
From mayutan.arumaithurai@gmail.com  Wed Mar  3 02:55:24 2010
Return-Path: <mayutan.arumaithurai@gmail.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 5A60B28C325 for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 02:55:24 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.418
X-Spam-Level: 
X-Spam-Status: No, score=-1.418 tagged_above=-999 required=5 tests=[AWL=1.180,  BAYES_00=-2.599, HTML_MESSAGE=0.001]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id DdZUZnvdC+Ng for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 02:55:23 -0800 (PST)
Received: from mail-ww0-f44.google.com (mail-ww0-f44.google.com [74.125.82.44]) by core3.amsl.com (Postfix) with ESMTP id 1F6023A70E2 for <ledbat@ietf.org>; Wed,  3 Mar 2010 02:55:22 -0800 (PST)
Received: by wwb18 with SMTP id 18so233263wwb.31 for <ledbat@ietf.org>; Wed, 03 Mar 2010 02:55:20 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:date:message-id:subject :from:to:cc:content-type; bh=FBdULvlkxY8PwUXBaZlj/Qaa82QdDNAlSqoBO7c8gJM=; b=bEkPOmgH4bZK992+syz1wcufwkoeuP57nNaof27SpBgMDg5QfRKQDafzuH6zu6qOKa LHCNSnYL4OZA01L2Kgwc7ryu3/CupEGYhuSfMVlXwBdoJ8F8e0AD8D+CE+5j6yWkXI1+ G0M1Wkzi/wfEPMRvHsHpdt/vaZ2f7fslmt/40=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:cc:content-type; b=pK4vYZYKpaE7/TIyJ0kJ9zkfz6kYBWRu5aS8Xri90x3zz9XGpj4twxVxR9qdWZ8tmE CdwQatVG631svfd48vqyX3lOdh8rz21WCVaoedmK6S7LwXOciEpBlGFlhMfDKnS3vOuv h+dl8SrsEQLuQimX1L8mpq+PUblwEXVx8L+tY=
MIME-Version: 1.0
Received: by 10.216.88.12 with SMTP id z12mr638787wee.165.1267613720714; Wed,  03 Mar 2010 02:55:20 -0800 (PST)
Date: Wed, 3 Mar 2010 11:55:20 +0100
Message-ID: <f18355b81003030255m551de738ldc1edcdade1f32aa@mail.gmail.com>
From: "Mayutan A." <mayutan.arumaithurai@gmail.com>
To: "ledbat@ietf.org\"" <ledbat@ietf.org>
Content-Type: multipart/alternative; boundary=0016e6da7ae5891eb10480e351d1
Cc: Xiaoming Fu <fu@cs.uni-goettingen.de>, "RAMAKRISHNAN, KADANGODE K \(K. K.\)" <kkrama@research.att.com>
Subject: [ledbat] New draft for review: draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 03 Mar 2010 10:55:24 -0000

--0016e6da7ae5891eb10480e351d1
Content-Type: text/plain; charset=ISO-8859-1

We have submitted a new draft to the LEDBAT WG and are looking forward to
all your comments.
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00

The basic idea is to have an architecture framework, to enable the
standardization of the various mechanisms of a network friendly congestion
control such as available bandwidth estimation, flow control and congestion
detection separately. This could result in pluggable components that could
be used in the overall congestion control protocol/s.

Abstract:

   The Low Extra Delay Background Transport (LEDBAT) working group is
   considering protocols for an alternative congestion control protocol
   that enables a delay-insensitive networking application to minimize
   the extra queueing delay it causes to other applications because of
   additional queueing at the bottleneck, when these connections
   carrying traffic for such applications attempt to use the available
   bandwidth.

   This document proposes an architectural framework for LEDBAT
   congestion control mechanisms, based on existing work on congestion
   control protocols and the requirements of the LEDBAT working group.
   The architectural framework consists of a LEDBAT-congestion control
   (LEDBAT-CC) suite that provides flexibility in utilizing different
   components for providing congestion control for transport connections
   carrying delay-insensitive traffic.  The LEDBAT-CC suite of protocols
   is envisioned to support the multiple alternative mechanisms for
   bandwidth estimation, congestion detection and indication and end-
   system flow control to comprise a network friendly congestion
   avoidance protocol.


   This document is inspired by the need to standardize the various
   components that constitute the network friendly congestion control
   protocol to avoid having to individually standardize a multitude of
   distinct and monolithic solutions.


Feedback is welcome,
Mayutan Arumaithurai

--0016e6da7ae5891eb10480e351d1
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

We have submitted a new draft to the LEDBAT WG and are looking forward to a=
ll your comments. <br><a href=3D"http://tools.ietf.org/html/draft-mayutan-l=
edbat-congestionarchitecture-00" target=3D"_blank">http://tools.ietf.org/ht=
ml/draft-mayutan-ledbat-congestionarchitecture-00</a><br>
<br>The
basic idea is to have an architecture framework, to enable the
standardization of the various mechanisms of a network friendly congestion =
control such as
available bandwidth estimation, flow control and congestion detection
separately. This could result in pluggable components that could be
used in the overall congestion control protocol/s. <br>
<br>Abstract:<br><pre>   The Low Extra Delay Background Transport (LEDBAT) =
working group is<br>   considering protocols for an alternative congestion =
control protocol<br>   that enables a delay-insensitive networking applicat=
ion to minimize<br>
   the extra queueing delay it causes to other applications because of<br> =
  additional queueing at the bottleneck, when these connections<br>   carry=
ing traffic for such applications attempt to use the available<br>   bandwi=
dth.<br>
<br>   This document proposes an architectural framework for LEDBAT<br>   c=
ongestion control mechanisms, based on existing work on congestion<br>   co=
ntrol protocols and the requirements of the LEDBAT working group.<br>   The=
 architectural framework consists of a LEDBAT-congestion control<br>
   (LEDBAT-CC) suite that provides flexibility in utilizing different<br>  =
 components for providing congestion control for transport connections<br> =
  carrying delay-insensitive traffic.  The LEDBAT-CC suite of protocols<br>
   is envisioned to support the multiple alternative mechanisms for<br>   b=
andwidth estimation, congestion detection and indication and end-<br>   sys=
tem flow control to comprise a network friendly congestion<br>   avoidance =
protocol.<br>
<br><br>   This document is inspired by the need to standardize the various=
<br>   components that constitute the network friendly congestion control<b=
r>   protocol to avoid having to individually standardize a multitude of<br=
>
   distinct and monolithic solutions.<br></pre>=A0<br>Feedback is welcome, =
<br>Mayutan Arumaithurai

--0016e6da7ae5891eb10480e351d1--

From victor.grishchenko@gmail.com  Wed Mar  3 07:40:12 2010
Return-Path: <victor.grishchenko@gmail.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 269323A8D6D for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 07:40:12 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[BAYES_00=-2.599]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 4gXCAb5LIyN5 for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 07:40:09 -0800 (PST)
Received: from ey-out-2122.google.com (ey-out-2122.google.com [74.125.78.25]) by core3.amsl.com (Postfix) with ESMTP id CAA4E3A8B47 for <ledbat@ietf.org>; Wed,  3 Mar 2010 07:40:08 -0800 (PST)
Received: by ey-out-2122.google.com with SMTP id d26so284187eyd.51 for <ledbat@ietf.org>; Wed, 03 Mar 2010 07:40:07 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:date:message-id:subject :from:to:content-type; bh=t5ztTYTWxi029QRIRVeJQDrP6YxGhKG7hykSQ3FLIIk=; b=ISfwAac/4/PXuSrAbDQ29jwc+SXoc3t0+eUDV96JuRdnGEw9eWLBMKDMDrzVH1BdNG aWfE0sFVyIBVdmKkwDoUj9fJh2ii8LPtLR/VHsbWKTRGLyC2Yit+gzt3ONfdsaQmS/3I 5XXSOo/aGHpgjaslQySAskRF8KlLf+Jf/+gCY=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type; b=Ys+InKEd0IPgXCEmEPf5Rklin4w3v3nTDlrq+gVK0qwwqnaqDwMRNVJLpfCZRABPZE CfJLkCZ2ymvZe8A7WhskPJQ5dAd1+yJOWpVE8FiuovfA5nDBrqk6xg52elP/El3NNcm3 eaV1CFGVX5/PbCY0yV1eFiHVrAMnoZoTdE4LM=
MIME-Version: 1.0
Received: by 10.213.100.129 with SMTP id y1mr153747ebn.47.1267630415990; Wed,  03 Mar 2010 07:33:35 -0800 (PST)
Date: Wed, 3 Mar 2010 16:33:35 +0100
Message-ID: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com>
From: Victor Grishchenko <victor.grishchenko@gmail.com>
To: ledbat@ietf.org
Content-Type: text/plain; charset=ISO-8859-1
Subject: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 03 Mar 2010 15:40:12 -0000

Hi!

I think, BitTorrent guys are already perfectly aware of the details of
the recent screw-up, so I'll post it here for archival purposes only.
uTP has a smart feature of sending smaller packets if congestion is
detected:
http://bittorrent.org/beps/bep_0029.html#packet-sizes
The intended purpose is to contribute less delay to congested/slow
links. The problem is, sometimes CPU is the reason for congestion.
That happens to Linux/BSD shapers, cheap home routers and, according
to some field reports, to some bigger hardware, in case it does some
overly intelligent stuff. Once CPU hits the ceiling once, uTP switches
to smaller packets. That further increases the router's CPU load, then
everything goes into downward spiral. In the end, the network is
effectively DDoSed with 150-byte packets (one-tenth the normal size).
Again, according to the field reports, those rogue ISPs tend to
install uTP-kill filters instead of ordering more expensive hardware.
In-depth coverage: http://forum.nag.ru/forum/index.php?showtopic=55025 (Russian)
AMS-IX load graphs show a jump in PPS, but it is unclear whether it
could be attributed to the recent uTP rollout.

That is more like an implementation bug than a general defect of LEDBAT.
So far, from my experience, the LEDBAT itself has problems on...
a) Switched networks: no queue, so no delay, LEDBAT goes into AIMD
mode. May be even more aggressive than TCP, but nobody cares.
b) Long-fat networks: cwnd is determined by the accidental drop rate.
One-way delay has no chance to grow. Not sure what happens if
accidental drop is ignored. Likely, a Bad Thing.
c) In general, when queues are shorter than the target delay.

Yours,

    Victor

From muraris@microsoft.com  Wed Mar  3 10:34:54 2010
Return-Path: <muraris@microsoft.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 829B428C456 for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 10:34:54 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.599
X-Spam-Level: 
X-Spam-Status: No, score=-10.599 tagged_above=-999 required=5 tests=[BAYES_00=-2.599, RCVD_IN_DNSWL_HI=-8]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id IKsLOEJuwxXm for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 10:34:51 -0800 (PST)
Received: from smtp.microsoft.com (mail2.microsoft.com [131.107.115.215]) by core3.amsl.com (Postfix) with ESMTP id AF4AB28C450 for <ledbat@ietf.org>; Wed,  3 Mar 2010 10:34:51 -0800 (PST)
Received: from TK5EX14HUBC102.redmond.corp.microsoft.com (157.54.7.154) by TK5-EXGWY-E802.partners.extranet.microsoft.com (10.251.56.168) with Microsoft SMTP Server (TLS) id 8.2.176.0; Wed, 3 Mar 2010 10:34:53 -0800
Received: from TK5EX14MBXC128.redmond.corp.microsoft.com ([169.254.7.20]) by TK5EX14HUBC102.redmond.corp.microsoft.com ([157.54.7.154]) with mapi; Wed, 3 Mar 2010 10:34:47 -0800
From: Murari Sridharan <muraris@microsoft.com>
To: Victor Grishchenko <victor.grishchenko@gmail.com>, "ledbat@ietf.org" <ledbat@ietf.org>
Thread-Topic: [ledbat] The pps story
Thread-Index: AQHKuugDw9KzafzxKEKgHlZenoxwppHgiSYw
Date: Wed, 3 Mar 2010 18:34:32 +0000
Message-ID: <03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com>
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com>
In-Reply-To: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 03 Mar 2010 18:34:54 -0000

Victor, thanks for your comments.=20

The small packet problem you mention seems to be interesting. When you say =
CPU is the source of congestion which CPU are you referring to? Or are you =
simply saying any system level load will increase latency and will be inter=
preted as congestion? The framing and switching to smaller packets etc are =
right now not in the scope of the document although you are making an inter=
esting point. Stas is this something you have seen? I have noticed this typ=
e of problem when dealing with delay based congestion control, usually flow=
 control at the switches, interrupt moderation etc tend to show up as delay=
 and that prevents the controller from further increases. However how the s=
ources react is upto the protocol.  When it sees no delay ledbat should onl=
y be as aggressive as TCP.=20

Thanks

-----Original Message-----
From: ledbat-bounces@ietf.org [mailto:ledbat-bounces@ietf.org] On Behalf Of=
 Victor Grishchenko
Sent: Wednesday, March 03, 2010 7:34 AM
To: ledbat@ietf.org
Subject: [ledbat] The pps story

Hi!

I think, BitTorrent guys are already perfectly aware of the details of
the recent screw-up, so I'll post it here for archival purposes only.
uTP has a smart feature of sending smaller packets if congestion is
detected:
http://bittorrent.org/beps/bep_0029.html#packet-sizes
The intended purpose is to contribute less delay to congested/slow
links. The problem is, sometimes CPU is the reason for congestion.
That happens to Linux/BSD shapers, cheap home routers and, according
to some field reports, to some bigger hardware, in case it does some
overly intelligent stuff. Once CPU hits the ceiling once, uTP switches
to smaller packets. That further increases the router's CPU load, then
everything goes into downward spiral. In the end, the network is
effectively DDoSed with 150-byte packets (one-tenth the normal size).
Again, according to the field reports, those rogue ISPs tend to
install uTP-kill filters instead of ordering more expensive hardware.
In-depth coverage: http://forum.nag.ru/forum/index.php?showtopic=3D55025 (R=
ussian)
AMS-IX load graphs show a jump in PPS, but it is unclear whether it
could be attributed to the recent uTP rollout.

That is more like an implementation bug than a general defect of LEDBAT.
So far, from my experience, the LEDBAT itself has problems on...
a) Switched networks: no queue, so no delay, LEDBAT goes into AIMD
mode. May be even more aggressive than TCP, but nobody cares.
b) Long-fat networks: cwnd is determined by the accidental drop rate.
One-way delay has no chance to grow. Not sure what happens if
accidental drop is ignored. Likely, a Bad Thing.
c) In general, when queues are shorter than the target delay.

Yours,

    Victor
_______________________________________________
ledbat mailing list
ledbat@ietf.org
https://www.ietf.org/mailman/listinfo/ledbat


From muraris@microsoft.com  Wed Mar  3 10:36:02 2010
Return-Path: <muraris@microsoft.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 8626B3A8B6D for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 10:36:02 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.599
X-Spam-Level: 
X-Spam-Status: No, score=-10.599 tagged_above=-999 required=5 tests=[AWL=-0.000, BAYES_00=-2.599, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_HI=-8]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id JU56NH6flFl8 for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 10:36:01 -0800 (PST)
Received: from smtp.microsoft.com (mailb.microsoft.com [131.107.115.215]) by core3.amsl.com (Postfix) with ESMTP id D86663A87DE for <ledbat@ietf.org>; Wed,  3 Mar 2010 10:35:59 -0800 (PST)
Received: from TK5EX14HUBC101.redmond.corp.microsoft.com (157.54.7.153) by TK5-EXGWY-E802.partners.extranet.microsoft.com (10.251.56.168) with Microsoft SMTP Server (TLS) id 8.2.176.0; Wed, 3 Mar 2010 10:36:01 -0800
Received: from TK5EX14MBXC128.redmond.corp.microsoft.com ([169.254.7.20]) by TK5EX14HUBC101.redmond.corp.microsoft.com ([157.54.7.153]) with mapi; Wed, 3 Mar 2010 10:35:51 -0800
From: Murari Sridharan <muraris@microsoft.com>
To: Mayutan A. <mayutan.arumaithurai@gmail.com>, "shalunov@bittorrent.com" <shalunov@bittorrent.com>
Thread-Topic: Request for a presentation slot at the LEDBAT WG (IETF 77)
Thread-Index: AQHKurSEYfr5bV9cHEi6LRidJov8Y5HgiwQw
Date: Wed, 3 Mar 2010 18:35:25 +0000
Message-ID: <03520536067DF14395EA93FE7ECFDCF028165B97@TK5EX14MBXC128.redmond.corp.microsoft.com>
References: <f18355b81003030132j1440cd02ldb94f173e97e9c20@mail.gmail.com>
In-Reply-To: <f18355b81003030132j1440cd02ldb94f173e97e9c20@mail.gmail.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Content-Type: multipart/alternative; boundary="_000_03520536067DF14395EA93FE7ECFDCF028165B97TK5EX14MBXC128r_"
MIME-Version: 1.0
Cc: "ledbat@ietf.org" <ledbat@ietf.org>
Subject: Re: [ledbat] Request for a presentation slot at the LEDBAT WG (IETF 77)
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 03 Mar 2010 18:36:02 -0000

--_000_03520536067DF14395EA93FE7ECFDCF028165B97TK5EX14MBXC128r_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

Adding the ledbat mailing list.

Mayutan, I will include you in the agenda.

Thanks

From: Mayutan A. [mailto:mayutan.arumaithurai@gmail.com]
Sent: Wednesday, March 03, 2010 1:32 AM
To: Murari Sridharan; shalunov@bittorrent.com
Subject: Request for a presentation slot at the LEDBAT WG (IETF 77)

Hi,

I am Mayutan Arumaithurai, a PhD student at the University of Goettingen, G=
ermany. I would like to request for a short presentation slot to present th=
e draft I coauthored along with Xiaoming Fu (University of Goettingen) and =
K.K. Ramakrishnan (AT&T).

I have already submitted a -00 version:
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00

The basic idea is to have an architecture framework, to enable the standard=
ization of the various mechanisms of congestion control such as available b=
andwidth estimation, flow control and congestion detection separately. This=
 could result in pluggable components that could be used in the overall con=
gestion control protocol/s.

Abstract:

   The Low Extra Delay Background Transport (LEDBAT) working group is

   considering protocols for an alternative congestion control protocol

   that enables a delay-insensitive networking application to minimize





   the extra queueing delay it causes to other applications because of

   additional queueing at the bottleneck, when these connections

   carrying traffic for such applications attempt to use the available

   bandwidth.






   This document proposes an architectural framework for LEDBAT

   congestion control mechanisms, based on existing work on congestion

   control protocols and the requirements of the LEDBAT working group.

