9front - general discussion about 9front
 help / color / mirror / Atom feed
From: Arne Meyer <meyer.arne83@netcologne.de>
To: 9front@9front.org
Subject: Re: [9front] [patch] ethervgbe: add rx checksum offloading
Date: Sat, 19 Nov 2022 21:09:09 +0100 (CET)	[thread overview]
Message-ID: <632533984.161412.1668888549169@comcenter.netcologne.de> (raw)
In-Reply-To: <1485335506.4596272.1668188142183@comcenter.netcologne.de>

Is hw offloading something we want? I ask because I think there is something wrong with ether8169 offloading and I'm working on a patch to fix or axe this.

> Arne Meyer <meyer.arne83@netcologne.de> hat am 11.11.2022 17:35 GMT geschrieben:
> To be honest, no. I was reading through the source code and found out that
> the ip stack supports RX checksum offloading, so i thought it was fun to implement it.
> The vgbe driver is my pet project.
> It's been in my local repo and kernel for about a week now and it didn't hurt. Blocks get send up the stack anyway, 
> the only difference is that the code sets the flags for the blocks. Worst case scenario here is that the driver flags checksums as valid even when they are not.
> OpenBSD and FreeBSD both support it, so i think it's stable(ish). But as a fellow network admin, I somewhat agree
> with you.
> > hiro <23hiro@gmail.com> hat am 11.11.2022 17:01 GMT geschrieben:
> > 
> >  
> > did you find concrete use cases where it's worth offloading this?
> > some kind of actual bottleneck?
> > in practice one of my most frequent network administration related
> > tasks is to turn off all kinds of weird (broken) offloading features
> > on random ethernet cards.
> > 
> > On 11/11/22, Arne Meyer <meyer.arne83@netcologne.de> wrote:
> > > Hello,
> > >
> > > this patch implements rx tcp and udp checksum offloading for ipv4 for the
> > > ethervgbe nic driver.
> > >
> > > Greetings,
> > > Arne

  reply	other threads:[~2022-11-19 20:12 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-11 16:13 Arne Meyer
2022-11-11 17:01 ` hiro
2022-11-11 17:35   ` Arne Meyer
2022-11-19 20:09     ` Arne Meyer [this message]
2022-11-19 21:36       ` ori
2022-11-20 12:44         ` hiro
2022-12-07 19:12           ` hiro
2022-12-08  1:41             ` cinap_lenrek

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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=632533984.161412.1668888549169@comcenter.netcologne.de \
    --to=meyer.arne83@netcologne.de \
    --cc=9front@9front.org \


* 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;
as well as URLs for NNTP newsgroup(s).