From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: CBQ broken in 2.6 Date: Thu, 28 Jan 2010 12:53:17 +0000 Message-ID: <20100128125317.GA8931@ff.dom.local> References: <1264595308.29501.30.camel@tranquility.sigsegv.cx> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: David Miller , netdev@vger.kernel.org To: Anton Ivanov Return-path: Received: from mail-fx0-f220.google.com ([209.85.220.220]:60162 "EHLO mail-fx0-f220.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755285Ab0A1Mx0 (ORCPT ); Thu, 28 Jan 2010 07:53:26 -0500 Received: by fxm20 with SMTP id 20so618329fxm.21 for ; Thu, 28 Jan 2010 04:53:25 -0800 (PST) Content-Disposition: inline In-Reply-To: <1264595308.29501.30.camel@tranquility.sigsegv.cx> Sender: netdev-owner@vger.kernel.org List-ID: On 27-01-2010 13:28, Anton Ivanov wrote: > Thanks it is indeed sch_cbq.c, > > I have been going through the code in the meantime and found a place > where cl->tparent can be modified further down in the routine in > question. There is an invocation of cbq_set_lss() around the end of > cbq_change_class() which can do that. > > I am rebuilding the kernel for my CBQ box with a few printks at the > moment to see if it modified there or not. > > In any case here is the tell-tale symptom: > > class cbq 1:16 parent 1: leaf 76: rate 5600Kbit (bounded,isolated) prio > 2 > Sent 162051 bytes 925 pkt (dropped 0, overlimits 0 requeues 0) > rate 0bit 0pps backlog 0b 0p requeues 0 > borrowed 201 overactions 0 avgidle 78 undertime 0 > > That is a bounded class. Its borrowed should be always 0 no matter what. > That is basically a broken CBQ implementation. > > An elementary network test suite shows the same result - it is being > allowed to borrow. > > I am happy to send the whole config if necessary if someone wants to > look at it. Was this class created as bounded or changed later? Did it have any child? Jarek P.