Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 25 May 2006 12:20:17 -0400 (EDT)
From:      Andrew Gallatin <gallatin@cs.duke.edu>
To:        Peter Jeremy <peterjeremy@optushome.com.au>
Cc:        Gordon Bergling <gbergling@0xfce3.net>, freebsd-current@freebsd.org, Max Laier <max@love2party.net>
Subject:   Re: Take 2: new IP Checksum Code from DragonFlyBSD
Message-ID:  <17525.55617.272397.806798@grasshopper.cs.duke.edu>
In-Reply-To: <20060525115447.GB724@turion.vk2pj.dyndns.org>
References:  <20060524180802.GA59176@central.0xfce3.net> <200605250517.12054.max@love2party.net> <20060525104000.GA4962@central.0xfce3.net> <20060525115447.GB724@turion.vk2pj.dyndns.org>

next in thread | previous in thread | raw e-mail | index | archive | help

Peter Jeremy writes:
 > On Thu, 2006-May-25 12:40:00 +0200, Gordon Bergling wrote:
 > >* Thus spake Max Laier (max@love2party.net):
 > >> I'm a little scared about this.  We have had several problems in the 
 > >> checksumming code that were due to -O2 or -O0 that screwed up just a little 
 > 
 > > | * This routine is very heavily used in the network
 > > | * code and should be modified for each CPU to be as fast as
 > > | * possible.
 > 
 > But _correct_ code is far more important.  And I'm not sure that comment
 > is still as relevant as it used to be - most (if not all) gigabit NICs
 > have checksum offloading and processors are fast enough that generic
 > checksum code should be "good enough" for most lesser purposes.

The benchmark quoted in the original post is interesting in that it is
the best example of where improving the checksumming code would help,
yet we really should not be checksumming packets sent across lo0
anyway.

If we're going to do anything,  I'd prefer to see us skip
the checksum on everything sent across lo0 and stick with
the slower, yet known to work, existing checksum code for
slow interfaces.

Drew






Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?17525.55617.272397.806798>