Re: [aqm] Is bufferbloat a real problem?

Mikael Abrahamsson <swmike@swm.pp.se> Sat, 28 February 2015 05:45 UTC

Return-Path: <swmike@swm.pp.se>
X-Original-To: aqm@ietfa.amsl.com
Delivered-To: aqm@ietfa.amsl.com
Received: from localhost (ietfa.amsl.com [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 4BF5B1A1BA4 for <aqm@ietfa.amsl.com>; Fri, 27 Feb 2015 21:45:15 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.062
X-Spam-Level:
X-Spam-Status: No, score=-2.062 tagged_above=-999 required=5 tests=[BAYES_20=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HELO_EQ_SE=0.35, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, T_RP_MATCHES_RCVD=-0.01] autolearn=ham
Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id EedddTDKdM_y for <aqm@ietfa.amsl.com>; Fri, 27 Feb 2015 21:45:13 -0800 (PST)
Received: from uplift.swm.pp.se (swm.pp.se [212.247.200.143]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id F07751A1BA3 for <aqm@ietf.org>; Fri, 27 Feb 2015 21:45:12 -0800 (PST)
Received: by uplift.swm.pp.se (Postfix, from userid 501) id 41DC6A3; Sat, 28 Feb 2015 06:45:09 +0100 (CET)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=swm.pp.se; s=mail; t=1425102309; bh=NH3s9vi65GfQnSisZzSTEjFeoTjlTBQraS18upoKOfQ=; h=Date:From:To:cc:Subject:In-Reply-To:References:From; b=I/wseSBUDHEaobPSInR29E760RpxWslib088zuVm4HZu2OFLbLo3P7nRD2C66wm4+ VhXHBBoYUxIlZNbHpg2fu2KmNLEjxystnYH3sOyR90ErdWVuyLWhHLNbx/wS3TxZNW PAiXxr6aXAyyo/AOEGl4QHMtYKLq77xh3Y70ZgCs=
Received: from localhost (localhost [127.0.0.1]) by uplift.swm.pp.se (Postfix) with ESMTP id 3D6D0A2; Sat, 28 Feb 2015 06:45:09 +0100 (CET)
Date: Sat, 28 Feb 2015 06:45:09 +0100 (CET)
From: Mikael Abrahamsson <swmike@swm.pp.se>
To: Daniel Havey <dhavey@gmail.com>
In-Reply-To: <CAO1c0ARbAt4H5AupHMSa7ziL6JZXJEw-kxbua2xz3QAHt4UgiA@mail.gmail.com>
Message-ID: <alpine.DEB.2.02.1502280641270.4007@uplift.swm.pp.se>
References: <2134947047.1078309.1424979858723.JavaMail.yahoo@mail.yahoo.com> <201502271852.t1RIqekh018253@maildrop31.somerville.occnc.com> <CAO1c0ARbAt4H5AupHMSa7ziL6JZXJEw-kxbua2xz3QAHt4UgiA@mail.gmail.com>
User-Agent: Alpine 2.02 (DEB 1266 2009-07-14)
Organization: People's Front Against WWW
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed
Archived-At: <http://mailarchive.ietf.org/arch/msg/aqm/Gut_1KN4O2I3p6jHPjY7TZ4z27Q>
Cc: "aqm@ietf.org" <aqm@ietf.org>, Daniel Havey <dhavey@yahoo.com>, curtis@ipv6.occnc.com
Subject: Re: [aqm] Is bufferbloat a real problem?
X-BeenThere: aqm@ietf.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: "Discussion list for active queue management and flow isolation." <aqm.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/aqm>, <mailto:aqm-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/aqm/>
List-Post: <mailto:aqm@ietf.org>
List-Help: <mailto:aqm-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/aqm>, <mailto:aqm-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sat, 28 Feb 2015 05:45:15 -0000

On Fri, 27 Feb 2015, Daniel Havey wrote:

> Like I said, I agree that bufferbloat is only 1 part of a two sided 
> problem.  The queue with respect to each flow can be either two large or 
> too small (and sometimes just right?).  Anyways, I'm just wondering if 
> there are any measurement studies out there that show the effects of 
> this problem in a formal way.

There are even videos showing this on youtube, where downloading at the 
same time as doing video conferencing means the video conferencing works a 
lot worse, and also that loading a web page takes a lot longer (due to DNS 
resolving packets, SYNs etc being stuck behind a lot of data packets).

https://www.youtube.com/watch?v=-D-cJNtKwuw for instance.

Jim Gettys and Dave Taht (and others) have done wonderful jobs in 
demonstrating that this is indeed a problem. I know gobs of users who know 
this is a problem as well, but they don't know how to fix it. People 
active in the bufferbloat movement have shown that there are solutions, 
and have shown these to work. There are papers and there are videos to 
show this. Even the RRUL test tool kit shows this very well if you 
understand what "500ms add latency" will mean to your Internet experience.

-- 
Mikael Abrahamsson    email: swmike@swm.pp.se