From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnaldo Carvalho de Melo Subject: Re: fedora 14 kernel performance with ip forwarding workload Date: Wed, 6 Apr 2011 17:13:05 -0300 Message-ID: <20110406201305.GF14697@ghostprotocols.net> References: <20110406.121208.189703414.davem@davemloft.net> <20110406195719.GE14697@ghostprotocols.net> <20110406.130239.232756965.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: fedora-kernel-list-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, jesse.brandeburg-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, jesse.brandeburg-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org To: David Miller Return-path: Content-Disposition: inline In-Reply-To: <20110406.130239.232756965.davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kernel-bounces-TuqUDEhatI4ANWPb/1PvSmm0pvjS0E/A@public.gmane.org Errors-To: kernel-bounces-TuqUDEhatI4ANWPb/1PvSmm0pvjS0E/A@public.gmane.org List-Id: netdev.vger.kernel.org Em Wed, Apr 06, 2011 at 01:02:39PM -0700, David Miller escreveu: > From: Arnaldo Carvalho de Melo > Date: Wed, 6 Apr 2011 16:57:19 -0300 > > > Something like ftrace code changing when the user inserts the first > > rule? > > > > People wanting top performance disable it in the build, but thos wanting > > to stick to vendor provided kernels don't have that choice :) > > Using ftrace-like stubs would be an interesting idea, and I highly encourage > people to work on something like that. cool, these code modification and JIT mechanizms open up a lot of possibilities indeed ;-) > However I want to reiterate that I think that real rules are installed > in Jesse's case, and once he removes those the majority of the > overhead will disappear. The FC14 workstation I'm using right now, on > > which I've made no modifications to the installer's netfilter settings, > has the following rules: > I suspect Jesse has something similar on his test box. > > When no rules are loaded, all the stubs make happen is a function call > plus a list_empty() check. Nothing more. I really can't see that, all > by itself, obliterating routing performance. Yeah, would be nice, since he is playing with it, for him to post numbers about the overheads. > In fact I've done udp flood tests, as recently as a month ago, with just > NETFILTER=y and no rules installed, and the impact was minimal. > > And that was on sparc64 where function calls are expensive :) :-) - Arnaldo