Re: [aqm] Questioning each PIE heuristic - moving averages and rate measurement
Michael Menth <menth@uni-tuebingen.de> Thu, 30 March 2017 09:57 UTC
Return-Path: <menth@uni-tuebingen.de>
X-Original-To: aqm@ietfa.amsl.com
Delivered-To: aqm@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id F1DFC12946B; Thu, 30 Mar 2017 02:57:42 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -4.201
X-Spam-Level:
X-Spam-Status: No, score=-4.201 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_MED=-2.3, RP_MATCHES_RCVD=-0.001] autolearn=ham autolearn_force=no
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 0km1WCzFG4Qb; Thu, 30 Mar 2017 02:57:40 -0700 (PDT)
Received: from mx04.uni-tuebingen.de (mx04.uni-tuebingen.de [134.2.5.214]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 674EC129426; Thu, 30 Mar 2017 02:57:40 -0700 (PDT)
Received: from [134.2.11.131] (chaos.informatik.uni-tuebingen.de [134.2.11.131]) by mx04.uni-tuebingen.de (Postfix) with ESMTPSA id 3CA1A12FA2; Thu, 30 Mar 2017 11:57:38 +0200 (CEST)
To: Jonathan Morton <chromatix99@gmail.com>, Bob Briscoe <ietf@bobbriscoe.net>
References: <9ddba389-e368-9050-3b14-aa235c99fcb8@bobbriscoe.net> <D4FDD717.2636D%ropan@cisco.com> <77D4FC66-C99F-49D0-BB73-27A0CEF70F31@gmail.com> <99a7b737-fc3c-efd0-b6c8-d71a089b7de8@bobbriscoe.net> <FB0F3D38-63E2-441E-BAB4-2541D7E9FE94@gmail.com>
Cc: "Rong Pan (ropan)" <ropan@cisco.com>, tsvwg IETF list <tsvwg@ietf.org>, AQM IETF list <aqm@ietf.org>
From: Michael Menth <menth@uni-tuebingen.de>
Message-ID: <471e91b1-c469-3d36-9af1-0411e5661286@uni-tuebingen.de>
Date: Thu, 30 Mar 2017 11:57:10 +0200
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Thunderbird/45.8.0
MIME-Version: 1.0
In-Reply-To: <FB0F3D38-63E2-441E-BAB4-2541D7E9FE94@gmail.com>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 8bit
Archived-At: <https://mailarchive.ietf.org/arch/msg/aqm/px74T_HieiCwtLmsT0dDq6WPUdk>
Subject: Re: [aqm] Questioning each PIE heuristic - moving averages and rate measurement
X-BeenThere: aqm@ietf.org
X-Mailman-Version: 2.1.22
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: <https://mailarchive.ietf.org/arch/browse/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: Thu, 30 Mar 2017 09:57:43 -0000
Hi all, Am 30.03.2017 um 11:08 schrieb Jonathan Morton: > >> On 30 Mar, 2017, at 10:46, Bob Briscoe <ietf@bobbriscoe.net> wrote: >> >> For PI2 we removed all but 2 and it worked the same or better than PIE in all our tests. I have been assessing each of the other 7 one by one for reinstatement. So far I've rejected 6. I think I can reject this last one by making the sampling time of the base PI algo dependent on the max link rate. Then when the queue goes idle, the base PI algo will decay drop down to zero no slower than the queue drains, without needing this extra heuristic. > > That’s fair enough. > > It sounds like the fairly coarsely discrete time intervals in PIE are the main justification for this particular heuristic, so it might be sufficient to document that WRT PIE itself. Using finer time intervals is clearly a better choice for the future. PIE uses time intervals for measurement purposes and several parameters contribute. We've recently done some basic work on measurement methodology that facilitates a comparison of different measurement approaches and better-informed parametrization by introduction of the "memory" concept. https://atlas.informatik.uni-tuebingen.de/~menth/papers/Menth17c.pdf PIE essentially implements TDRM-DTWMA-UEMA illustrated in Fig. 6d. The concept of "memory" can also be applied to moving averages which are also used in PIE for several purposes. Configuration via a "memory" can make some heuristics more intuitive. Best wishes, Michael > > - Jonathan Morton > -- Prof. Dr. habil. Michael Menth University of Tuebingen Faculty of Science Department of Computer Science Chair of Communication Networks Sand 13, 72076 Tuebingen, Germany phone: (+49)-7071/29-70505 fax: (+49)-7071/29-5220 mailto:menth@uni-tuebingen.de http://kn.inf.uni-tuebingen.de
- [aqm] Questioning each PIE heuristic Bob Briscoe
- Re: [aqm] Questioning each PIE heuristic Rong Pan (ropan)
- Re: [aqm] Questioning each PIE heuristic Jonathan Morton
- Re: [aqm] Questioning each PIE heuristic Fred Baker
- Re: [aqm] Questioning each PIE heuristic Jonathan Morton
- Re: [aqm] Questioning each PIE heuristic Bless, Roland (TM)
- Re: [aqm] Questioning each PIE heuristic Bob Briscoe
- Re: [aqm] Questioning each PIE heuristic Rong Pan (ropan)
- Re: [aqm] Questioning each PIE heuristic Luca Muscariello
- Re: [aqm] Questioning each PIE heuristic Rong Pan (ropan)
- Re: [aqm] Questioning each PIE heuristic Lautenschlaeger, Wolfram (Nokia - DE/Stuttgart)
- Re: [aqm] Questioning each PIE heuristic Bob Briscoe
- Re: [aqm] Questioning each PIE heuristic Rong Pan (ropan)
- Re: [aqm] Questioning each PIE heuristic Bob Briscoe
- Re: [aqm] Questioning each PIE heuristic Jonathan Morton
- Re: [aqm] Questioning each PIE heuristic - moving… Michael Menth
- Re: [aqm] Questioning each PIE heuristic Dave Dolson
- Re: [aqm] Questioning each PIE heuristic - moving… Bob Briscoe
- Re: [aqm] Questioning each PIE heuristic - moving… Michael Menth
- Re: [aqm] Questioning each PIE heuristic - moving… Bob Briscoe
- Re: [aqm] Questioning each PIE heuristic - moving… Rong Pan (ropan)
- Re: [aqm] Questioning each PIE heuristic - moving… Rong Pan (ropan)
- Re: [aqm] Questioning each PIE heuristic - moving… Bob Briscoe