   The architectural framework consists of a LEDBAT-congestion control





   (LEDBAT-CC) suite that provides flexibility in utilizing different

   components for providing congestion control for transport connections

   carrying delay-insensitive traffic.  The LEDBAT-CC suite of protocols





   is envisioned to support the multiple alternative mechanisms for

   bandwidth estimation, congestion detection and indication and end-

   system flow control to comprise a network friendly congestion

   avoidance protocol.






   This document is inspired by the need to standardize the various

   components that constitute the network friendly congestion control

   protocol to avoid having to individually standardize a multitude of





   distinct and monolithic solutions.

Feedback is welcome,
Mayutan Arumaithurai

--_000_03520536067DF14395EA93FE7ECFDCF028165B97TK5EX14MBXC128r_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:x=3D"urn:schemas-microsoft-com:office:excel" xmlns:p=3D"urn:schemas-m=
icrosoft-com:office:powerpoint" xmlns:a=3D"urn:schemas-microsoft-com:office=
:access" xmlns:dt=3D"uuid:C2F41010-65B3-11d1-A29F-00AA00C14882" xmlns:s=3D"=
uuid:BDC6E3F0-6DA3-11d1-A2A3-00AA00C14882" xmlns:rs=3D"urn:schemas-microsof=
t-com:rowset" xmlns:z=3D"#RowsetSchema" xmlns:b=3D"urn:schemas-microsoft-co=
m:office:publisher" xmlns:ss=3D"urn:schemas-microsoft-com:office:spreadshee=
t" xmlns:c=3D"urn:schemas-microsoft-com:office:component:spreadsheet" xmlns=
:odc=3D"urn:schemas-microsoft-com:office:odc" xmlns:oa=3D"urn:schemas-micro=
soft-com:office:activation" xmlns:html=3D"http://www.w3.org/TR/REC-html40" =
xmlns:q=3D"http://schemas.xmlsoap.org/soap/envelope/" xmlns:rtc=3D"http://m=
icrosoft.com/officenet/conferencing" xmlns:D=3D"DAV:" xmlns:Repl=3D"http://=
schemas.microsoft.com/repl/" xmlns:mt=3D"http://schemas.microsoft.com/share=
point/soap/meetings/" xmlns:x2=3D"http://schemas.microsoft.com/office/excel=
/2003/xml" xmlns:ppda=3D"http://www.passport.com/NameSpace.xsd" xmlns:ois=
=3D"http://schemas.microsoft.com/sharepoint/soap/ois/" xmlns:dir=3D"http://=
schemas.microsoft.com/sharepoint/soap/directory/" xmlns:ds=3D"http://www.w3=
.org/2000/09/xmldsig#" xmlns:dsp=3D"http://schemas.microsoft.com/sharepoint=
/dsp" xmlns:udc=3D"http://schemas.microsoft.com/data/udc" xmlns:xsd=3D"http=
://www.w3.org/2001/XMLSchema" xmlns:sub=3D"http://schemas.microsoft.com/sha=
repoint/soap/2002/1/alerts/" xmlns:ec=3D"http://www.w3.org/2001/04/xmlenc#"=
 xmlns:sp=3D"http://schemas.microsoft.com/sharepoint/" xmlns:sps=3D"http://=
schemas.microsoft.com/sharepoint/soap/" xmlns:xsi=3D"http://www.w3.org/2001=
/XMLSchema-instance" xmlns:udcs=3D"http://schemas.microsoft.com/data/udc/so=
ap" xmlns:udcxf=3D"http://schemas.microsoft.com/data/udc/xmlfile" xmlns:udc=
p2p=3D"http://schemas.microsoft.com/data/udc/parttopart" xmlns:wf=3D"http:/=
/schemas.microsoft.com/sharepoint/soap/workflow/" xmlns:dsss=3D"http://sche=
mas.microsoft.com/office/2006/digsig-setup" xmlns:dssi=3D"http://schemas.mi=
crosoft.com/office/2006/digsig" xmlns:mdssi=3D"http://schemas.openxmlformat=
s.org/package/2006/digital-signature" xmlns:mver=3D"http://schemas.openxmlf=
ormats.org/markup-compatibility/2006" xmlns:m=3D"http://schemas.microsoft.c=
om/office/2004/12/omml" xmlns:mrels=3D"http://schemas.openxmlformats.org/pa=
ckage/2006/relationships" xmlns:spwp=3D"http://microsoft.com/sharepoint/web=
partpages" xmlns:ex12t=3D"http://schemas.microsoft.com/exchange/services/20=
06/types" xmlns:ex12m=3D"http://schemas.microsoft.com/exchange/services/200=
6/messages" xmlns:pptsl=3D"http://schemas.microsoft.com/sharepoint/soap/Sli=
deLibrary/" xmlns:spsl=3D"http://microsoft.com/webservices/SharePointPortal=
Server/PublishedLinksService" xmlns:Z=3D"urn:schemas-microsoft-com:" xmlns:=
st=3D"&#1;" xmlns=3D"http://www.w3.org/TR/REC-html40">

<head>
<META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3DGenerator content=3D"Microsoft Word 12 (filtered medium)">
<style>
<!--
 /* Font Definitions */
 @font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
	{font-family:Tahoma;
	panose-1:2 11 6 4 3 5 4 4 2 4;}
@font-face
	{font-family:Consolas;
	panose-1:2 11 6 9 2 2 4 3 2 4;}
 /* Style Definitions */
 p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0in;
	margin-bottom:.0001pt;
	font-size:12.0pt;
	font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:blue;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{mso-style-priority:99;
	color:purple;
	text-decoration:underline;}
pre
	{mso-style-priority:99;
	mso-style-link:"HTML Preformatted Char";
	margin:0in;
	margin-bottom:.0001pt;
	font-size:10.0pt;
	font-family:"Courier New";}
span.HTMLPreformattedChar
	{mso-style-name:"HTML Preformatted Char";
	mso-style-priority:99;
	mso-style-link:"HTML Preformatted";
	font-family:Consolas;}
span.EmailStyle19
	{mso-style-type:personal-reply;
	font-family:"Calibri","sans-serif";
	color:#1F497D;}
.MsoChpDefault
	{mso-style-type:export-only;}
@page Section1
	{size:8.5in 11.0in;
	margin:1.0in 1.0in 1.0in 1.0in;}
div.Section1
	{page:Section1;}
-->
</style>
<!--[if gte mso 9]><xml>
 <o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
 <o:shapelayout v:ext=3D"edit">
  <o:idmap v:ext=3D"edit" data=3D"1" />
 </o:shapelayout></xml><![endif]-->
</head>

<body lang=3DEN-US link=3Dblue vlink=3Dpurple>

<div class=3DSection1>

<p class=3DMsoNormal><span style=3D'font-size:11.0pt;font-family:"Calibri",=
"sans-serif";
color:#1F497D'>Adding the ledbat mailing list. <o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:11.0pt;font-family:"Calibri",=
"sans-serif";
color:#1F497D'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:11.0pt;font-family:"Calibri",=
"sans-serif";
color:#1F497D'>Mayutan, I will include you in the agenda. <o:p></o:p></span=
></p>

<p class=3DMsoNormal><span style=3D'font-size:11.0pt;font-family:"Calibri",=
"sans-serif";
color:#1F497D'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:11.0pt;font-family:"Calibri",=
"sans-serif";
color:#1F497D'>Thanks <o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:11.0pt;font-family:"Calibri",=
"sans-serif";
color:#1F497D'><o:p>&nbsp;</o:p></span></p>

<div style=3D'border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in =
0in 0in'>

<p class=3DMsoNormal><b><span style=3D'font-size:10.0pt;font-family:"Tahoma=
","sans-serif"'>From:</span></b><span
style=3D'font-size:10.0pt;font-family:"Tahoma","sans-serif"'> Mayutan A.
[mailto:mayutan.arumaithurai@gmail.com] <br>
<b>Sent:</b> Wednesday, March 03, 2010 1:32 AM<br>
<b>To:</b> Murari Sridharan; shalunov@bittorrent.com<br>
<b>Subject:</b> Request for a presentation slot at the LEDBAT WG (IETF 77)<=
o:p></o:p></span></p>

</div>

<p class=3DMsoNormal><o:p>&nbsp;</o:p></p>

<p class=3DMsoNormal>Hi, <br>
<br>
I am Mayutan Arumaithurai, a PhD student at the University of Goettingen,
Germany. I would like to request for a short presentation slot to present t=
he
draft I coauthored along with Xiaoming Fu (University of Goettingen) and K.=
K.
Ramakrishnan (AT&amp;T). <br>
<br>
I have already submitted a -00 version:<br>
<a
href=3D"http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitect=
ure-00">http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitect=
ure-00</a><br>
<br>
The basic idea is to have an architecture framework, to enable the
standardization of the various mechanisms of congestion control such as
available bandwidth estimation, flow control and congestion detection
separately. This could result in pluggable components that could be used in=
 the
overall congestion control protocol/s. <br>
<br>
Abstract:<o:p></o:p></p>

<pre>&nbsp;&nbsp; The Low Extra Delay Background Transport (LEDBAT) working=
 group is<br>
&nbsp;&nbsp; considering protocols for an alternative congestion control pr=
otocol<br>
&nbsp;&nbsp; that enables a delay-insensitive networking application to min=
imize<br>
<br>
<o:p></o:p></pre><pre>&nbsp;&nbsp; the extra queueing delay it causes to ot=
her applications because of<br>
&nbsp;&nbsp; additional queueing at the bottleneck, when these connections<=
br>
&nbsp;&nbsp; carrying traffic for such applications attempt to use the avai=
lable<br>
&nbsp;&nbsp; bandwidth.<br>
<br>
<o:p></o:p></pre><pre><br>
&nbsp;&nbsp; This document proposes an architectural framework for LEDBAT<b=
r>
&nbsp;&nbsp; congestion control mechanisms, based on existing work on conge=
stion<br>
&nbsp;&nbsp; control protocols and the requirements of the LEDBAT working g=
roup.<br>
&nbsp;&nbsp; The architectural framework consists of a LEDBAT-congestion co=
ntrol<br>
<br>
<o:p></o:p></pre><pre>&nbsp;&nbsp; (LEDBAT-CC) suite that provides flexibil=
ity in utilizing different<br>
&nbsp;&nbsp; components for providing congestion control for transport conn=
ections<br>
&nbsp;&nbsp; carrying delay-insensitive traffic.&nbsp; The LEDBAT-CC suite =
of protocols<br>
<br>
<o:p></o:p></pre><pre>&nbsp;&nbsp; is envisioned to support the multiple al=
ternative mechanisms for<br>
&nbsp;&nbsp; bandwidth estimation, congestion detection and indication and =
end-<br>
&nbsp;&nbsp; system flow control to comprise a network friendly congestion<=
br>
&nbsp;&nbsp; avoidance protocol.<br>
<br>
<o:p></o:p></pre><pre><br>
&nbsp;&nbsp; This document is inspired by the need to standardize the vario=
us<br>
&nbsp;&nbsp; components that constitute the network friendly congestion con=
trol<br>
&nbsp;&nbsp; protocol to avoid having to individually standardize a multitu=
de of<br>
<br>
<o:p></o:p></pre><pre>&nbsp;&nbsp; distinct and monolithic solutions.<o:p><=
/o:p></pre>

<p class=3DMsoNormal>&nbsp;<br>
Feedback is welcome, <br>
Mayutan Arumaithurai<o:p></o:p></p>

</div>

</body>

</html>

--_000_03520536067DF14395EA93FE7ECFDCF028165B97TK5EX14MBXC128r_--

From matthew@matthew.at  Wed Mar  3 12:43:00 2010
Return-Path: <matthew@matthew.at>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id DD5223A8C8A for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 12:43:00 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.43
X-Spam-Level: 
X-Spam-Status: No, score=-1.43 tagged_above=-999 required=5 tests=[BAYES_00=-2.599, HELO_EQ_AT=0.424, HOST_EQ_AT=0.745]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id s8Hx25DSDBDO for <ledbat@core3.amsl.com>; Wed,  3 Mar 2010 12:43:00 -0800 (PST)
Received: from where.matthew.at (where.matthew.at [198.202.199.1]) by core3.amsl.com (Postfix) with ESMTP id 31A023A8BFE for <ledbat@ietf.org>; Wed,  3 Mar 2010 12:42:57 -0800 (PST)
Received: from [10.10.155.2] (unknown [10.10.155.2]) by where.matthew.at (Postfix) with ESMTP id B64A814805B; Wed,  3 Mar 2010 12:42:58 -0800 (PST)
Message-ID: <4B8EC9D1.6010505@matthew.at>
Date: Wed, 03 Mar 2010 12:42:57 -0800
From: Matthew Kaufman <matthew@matthew.at>
User-Agent: Thunderbird 2.0.0.23 (Windows/20090812)
MIME-Version: 1.0
To: Murari Sridharan <muraris@microsoft.com>
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com> <03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com>
In-Reply-To: <03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
Reply-To: matthew@matthew.at
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 03 Mar 2010 20:43:01 -0000

Making packets smaller almost never helps these days, in my experience. 
Among other things, far too many of the hops are over layer 2 media with 
huge per-packet overhead. Consider how many byte-length periods are used 
sending a 100 Mbps Ethernet packet of 150 bytes vs 1500 bytes, for instance.

Then inside the routers, the per-packet overhead in tracking buffers is 
also non-zero, so it doesn't help them much either.

In both cases, you'd be better off sending long packets less often (less 
link-layer overhead, less router management overhead, and fewer 
send/receives to interrupt and/or schedule)

Trying to prevent head-of-line blocking by making packets smaller made 
sense on dialup modems, but it really hasn't been useful since.

Matthew Kaufman


From michawe@ifi.uio.no  Fri Mar  5 14:32:31 2010
Return-Path: <michawe@ifi.uio.no>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 57EA228C393 for <ledbat@core3.amsl.com>; Fri,  5 Mar 2010 14:32:31 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[BAYES_00=-2.599]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id gQ7-8fkwHHmJ for <ledbat@core3.amsl.com>; Fri,  5 Mar 2010 14:32:30 -0800 (PST)
Received: from smtp.getmail.no (smtp.getmail.no [84.208.15.66]) by core3.amsl.com (Postfix) with ESMTP id 234E228C133 for <ledbat@ietf.org>; Fri,  5 Mar 2010 14:32:29 -0800 (PST)
MIME-version: 1.0
Content-transfer-encoding: 7BIT
Content-type: text/plain; charset=US-ASCII; format=flowed; delsp=yes
Received: from smtp.getmail.no ([10.5.16.4]) by get-mta-out02.get.basefarm.net (Sun Java(tm) System Messaging Server 7.0-0.04 64bit (built Jun 20 2008)) with ESMTP id <0KYT00J5WYM79Q90@get-mta-out02.get.basefarm.net> for ledbat@ietf.org; Fri, 05 Mar 2010 23:32:31 +0100 (MET)
Received: from [192.168.0.194] ([84.208.136.71]) by get-mta-in02.get.basefarm.net (Sun Java(tm) System Messaging Server 7.0-0.04 64bit (built Jun 20 2008)) with ESMTP id <0KYT00MQ1YLKS530@get-mta-in02.get.basefarm.net> for ledbat@ietf.org; Fri, 05 Mar 2010 23:32:30 +0100 (MET)
X-PMX-Version: 5.5.3.366731, Antispam-Engine: 2.7.0.366912, Antispam-Data: 2010.3.5.221826
Message-id: <03ACCD16-4B19-4B16-8F2F-7F35F8FC0323@ifi.uio.no>
From: Michael Welzl <michawe@ifi.uio.no>
To: ledbat@ietf.org
Date: Fri, 05 Mar 2010 23:32:08 +0100
References: <20100301220610.BE1EA28C1D3@core3.amsl.com>
X-Mailer: Apple Mail (2.936)
Cc: David Ros <David.Ros@telecom-bretagne.eu>
Subject: [ledbat] Fwd: New Version Notification for draft-ietf-ledbat-survey-00
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Fri, 05 Mar 2010 22:32:31 -0000

Folks,

After my survey was approved as a WG item after the Stockholm meeting,
I added David Ros as co-author (after approval of the chairs); he made
an update - the announcement is below, and comments are very welcome!

Cheers,
Michael


Begin forwarded message:

> From: IETF I-D Submission Tool <idsubmission@ietf.org>
> Date: March 1, 2010 11:06:10 PM GMT+01:00
> To: david.ros@telecom-bretagne.eu
> Cc: michawe@ifi.uio.no
> Subject: New Version Notification for draft-ietf-ledbat-survey-00
>
>
> A new version of I-D, draft-ietf-ledbat-survey-00.txt has been  
> successfuly submitted by David Ros and posted to the IETF repository.
>
> Filename:	 draft-ietf-ledbat-survey
> Revision:	 00
> Title:		 A Survey of Lower-than-Best-Effort Transport Protocols
> Creation_date:	 2010-03-01
> WG ID:		 ledbat
> Number_of_pages: 14
>
> Abstract:
> This document provides a survey of transport protocols which are
> designed to have a smaller bandwidth and/or delay impact on standard
> TCP than standard TCP itself when they share a bottleneck with it.
> Such protocols could be used for low-priority "background" traffic,
> as they provide what is sometimes called a "less than" (or "lower
> than") best-effort service.
>
>
>
> The IETF Secretariat.
>
>


From rbriscoe@jungle.bt.co.uk  Mon Mar  8 05:54:38 2010
Return-Path: <rbriscoe@jungle.bt.co.uk>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 2B6213A683E for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 05:54:38 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.017
X-Spam-Level: 
X-Spam-Status: No, score=-2.017 tagged_above=-999 required=5 tests=[AWL=0.100,  BAYES_00=-2.599, DNS_FROM_RFC_BOGUSMX=1.482, RCVD_IN_DNSWL_LOW=-1]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 3jOzy9GAqb1D for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 05:54:31 -0800 (PST)
Received: from smtp4.smtp.bt.com (smtp4.smtp.bt.com [217.32.164.151]) by core3.amsl.com (Postfix) with ESMTP id 18B903A6991 for <ledbat@ietf.org>; Mon,  8 Mar 2010 05:54:30 -0800 (PST)
Received: from i2kc06-ukbr.domain1.systemhost.net ([193.113.197.70]) by smtp4.smtp.bt.com with Microsoft SMTPSVC(6.0.3790.3959);  Mon, 8 Mar 2010 13:54:34 +0000
Received: from cbibipnt05.iuser.iroot.adidom.com ([147.149.196.177]) by i2kc06-ukbr.domain1.systemhost.net with Microsoft SMTPSVC(6.0.3790.3959); Mon, 8 Mar 2010 13:54:34 +0000
Received: From bagheera.jungle.bt.co.uk ([132.146.168.158]) by cbibipnt05.iuser.iroot.adidom.com (WebShield SMTP v4.5 MR1a P0803.399); id 1268056472809; Mon, 8 Mar 2010 13:54:32 +0000
Received: from MUT.jungle.bt.co.uk ([10.215.130.87]) by bagheera.jungle.bt.co.uk (8.13.5/8.12.8) with ESMTP id o28DsSlT023371; Mon, 8 Mar 2010 13:54:28 GMT
Message-Id: <201003081354.o28DsSlT023371@bagheera.jungle.bt.co.uk>
X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9
Date: Mon, 08 Mar 2010 13:54:32 +0000
To: matthew@matthew.at
From: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
In-Reply-To: <4B8EC9D1.6010505@matthew.at>
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com> <03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com> <4B8EC9D1.6010505@matthew.at>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"; format=flowed
X-Scanned-By: MIMEDefang 2.56 on 132.146.168.158
X-OriginalArrivalTime: 08 Mar 2010 13:54:34.0239 (UTC) FILETIME=[E24400F0:01CABEC6]
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 08 Mar 2010 13:54:38 -0000

Matthew,

At 20:42 03/03/2010, Matthew Kaufman wrote:
>Making packets smaller almost never helps these days, in my experience.

