From mboxrd@z Thu Jan 1 00:00:00 1970 From: Patrick McHardy Subject: Re: [PATCH 4/5] netem: avoid excessive requeues Date: Fri, 23 Mar 2007 14:26:15 +0100 Message-ID: <4603D577.4010509@trash.net> References: <20070321174231.890361963@linux-foundation.org> <20070321174422.767901837@linux-foundation.org> <4602E9CB.8030500@trash.net> <20070322.140816.104054993.davem@davemloft.net> <4603B4A6.7050202@trash.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Cc: shemminger@linux-foundation.org, netdev@vger.kernel.org To: David Miller Return-path: Received: from stinky.trash.net ([213.144.137.162]:61231 "EHLO stinky.trash.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932960AbXCWN0n (ORCPT ); Fri, 23 Mar 2007 09:26:43 -0400 In-Reply-To: <4603B4A6.7050202@trash.net> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Patrick McHardy wrote: > David Miller wrote: > >>>Perhaps we should put this in qdisc_restart, other qdiscs have the >>>same problem. >> >> >>Agreed, patches welcome :) > > > I've tried this, but for some reason it makes TBF stay about > 5% under the configured rate. Probably because of late timers, > the strange thing is that the 5% happen constantly even with > very low rates. Turns out it was a mistake during testing, I measured on the ethernet device that is also used by my PPPoE connection, which had some traffic too. iptraf only measures IP packets, so it didn't show the bandwidth used by PPPoE. Patch coming up :)