Date: Wed, 12 Mar 2003 09:20:05 -0800 From: "Crist J. Clark" <crist.clark@attbi.com> To: Luigi Rizzo <rizzo@icir.org> Cc: ipfw@FreeBSD.ORG Subject: Re: Anti-Spoofing Option Message-ID: <20030312172005.GA16143@blossom.cjclark.org> In-Reply-To: <20030312014600.A96366@xorpc.icir.org> References: <20030312080622.GA42446@blossom.cjclark.org> <20030312014600.A96366@xorpc.icir.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Mar 12, 2003 at 01:46:00AM -0800, Luigi Rizzo wrote:
> any idea on the cost (time ?) of the processing of verrevpath ?
> I am not sure on what rtalloc_ign() does, whether it allocates
> memory or not, etc.
>
> E.g. it would be nice if you had some comparison of the pps throughput of
>
> ipfw add 100 pass ip from any to any verrevpath
>
> vs.
>
> ipfw add 100 pass ip from any to any
>
> on some system (maybe you should take a slow box or you
> won't see much degradation as there are spare CPU cycles even
> when the interface is maxed out).
Oh-ho, I got slow boxes to test on. I'll set up some runs.
However, I don't think this would be too great of a hit. After all,
this is what is done for each packet leaving the system already. The
code to look up the route is pretty much identical to how it is done
in ip_output().
--
Crist J. Clark | cjclark@alum.mit.edu
| cjclark@jhu.edu
http://people.freebsd.org/~cjc/ | cjc@freebsd.org
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-ipfw" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030312172005.GA16143>