I agree with what I think you meant to say, but not the exact words 
you used. To be clear, I think you mean _increasing the packet rate_ 
never helps. "Making packets smaller" is surely a valid approach if 
you still send at the same packet rate - I believe this approach is 
common for congestion control of video streams - the packets are 
still sent at the same rate, but they are smaller, thus sending less bytes.

>Among other things, far too many of the hops are over layer 2 media 
>with huge per-packet overhead. Consider how many byte-length periods 
>are used sending a 100 Mbps Ethernet packet of 150 bytes vs 1500 
>bytes, for instance.
>
>Then inside the routers, the per-packet overhead in tracking buffers 
>is also non-zero, so it doesn't help them much either.
>
>In both cases, you'd be better off sending long packets less often 
>(less link-layer overhead, less router management overhead, and 
>fewer send/receives to interrupt and/or schedule)

A more general statement of the rule to follow should be "Neither 
increase bit-rate nor packet-rate in response to congestion, because 
you don't know whether congestion is by bits or packets."

There's a draft on pkt vs byte congestion going thru tsvwg at the 
moment. It's mostly about what network equipment should and shouldn't 
do to avoid giving transports perverse incentives to send small 
packets. <http://tools.ietf.org/wg/tsvwg/draft-ietf-tsvwg-byte-pkt-congest/>
Any comments on the recommendations it gives would be gratefully 
received. It is due for a major re-write, as it has become tangled 
due to multiple updates. So if you have any requests for big changes, 
now's a good time.



Cheers


Bob




>Trying to prevent head-of-line blocking by making packets smaller 
>made sense on dialup modems, but it really hasn't been useful since.
>
>Matthew Kaufman
>
>_______________________________________________
>ledbat mailing list
>ledbat@ietf.org
>https://www.ietf.org/mailman/listinfo/ledbat

________________________________________________________________
Bob Briscoe,                                BT Innovate & Design 


From Rolf.Winter@nw.neclab.eu  Mon Mar  8 08:43:57 2010
Return-Path: <Rolf.Winter@nw.neclab.eu>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 102E53A6A38 for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 08:43:57 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[BAYES_00=-2.599]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id Edlo8KaUIoUD for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 08:43:56 -0800 (PST)
Received: from smtp0.neclab.eu (smtp0.neclab.eu [195.37.70.41]) by core3.amsl.com (Postfix) with ESMTP id 04FB73A69C8 for <ledbat@ietf.org>; Mon,  8 Mar 2010 08:43:56 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp0.neclab.eu (Postfix) with ESMTP id 54AA72C020507; Mon,  8 Mar 2010 17:43:59 +0100 (CET)
X-Virus-Scanned: Amavisd on Debian GNU/Linux (atlas2.office)
Received: from smtp0.neclab.eu ([127.0.0.1]) by localhost (atlas2.office [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id e9cqJJXlpt-R; Mon,  8 Mar 2010 17:43:59 +0100 (CET)
Received: from VENUS.office (mx1.office [192.168.24.3]) by smtp0.neclab.eu (Postfix) with ESMTP id 34EF42C000352; Mon,  8 Mar 2010 17:43:39 +0100 (CET)
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Date: Mon, 8 Mar 2010 17:43:34 +0100
Message-ID: <547F018265F92642B577B986577D671C012358C2@VENUS.office>
In-Reply-To: <4B8EC9D1.6010505@matthew.at>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [ledbat] The pps story
Thread-Index: Acq7Ei3CynS+arAJSCWfwGjshooT3ADyubHA
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com><03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com> <4B8EC9D1.6010505@matthew.at>
From: "Rolf Winter" <Rolf.Winter@nw.neclab.eu>
To: <matthew@matthew.at>, "Murari Sridharan" <muraris@microsoft.com>
Cc: ledbat@ietf.org, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 08 Mar 2010 16:43:57 -0000

Hi,

In the environment you are describing I agree. However, LEDBAT is trying =
to avoid delay building up as a result of the queuing delay in DSL =
modems in the upstream direction. Here, we today still have very low =
bandwidth as in DSL the loop length determines rate the modem receives. =
In rural areas 512kb/s and less is not uncommon (you could argue it will =
at some point). A single 1500 byte Ethernet frame can then already =
violate the 25ms delay target. The question is whether that is a =
scenario that LEDBAT simply does not support, i.e. LEBBAT will not be =
able to achieve a 25ms delay target, or should there be a mechanism such =
as adaptive packet sizing to let LEDBAT achieve the 25ms delay target. =
Such a mechanism is not trivial as flows will independently arrive at a =
packet size and avoiding inter-flow (un)fairness (there I said it) will =
be probably tough to solve.

So the question is will the LEDBAT spec include such a mechanism at some =
point? It seems to be implemented already...

Best,

	Rolf

NEC Europe Limited | Registered Office: NEC House, 1 Victoria Road, =
London W3 6BL | Registered in England 2832014=20
=20

> -----Original Message-----
> From: ledbat-bounces@ietf.org [mailto:ledbat-bounces@ietf.org] On
> Behalf Of Matthew Kaufman
> Sent: Mittwoch, 3. M=E4rz 2010 21:43
> To: Murari Sridharan
> Cc: ledbat@ietf.org; Victor Grishchenko
> Subject: Re: [ledbat] The pps story
>=20
> Making packets smaller almost never helps these days, in my =
experience.
> Among other things, far too many of the hops are over layer 2 media
> with
> huge per-packet overhead. Consider how many byte-length periods are
> used
> sending a 100 Mbps Ethernet packet of 150 bytes vs 1500 bytes, for
> instance.
>=20
> Then inside the routers, the per-packet overhead in tracking buffers =
is
> also non-zero, so it doesn't help them much either.
>=20
> In both cases, you'd be better off sending long packets less often
> (less
> link-layer overhead, less router management overhead, and fewer
> send/receives to interrupt and/or schedule)
>=20
> Trying to prevent head-of-line blocking by making packets smaller made
> sense on dialup modems, but it really hasn't been useful since.
>=20
> Matthew Kaufman
>=20
> _______________________________________________
> ledbat mailing list
> ledbat@ietf.org
> https://www.ietf.org/mailman/listinfo/ledbat

From nweaver@ICSI.Berkeley.EDU  Mon Mar  8 08:47:10 2010
Return-Path: <nweaver@ICSI.Berkeley.EDU>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 969D83A6A76 for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 08:47:10 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -6.11
X-Spam-Level: 
X-Spam-Status: No, score=-6.11 tagged_above=-999 required=5 tests=[AWL=0.489,  BAYES_00=-2.599, RCVD_IN_DNSWL_MED=-4]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id ge8VCGzBiwrJ for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 08:47:09 -0800 (PST)
Received: from fruitcake.ICSI.Berkeley.EDU (fruitcake.ICSI.Berkeley.EDU [192.150.186.11]) by core3.amsl.com (Postfix) with ESMTP id B3C083A6A66 for <ledbat@ietf.org>; Mon,  8 Mar 2010 08:47:09 -0800 (PST)
Received: from [IPv6:::1] (jack.ICSI.Berkeley.EDU [192.150.186.73]) by fruitcake.ICSI.Berkeley.EDU (8.12.11.20060614/8.12.11) with ESMTP id o28GlBp5014149; Mon, 8 Mar 2010 08:47:11 -0800 (PST)
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com><03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com> <4B8EC9D1.6010505@matthew.at> <547F018265F92642B577B986577D671C012358C2@VENUS.office>
In-Reply-To: <547F018265F92642B577B986577D671C012358C2@VENUS.office>
Mime-Version: 1.0 (Apple Message framework v1077)
Content-Type: text/plain; charset=us-ascii
Message-Id: <F1306C82-D3C2-4269-AB32-160728D57C93@icsi.berkeley.edu>
Content-Transfer-Encoding: quoted-printable
From: Nicholas Weaver <nweaver@ICSI.Berkeley.EDU>
Date: Mon, 8 Mar 2010 08:47:11 -0800
To: "Rolf Winter" <Rolf.Winter@nw.neclab.eu>
X-Mailer: Apple Mail (2.1077)
Cc: ledbat@ietf.org, Nicholas Weaver <nweaver@ICSI.Berkeley.EDU>, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 08 Mar 2010 16:47:10 -0000

On Mar 8, 2010, at 8:43 AM, Rolf Winter wrote:

> Hi,
>=20
> In the environment you are describing I agree. However, LEDBAT is =
trying to avoid delay building up as a result of the queuing delay in =
DSL modems in the upstream direction. Here, we today still have very low =
bandwidth as in DSL the loop length determines rate the modem receives. =
In rural areas 512kb/s and less is not uncommon (you could argue it will =
at some point). A single 1500 byte Ethernet frame can then already =
violate the 25ms delay target. The question is whether that is a =
scenario that LEDBAT simply does not support, i.e. LEBBAT will not be =
able to achieve a 25ms delay target, or should there be a mechanism such =
as adaptive packet sizing to let LEDBAT achieve the 25ms delay target. =
Such a mechanism is not trivial as flows will independently arrive at a =
packet size and avoiding inter-flow (un)fairness (there I said it) will =
be probably tough to solve.
>=20
> So the question is will the LEDBAT spec include such a mechanism at =
some point? It seems to be implemented already...

Why not do a packet-pair measurement at the start, to estimate raw =
channel capacity, and use THAT in factoring the delay target, so the =
delay target is not 25ms, but the greater of 25ms or 3x the time for a =
MTU packet?



From Rolf.Winter@nw.neclab.eu  Mon Mar  8 09:30:35 2010
Return-Path: <Rolf.Winter@nw.neclab.eu>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id CF6E13A6A9A for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 09:30:35 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[BAYES_00=-2.599]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id dCAj3xL7QrAR for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 09:30:35 -0800 (PST)
Received: from smtp0.neclab.eu (smtp0.neclab.eu [195.37.70.41]) by core3.amsl.com (Postfix) with ESMTP id B4DF83A6A0A for <ledbat@ietf.org>; Mon,  8 Mar 2010 09:30:34 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp0.neclab.eu (Postfix) with ESMTP id 89A252C017B2E; Mon,  8 Mar 2010 18:30:38 +0100 (CET)
X-Virus-Scanned: Amavisd on Debian GNU/Linux (atlas2.office)
Received: from smtp0.neclab.eu ([127.0.0.1]) by localhost (atlas2.office [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id hGB8OV6EDzg5; Mon,  8 Mar 2010 18:30:38 +0100 (CET)
Received: from VENUS.office (mx1.office [192.168.24.3]) by smtp0.neclab.eu (Postfix) with ESMTP id 665032C020507; Mon,  8 Mar 2010 18:30:23 +0100 (CET)
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Date: Mon, 8 Mar 2010 18:30:16 +0100
Message-ID: <547F018265F92642B577B986577D671C012358DD@VENUS.office>
In-Reply-To: <F1306C82-D3C2-4269-AB32-160728D57C93@icsi.berkeley.edu>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [ledbat] The pps story
Thread-Index: Acq+305aaVyUuVZbSqK6TIrYjK+bZwABTxHQ
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com><03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com><4B8EC9D1.6010505@matthew.at><547F018265F92642B577B986577D671C012358C2@VENUS.office> <F1306C82-D3C2-4269-AB32-160728D57C93@icsi.berkeley.edu>
From: "Rolf Winter" <Rolf.Winter@nw.neclab.eu>
To: "Nicholas Weaver" <nweaver@ICSI.Berkeley.EDU>
Cc: ledbat@ietf.org, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 08 Mar 2010 17:30:35 -0000

Good point. We did that in some tests and a bunch of the home gateways =
that we tested did not do drop tail for background priority traffic =
(which is what we are talking about) but something different. Packet =
pairs did not result in correct measurements which screwed up that idea. =
But yes, that was our first attempt as well and would work in simple =
home gateways of if LEDBAT will not be classified as low priority =
traffic. I could show some results we have if that is of interest.

NEC Europe Limited | Registered Office: NEC House, 1 Victoria Road, =
London W3 6BL | Registered in England 2832014=20
=20

> -----Original Message-----
> From: ledbat-bounces@ietf.org [mailto:ledbat-bounces@ietf.org] On
> Behalf Of Nicholas Weaver
> Sent: Montag, 8. M=E4rz 2010 17:47
> To: Rolf Winter
> Cc: ledbat@ietf.org; Nicholas Weaver; Victor Grishchenko
> Subject: Re: [ledbat] The pps story
>=20
>=20
> On Mar 8, 2010, at 8:43 AM, Rolf Winter wrote:
>=20
> > Hi,
> >
> > In the environment you are describing I agree. However, LEDBAT is
> trying to avoid delay building up as a result of the queuing delay in
> DSL modems in the upstream direction. Here, we today still have very
> low bandwidth as in DSL the loop length determines rate the modem
> receives. In rural areas 512kb/s and less is not uncommon (you could
> argue it will at some point). A single 1500 byte Ethernet frame can
> then already violate the 25ms delay target. The question is whether
> that is a scenario that LEDBAT simply does not support, i.e. LEBBAT
> will not be able to achieve a 25ms delay target, or should there be a
> mechanism such as adaptive packet sizing to let LEDBAT achieve the =
25ms
> delay target. Such a mechanism is not trivial as flows will
> independently arrive at a packet size and avoiding inter-flow
> (un)fairness (there I said it) will be probably tough to solve.
> >
> > So the question is will the LEDBAT spec include such a mechanism at
> some point? It seems to be implemented already...
>=20
> Why not do a packet-pair measurement at the start, to estimate raw
> channel capacity, and use THAT in factoring the delay target, so the
> delay target is not 25ms, but the greater of 25ms or 3x the time for a
> MTU packet?
>=20
>=20
> _______________________________________________
> ledbat mailing list
> ledbat@ietf.org
> https://www.ietf.org/mailman/listinfo/ledbat

From matthew@matthew.at  Mon Mar  8 10:21:50 2010
Return-Path: <matthew@matthew.at>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 235663A6AEF for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 10:21:50 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.43
X-Spam-Level: 
X-Spam-Status: No, score=-1.43 tagged_above=-999 required=5 tests=[BAYES_00=-2.599, HELO_EQ_AT=0.424, HOST_EQ_AT=0.745]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 4CueLjhJBBDY for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 10:21:48 -0800 (PST)
Received: from where.matthew.at (where.matthew.at [198.202.199.1]) by core3.amsl.com (Postfix) with ESMTP id B86223A6A6F for <ledbat@ietf.org>; Mon,  8 Mar 2010 10:21:44 -0800 (PST)
Received: from [10.10.155.2] (unknown [10.10.155.2]) by where.matthew.at (Postfix) with ESMTP id F2F3B148048; Mon,  8 Mar 2010 10:21:48 -0800 (PST)
Message-ID: <4B95403C.9000201@matthew.at>
Date: Mon, 08 Mar 2010 10:21:48 -0800
From: Matthew Kaufman <matthew@matthew.at>
User-Agent: Thunderbird 2.0.0.23 (Windows/20090812)
MIME-Version: 1.0
To: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com> <03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com> <4B8EC9D1.6010505@matthew.at> <201003081354.o28DsSlT023371@bagheera.jungle.bt.co.uk>
In-Reply-To: <201003081354.o28DsSlT023371@bagheera.jungle.bt.co.uk>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
Reply-To: matthew@matthew.at
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 08 Mar 2010 18:21:50 -0000

Bob Briscoe wrote:
> Matthew,
>
> At 20:42 03/03/2010, Matthew Kaufman wrote:
>> Making packets smaller almost never helps these days, in my experience.
>
> I agree with what I think you meant to say, but not the exact words 
> you used. To be clear, I think you mean _increasing the packet rate_ 
> never helps. "Making packets smaller" is surely a valid approach if 
> you still send at the same packet rate - I believe this approach is 
> common for congestion control of video streams - the packets are still 
> sent at the same rate, but they are smaller, thus sending less bytes.
When I'm thinking LEDBAT, I'm thinking "file transfer", a case where the 
content is of fixed size and you're simply trying to move it from one 
end to the other.

And yes, the rare video scheme with congestion control sometimes works 
this way, but you get even better performance if you make the video 
packets small enough that you can put two of them in a single packet.
>
>> Among other things, far too many of the hops are over layer 2 media 
>> with huge per-packet overhead. Consider how many byte-length periods 
>> are used sending a 100 Mbps Ethernet packet of 150 bytes vs 1500 
>> bytes, for instance.
>>
>> Then inside the routers, the per-packet overhead in tracking buffers 
>> is also non-zero, so it doesn't help them much either.
>>
>> In both cases, you'd be better off sending long packets less often 
>> (less link-layer overhead, less router management overhead, and fewer 
>> send/receives to interrupt and/or schedule)
>
> A more general statement of the rule to follow should be "Neither 
> increase bit-rate nor packet-rate in response to congestion, because 
> you don't know whether congestion is by bits or packets."
That sounds like a good rule, yes. But there's also "if you are not 
sensing congestion, growing the packet size is better than growing the 
packet rate, all else being equal", at least with the technologies 
currently in use.
>
> There's a draft on pkt vs byte congestion going thru tsvwg at the 
> moment. It's mostly about what network equipment should and shouldn't 
> do to avoid giving transports perverse incentives to send small 
> packets. 
> <http://tools.ietf.org/wg/tsvwg/draft-ietf-tsvwg-byte-pkt-congest/>
> Any comments on the recommendations it gives would be gratefully 
> received. It is due for a major re-write, as it has become tangled due 
> to multiple updates. So if you have any requests for big changes, 
> now's a good time.
I'll give it a read.

