From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andy Furniss Subject: Re: [NET_SCHED 00/04]: External SFQ classifiers/flow classifier Date: Fri, 04 Apr 2008 18:01:18 +0100 Message-ID: <47F65EDE.3010507@andyfurniss.entadsl.com> References: <20080131175758.25151.20370.sendpatchset@localhost.localdomain> <47A4FB81.80700@fatooh.org> <47A74FEE.6080103@trash.net> <47EED247.50801@andyfurniss.entadsl.com> <47F22CF5.4080806@trash.net> <47F28758.1010401@andyfurniss.entadsl.com> <47F37139.9080303@andyfurniss.entadsl.com> <47F37E04.4010001@trash.net> <47F3B3C5.6000701@andyfurniss.entadsl.com> <47F6062E.9050804@andyfurniss.entadsl.com> <47F606D8.108@trash.net> 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: Corey Hickey , Linux Netdev List To: Patrick McHardy Return-path: Received: from mx1.ukfsn.org ([77.75.108.10]:55702 "EHLO mail.ukfsn.org" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751114AbYDDQ7w (ORCPT ); Fri, 4 Apr 2008 12:59:52 -0400 In-Reply-To: <47F606D8.108@trash.net> Sender: netdev-owner@vger.kernel.org List-ID: Patrick McHardy wrote: > Andy Furniss wrote: >> I notice allot is short (16bits?) in sfq but see >> >> +struct tc_sfq_xstats >> +{ >> + __s32 allot; >> +}; > > That doesn't matter, its promoted to a 32 bit value. But now > that you mention it, the SFQ patch for iproute I submitted > used a different type. Stephen has resynced it with the kernel > in the mean time, but you might be using the broken version. OK - I have the __s32 version in iproute git and in kernel 2.6.25-rc7. I did have some hassle building iproute2 though, tc built OK once I removed ip from the build, so maybe I'll try again over the weekend from scratch just incase I messed something up. Looking at the sfq code it seems that enqueue doesn't init/zero allot for a new flow unless it's the first and most of what I see fits with this. But rarely it doesn't look like that's all there is to it. Andy.