From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail2.tohojo.dk (mail2.tohojo.dk [77.235.48.147]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id C4C083B25E; Wed, 10 Aug 2016 16:06:49 -0400 (EDT) X-Virus-Scanned: amavisd-new at mail2.tohojo.dk DKIM-Filter: OpenDKIM Filter v2.10.3 mail2.tohojo.dk A015A40D5E DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=toke.dk; s=201310; t=1470859606; bh=LkGqBUd/U7LupMHYXR7Gda7OOYof3ch6fMpzJvFogvo=; h=In-Reply-To:References:Subject:From:Date:To:CC:From; b=lPZpeHwPLrd/ogAWsFLfLp1QAWy89OUp6U0nZsI/HNATGxOzJQqImokBK0diSeVN8 IPLwcLTfj3in6SFD/RtoAnJ37zBSlKF8t29jlOiq566wKmE6JkawC/d2f8eZRwqiGI HaTbiCe44ETU/yG7uvG9A4F7Mp+gpA/1rPuX9hxg= Sender: toke@toke.dk In-Reply-To: References: <76eb6a6a-2f39-3b36-d4c1-04198083c0f6@gmail.com> <87oa50acnr.fsf@toke.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 From: =?ISO-8859-1?Q?Toke_H=F8iland-J=F8rgensen?= Date: Wed, 10 Aug 2016 22:06:39 +0200 To: Dave Taht CC: Noah Causin , make-wifi-fast@lists.bufferbloat.net, "cerowrt-devel@lists.bufferbloat.net" , Felix Fietkau , Simon Wunderlich X-Clacks-Overhead: GNU Terry Pratchett Message-ID: Content-Transfer-Encoding: quoted-printable Subject: Re: [Cerowrt-devel] [Make-wifi-fast] wifi airtime fairness patches could use eyeballs and testing X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Aug 2016 20:06:49 -0000 On 10 August 2016 21:35:40 CEST, Dave Taht wrote: >Wow, that *is* weird. It is good to see the tcp window changing on >this set of data (it wasn't before), and CWRs, but... hmmm... SCIENCE. > >Enabling ecn on both sides will rule out some potential bugs. Yeah, couldn't get ecn to work on the host I was using as the other endpo= int on that test. Will try with another box that's not on quite as ancien= t a kernel. Was also planning to disable codel (by setting a very high t= arget) to try to narrow down the problem. >Doubling the quantum again (3028) will go easier on the other side's >tcp stack. (unless 3028 is the wrong number at this layer) The endpoints have plenty of CPU. >Are you thinking timestamps are being scribbled on? Not necessarily; that was related to something else... -Toke