Matthew Kaufman


From muraris@microsoft.com  Mon Mar  8 12:06:25 2010
Return-Path: <muraris@microsoft.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 760F63A6AB7 for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 12:06:25 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.599
X-Spam-Level: 
X-Spam-Status: No, score=-10.599 tagged_above=-999 required=5 tests=[AWL=0.000, BAYES_00=-2.599, RCVD_IN_DNSWL_HI=-8]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id R8pL7MKLov4N for <ledbat@core3.amsl.com>; Mon,  8 Mar 2010 12:06:24 -0800 (PST)
Received: from smtp.microsoft.com (mailb.microsoft.com [131.107.115.215]) by core3.amsl.com (Postfix) with ESMTP id A91EE3A6B92 for <ledbat@ietf.org>; Mon,  8 Mar 2010 12:06:16 -0800 (PST)
Received: from TK5EX14MLTC104.redmond.corp.microsoft.com (157.54.79.159) by TK5-EXGWY-E802.partners.extranet.microsoft.com (10.251.56.168) with Microsoft SMTP Server (TLS) id 8.2.176.0; Mon, 8 Mar 2010 12:06:20 -0800
Received: from TK5EX14MBXC128.redmond.corp.microsoft.com ([169.254.7.125]) by TK5EX14MLTC104.redmond.corp.microsoft.com ([157.54.79.159]) with mapi; Mon, 8 Mar 2010 12:06:00 -0800
From: Murari Sridharan <muraris@microsoft.com>
To: "matthew@matthew.at" <matthew@matthew.at>, Bob Briscoe <rbriscoe@jungle.bt.co.uk>
Thread-Topic: [ledbat] The pps story
Thread-Index: AQHKuugDw9KzafzxKEKgHlZenoxwppHgiSYwgACrXICAB2mMAIAASqwA//+UpaA=
Date: Mon, 8 Mar 2010 20:05:51 +0000
Message-ID: <03520536067DF14395EA93FE7ECFDCF0286C4729@TK5EX14MBXC128.redmond.corp.microsoft.com>
References: <1454bf6f1003030733v742efbe8jb6e661b03c3f5f91@mail.gmail.com> <03520536067DF14395EA93FE7ECFDCF028165B8C@TK5EX14MBXC128.redmond.corp.microsoft.com> <4B8EC9D1.6010505@matthew.at> <201003081354.o28DsSlT023371@bagheera.jungle.bt.co.uk> <4B95403C.9000201@matthew.at>
In-Reply-To: <4B95403C.9000201@matthew.at>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, Victor Grishchenko <victor.grishchenko@gmail.com>
Subject: Re: [ledbat] The pps story
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 08 Mar 2010 20:06:25 -0000

The idea that the delay target is fixed and not specific to the channel cap=
acity has been brought up in the past meetings. Several people wanted to ge=
t more clarity on these "magic" numbers as they characterized it.=20

The following is text from the draft.=20

   Consider a protocol that uses packets of equal size and acknowledges
   each of them separately.  (Variable-sized packets and delayed
   acknowledgements are possible and are being implemented, but
   complicate the exposition.)

I think it is worth while discussing this further and providing clarity alo=
ng the lines that Bob mentioned below in terms of byte vs packet congestion=
 and what we recommend to protocols using this controller. We will worry ab=
out where such text should go, whether it is within scope at the next meeti=
ng.=20

Thanks

-----Original Message-----
From: Matthew Kaufman [mailto:matthew@matthew.at]=20
Sent: Monday, March 08, 2010 10:22 AM
To: Bob Briscoe
Cc: Murari Sridharan; ledbat@ietf.org; Victor Grishchenko
Subject: Re: [ledbat] The pps story

Bob Briscoe wrote:
> Matthew,
>
> At 20:42 03/03/2010, Matthew Kaufman wrote:
>> Making packets smaller almost never helps these days, in my experience.
>
> I agree with what I think you meant to say, but not the exact words=20
> you used. To be clear, I think you mean _increasing the packet rate_=20
> never helps. "Making packets smaller" is surely a valid approach if=20
> you still send at the same packet rate - I believe this approach is=20
> common for congestion control of video streams - the packets are still=20
> sent at the same rate, but they are smaller, thus sending less bytes.
When I'm thinking LEDBAT, I'm thinking "file transfer", a case where the=20
content is of fixed size and you're simply trying to move it from one=20
end to the other.

And yes, the rare video scheme with congestion control sometimes works=20
this way, but you get even better performance if you make the video=20
packets small enough that you can put two of them in a single packet.
>
>> Among other things, far too many of the hops are over layer 2 media=20
>> with huge per-packet overhead. Consider how many byte-length periods=20
>> are used sending a 100 Mbps Ethernet packet of 150 bytes vs 1500=20
>> bytes, for instance.
>>
>> Then inside the routers, the per-packet overhead in tracking buffers=20
>> is also non-zero, so it doesn't help them much either.
>>
>> In both cases, you'd be better off sending long packets less often=20
>> (less link-layer overhead, less router management overhead, and fewer=20
>> send/receives to interrupt and/or schedule)
>
> A more general statement of the rule to follow should be "Neither=20
> increase bit-rate nor packet-rate in response to congestion, because=20
> you don't know whether congestion is by bits or packets."
That sounds like a good rule, yes. But there's also "if you are not=20
sensing congestion, growing the packet size is better than growing the=20
packet rate, all else being equal", at least with the technologies=20
currently in use.
>
> There's a draft on pkt vs byte congestion going thru tsvwg at the=20
> moment. It's mostly about what network equipment should and shouldn't=20
> do to avoid giving transports perverse incentives to send small=20
> packets.=20
> <http://tools.ietf.org/wg/tsvwg/draft-ietf-tsvwg-byte-pkt-congest/>
> Any comments on the recommendations it gives would be gratefully=20
> received. It is due for a major re-write, as it has become tangled due=20
> to multiple updates. So if you have any requests for big changes,=20
> now's a good time.
I'll give it a read.

Matthew Kaufman



From rbriscoe@jungle.bt.co.uk  Sat Mar 20 18:41:06 2010
Return-Path: <rbriscoe@jungle.bt.co.uk>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id E044E3A689A for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 18:41:06 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 2.613
X-Spam-Level: **
X-Spam-Status: No, score=2.613 tagged_above=-999 required=5 tests=[BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, DNS_FROM_RFC_BOGUSMX=1.482]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id mglOZq9JCJMT for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 18:41:00 -0700 (PDT)
Received: from hiltoncluster2.worldspice.net (hiltoncluster2.worldspice.net [216.37.94.62]) by core3.amsl.com (Postfix) with ESMTP id C08CE3A67B2 for <ledbat@ietf.org>; Sat, 20 Mar 2010 18:40:59 -0700 (PDT)
Received: (qmail 24442 invoked by uid 0); 21 Mar 2010 01:41:11 -0000
Received: by simscan 1.4.0 ppid: 24069, pid: 24376, t: 2.0033s scanners: clamav: 0.95.3/m:51/d:10354 spam: 3.3.0
Received: from unknown (HELO MUT.jungle.bt.co.uk) (rbriscoe@12.187.138.130) by hiltoncluster02.worldspice.net with ESMTPA; 21 Mar 2010 01:41:09 -0000
X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9
Date: Sat, 20 Mar 2010 23:48:12 +0000
To: "Mayutan A." <mayutan.arumaithurai@gmail.com>, Xiaoming Fu <fu@cs.uni-goettingen.de>, KK RAMAKRISHNAN <kkrama@research.att.com>
From: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
In-Reply-To: <f18355b81003031140k2eb2d2yaeaa3f6233552729@mail.gmail.com>
References: <f18355b81003031140k2eb2d2yaeaa3f6233552729@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"; format=flowed
Message-Id: <20100321014059.C08CE3A67B2@core3.amsl.com>
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: [ledbat] #1/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 01:41:07 -0000

Mayutan, Xiaoming, KK,

It seems a good idea to try to decompose the sub-functions of CC. I 
suspect this is best kept to the CC design process though (primarily 
ICCRG). Rather than an organising principle for standardisation as 
well (as suggested in the draft).

So I'll split my thoughts into 2 mails:
#1 (this one) Applicability of the decomposition: design, or standards too?
#2 (next) thoughts on the decomposition itself

Sub-questions to help determine whether we should decompose CC standards:

Q1. Are we likely to need lots of different scavenger CCs, or are we 
more likely to be refining and improving a single track of 
progressively more generic/graceful/cool ones?
A1. I say we probably need just one track

Q2. Does experience show that the sub-functions are cleanly 
separated, to the extent that they could be plugged together in different ways?
A2. I think the skill of designing a good congestion control is about 
how well the parts complement each other. In fact, one theme of the 
talk I'm planning for ICCRG this week is that we need to be more 
careful to think about the cross-effects of some flows in slow-start 
on others in congestion avoidance (& vv) when designing CC.

So rather than showing Fig 1 as if there is one common interface 
between the paris of modules, it's more important to show that the 
interface depends on which type of outer module is used. For instance 
"CONGESTION_DETECTED" could be a binary congestion event, or a delay 
variable, or a QS bit-rate.


Here's an example of where we've already got more modularisation than 
we should have in the TCP standards (in your I-D's terminology, the 
flow control module behaviour should depend on the which congestion 
detection module we choose):

If my window is 30x yours, and I get 40 ECN marks within one RTT and 
you get 1, I should reduce more than once within the RTT. Whereas if 
I get 40 drops in one RTT, it's more correct to only reduce once.

Reasoning: If congestion detection is by ECN not drop, it implies the 
congestion must be from AQM not tail drop. Whereas 40 drops can mean 
a whole load of synchronised tail drop, 40 ECN marks can't mean 
synchronised drop. So I should take 40 ECN marks more seriously.


Finally, another thought on applicability: This I-D isn't only 
applicable to scavenger CCs. It's clearly applicable to all CC design 
work (again primarily ICCRG).

That's not to say it can't help LEDBAT in future. LEDBAT is on the 
experimental track, so it would be fine if we learn something from 
this decomposition that can help improve LEDBAT between experimental 
and Proposed Standard stages.


Bob


At 19:40 03/03/2010, Mayutan A. wrote:

>We have submitted a new draft to the LEDBAT WG and are planning to 
>make a short presentation at the LEDBAT WG and the ICCRG.
>We are looking forward to all your comments.
><http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00>http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>
>
>Feedback is welcome,
>Mayutan Arumaithurai




________________________________________________________________
Bob Briscoe,                                BT Innovate & Design  


From rbriscoe@jungle.bt.co.uk  Sat Mar 20 18:41:13 2010
Return-Path: <rbriscoe@jungle.bt.co.uk>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 9F3373A6973 for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 18:41:13 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 2.613
X-Spam-Level: **
X-Spam-Status: No, score=2.613 tagged_above=-999 required=5 tests=[BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, DNS_FROM_RFC_BOGUSMX=1.482]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id zyM0FYuQ+kLK for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 18:41:06 -0700 (PDT)
Received: from hiltoncluster2.worldspice.net (hiltoncluster2.worldspice.net [216.37.94.62]) by core3.amsl.com (Postfix) with ESMTP id 4A8BA3A6829 for <ledbat@ietf.org>; Sat, 20 Mar 2010 18:41:01 -0700 (PDT)
Received: (qmail 24525 invoked by uid 0); 21 Mar 2010 01:41:13 -0000
Received: by simscan 1.4.0 ppid: 24069, pid: 24482, t: 1.3194s scanners: clamav: 0.95.3/m:51/d:10354 spam: 3.3.0
Received: from unknown (HELO MUT.jungle.bt.co.uk) (rbriscoe@12.187.138.130) by hiltoncluster02.worldspice.net with ESMTPA; 21 Mar 2010 01:41:12 -0000
X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9
Date: Sun, 21 Mar 2010 00:03:09 +0000
To: "Mayutan A." <mayutan.arumaithurai@gmail.com>, Xiaoming Fu <fu@cs.uni-goettingen.de>, KK RAMAKRISHNAN <kkrama@research.att.com>
From: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"; format=flowed
Message-Id: <20100321014101.4A8BA3A6829@core3.amsl.com>
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: [ledbat] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 01:41:13 -0000

Mayutan, Xiaoming, KK,

Mail #2 of 2: Thoughts on the decomposition itself

Bandwidth-estimation module
---------------------------
I propose it's better to think of this as a Window-overshoot-mitigation module.

i) Bandwidth is the wrong concept. A cc is looking for how much data 
it can risk setting off in flight when it's got insufficient 
information to determine a precise answer. That's a window concept 
[unit: byte], not a bandwidth concept [unit: b/s]. Take QS. The 
router thinks in terms of spare b/s. But the transport has to 
multiply that by RTT to get the initial window it should use.

ii) It's not so much about estimating the right window. It's more 
about ensuring the window is not too wrong, while trying to otherwise 
be as greedy as possible.

Flow-control module
-------------------
Unfortunately ambiguous terminology.
How about Load-response module?

Suggestions for additional functions?
------------------------------------
- Congestion signal conditioning (filtering out synchronised loss 
within a RTT, smoothing in TFRC, etc)

Finally, it needs to be stated explicitly whether this decomposition 
is meant to be all within the sender, or within the transport 
(sender-receiver-pair), or too abstract for this question to be relevant.




Bob


At 19:40 03/03/2010, Mayutan A. wrote:

>We have submitted a new draft to the LEDBAT WG and are planning to 
>make a short presentation at the LEDBAT WG and the ICCRG.
>We are looking forward to all your comments.
><http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00>http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>
>
>Feedback is welcome,
>Mayutan Arumaithurai




________________________________________________________________
Bob Briscoe,                                BT Innovate & Design  


From wesley.m.eddy@nasa.gov  Sat Mar 20 19:43:27 2010
Return-Path: <wesley.m.eddy@nasa.gov>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 7DD003A695F for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 19:43:27 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -4.57
X-Spam-Level: 
X-Spam-Status: No, score=-4.57 tagged_above=-999 required=5 tests=[AWL=-1.701,  BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, RCVD_IN_DNSWL_MED=-4]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id AClAqRheB+1I for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 19:43:25 -0700 (PDT)
Received: from ndjsnpf03.ndc.nasa.gov (ndjsnpf03.ndc.nasa.gov [198.117.1.123]) by core3.amsl.com (Postfix) with ESMTP id A59723A6821 for <ledbat@ietf.org>; Sat, 20 Mar 2010 19:43:25 -0700 (PDT)
Received: from ndjsppt03.ndc.nasa.gov (ndjsppt03.ndc.nasa.gov [198.117.1.102]) by ndjsnpf03.ndc.nasa.gov (Postfix) with ESMTP id E10612D80BD; Sat, 20 Mar 2010 21:43:40 -0500 (CDT)
Received: from ndjshub01.ndc.nasa.gov (ndjshub01-pub.ndc.nasa.gov [198.117.1.160]) by ndjsppt03.ndc.nasa.gov (8.14.3/8.14.3) with ESMTP id o2L2heaE013485;  Sat, 20 Mar 2010 21:43:40 -0500
Received: from NDJSSCC01.ndc.nasa.gov ([198.117.4.166]) by ndjshub01.ndc.nasa.gov ([198.117.1.160]) with mapi; Sat, 20 Mar 2010 21:43:40 -0500
From: "Eddy, Wesley M. (GRC-MS00)[ASRC AEROSPACE CORP]" <wesley.m.eddy@nasa.gov>
To: Bob Briscoe <rbriscoe@jungle.bt.co.uk>, "Mayutan A." <mayutan.arumaithurai@gmail.com>, Xiaoming Fu <fu@cs.uni-goettingen.de>, KK RAMAKRISHNAN <kkrama@research.att.com>
Date: Sat, 20 Mar 2010 21:43:39 -0500
Thread-Topic: [Iccrg] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
Thread-Index: AcrImFCSCy2CfVyQT9OqXObcg1KiWwAA/t56
Message-ID: <C304DB494AC0C04C87C6A6E2FF5603DB47E0EC6A05@NDJSSCC01.ndc.nasa.gov>
References: <"ess3.cs.uc.624:21.02.10.01.42.15"@cs.ucl.ac.uk>
In-Reply-To: <"ess3.cs.uc.624:21.02.10.01.42.15"@cs.ucl.ac.uk>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
acceptlanguage: en-US
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-Proofpoint-Virus-Version: vendor=fsecure engine=1.12.8161:2.4.5, 1.2.40, 4.0.166 definitions=2010-03-20_02:2010-02-06, 2010-03-20, 2010-03-20 signatures=0
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: Re: [ledbat] [Iccrg] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 02:43:27 -0000

The decomposition struck me as a nice start for an abstraction,
though it seems to me like the implementation is probably a lot
more complex :).  I think the interfaces between modules are
probably quite a bit more complex when fleshed out, and then
it could be "fun" to try to orchestrate the data flow between the
modules (who gets to look at, and react to, packets first, who
gets to handle timers first, do modules operate in serial or in
parallel with one another, etc.).

I think I agree with some of Bob's comments, but I have a more
basic question that would be good to clear up, if possible, before
the presentation.  To me, it seems like the "flow-control module" is
hooked up to a set of sensors that tell it how fast it might be able to
go (the "bandwidth-estimation module") and another set of sensors
that tell it when it needs to slow down (the "congestion-detection
module").  But if we rely on same ACK traffic within a flow to feed
both of those sets of sensors, then isn't that division a bit artificial?

I took a little bit of a leap in reading it by assuming that maybe you
would have this incorporated with something like the Congestion
Manager (RFC 3124) so maybe the sets of signals would be shared
between flows as appropriate, in which case it then made a little more
sense to me to split the bandwidth-estimation from the congestion-
detection since they might each be happening through other
processes outside of the flow controlled by an individual flow-
controller.  But the document didn't exactly say this, so I don't know
if that's an assumption or part of the rationale for this decomposition
or not.

Also, there might be potential for the modules to fight with each other
a bit ... won't doing some types of packet probing in the bandwidth-
estimation module adversely impact a delay-based congestion-
detection module, for instance.  I guess there may be certain
combinations that are to be avoided?


