From: Holger Eitzenberger Subject: Re: [patch 0/6] netfilter: ctnetlink allocation improvement Date: Tue, 17 Mar 2009 11:03:51 +0100 Message-ID: <20090317100350.GA3526@mail.eitzenberger.org> References: <20090316220659.756862181@jonathan.eitzenberger.org> <49BF720C.2010603@netfilter.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Patrick McHardy , David Miller , netfilter-devel@vger.kernel.org, netdev@vger.kernel.org To: Pablo Neira Ayuso Return-path: Content-Disposition: inline In-Reply-To: <49BF720C.2010603@netfilter.org> Sender: netfilter-devel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Tue, Mar 17, 2009 at 10:49:00AM +0100, Pablo Neira Ayuso wrote: > > Though I haven't got any hard performance numbers yet I think this > > might introduce a noticable performance gain. > > I'm not sure about this. Instead, I noticed with oprofile that we spend > more cycles to calculate the message size. I think it's more like a > trade-off, reducing the message size to what we need reduces the chances > to hit ENOBUFS. Hi Pablo, your patch is a bit different, as you do the message length calculation on each packet. Instead I do it once at compile time for the proto independant part and then later for each protocol helper at the time it is registered. At unload time the helper is replaced by the generic one (which implies =0 always). Cheers, /holger