From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andy Furniss Subject: Re: [RFC NET_SCHED 00/02]: Flexible SFQ flow classification Date: Wed, 30 May 2007 12:18:18 +0100 Message-ID: <465D5D7A.8090200@andyfurniss.entadsl.com> References: <20070530094020.24073.84277.sendpatchset@localhost.localdomain> Reply-To: lists@andyfurniss.entadsl.com Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, hadi@cyberus.ca To: Patrick McHardy Return-path: Received: from s2.ukfsn.org ([217.158.120.143]:48385 "EHLO mail.ukfsn.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751506AbXE3LSF (ORCPT ); Wed, 30 May 2007 07:18:05 -0400 In-Reply-To: <20070530094020.24073.84277.sendpatchset@localhost.localdomain> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Patrick McHardy wrote: > One good thing about ESFQ is the more flexible flow classification, but > I don't like the concept of having a set of selectable hash functions > very much. > > These patches change SFQ to allow attaching external classifiers and add > a new "flow" classifier that allows to classify flows based on an arbitary > combination of pre-defined keys. Its probably not the fastest classifier > when used with multiple keys, but frankly, I don't think speed is very > important in most situations where the current SFQ implementation is used. > > It currently does not support perturbation, I didn't want to move this into > the classifier, so I need to think about a way to handle it within SFQ. > Cool, but isn't this going to show the same collision problems that the pre jhash esfq saw? Andy.