________________________________________
From: iccrg-bounces@cs.ucl.ac.uk [iccrg-bounces@cs.ucl.ac.uk] On Behalf Of =
Bob Briscoe [rbriscoe@jungle.bt.co.uk]
Sent: Saturday, March 20, 2010 8:03 PM
To: Mayutan A.; Xiaoming Fu; KK RAMAKRISHNAN
Cc: ledbat@ietf.org; iccrg
Subject: [Iccrg] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt

Mayutan, Xiaoming, KK,

Mail #2 of 2: Thoughts on the decomposition itself

Bandwidth-estimation module
---------------------------
I propose it's better to think of this as a Window-overshoot-mitigation mod=
ule.

i) Bandwidth is the wrong concept. A cc is looking for how much data
it can risk setting off in flight when it's got insufficient
information to determine a precise answer. That's a window concept
[unit: byte], not a bandwidth concept [unit: b/s]. Take QS. The
router thinks in terms of spare b/s. But the transport has to
multiply that by RTT to get the initial window it should use.

ii) It's not so much about estimating the right window. It's more
about ensuring the window is not too wrong, while trying to otherwise
be as greedy as possible.

Flow-control module
-------------------
Unfortunately ambiguous terminology.
How about Load-response module?

Suggestions for additional functions?
------------------------------------
- Congestion signal conditioning (filtering out synchronised loss
within a RTT, smoothing in TFRC, etc)

Finally, it needs to be stated explicitly whether this decomposition
is meant to be all within the sender, or within the transport
(sender-receiver-pair), or too abstract for this question to be relevant.




Bob


At 19:40 03/03/2010, Mayutan A. wrote:

>We have submitted a new draft to the LEDBAT WG and are planning to
>make a short presentation at the LEDBAT WG and the ICCRG.
>We are looking forward to all your comments.
><http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00=
>http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>
>
>Feedback is welcome,
>Mayutan Arumaithurai




________________________________________________________________
Bob Briscoe,                                BT Innovate & Design


_______________________________________________
Iccrg mailing list
Iccrg@cs.ucl.ac.uk
http://oakham.cs.ucl.ac.uk/mailman/listinfo/iccrg=

From muraris@microsoft.com  Sat Mar 20 21:54:22 2010
Return-Path: <muraris@microsoft.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 4350F3A67B0 for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 21:54:22 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -8.533
X-Spam-Level: 
X-Spam-Status: No, score=-8.533 tagged_above=-999 required=5 tests=[AWL=-2.065, BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_HI=-8, SARE_BAYES_6x6=0.4]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id BQ6ioJPHtJGL for <ledbat@core3.amsl.com>; Sat, 20 Mar 2010 21:54:21 -0700 (PDT)
Received: from smtp.microsoft.com (mail2.microsoft.com [131.107.115.215]) by core3.amsl.com (Postfix) with ESMTP id D8A523A682C for <ledbat@ietf.org>; Sat, 20 Mar 2010 21:54:20 -0700 (PDT)
Received: from TK5EX14CASC129.redmond.corp.microsoft.com (157.54.52.7) by TK5-EXGWY-E802.partners.extranet.microsoft.com (10.251.56.168) with Microsoft SMTP Server (TLS) id 8.2.176.0; Sat, 20 Mar 2010 21:54:36 -0700
Received: from TK5EX14MBXC128.redmond.corp.microsoft.com ([169.254.7.44]) by TK5EX14CASC129.redmond.corp.microsoft.com ([157.54.52.7]) with mapi; Sat, 20 Mar 2010 21:54:34 -0700
From: Murari Sridharan <muraris@microsoft.com>
To: "ledbat@ietf.org" <ledbat@ietf.org>
Thread-Topic: Presentation material
Thread-Index: AcrIspYl5qVdIhKgSx6baCBMD6VpLQ==
Date: Sun, 21 Mar 2010 04:54:28 +0000
Message-ID: <03520536067DF14395EA93FE7ECFDCF029125B9D@TK5EX14MBXC128.redmond.corp.microsoft.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Content-Type: multipart/alternative; boundary="_000_03520536067DF14395EA93FE7ECFDCF029125B9DTK5EX14MBXC128r_"
MIME-Version: 1.0
Subject: [ledbat] Presentation material
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 04:54:22 -0000

--_000_03520536067DF14395EA93FE7ECFDCF029125B9DTK5EX14MBXC128r_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

Authors, please send me your slides ahead of time so I can post the meeting=
 materials by tomorrow.

LEDBAT IETF 77 Meeting Agenda
Chairs:  S. Shalunov
         M. Sridharan

Monday, March 22, 2010
0900-1130
Manhattan

Preliminaries (10 minutes)

Note well
Blue Sheets
Minute Takers
Jabber Scribe
Agenda bashing
Document Status

9:10 - 9:40 LEDBAT Practices and Recommendations, R. Penno (30 minutes)
http://tools.ietf.org/id/draft-penno-ledbat-app-practices-recommendations-0=
1.txt

9:40 - 10:10 LEDBAT Congestion Architecture, M. Arumaithurai (30 minutes)
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00

10:10 - 10:40 Low Extra Delay Background Transport (LEDBAT), S. Shalunov (3=
0 minutes)
http://tools.ietf.org/html/draft-ietf-ledbat-congestion-00

A Survey of Lower-than-Best-Effort Transport Protocols (No Presentation, up=
dated document)
http://tools.ietf.org/html/draft-ietf-ledbat-survey-00

Next Steps and Wrapup (20 minutes)


--_000_03520536067DF14395EA93FE7ECFDCF029125B9DTK5EX14MBXC128r_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40">

<head>
<META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3DGenerator content=3D"Microsoft Word 12 (filtered medium)">
<style>
<!--
 /* Font Definitions */
 @font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
 /* Style Definitions */
 p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0in;
	margin-bottom:.0001pt;
	font-size:11.0pt;
	font-family:"Calibri","sans-serif";}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:blue;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{mso-style-priority:99;
	color:purple;
	text-decoration:underline;}
pre
	{mso-style-priority:99;
	mso-style-link:"HTML Preformatted Char";
	margin:0in;
	margin-bottom:.0001pt;
	font-size:10.0pt;
	font-family:"Courier New";}
span.EmailStyle17
	{mso-style-type:personal-compose;
	font-family:"Calibri","sans-serif";
	color:windowtext;}
span.HTMLPreformattedChar
	{mso-style-name:"HTML Preformatted Char";
	mso-style-priority:99;
	mso-style-link:"HTML Preformatted";
	font-family:"Courier New";}
.MsoChpDefault
	{mso-style-type:export-only;}
@page Section1
	{size:8.5in 11.0in;
	margin:1.0in 1.0in 1.0in 1.0in;}
div.Section1
	{page:Section1;}
-->
</style>
<!--[if gte mso 9]><xml>
 <o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
 <o:shapelayout v:ext=3D"edit">
  <o:idmap v:ext=3D"edit" data=3D"1" />
 </o:shapelayout></xml><![endif]-->
</head>

<body lang=3DEN-US link=3Dblue vlink=3Dpurple>

<div class=3DSection1>

<p class=3DMsoNormal>Authors, please send me your slides ahead of time so I=
 can
post the meeting materials by tomorrow. <o:p></o:p></p>

<div style=3D'mso-element:para-border-div;border:none;border-bottom:solid w=
indowtext 1.0pt;
padding:0in 0in 1.0pt 0in'>

<p class=3DMsoNormal style=3D'border:none;padding:0in'><o:p>&nbsp;</o:p></p=
>

</div>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>LEDBAT
IETF 77 Meeting Agenda <o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Chairs:&nbsp;
S. Shalunov<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
M. Sridharan<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Monday,
March 22, 2010<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>0900-1130
<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Manhattan<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Preliminaries
(10 minutes)<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Note
well<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Blue
Sheets<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Minute
Takers<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Jabber
Scribe<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Agenda
bashing<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Document
Status<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>9:10
- 9:40&nbsp;LEDBAT Practices and Recommendations, R. Penno (30 minutes)<o:p=
></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/id/draft-penno-ledbat-app-practices-recommendati=
ons-01.txt<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>9:40
- 10:10 LEDBAT Congestion Architecture, M. Arumaithurai (30 minutes)<o:p></=
o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture=
-00<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>10:10
- 10:40 Low Extra Delay Background Transport (LEDBAT), S. Shalunov (30 minu=
tes)<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/html/draft-ietf-ledbat-congestion-00<o:p></o:p><=
/span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>A
Survey of Lower-than-Best-Effort Transport Protocols (No Presentation, upda=
ted
document)<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/html/draft-ietf-ledbat-survey-00<o:p></o:p></spa=
n></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Next
Steps and Wrapup (20 minutes)<o:p></o:p></span></p>

<p class=3DMsoNormal><o:p>&nbsp;</o:p></p>

</div>

</body>

</html>

--_000_03520536067DF14395EA93FE7ECFDCF029125B9DTK5EX14MBXC128r_--

From michawe@ifi.uio.no  Sun Mar 21 06:01:34 2010
Return-Path: <michawe@ifi.uio.no>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 9E0CE3A686C for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 06:01:34 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.034
X-Spam-Level: 
X-Spam-Status: No, score=-2.034 tagged_above=-999 required=5 tests=[AWL=-0.565, BAYES_00=-2.599, DNS_FROM_OPENWHOIS=1.13]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id g86S9SJdwZ1P for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 06:01:33 -0700 (PDT)
Received: from smtp.getmail.no (smtp.getmail.no [84.208.15.66]) by core3.amsl.com (Postfix) with ESMTP id 225053A685D for <ledbat@ietf.org>; Sun, 21 Mar 2010 06:01:32 -0700 (PDT)
MIME-version: 1.0
Content-transfer-encoding: 7BIT
Content-type: text/plain; charset=US-ASCII; format=flowed; delsp=yes
Received: from smtp.getmail.no ([10.5.16.4]) by get-mta-out02.get.basefarm.net (Sun Java(tm) System Messaging Server 7.0-0.04 64bit (built Jun 20 2008)) with ESMTP id <0KZM00HH8UUY8D70@get-mta-out02.get.basefarm.net> for ledbat@ietf.org; Sun, 21 Mar 2010 14:01:46 +0100 (MET)
Received: from [192.168.0.194] ([84.208.136.71]) by get-mta-in01.get.basefarm.net (Sun Java(tm) System Messaging Server 7.0-0.04 64bit (built Jun 20 2008)) with ESMTP id <0KZM0026QUUB0B10@get-mta-in01.get.basefarm.net> for ledbat@ietf.org; Sun, 21 Mar 2010 14:01:46 +0100 (MET)
X-PMX-Version: 5.5.3.366731, Antispam-Engine: 2.7.0.366912, Antispam-Data: 2010.3.21.124829
Message-id: <E09851FF-15F9-4428-B915-2B62170F53A1@ifi.uio.no>
From: Michael Welzl <michawe@ifi.uio.no>
To: "Eddy, Wesley M. (GRC-MS00)[ASRC AEROSPACE CORP]" <wesley.m.eddy@nasa.gov>
In-reply-to: <C304DB494AC0C04C87C6A6E2FF5603DB47E0EC6A05@NDJSSCC01.ndc.nasa.gov>
Date: Sun, 21 Mar 2010 14:01:23 +0100
References: <"ess3.cs.uc.624:21.02.10.01.42.15"@cs.ucl.ac.uk> <C304DB494AC0C04C87C6A6E2FF5603DB47E0EC6A05@NDJSSCC01.ndc.nasa.gov>
X-Mailer: Apple Mail (2.936)
Cc: iccrg <iccrg@cs.ucl.ac.uk>, "ledbat@ietf.org" <ledbat@ietf.org>, KK RAMAKRISHNAN <kkrama@research.att.com>
Subject: Re: [ledbat] [Iccrg] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 13:01:34 -0000

Hi,

Sorry if I'm simply getting something wrong here - I might...
but really, I wonder what's the point in trying to standardize something
as described in this draft?

The "CC. other than LEDBAT" case:

Pluggable congestion control already exists in Linux and BSD, and
seems to work fine there, without the need for a standard. What exactly
would become better because of this draft?

It seems to me that following such a new specification would probably  
mean
a major code rewrite, with no benefits attained except for being able to
say that it complies to this specification.


The LEDBAT case:

I think that, what LEDBAT needs is a specified encapsulation, i.e.
something explaining how the packets and ACKs look, or how this
could be implemented by, e.g., changing TCP a bit without changing
the way packets look (it seems likely that this could be done,
and because of TCP's great ability to fly through firewalls, it seems
to be a good choice to me).
- but how does this generic building block description help LEDBAT?


Again, sorry if this is just me misunderstanding things.

Cheers,
Michael


On Mar 21, 2010, at 3:43 AM, Eddy, Wesley M. (GRC-MS00)[ASRC AEROSPACE  
CORP] wrote:

> The decomposition struck me as a nice start for an abstraction,
> though it seems to me like the implementation is probably a lot
> more complex :).  I think the interfaces between modules are
> probably quite a bit more complex when fleshed out, and then
> it could be "fun" to try to orchestrate the data flow between the
> modules (who gets to look at, and react to, packets first, who
> gets to handle timers first, do modules operate in serial or in
> parallel with one another, etc.).
>
> I think I agree with some of Bob's comments, but I have a more
> basic question that would be good to clear up, if possible, before
> the presentation.  To me, it seems like the "flow-control module" is
> hooked up to a set of sensors that tell it how fast it might be able  
> to
> go (the "bandwidth-estimation module") and another set of sensors
> that tell it when it needs to slow down (the "congestion-detection
> module").  But if we rely on same ACK traffic within a flow to feed
> both of those sets of sensors, then isn't that division a bit  
> artificial?
>
> I took a little bit of a leap in reading it by assuming that maybe you
> would have this incorporated with something like the Congestion
> Manager (RFC 3124) so maybe the sets of signals would be shared
> between flows as appropriate, in which case it then made a little more
> sense to me to split the bandwidth-estimation from the congestion-
> detection since they might each be happening through other
> processes outside of the flow controlled by an individual flow-
> controller.  But the document didn't exactly say this, so I don't know
> if that's an assumption or part of the rationale for this  
> decomposition
> or not.
>
> Also, there might be potential for the modules to fight with each  
> other
> a bit ... won't doing some types of packet probing in the bandwidth-
> estimation module adversely impact a delay-based congestion-
> detection module, for instance.  I guess there may be certain
> combinations that are to be avoided?
>
>
> ________________________________________
> From: iccrg-bounces@cs.ucl.ac.uk [iccrg-bounces@cs.ucl.ac.uk] On  
> Behalf Of Bob Briscoe [rbriscoe@jungle.bt.co.uk]
> Sent: Saturday, March 20, 2010 8:03 PM
> To: Mayutan A.; Xiaoming Fu; KK RAMAKRISHNAN
> Cc: ledbat@ietf.org; iccrg
> Subject: [Iccrg] #2/2 draft-mayutan-ledbat- 
> congestionarchitecture-00.txt
>
> Mayutan, Xiaoming, KK,
>
> Mail #2 of 2: Thoughts on the decomposition itself
>
> Bandwidth-estimation module
> ---------------------------
> I propose it's better to think of this as a Window-overshoot- 
> mitigation module.
>
> i) Bandwidth is the wrong concept. A cc is looking for how much data
> it can risk setting off in flight when it's got insufficient
> information to determine a precise answer. That's a window concept
> [unit: byte], not a bandwidth concept [unit: b/s]. Take QS. The
> router thinks in terms of spare b/s. But the transport has to
> multiply that by RTT to get the initial window it should use.
>
> ii) It's not so much about estimating the right window. It's more
> about ensuring the window is not too wrong, while trying to otherwise
> be as greedy as possible.
>
> Flow-control module
> -------------------
> Unfortunately ambiguous terminology.
> How about Load-response module?
>
> Suggestions for additional functions?
> ------------------------------------
> - Congestion signal conditioning (filtering out synchronised loss
> within a RTT, smoothing in TFRC, etc)
>
> Finally, it needs to be stated explicitly whether this decomposition
> is meant to be all within the sender, or within the transport
> (sender-receiver-pair), or too abstract for this question to be  
> relevant.
>
>
>
>
> Bob
>
>
> At 19:40 03/03/2010, Mayutan A. wrote:
>
>> We have submitted a new draft to the LEDBAT WG and are planning to
>> make a short presentation at the LEDBAT WG and the ICCRG.
>> We are looking forward to all your comments.
>> <http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00 
>> >http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>>
>>
>> Feedback is welcome,
>> Mayutan Arumaithurai
>
>
>
>
> ________________________________________________________________
> Bob Briscoe,                                BT Innovate & Design
>
>
> _______________________________________________
> Iccrg mailing list
> Iccrg@cs.ucl.ac.uk
> http://oakham.cs.ucl.ac.uk/mailman/listinfo/iccrg
> _______________________________________________
> ledbat mailing list
> ledbat@ietf.org
> https://www.ietf.org/mailman/listinfo/ledbat


From mayutan.arumaithurai@gmail.com  Sun Mar 21 08:19:15 2010
Return-Path: <mayutan.arumaithurai@gmail.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 7DC373A6937 for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 08:19:15 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 0.152
X-Spam-Level: 
X-Spam-Status: No, score=0.152 tagged_above=-999 required=5 tests=[AWL=-0.980,  BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, HTML_MESSAGE=0.001]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id UkWaWu6B7fqS for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 08:19:14 -0700 (PDT)
Received: from mail-wy0-f172.google.com (mail-wy0-f172.google.com [74.125.82.172]) by core3.amsl.com (Postfix) with ESMTP id 210D53A68B4 for <ledbat@ietf.org>; Sun, 21 Mar 2010 08:19:12 -0700 (PDT)
Received: by wyb29 with SMTP id 29so2148264wyb.31 for <ledbat@ietf.org>; Sun, 21 Mar 2010 08:19:25 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type; bh=UL5k+UADpucGKMpVz9iSQ/hEhCqPi9B6oqGu1jR1RrI=; b=L5DepATKZ+kghi/aJfsPG/jRBkuLqaLIdyEmzU9QYisY6DBicZvQAZ3Q1rghEx958g moDVrDEHSbAr+UD7fY0uij7C9eC49ZvVGbjwUcF5uTnmJrn1gg1hehiiYhyf7s4981i0 meZft0iNGxV/KjQ0KOrrMiPHRZLVSG/XqhnJs=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=kEPYXIH8dnUi/3xLOqu19sxescGmQ+FtUlDR8i9xPDGTgNcEfO70RyM4CaAE9LWj1l 55mn8I+9uEJkQdWTFykyjoMuBZoH5gq9dUGCJUjhL3ciYNQ4Cir5EBwFiRNDlgbamAyH nd89V+ci8rq0dFKvXg8nXKnuGbltPyy9WVtsU=
MIME-Version: 1.0
Received: by 10.216.93.77 with SMTP id k55mr936844wef.196.1269184765769; Sun,  21 Mar 2010 08:19:25 -0700 (PDT)
In-Reply-To: <4ba5793a.0502be0a.7c06.ffffd7f1SMTPIN_ADDED@mx.google.com>
References: <f18355b81003031140k2eb2d2yaeaa3f6233552729@mail.gmail.com> <4ba5793a.0502be0a.7c06.ffffd7f1SMTPIN_ADDED@mx.google.com>
Date: Sun, 21 Mar 2010 16:19:25 +0100
Message-ID: <f18355b81003210819j152c926ck916205c48201569d@mail.gmail.com>
From: "Mayutan A." <mayutan.arumaithurai@gmail.com>
To: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
Content-Type: multipart/alternative; boundary=0016e6d77e121e388d0482511ba7
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, KK RAMAKRISHNAN <kkrama@research.att.com>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: Re: [ledbat] #1/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 15:19:16 -0000

--0016e6d77e121e388d0482511ba7
Content-Type: text/plain; charset=ISO-8859-1

Hello Bob,

Thanks a lot for your feedback. See inline for comments.

