Date: Mon, 13 May 2002 06:01:18 -0700 From: Luigi Rizzo <luigi@FreeBSD.org> To: Poul-Henning Kamp <phk@critter.freebsd.dk> Cc: cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/net if_ethersubr.c src/sys/netinet ip_dummynet.c ip_dummynet.h Message-ID: <20020513060117.A31701@iguana.icir.org> In-Reply-To: <13421.1021290315@critter.freebsd.dk> References: <20020513043915.B30792@iguana.icir.org> <13421.1021290315@critter.freebsd.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
oh, whatever... i'll be glad to be proven wrong by some working code (and i am out of this discussion...) cheers luigi On Mon, May 13, 2002 at 01:45:15PM +0200, Poul-Henning Kamp wrote: > > >This said... if the ipfw ruleset is properly written, I am not sure > >that you can improve by more than a factor of 2..5, but I'll be glad to be > >proven wrong. > > A factor 5 isn't a bad thing. I think you overlook that by compiling > it to C we can leverage the GCC optimizer. > > For instance, a sequence like: > > ... > allow tcp from any to any 25 > allow tcp from any to any 113 > allow tcp from foohost to any 23 > ... > > The compile C code would likely only test for it being TCP once > > -- > Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 > phk@FreeBSD.ORG | TCP/IP since RFC 956 > FreeBSD committer | BSD since 4.3-tahoe > Never attribute to malice what can adequately be explained by incompetence. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020513060117.A31701>