lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250629123339.0dd73fb1@pumpkin>
Date: Sun, 29 Jun 2025 12:33:39 +0100
From: David Laight <david.laight.linux@...il.com>
To: Eric Dumazet <edumazet@...gle.com>
Cc: Feng Yang <yangfeng59949@....com>, davem@...emloft.net, kuba@...nel.org,
 pabeni@...hat.com, horms@...nel.org, willemb@...gle.com,
 almasrymina@...gle.com, kerneljasonxing@...il.com, ebiggers@...gle.com,
 asml.silence@...il.com, aleksander.lobakin@...el.com, stfomichev@...il.com,
 yangfeng@...inos.cn, netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] skbuff: Improve the sending efficiency of
 __skb_send_sock

On Fri, 27 Jun 2025 03:19:27 -0700
Eric Dumazet <edumazet@...gle.com> wrote:

> On Fri, Jun 27, 2025 at 2:44 AM Feng Yang <yangfeng59949@....com> wrote:
> >
> > From: Feng Yang <yangfeng@...inos.cn>
> >
> > By aggregating skb data into a bvec array for transmission, when using sockmap to forward large packets,
> > what previously required multiple transmissions now only needs a single transmission, which significantly enhances performance.
> > For small packets, the performance remains comparable to the original level.
> >
> > When using sockmap for forwarding, the average latency for different packet sizes
> > after sending 10,000 packets is as follows:
> > size    old(us)         new(us)
> > 512     56              55
> > 1472    58              58
> > 1600    106             79
> > 3000    145             108
> > 5000    182             123
> >
> > Signed-off-by: Feng Yang <yangfeng@...inos.cn>  
> 
> Instead of changing everything, have you tried strategically adding
> MSG_MORE in this function ?
> 

Does (could) this code ever be used for protocols other than TCP?
For UDP setting MSG_MORE will generate a single datagram.
For SCTP all the data actually has to be sent as a single sendmsg()
in order to generate a single DATA chunk.

Prior to 6.5 the code used sock->ops->sendpage_locked() so had to do
a separate call per page.
But if all the overheads of 'ioc_iter' are being added it does seen
appropriate to make use of its features!

	David
 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