From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [RFC PATCH 0/5] IPsec parallelization Date: Mon, 01 Dec 2008 12:20:22 +0100 Message-ID: <87hc5o5eh5.fsf@basil.nowhere.org> References: <20081201071614.GP476@secunet.com> <20081201084902.GA19904@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Steffen Klassert , netdev@vger.kernel.org, davem@davemloft.net, klassert@mathematik.tu-chemnitz.de To: Herbert Xu Return-path: Received: from one.firstfloor.org ([213.235.205.2]:55305 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751251AbYLALUP (ORCPT ); Mon, 1 Dec 2008 06:20:15 -0500 In-Reply-To: <20081201084902.GA19904@gondor.apana.org.au> (Herbert Xu's message of "Mon, 1 Dec 2008 16:49:02 +0800") Sender: netdev-owner@vger.kernel.org List-ID: Herbert Xu writes: > > I still think that you're much better off doing this in the > crypto layer. As it stands the only reason why this is attractive > is because crypto is slow. > > Pretty soon processors will start providing crypto support natively > so this will no longer be the case. I'm not sure that's a useful argument. When cryptography is not CPU bound anymore it will be memory bandwidth bound. And in this case you can still get a win out of parallelization if you parallelize over multiple sockets with own memory controller or own FSB because that will give you more bandwidth. -Andi -- ak@linux.intel.com