On Sun, Mar 21, 2010 at 12:48 AM, Bob Briscoe <rbriscoe@jungle.bt.co.uk>wrote:

> Mayutan, Xiaoming, KK,
>
> It seems a good idea to try to decompose the sub-functions of CC. I suspect
> this is best kept to the CC design process though (primarily ICCRG). Rather
> than an organising principle for standardisation as well (as suggested in
> the draft).
>

Our primary focus was to attempt such a decoupling in the LEDBAT WG for a
scavenger transport protocol, before attempting a more general one in the
ICCRG.

>
> So I'll split my thoughts into 2 mails:
> #1 (this one) Applicability of the decomposition: design, or standards too?
> #2 (next) thoughts on the decomposition itself
>
> Sub-questions to help determine whether we should decompose CC standards:
>
> Q1. Are we likely to need lots of different scavenger CCs, or are we more
> likely to be refining and improving a single track of progressively more
> generic/graceful/cool ones?
> A1. I say we probably need just one track
>

I would agree to having just one track too, but based on a decoupled
architecture (not completely decoupled though). This would make it easier to
propose extensions. For e.g, if someone comes up with a better delay based
congestion detection tool, or a more efficient available bandwidth
estimation tool, we could just standardize the mechanism. The mechanism
could then be used not only by a scavenger protocol, but also by other
congestion control protocols. To phrase it differently, once the LEDBAT WG
standardizes a one-way delay based scavenger protocol, other CC protocols
may want to use the one-way delay based mechanism to detect congestion, but
their reaction to detected congestion might vary from that of a scavenger CC
protocol.

>
> Q2. Does experience show that the sub-functions are cleanly separated, to
> the extent that they could be plugged together in different ways?
> A2. I think the skill of designing a good congestion control is about how
> well the parts complement each other. In fact, one theme of the talk I'm
> planning for ICCRG this week is that we need to be more careful to think
> about the cross-effects of some flows in slow-start on others in congestion
> avoidance (& vv) when designing CC.
>

I agree that the various modules need to complement each other. This draft
is an attempt to study how and to what extent can we decouple the various
components.

So rather than showing Fig 1 as if there is one common interface between the
> paris of modules, it's more important to show that the interface depends on
> which type of outer module is used. For instance "CONGESTION_DETECTED" could
> be a binary congestion event, or a delay variable, or a QS bit-rate.
>

Currently, what I had in mind was a binary indicator
(congested/not-congested) or a multilevel indicator.  We need to give more
thought to whether we require multiple interfaces between the modules or
could we come up with a method to map the various indicators to a common
"CONGESTION_DETECTED" indicator.

>
>
> Here's an example of where we've already got more modularisation than we
> should have in the TCP standards (in your I-D's terminology, the flow
> control module behaviour should depend on the which congestion detection
> module we choose):
>
> If my window is 30x yours, and I get 40 ECN marks within one RTT and you
> get 1, I should reduce more than once within the RTT. Whereas if I get 40
> drops in one RTT, it's more correct to only reduce once.
>
> Reasoning: If congestion detection is by ECN not drop, it implies the
> congestion must be from AQM not tail drop. Whereas 40 drops can mean a whole
> load of synchronised tail drop, 40 ECN marks can't mean synchronised drop.
> So I should take 40 ECN marks more seriously.
>
> I would take this example as a pro for a decoupled architecture. The
congestion-detection module could take this into consideration while mapping
the
obtained indication to the  "CONGESTION_DETECTED"  variable. The flow
control module could be designed based on just the value returned by the
"CONGESTION_DETECTED" variable and need not have to differentiate between a
drop, an ecn marking or increase in delay.


>
> Finally, another thought on applicability: This I-D isn't only applicable
> to scavenger CCs. It's clearly applicable to all CC design work (again
> primarily ICCRG).
>
> That's not to say it can't help LEDBAT in future. LEDBAT is on the
> experimental track, so it would be fine if we learn something from this
> decomposition that can help improve LEDBAT between experimental and Proposed
> Standard stages.
>

Yes, we are planning to present it at the LEDBAT and make a short
presentation at the ICCRG too. We feel that the LEDBAT WG might be a good
starting point, and that the approach could be extended to all kinds of
congestion control protocols.

Mayutan

>
> Bob
>
>
> At 19:40 03/03/2010, Mayutan A. wrote:
>
>  We have submitted a new draft to the LEDBAT WG and are planning to make a
>> short presentation at the LEDBAT WG and the ICCRG.
>> We are looking forward to all your comments.
>> <
>> http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>> >
>> http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>>
>>
>> Feedback is welcome,
>> Mayutan Arumaithurai
>>
>
>
>
>
> ________________________________________________________________
> Bob Briscoe,                                BT Innovate & Design
>



-- 
Mayutan Arumaithurai
0049-551-2712647 (Home number)
0049-176-20322049 (mobile number)

--0016e6d77e121e388d0482511ba7
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Hello Bob,<br><br>Thanks a lot for your feedback. See inline for comments. =
<br><br><div class=3D"gmail_quote">On Sun, Mar 21, 2010 at 12:48 AM, Bob Br=
iscoe <span dir=3D"ltr">&lt;<a href=3D"mailto:rbriscoe@jungle.bt.co.uk" tar=
get=3D"_blank">rbriscoe@jungle.bt.co.uk</a>&gt;</span> wrote:<br>

<blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb(204, =
204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Mayutan, Xiaoming=
, KK,<br>
<br>
It seems a good idea to try to decompose the sub-functions of CC. I suspect=
 this is best kept to the CC design process though (primarily ICCRG). Rathe=
r than an organising principle for standardisation as well (as suggested in=
 the draft).<br>

</blockquote><div><br style=3D"color: rgb(51, 102, 255);"><span style=3D"co=
lor: rgb(51, 102, 255);">Our primary focus was to attempt such a decoupling=
 in the LEDBAT WG for a scavenger transport protocol, before attempting a m=
ore general one in the ICCRG</span>. =A0 <br>

</div><blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb=
(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
So I&#39;ll split my thoughts into 2 mails:<br>
#1 (this one) Applicability of the decomposition: design, or standards too?=
<br>
#2 (next) thoughts on the decomposition itself<br>
<br>
Sub-questions to help determine whether we should decompose CC standards:<b=
r>
<br>
Q1. Are we likely to need lots of different scavenger CCs, or are we more l=
ikely to be refining and improving a single track of progressively more gen=
eric/graceful/cool ones?<br>
A1. I say we probably need just one track<br></blockquote><div><br><span st=
yle=3D"color: rgb(51, 102, 255);">I would agree to having just one track to=
o, but based on a decoupled architecture (not completely decoupled though).=
 This would make it easier to propose extensions. For e.g, if someone comes=
 up with a better delay based congestion detection tool, or a more efficien=
t available bandwidth estimation tool, we could just standardize the mechan=
ism. The mechanism could then be used not only by a scavenger protocol, but=
 also by other congestion control protocols. To phrase it differently, once=
 the LEDBAT WG standardizes a one-way delay based scavenger protocol, other=
 CC protocols may want to use the one-way delay based mechanism to detect c=
ongestion, but their reaction to detected congestion might vary from that o=
f a scavenger CC protocol. =A0 </span><br>

</div><blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb=
(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
Q2. Does experience show that the sub-functions are cleanly separated, to t=
he extent that they could be plugged together in different ways?<br>
A2. I think the skill of designing a good congestion control is about how w=
ell the parts complement each other. In fact, one theme of the talk I&#39;m=
 planning for ICCRG this week is that we need to be more careful to think a=
bout the cross-effects of some flows in slow-start on others in congestion =
avoidance (&amp; vv) when designing CC.<br>

</blockquote><div><br><span style=3D"color: rgb(51, 102, 255);">I agree tha=
t the various modules need to complement each other. This draft is an attem=
pt to study how and to what extent can we decouple the various components.<=
/span><br>

<br></div><blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid=
 rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
So rather than showing Fig 1 as if there is one common interface between th=
e paris of modules, it&#39;s more important to show that the interface depe=
nds on which type of outer module is used. For instance &quot;CONGESTION_DE=
TECTED&quot; could be a binary congestion event, or a delay variable, or a =
QS bit-rate.<br>

</blockquote><div><br><span style=3D"color: rgb(51, 102, 255);">Currently, =
what I had in mind was a binary indicator (congested/not-congested) or a mu=
ltilevel indicator.=A0 We need to give more thought to whether we require m=
ultiple interfaces between the modules or could we come up with a method to=
 map the various indicators to a common &quot;CONGESTION_DETECTED&quot; ind=
icator.=A0 </span></div>

<blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb(204, =
204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
<br>
Here&#39;s an example of where we&#39;ve already got more modularisation th=
an we should have in the TCP standards (in your I-D&#39;s terminology, the =
flow control module behaviour should depend on the which congestion detecti=
on module we choose):<br>


<br>
If my window is 30x yours, and I get 40 ECN marks within one RTT and you ge=
t 1, I should reduce more than once within the RTT. Whereas if I get 40 dro=
ps in one RTT, it&#39;s more correct to only reduce once.<br>
<br>
Reasoning: If congestion detection is by ECN not drop, it implies the conge=
stion must be from AQM not tail drop. Whereas 40 drops can mean a whole loa=
d of synchronised tail drop, 40 ECN marks can&#39;t mean synchronised drop.=
 So I should take 40 ECN marks more seriously.<br>


<br></blockquote><div><span style=3D"color: rgb(51, 102, 255);">I would tak=
e this example as a pro for a decoupled architecture. The congestion-detect=
ion module could take this into consideration while mapping the <br>obtaine=
d indication to the=A0 &quot;CONGESTION_DETECTED&quot;=A0 variable. The flo=
w control module could be designed based on just the value returned by the =
&quot;CONGESTION_DETECTED&quot; variable and need not have to differentiate=
 between a drop, an ecn marking or increase in delay.=A0 </span><br>

=A0</div><blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid =
rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
Finally, another thought on applicability: This I-D isn&#39;t only applicab=
le to scavenger CCs. It&#39;s clearly applicable to all CC design work (aga=
in primarily ICCRG).<br>
<br>
That&#39;s not to say it can&#39;t help LEDBAT in future. LEDBAT is on the =
experimental track, so it would be fine if we learn something from this dec=
omposition that can help improve LEDBAT between experimental and Proposed S=
tandard stages.<br>

</blockquote><div><br><span style=3D"color: rgb(51, 102, 255);">Yes, we are=
 planning to present it at the LEDBAT and make a short presentation at the =
ICCRG too. We feel that the LEDBAT WG might be a good starting point, and t=
hat the approach could be extended to all kinds of congestion control proto=
cols. </span><br>

<br>Mayutan <br></div><blockquote class=3D"gmail_quote" style=3D"border-lef=
t: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1=
ex;">
<br>
Bob<br>
<br>
<br>
At 19:40 03/03/2010, Mayutan A. wrote:<br>
<br>
<blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb(204, =
204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
We have submitted a new draft to the LEDBAT WG and are planning to make a s=
hort presentation at the LEDBAT WG and the ICCRG.<br>
We are looking forward to all your comments.<br>
&lt;<a href=3D"http://tools.ietf.org/html/draft-mayutan-ledbat-congestionar=
chitecture-00" target=3D"_blank">http://tools.ietf.org/html/draft-mayutan-l=
edbat-congestionarchitecture-00</a>&gt;<a href=3D"http://tools.ietf.org/htm=
l/draft-mayutan-ledbat-congestionarchitecture-00" target=3D"_blank">http://=
tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00</a><br>


<br>
<br>
Feedback is welcome,<br>
Mayutan Arumaithurai<br>
</blockquote>
<br>
<br>
<br>
<br>
________________________________________________________________<br><font c=
olor=3D"#888888">
Bob Briscoe, =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =
=A0BT Innovate &amp; Design =A0<br>
</font></blockquote></div><br><br clear=3D"all"><br>-- <br>Mayutan Arumaith=
urai<br>0049-551-2712647 (Home number) <br>0049-176-20322049 (mobile number=
)<br>

--0016e6d77e121e388d0482511ba7--

From mayutan.arumaithurai@gmail.com  Sun Mar 21 08:37:47 2010
Return-Path: <mayutan.arumaithurai@gmail.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 782E13A6937 for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 08:37:47 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.952
X-Spam-Level: 
X-Spam-Status: No, score=-0.952 tagged_above=-999 required=5 tests=[AWL=0.516,  BAYES_00=-2.599, DNS_FROM_OPENWHOIS=1.13, HTML_MESSAGE=0.001]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id mdiTMrfrP2xu for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 08:37:46 -0700 (PDT)
Received: from mail-wy0-f172.google.com (mail-wy0-f172.google.com [74.125.82.172]) by core3.amsl.com (Postfix) with ESMTP id C416F3A6823 for <ledbat@ietf.org>; Sun, 21 Mar 2010 08:37:45 -0700 (PDT)
Received: by wyb29 with SMTP id 29so2152106wyb.31 for <ledbat@ietf.org>; Sun, 21 Mar 2010 08:37:58 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type; bh=gKjh1KCOClLn+P6eW2QbW56CpALNgqgm4JjWsUk/7wY=; b=c00y+2Ne6RKW+xBdDC36gu3RdzxtAaNISbkYhmq5BzynydhErhfsODjSwf1kNmn95C gbn0gY460NY1cZsoSW3VqoiHg/BZgE37LAfkzkhhUf/PADhwAOm13MDb8laCdRABU+sG P4sPljEamF0yXo3J76NL/pCpBHEDQqph4pzfc=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=XsG44VsJ0DZ1V7nq5eUr4/tv0KYSm7StAPZlFJSW+1k4gisgtGSWz8CM8IzlFkDpKY c+z5yvKnbmf5BVG9Emoeof9OHm8cInPiKDHXIQODoiAxsM/ZWZuUnYseGz2qk4asgR5a mmMJ5ObUZ4P5TKDttIuSoBPeSuX0Zeth/Rj9c=
MIME-Version: 1.0
Received: by 10.216.87.16 with SMTP id x16mr640062wee.27.1269185878445; Sun,  21 Mar 2010 08:37:58 -0700 (PDT)
In-Reply-To: <4ba5793c.0502be0a.69ee.ffffcbcfSMTPIN_ADDED@mx.google.com>
References: <4ba5793c.0502be0a.69ee.ffffcbcfSMTPIN_ADDED@mx.google.com>
Date: Sun, 21 Mar 2010 16:37:58 +0100
Message-ID: <f18355b81003210837j2431c0cdh41ddbc4ce1d178e5@mail.gmail.com>
From: "Mayutan A." <mayutan.arumaithurai@gmail.com>
To: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
Content-Type: multipart/alternative; boundary=0016e6dab1507050d00482515dd2
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, KK RAMAKRISHNAN <kkrama@research.att.com>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: Re: [ledbat] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 15:37:47 -0000

--0016e6dab1507050d00482515dd2
Content-Type: text/plain; charset=ISO-8859-1

Hi Bob,

Thanks once again for your feedback. See inline.

On Sun, Mar 21, 2010 at 1:03 AM, Bob Briscoe <rbriscoe@jungle.bt.co.uk>wrote:

> Mayutan, Xiaoming, KK,
>
> Mail #2 of 2: Thoughts on the decomposition itself
>
> Bandwidth-estimation module
> ---------------------------
> I propose it's better to think of this as a Window-overshoot-mitigation
> module.
>
> i) Bandwidth is the wrong concept. A cc is looking for how much data it can
> risk setting off in flight when it's got insufficient information to
> determine a precise answer. That's a window concept [unit: byte], not a
> bandwidth concept [unit: b/s]. Take QS. The router thinks in terms of spare
> b/s. But the transport has to multiply that by RTT to get the initial window
> it should use.
>

Currently, what I have in mind is the estimation of actual bandwidth to
assist the flow-control module and leave it to the flow-control module to
convert this to a relevant window size. In theory, this module could
indicate window size too. Thanks for the alternate name suggestion.

>
> ii) It's not so much about estimating the right window. It's more about
> ensuring the window is not too wrong, while trying to otherwise be as greedy
> as possible.
>

By estimation, I meant the above. Thanks for phrasing it well. I should
probably use a different word here or the name suggested by you.


> Flow-control module
> -------------------
> Unfortunately ambiguous terminology.
> How about Load-response module?
>

Yes, this sounds good too.


>
> Suggestions for additional functions?
> ------------------------------------
> - Congestion signal conditioning (filtering out synchronised loss within a
> RTT, smoothing in TFRC, etc)
>
> Finally, it needs to be stated explicitly whether this decomposition is
> meant to be all within the sender, or within the transport
> (sender-receiver-pair), or too abstract for this question to be relevant.
>

The decomposition could be performed within the sender, and might be
necessary within the transport depending on the choice of the bandwidth
estimation mechanism. According to me, this kind of a decomposition is
implicitly followed in some of the current specifications. For e.g TCP
variants state that an ECN marking is to be treated similar to a loss, or
that the reaction to loss is to halve the congestion window, similar to that
performed by standard TCP.


