch introduces the following performance changes:
>
>Tool: Uperf
>Env: Phys Host + L1 Guest
>Payload: 64k
>Threads: 16
>Test Runs: 10
>Type: SOCK_STREAM
>Before: commit b7bfaa761d760 ("Linux 6.2-rc3")
>
>Before
>------
>g2h: 16.77Gb/s
>h2g: 10.56Gb/s
>
>After
>-----
>g2h: 21.04Gb/s
>h2g: 10.76Gb/s
>
>Signed-off-by: Bobby Eshleman <bobby.eshleman@...edance.com>
>
>---
>Changes in v10:
>- vhost/vsock: use virtio_vsock_skb_dequeue()
>- vhost/vsock: remove extra iov_length() call
>- vhost/vsock: also consider hdr when evaluating that incoming size is
> valid
>- new uperf data
Tests seem fine!
Reviewed-by: Stefano Garzarella <sgarzare@...hat.com>
Powered by blists - more mailing lists