From mboxrd@z Thu Jan 1 00:00:00 1970 From: Changli Gao Subject: Re: [PATCH] sch_htb.c consume the classes's tokens bellow the HTB_CAN_SEND level Date: Thu, 5 Nov 2009 13:44:25 +0800 Message-ID: <412e6f7f0911042144u1e5a4797kcb42b8d02b618086@mail.gmail.com> References: <4AEF9862.8040404@gmail.com> <412e6f7f0911031753m4af1467fn1b0326bdf17fe48b@mail.gmail.com> <20091104082808.GA6224@ff.dom.local> <412e6f7f0911040116q6b25b705k83e5a45464698af1@mail.gmail.com> <20091104104245.GB6224@ff.dom.local> <4AF15E73.30806@cdi.cz> <412e6f7f0911040330uc5ebbcekfef57854fce501f@mail.gmail.com> <4AF16C49.409@cdi.cz> <412e6f7f0911040408w5adcdde8yc1add4a561e90e40@mail.gmail.com> <4AF17066.1050504@cdi.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Jarek Poplawski , Jamal Hadi Salim , netdev@vger.kernel.org To: Martin Devera Return-path: Received: from mail-pw0-f42.google.com ([209.85.160.42]:54181 "EHLO mail-pw0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750787AbZKEFoU convert rfc822-to-8bit (ORCPT ); Thu, 5 Nov 2009 00:44:20 -0500 Received: by pwj9 with SMTP id 9so3671596pwj.21 for ; Wed, 04 Nov 2009 21:44:25 -0800 (PST) In-Reply-To: <4AF17066.1050504@cdi.cz> Sender: netdev-owner@vger.kernel.org List-ID: On Wed, Nov 4, 2009 at 8:15 PM, Martin Devera wr= ote: > Changli Gao wrote: > > Ok, then the reason is in "logic". When you have parent P and childre= n > A,B each with half of rate and only A is sending, than we want A to u= se > its own rate and also B's rate. B's rate is available as excess in P. > Here I see correct to charge part to A and part to P, while you want > to charge one P and twice A. Only mbuffer will limit the duplicity. > And it is not good idea because tokens can go very negative and then > ittroduce A's stall for some time. > I see no principial benefit... > I get it. After reviewing the code, I find mbuffer is 1 minute. It means that bandwidth will be unfair between A and B(A/B =3D 1/3) for at least 2 minute long. It is unacceptable. I'm wrong, and need to think it again! --=20 Regards=EF=BC=8C Changli Gao(xiaosuo@gmail.com)