>
>
> Bob
>
>
> At 19:40 03/03/2010, Mayutan A. wrote:
>
>  We have submitted a new draft to the LEDBAT WG and are planning to make a
>> short presentation at the LEDBAT WG and the ICCRG.
>> We are looking forward to all your comments.
>> <
>> http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>> >
>> http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00
>>
>>
>> Feedback is welcome,
>> Mayutan Arumaithurai
>>
>
>
>
>
> ________________________________________________________________
> Bob Briscoe,                                BT Innovate & Design
>



-- 
Mayutan Arumaithurai
0049-551-2712647 (Home number)
0049-176-20322049 (mobile number)

--0016e6dab1507050d00482515dd2
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<span style=3D"color: rgb(51, 102, 255);">Hi Bob,</span><br style=3D"color:=
 rgb(51, 102, 255);"><br style=3D"color: rgb(51, 102, 255);"><span style=3D=
"color: rgb(51, 102, 255);">Thanks once again for your feedback. See inline=
. </span><br>
<br><div class=3D"gmail_quote">On Sun, Mar 21, 2010 at 1:03 AM, Bob Briscoe=
 <span dir=3D"ltr">&lt;<a href=3D"mailto:rbriscoe@jungle.bt.co.uk">rbriscoe=
@jungle.bt.co.uk</a>&gt;</span> wrote:<br><blockquote class=3D"gmail_quote"=
 style=3D"border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.=
8ex; padding-left: 1ex;">
Mayutan, Xiaoming, KK,<br>
<br>
Mail #2 of 2: Thoughts on the decomposition itself<br>
<br>
Bandwidth-estimation module<br>
---------------------------<br>
I propose it&#39;s better to think of this as a Window-overshoot-mitigation=
 module.<br>
<br>
i) Bandwidth is the wrong concept. A cc is looking for how much data it can=
 risk setting off in flight when it&#39;s got insufficient information to d=
etermine a precise answer. That&#39;s a window concept [unit: byte], not a =
bandwidth concept [unit: b/s]. Take QS. The router thinks in terms of spare=
 b/s. But the transport has to multiply that by RTT to get the initial wind=
ow it should use.<br>
</blockquote><div><br style=3D"color: rgb(51, 102, 255);"><span style=3D"co=
lor: rgb(51, 102, 255);">Currently, what I have in mind is the estimation o=
f actual bandwidth to
assist the flow-control module and leave it to the flow-control module
to convert this to a relevant window size. In theory, this module could
indicate window size too. Thanks for the alternate name suggestion.=A0 </sp=
an><br></div><blockquote class=3D"gmail_quote" style=3D"border-left: 1px so=
lid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
ii) It&#39;s not so much about estimating the right window. It&#39;s more a=
bout ensuring the window is not too wrong, while trying to otherwise be as =
greedy as possible.<br></blockquote><div><br><span style=3D"color: rgb(51, =
102, 255);">By estimation, I meant the above. Thanks for phrasing it well. =
I should probably use a different word here or the name suggested by you. <=
/span><br>
<br></div><blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid=
 rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
Flow-control module<br>
-------------------<br>
Unfortunately ambiguous terminology.<br>
How about Load-response module?<br></blockquote><div><br><span style=3D"col=
or: rgb(51, 102, 255);">Yes, this sounds good too. </span><br>=A0</div><blo=
ckquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb(204, 204,=
 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">

<br>
Suggestions for additional functions?<br>
------------------------------------<br>
- Congestion signal conditioning (filtering out synchronised loss within a =
RTT, smoothing in TFRC, etc)<br>
<br>
Finally, it needs to be stated explicitly whether this decomposition is mea=
nt to be all within the sender, or within the transport (sender-receiver-pa=
ir), or too abstract for this question to be relevant.<br></blockquote>
<div><br><span style=3D"color: rgb(51, 102, 255);">The decomposition could =
be performed within the sender, and might be necessary within the transport=
 depending on the choice of the bandwidth estimation mechanism. According t=
o me, this kind of a decomposition is implicitly followed in some of the cu=
rrent specifications. For e.g TCP variants state that an ECN marking is to =
be treated similar to a loss, or that the reaction to loss is to halve the =
congestion window, similar to that performed by standard TCP. <br>
=A0</span><br></div><blockquote class=3D"gmail_quote" style=3D"border-left:=
 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex=
;">
<br>
<br>
Bob<br>
<br>
<br>
At 19:40 03/03/2010, Mayutan A. wrote:<br>
<br>
<blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb(204, =
204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
We have submitted a new draft to the LEDBAT WG and are planning to make a s=
hort presentation at the LEDBAT WG and the ICCRG.<br>
We are looking forward to all your comments.<br>
&lt;<a href=3D"http://tools.ietf.org/html/draft-mayutan-ledbat-congestionar=
chitecture-00" target=3D"_blank">http://tools.ietf.org/html/draft-mayutan-l=
edbat-congestionarchitecture-00</a>&gt;<a href=3D"http://tools.ietf.org/htm=
l/draft-mayutan-ledbat-congestionarchitecture-00" target=3D"_blank">http://=
tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00</a><br>

<br>
<br>
Feedback is welcome,<br>
Mayutan Arumaithurai<br>
</blockquote>
<br>
<br>
<br>
<br>
________________________________________________________________<br><font c=
olor=3D"#888888">
Bob Briscoe, =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =
=A0BT Innovate &amp; Design =A0<br>
</font></blockquote></div><br><br clear=3D"all"><br>-- <br>Mayutan Arumaith=
urai<br>0049-551-2712647 (Home number) <br>0049-176-20322049 (mobile number=
)<br>

--0016e6dab1507050d00482515dd2--

From rbriscoe@jungle.bt.co.uk  Sun Mar 21 13:04:03 2010
Return-Path: <rbriscoe@jungle.bt.co.uk>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 7CCEA3A68AE for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 13:04:03 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 1.063
X-Spam-Level: *
X-Spam-Status: No, score=1.063 tagged_above=-999 required=5 tests=[AWL=-2.008,  BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, DNS_FROM_RFC_BOGUSMX=1.482,  HTML_MESSAGE=0.001, MIME_HTML_ONLY=1.457, RCVD_IN_DNSWL_LOW=-1]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id ywOrjE4IOs7A for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 13:03:56 -0700 (PDT)
Received: from smtp2.smtp.bt.com (smtp2.smtp.bt.com [217.32.164.150]) by core3.amsl.com (Postfix) with ESMTP id EEDF03A6816 for <ledbat@ietf.org>; Sun, 21 Mar 2010 13:03:55 -0700 (PDT)
Received: from i2kc06-ukbr.domain1.systemhost.net ([193.113.197.70]) by smtp2.smtp.bt.com with Microsoft SMTPSVC(6.0.3790.3959);  Sun, 21 Mar 2010 20:04:11 +0000
Received: from cbibipnt05.iuser.iroot.adidom.com ([147.149.196.177]) by i2kc06-ukbr.domain1.systemhost.net with Microsoft SMTPSVC(6.0.3790.3959); Sun, 21 Mar 2010 20:04:11 +0000
Received: From bagheera.jungle.bt.co.uk ([132.146.168.158]) by cbibipnt05.iuser.iroot.adidom.com (WebShield SMTP v4.5 MR1a P0803.399); id 1269201849627; Sun, 21 Mar 2010 20:04:09 +0000
Received: from MUT.jungle.bt.co.uk ([10.73.128.74]) by bagheera.jungle.bt.co.uk (8.13.5/8.12.8) with ESMTP id o2LK448S014063; Sun, 21 Mar 2010 20:04:05 GMT
Message-Id: <201003212004.o2LK448S014063@bagheera.jungle.bt.co.uk>
X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9
Date: Sun, 21 Mar 2010 20:04:00 +0000
To: "Mayutan A." <mayutan.arumaithurai@gmail.com>
From: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
In-Reply-To: <f18355b81003210819j152c926ck916205c48201569d@mail.gmail.co m>
References: <f18355b81003031140k2eb2d2yaeaa3f6233552729@mail.gmail.com> <4ba5793a.0502be0a.7c06.ffffd7f1SMTPIN_ADDED@mx.google.com> <f18355b81003210819j152c926ck916205c48201569d@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/html; charset="us-ascii"
X-Scanned-By: MIMEDefang 2.56 on 132.146.168.158
X-OriginalArrivalTime: 21 Mar 2010 20:04:11.0404 (UTC) FILETIME=[AC4194C0:01CAC931]
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, KK RAMAKRISHNAN <kkrama@research.att.com>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: Re: [ledbat] #1/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 20:04:03 -0000

<html>
<body>
Mayutan,<br><br>
inline marked &quot;[BB]:&quot; <br><br>
At 15:19 21/03/2010, Mayutan A. wrote:<br>
<blockquote type=cite class=cite cite="">Hello Bob,<br><br>
Thanks a lot for your feedback. See inline for comments. <br><br>
On Sun, Mar 21, 2010 at 12:48 AM, Bob Briscoe
&lt;<a href="mailto:rbriscoe@jungle.bt.co.uk">rbriscoe@jungle.bt.co.uk</a>
&gt; wrote:<br>

<dl>
<dd>Mayutan, Xiaoming, KK,<br><br>

<dd>It seems a good idea to try to decompose the sub-functions of CC. I
suspect this is best kept to the CC design process though (primarily
ICCRG). Rather than an organising principle for standardisation as well
(as suggested in the draft).<br><br>

</dl><br>
Our primary focus was to attempt such a decoupling in the LEDBAT WG for a
scavenger transport protocol, before attempting a more general one in the
ICCRG.&nbsp;&nbsp; <br>

<dl><br>

<dd>So I'll split my thoughts into 2 mails:<br>

<dd>#1 (this one) Applicability of the decomposition: design, or
standards too?<br>

<dd>#2 (next) thoughts on the decomposition itself<br><br>

<dd>Sub-questions to help determine whether we should decompose CC
standards:<br><br>

<dd>Q1. Are we likely to need lots of different scavenger CCs, or are we
more likely to be refining and improving a single track of progressively
more generic/graceful/cool ones?<br>

<dd>A1. I say we probably need just one track<br><br>

</dl><br>
I would agree to having just one track too, but based on a decoupled
architecture (not completely decoupled though). This would make it easier
to propose extensions. For e.g, if someone comes up with a better delay
based congestion detection tool, or a more efficient available bandwidth
estimation tool, we could just standardize the mechanism. The mechanism
could then be used not only by a scavenger protocol, but also by other
congestion control protocols. To phrase it differently, once the LEDBAT
WG standardizes a one-way delay based scavenger protocol, other CC
protocols may want to use the one-way delay based mechanism to detect
congestion, but their reaction to detected congestion might vary from
that of a scavenger CC protocol.&nbsp;&nbsp; <br>

<dl><br>

<dd>Q2. Does experience show that the sub-functions are cleanly
separated, to the extent that they could be plugged together in different
ways?<br>

<dd>A2. I think the skill of designing a good congestion control is about
how well the parts complement each other. In fact, one theme of the talk
I'm planning for ICCRG this week is that we need to be more careful to
think about the cross-effects of some flows in slow-start on others in
congestion avoidance (&amp; vv) when designing CC.<br><br>

</dl><br>
I agree that the various modules need to complement each other. This
draft is an attempt to study how and to what extent can we decouple the
various components.<br><br>

<dl>
<dd>So rather than showing Fig 1 as if there is one common interface
between the paris of modules, it's more important to show that the
interface depends on which type of outer module is used. For instance
&quot;CONGESTION_DETECTED&quot; could be a binary congestion event, or a
delay variable, or a QS bit-rate.</blockquote>
</dl><br>
[BB]: Altho this sounds fine in theory, at a practical level, code that
responds to binary events is very different to code that uses numbers in
equations. In event-based code, the outcome emerges from the frequency of
different behaviours following different events. Whereas in the
equation-based code, the outcome is always present internally, in the
values of the parameters.<br><br>
Hence my point about using this at the conceptual design phase vs the
practical stages like standardisation and coding.<br><br>
<br><br>
<blockquote type=cite class=cite cite="">Currently, what I had in mind
was a binary indicator (congested/not-congested) or a multilevel
indicator.&nbsp; We need to give more thought to whether we require
multiple interfaces between the modules or could we come up with a method
to map the various indicators to a common &quot;CONGESTION_DETECTED&quot;
indicator.&nbsp; <br>

<dl><br><br>

<dd>Here's an example of where we've already got more modularisation than
we should have in the TCP standards (in your I-D's terminology, the flow
control module behaviour should depend on the which congestion detection
module we choose):<br><br>

<dd>If my window is 30x yours, and I get 40 ECN marks within one RTT and
you get 1, I should reduce more than once within the RTT. Whereas if I
get 40 drops in one RTT, it's more correct to only reduce once.<br><br>

<dd>Reasoning: If congestion detection is by ECN not drop, it implies the
congestion must be from AQM not tail drop. Whereas 40 drops can mean a
whole load of synchronised tail drop, 40 ECN marks can't mean
synchronised drop. So I should take 40 ECN marks more seriously.<br><br>

</dl>I would take this example as a pro for a decoupled architecture. The
congestion-detection module could take this into consideration while
mapping the <br>
obtained indication to the&nbsp; &quot;CONGESTION_DETECTED&quot;&nbsp;
variable. The flow control module could be designed based on just the
value returned by the &quot;CONGESTION_DETECTED&quot; variable and need
not have to differentiate between a drop, an ecn marking or increase in
delay.&nbsp; </blockquote><br>
[BB]: Yes, perhaps you're right. We'd need to try coding this.<br><br>
<blockquote type=cite class=cite cite="">&nbsp;<br>

<dl><br>

<dd>Finally, another thought on applicability: This I-D isn't only
applicable to scavenger CCs. It's clearly applicable to all CC design
work (again primarily ICCRG).<br><br>

<dd>That's not to say it can't help LEDBAT in future. LEDBAT is on the
experimental track, so it would be fine if we learn something from this
decomposition that can help improve LEDBAT between experimental and
Proposed Standard stages.<br><br>

</dl><br>
Yes, we are planning to present it at the LEDBAT and make a short
presentation at the ICCRG too. We feel that the LEDBAT WG might be a good
starting point, and that the approach could be extended to all kinds of
congestion control protocols. </blockquote><br>
[BB]: I'm suspect LEDBAT won't want to be distracted from it's very
focused task. While I suspect folks in ICCRG might be more receptive to
thinking like this.<br><br>
Cheers<br><br>
<br>
Bob<br><br>
<br>
<blockquote type=cite class=cite cite="">Mayutan <br>

<dl><br>

<dd>Bob<br><br>
<br>

<dd>At 19:40 03/03/2010, Mayutan A. wrote:<br><br>

<dl>
<dd>We have submitted a new draft to the LEDBAT WG and are planning to
make a short presentation at the LEDBAT WG and the ICCRG.<br>

<dd>We are looking forward to all your comments.<br>

<dd>
&lt;<a href="http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00">
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00</a>
&gt;<a href="http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00" eudora="autourl">
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00</a>
<br><br>
<br>

<dd>Feedback is welcome,<br>

<dd>Mayutan Arumaithurai<br><br>

</dl><br><br>
<br><br>

<dd>________________________________________________________________<br>

<dd><font color="#888888">Bob
Briscoe,&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
BT Innovate &amp; Design&nbsp; <br>
</font><br>

</dl><br><br>
<br>
-- <br>
Mayutan Arumaithurai<br>
0049-551-2712647 (Home number) <br>
0049-176-20322049 (mobile number)</blockquote>
<x-sigsep><p></x-sigsep>
________________________________________________________________<br>
Bob
Briscoe,&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
BT Innovate &amp; Design</body>
</html>


From rbriscoe@jungle.bt.co.uk  Sun Mar 21 13:13:48 2010
Return-Path: <rbriscoe@jungle.bt.co.uk>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 5D16F3A6813 for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 13:13:48 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 0.036
X-Spam-Level: 
X-Spam-Status: No, score=0.036 tagged_above=-999 required=5 tests=[AWL=-0.837,  BAYES_20=-0.74, DNS_FROM_OPENWHOIS=1.13, DNS_FROM_RFC_BOGUSMX=1.482,  HTML_MESSAGE=0.001, RCVD_IN_DNSWL_LOW=-1]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id rs3Z1TyxibKH for <ledbat@core3.amsl.com>; Sun, 21 Mar 2010 13:13:42 -0700 (PDT)
Received: from smtp3.smtp.bt.com (smtp3.smtp.bt.com [217.32.164.138]) by core3.amsl.com (Postfix) with ESMTP id EA3703A67FD for <ledbat@ietf.org>; Sun, 21 Mar 2010 13:13:41 -0700 (PDT)
Received: from i2kc08-ukbr.domain1.systemhost.net ([193.113.197.71]) by smtp3.smtp.bt.com with Microsoft SMTPSVC(6.0.3790.3959);  Sun, 21 Mar 2010 20:13:57 +0000
Received: from cbibipnt08.iuser.iroot.adidom.com ([147.149.100.81]) by i2kc08-ukbr.domain1.systemhost.net with Microsoft SMTPSVC(6.0.3790.3959); Sun, 21 Mar 2010 20:13:57 +0000
Received: From bagheera.jungle.bt.co.uk ([132.146.168.158]) by cbibipnt08.iuser.iroot.adidom.com (WebShield SMTP v4.5 MR1a P0803.399); id 1269202435784; Sun, 21 Mar 2010 20:13:55 +0000
Received: from MUT.jungle.bt.co.uk ([10.73.128.74]) by bagheera.jungle.bt.co.uk (8.13.5/8.12.8) with ESMTP id o2LKDn38014131; Sun, 21 Mar 2010 20:13:51 GMT
Message-Id: <201003212013.o2LKDn38014131@bagheera.jungle.bt.co.uk>
X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9
Date: Sun, 21 Mar 2010 20:13:41 +0000
To: "Mayutan A." <mayutan.arumaithurai@gmail.com>
From: Bob Briscoe <rbriscoe@jungle.bt.co.uk>
In-Reply-To: <f18355b81003210837j2431c0cdh41ddbc4ce1d178e5@mail.gmail.co m>
References: <4ba5793c.0502be0a.69ee.ffffcbcfSMTPIN_ADDED@mx.google.com> <f18355b81003210837j2431c0cdh41ddbc4ce1d178e5@mail.gmail.com>
Mime-Version: 1.0
Content-Type: multipart/alternative; boundary="=====================_460563755==.ALT"
X-Scanned-By: MIMEDefang 2.56 on 132.146.168.158
X-OriginalArrivalTime: 21 Mar 2010 20:13:57.0140 (UTC) FILETIME=[0961CD40:01CAC933]
Cc: "ledbat@ietf.org" <ledbat@ietf.org>, KK RAMAKRISHNAN <kkrama@research.att.com>, iccrg <iccrg@cs.ucl.ac.uk>
Subject: Re: [ledbat] #2/2 draft-mayutan-ledbat-congestionarchitecture-00.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sun, 21 Mar 2010 20:13:48 -0000

--=====================_460563755==.ALT
Content-Type: text/plain; charset="us-ascii"; format=flowed

Mayutan,

At 15:37 21/03/2010, Mayutan A. wrote:
>Hi Bob,
>
>Thanks once again for your feedback. See inline.
>
>On Sun, Mar 21, 2010 at 1:03 AM, Bob Briscoe 
><<mailto:rbriscoe@jungle.bt.co.uk>rbriscoe@jungle.bt.co.uk> wrote:
>Mayutan, Xiaoming, KK,
>
>Mail #2 of 2: Thoughts on the decomposition itself
>
>Bandwidth-estimation module
>---------------------------
>I propose it's better to think of this as a 
>Window-overshoot-mitigation module.
>
>i) Bandwidth is the wrong concept. A cc is looking for how much data 
>it can risk setting off in flight when it's got insufficient 
>information to determine a precise answer. That's a window concept 
>[unit: byte], not a bandwidth concept [unit: b/s]. Take QS. The 
>router thinks in terms of spare b/s. But the transport has to 
>multiply that by RTT to get the initial window it should use.
>
>
>Currently, what I have in mind is the estimation of actual bandwidth 
>to assist the flow-control module and leave it to the flow-control 
>module to convert this to a relevant window size. In theory, this 
>module could indicate window size too. Thanks for the alternate name 
>suggestion.

I'm not concerned about just the name. The semantics of window is 
what I think you need here, not bandwidth. This is important to get right.

[A similar example: Stas Shalunov pointed out to me once (I think 
repeating someone else) that if MTU had been defined in units of 
time, not bytes, packets would have grown naturally as link 
technology increased and data networking would have evolved very 
differently. Effectively the MTU is the liaison concept between IETF 
and IEEE. Similarly, the interface to your top module is important to 
get in the right units.]


>ii) It's not so much about estimating the right window. It's more 
>about ensuring the window is not too wrong, while trying to 
>otherwise be as greedy as possible.
>
>
>By estimation, I meant the above. Thanks for phrasing it well. I 
>should probably use a different word here or the name suggested by you.

Cheers



Bob


________________________________________________________________
Bob Briscoe,                                BT Innovate & Design 
--=====================_460563755==.ALT
Content-Type: text/html; charset="us-ascii"

<html>
<body>
Mayutan,<br><br>
At 15:37 21/03/2010, Mayutan A. wrote:<br>
<blockquote type=cite class=cite cite="">Hi Bob,<br><br>
Thanks once again for your feedback. See inline. <br><br>
On Sun, Mar 21, 2010 at 1:03 AM, Bob Briscoe
&lt;<a href="mailto:rbriscoe@jungle.bt.co.uk">rbriscoe@jungle.bt.co.uk</a>
&gt; wrote:<br>

<dl>
<dd>Mayutan, Xiaoming, KK,<br><br>

<dd>Mail #2 of 2: Thoughts on the decomposition itself<br><br>

<dd>Bandwidth-estimation module<br>

<dd>---------------------------<br>

<dd>I propose it's better to think of this as a
Window-overshoot-mitigation module.<br><br>

<dd>i) Bandwidth is the wrong concept. A cc is looking for how much data
it can risk setting off in flight when it's got insufficient information
to determine a precise answer. That's a window concept [unit: byte], not
a bandwidth concept [unit: b/s]. Take QS. The router thinks in terms of
spare b/s. But the transport has to multiply that by RTT to get the
initial window it should use.<br><br>

</dl><br>
Currently, what I have in mind is the estimation of actual bandwidth to
assist the flow-control module and leave it to the flow-control module to
convert this to a relevant window size. In theory, this module could
indicate window size too. Thanks for the alternate name suggestion.&nbsp;
</blockquote><br>
I'm not concerned about just the name. The semantics of window is what I
think you need here, not bandwidth. This is important to get
right.<br><br>
[A similar example: Stas Shalunov pointed out to me once (I think
repeating someone else) that if MTU had been defined in units of time,
not bytes, packets would have grown naturally as link technology
increased and data networking would have evolved very differently.
Effectively the MTU is the liaison concept between IETF and IEEE.
Similarly, the interface to your top module is important to get in the
right units.]<br><br>
<br>
<blockquote type=cite class=cite cite="">
<dl>
<dd>ii) It's not so much about estimating the right window. It's more
about ensuring the window is not too wrong, while trying to otherwise be
as greedy as possible.<br><br>

</dl><br>
By estimation, I meant the above. Thanks for phrasing it well. I should
probably use a different word here or the name suggested by you.
</blockquote><br>
Cheers<br><br>
<br><br>
Bob<br><br>
<x-sigsep><p></x-sigsep>
________________________________________________________________<br>
Bob
Briscoe,&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
BT Innovate &amp; Design</body>
</html>

--=====================_460563755==.ALT--


From shalunov@bittorrent.com  Mon Mar 22 03:55:40 2010
Return-Path: <shalunov@bittorrent.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 3E59928C0CF for <ledbat@core3.amsl.com>; Mon, 22 Mar 2010 03:55:40 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 2.953
X-Spam-Level: **
X-Spam-Status: No, score=2.953 tagged_above=-999 required=5 tests=[BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, FM_FORGED_GMAIL=0.622,  J_CHICKENPOX_33=0.6, J_CHICKENPOX_34=0.6]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id PgsUZwrriLu1 for <ledbat@core3.amsl.com>; Mon, 22 Mar 2010 03:55:37 -0700 (PDT)
Received: from qw-out-2122.google.com (qw-out-2122.google.com [74.125.92.24]) by core3.amsl.com (Postfix) with ESMTP id 6A8883A67A6 for <ledbat@ietf.org>; Mon, 22 Mar 2010 03:55:37 -0700 (PDT)
Received: by qw-out-2122.google.com with SMTP id 5so459718qwi.31 for <ledbat@ietf.org>; Mon, 22 Mar 2010 03:55:52 -0700 (PDT)
MIME-Version: 1.0
Received: by 10.229.224.79 with SMTP id in15mr1338187qcb.76.1269255351771;  Mon, 22 Mar 2010 03:55:51 -0700 (PDT)
Date: Mon, 22 Mar 2010 03:55:51 -0700
Message-ID: <6c82d1361003220355t420a42a9i3f6722b3727c5507@mail.gmail.com>
From: Stanislav Shalunov <shalunov@bittorrent.com>
To: ledbat@ietf.org
Content-Type: multipart/mixed; boundary=0016363b8edc5f22130482618a15
Subject: [ledbat] draft-ietf-ledbat-congestion-01a.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 22 Mar 2010 10:55:40 -0000

--0016363b8edc5f22130482618a15
Content-Type: text/plain; charset=ISO-8859-1

draft-ietf-ledbat-congestion-01 missed the submission deadline, so
we'll will be discussing tentative textual changes in the presentation
tomorrow. However, since the text does exist, I thought I'd send it to
the mailing list -- attached.

-- Stas

--
Stanislav Shalunov
BitTorrent Inc
shalunov@bittorrent.com

personal: http://shlang.com

--0016363b8edc5f22130482618a15
Content-Type: text/plain; charset=US-ASCII; name="draft-ietf-ledbat-congestion-01a.txt"
Content-Disposition: attachment; 
	filename="draft-ietf-ledbat-congestion-01a.txt"
Content-Transfer-Encoding: base64
X-Attachment-Id: f_g73583su0
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--0016363b8edc5f22130482618a15--

From muraris@microsoft.com  Mon Mar 22 08:34:56 2010
Return-Path: <muraris@microsoft.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 5B97E3A691E for <ledbat@core3.amsl.com>; Mon, 22 Mar 2010 08:34:56 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -9.317
X-Spam-Level: 
X-Spam-Status: No, score=-9.317 tagged_above=-999 required=5 tests=[AWL=-0.249, BAYES_00=-2.599, DNS_FROM_OPENWHOIS=1.13, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_HI=-8, SARE_BAYES_6x6=0.4]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id U9hiwG854Hbr for <ledbat@core3.amsl.com>; Mon, 22 Mar 2010 08:34:55 -0700 (PDT)
Received: from smtp.microsoft.com (mailc.microsoft.com [131.107.115.214]) by core3.amsl.com (Postfix) with ESMTP id 33E2F3A6975 for <ledbat@ietf.org>; Mon, 22 Mar 2010 08:34:55 -0700 (PDT)
Received: from TK5EX14MLTC103.redmond.corp.microsoft.com (157.54.79.174) by TK5-EXGWY-E803.partners.extranet.microsoft.com (10.251.56.169) with Microsoft SMTP Server (TLS) id 8.2.176.0; Mon, 22 Mar 2010 08:35:10 -0700
Received: from TK5EX14MBXC128.redmond.corp.microsoft.com ([169.254.7.44]) by TK5EX14MLTC103.redmond.corp.microsoft.com ([157.54.79.174]) with mapi; Mon, 22 Mar 2010 08:34:56 -0700
From: Murari Sridharan <muraris@microsoft.com>
To: Murari Sridharan <muraris@microsoft.com>, "ledbat@ietf.org" <ledbat@ietf.org>
Thread-Topic: Presentation material
Thread-Index: AcrIspYl5qVdIhKgSx6baCBMD6VpLQBIpgKg
Date: Mon, 22 Mar 2010 15:34:48 +0000
Message-ID: <03520536067DF14395EA93FE7ECFDCF02912FF6D@TK5EX14MBXC128.redmond.corp.microsoft.com>
References: <03520536067DF14395EA93FE7ECFDCF029125B9D@TK5EX14MBXC128.redmond.corp.microsoft.com>
In-Reply-To: <03520536067DF14395EA93FE7ECFDCF029125B9D@TK5EX14MBXC128.redmond.corp.microsoft.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Content-Type: multipart/alternative; boundary="_000_03520536067DF14395EA93FE7ECFDCF02912FF6DTK5EX14MBXC128r_"
MIME-Version: 1.0
Subject: Re: [ledbat] Presentation material
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 22 Mar 2010 15:34:56 -0000

--_000_03520536067DF14395EA93FE7ECFDCF02912FF6DTK5EX14MBXC128r_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

All presentation material uploaded to https://datatracker.ietf.org/meeting/=
77/materials.html

Thanks

From: ledbat-bounces@ietf.org [mailto:ledbat-bounces@ietf.org] On Behalf Of=
 Murari Sridharan
Sent: Saturday, March 20, 2010 9:54 PM
To: ledbat@ietf.org
Subject: [ledbat] Presentation material

Authors, please send me your slides ahead of time so I can post the meeting=
 materials by tomorrow.

LEDBAT IETF 77 Meeting Agenda
Chairs:  S. Shalunov
         M. Sridharan

Monday, March 22, 2010
0900-1130
Manhattan

Preliminaries (10 minutes)

Note well
Blue Sheets
Minute Takers
Jabber Scribe
Agenda bashing
Document Status

9:10 - 9:40 LEDBAT Practices and Recommendations, R. Penno (30 minutes)
http://tools.ietf.org/id/draft-penno-ledbat-app-practices-recommendations-0=
1.txt

9:40 - 10:10 LEDBAT Congestion Architecture, M. Arumaithurai (30 minutes)
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-00

10:10 - 10:40 Low Extra Delay Background Transport (LEDBAT), S. Shalunov (3=
0 minutes)
http://tools.ietf.org/html/draft-ietf-ledbat-congestion-00

A Survey of Lower-than-Best-Effort Transport Protocols (No Presentation, up=
dated document)
http://tools.ietf.org/html/draft-ietf-ledbat-survey-00

Next Steps and Wrapup (20 minutes)


--_000_03520536067DF14395EA93FE7ECFDCF02912FF6DTK5EX14MBXC128r_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40">

<head>
<META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3DGenerator content=3D"Microsoft Word 12 (filtered medium)">
<style>
<!--
 /* Font Definitions */
 @font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
	{font-family:Tahoma;
	panose-1:2 11 6 4 3 5 4 4 2 4;}
 /* Style Definitions */
 p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0in;
	margin-bottom:.0001pt;
	font-size:11.0pt;
	font-family:"Calibri","sans-serif";}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:blue;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{mso-style-priority:99;
	color:purple;
	text-decoration:underline;}
pre
	{mso-style-priority:99;
	mso-style-link:"HTML Preformatted Char";
	margin:0in;
	margin-bottom:.0001pt;
	font-size:10.0pt;
	font-family:"Courier New";}
span.HTMLPreformattedChar
	{mso-style-name:"HTML Preformatted Char";
	mso-style-priority:99;
	mso-style-link:"HTML Preformatted";
	font-family:"Courier New";}
span.EmailStyle19
	{mso-style-type:personal;
	font-family:"Calibri","sans-serif";
	color:windowtext;}
span.EmailStyle20
	{mso-style-type:personal-reply;
	font-family:"Calibri","sans-serif";
	color:#1F497D;}
.MsoChpDefault
	{mso-style-type:export-only;
	font-size:10.0pt;}
@page Section1
	{size:8.5in 11.0in;
	margin:1.0in 1.0in 1.0in 1.0in;}
div.Section1
	{page:Section1;}
-->
</style>
<!--[if gte mso 9]><xml>
 <o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
 <o:shapelayout v:ext=3D"edit">
  <o:idmap v:ext=3D"edit" data=3D"1" />
 </o:shapelayout></xml><![endif]-->
</head>

<body lang=3DEN-US link=3Dblue vlink=3Dpurple>

<div class=3DSection1>

<p class=3DMsoNormal><span style=3D'color:#1F497D'>All presentation materia=
l
uploaded to <a href=3D"https://datatracker.ietf.org/meeting/77/materials.ht=
ml">https://datatracker.ietf.org/meeting/77/materials.html</a><o:p></o:p></=
span></p>

<p class=3DMsoNormal><span style=3D'color:#1F497D'><o:p>&nbsp;</o:p></span>=
</p>

<p class=3DMsoNormal><span style=3D'color:#1F497D'>Thanks<o:p></o:p></span>=
</p>

<p class=3DMsoNormal><span style=3D'color:#1F497D'><o:p>&nbsp;</o:p></span>=
</p>

<div>

<div style=3D'border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in =
0in 0in'>

<p class=3DMsoNormal><b><span style=3D'font-size:10.0pt;font-family:"Tahoma=
","sans-serif"'>From:</span></b><span
style=3D'font-size:10.0pt;font-family:"Tahoma","sans-serif"'>
ledbat-bounces@ietf.org [mailto:ledbat-bounces@ietf.org] <b>On Behalf Of </=
b>Murari
Sridharan<br>
<b>Sent:</b> Saturday, March 20, 2010 9:54 PM<br>
<b>To:</b> ledbat@ietf.org<br>
<b>Subject:</b> [ledbat] Presentation material<o:p></o:p></span></p>

</div>

</div>

<p class=3DMsoNormal><o:p>&nbsp;</o:p></p>

<p class=3DMsoNormal>Authors, please send me your slides ahead of time so I=
 can
post the meeting materials by tomorrow. <o:p></o:p></p>

<div style=3D'border:none;border-bottom:solid windowtext 1.0pt;padding:0in =
0in 1.0pt 0in'>

<p class=3DMsoNormal><o:p>&nbsp;</o:p></p>

</div>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>LEDBAT
IETF 77 Meeting Agenda <o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Chairs:&nbsp;
S. Shalunov<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
M. Sridharan<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Monday,
March 22, 2010<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>0900-1130
<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Manhattan<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Preliminaries
(10 minutes)<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Note
well<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Blue
Sheets<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Minute
Takers<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Jabber
Scribe<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Agenda
bashing<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Document
Status<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>9:10
- 9:40&nbsp;LEDBAT Practices and Recommendations, R. Penno (30 minutes)<o:p=
></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/id/draft-penno-ledbat-app-practices-recommendati=
ons-01.txt<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>9:40
- 10:10 LEDBAT Congestion Architecture, M. Arumaithurai (30 minutes)<o:p></=
o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture=
-00<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>10:10
- 10:40 Low Extra Delay Background Transport (LEDBAT), S. Shalunov (30 minu=
tes)<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/html/draft-ietf-ledbat-congestion-00<o:p></o:p><=
/span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>A
Survey of Lower-than-Best-Effort Transport Protocols (No Presentation, upda=
ted
document)<o:p></o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>http://tools.ietf.org/html/draft-ietf-ledbat-survey-00<o:p></o:p></spa=
n></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'><o:p>&nbsp;</o:p></span></p>

<p class=3DMsoNormal><span style=3D'font-size:10.0pt;font-family:"Courier N=
ew"'>Next
Steps and Wrapup (20 minutes)<o:p></o:p></span></p>

<p class=3DMsoNormal><o:p>&nbsp;</o:p></p>

</div>

</body>

</html>

--_000_03520536067DF14395EA93FE7ECFDCF02912FF6DTK5EX14MBXC128r_--

From shalunov@bittorrent.com  Mon Mar 22 14:49:26 2010
Return-Path: <shalunov@bittorrent.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 69C3228C1AE for <ledbat@core3.amsl.com>; Mon, 22 Mar 2010 14:49:26 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 0.453
X-Spam-Level: 
X-Spam-Status: No, score=0.453 tagged_above=-999 required=5 tests=[AWL=1.300,  BAYES_00=-2.599, DNS_FROM_OPENWHOIS=1.13, FM_FORGED_GMAIL=0.622]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id wxhFKQI2RzBG for <ledbat@core3.amsl.com>; Mon, 22 Mar 2010 14:49:25 -0700 (PDT)
Received: from mail-qy0-f196.google.com (mail-qy0-f196.google.com [209.85.221.196]) by core3.amsl.com (Postfix) with ESMTP id 6FC3228C1AB for <ledbat@ietf.org>; Mon, 22 Mar 2010 14:49:22 -0700 (PDT)
Received: by qyk34 with SMTP id 34so141219qyk.22 for <ledbat@ietf.org>; Mon, 22 Mar 2010 14:49:36 -0700 (PDT)
MIME-Version: 1.0
Received: by 10.229.38.147 with SMTP id b19mr2207742qce.102.1269294575855;  Mon, 22 Mar 2010 14:49:35 -0700 (PDT)
In-Reply-To: <6c82d1361003220355t420a42a9i3f6722b3727c5507@mail.gmail.com>
References: <6c82d1361003220355t420a42a9i3f6722b3727c5507@mail.gmail.com>
Date: Mon, 22 Mar 2010 14:49:35 -0700
Message-ID: <6c82d1361003221449n7c67c548s320082357a320344@mail.gmail.com>
From: Stanislav Shalunov <shalunov@bittorrent.com>
To: ledbat@ietf.org
Content-Type: text/plain; charset=ISO-8859-1
Subject: Re: [ledbat] draft-ietf-ledbat-congestion-01a.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Mon, 22 Mar 2010 21:49:26 -0000

The current draft version is now at
http://tools.ietf.org/id/draft-ietf-ledbat-congestion-01.txt


On Mon, Mar 22, 2010 at 3:55 AM, Stanislav Shalunov
<shalunov@bittorrent.com> wrote:
> draft-ietf-ledbat-congestion-01 missed the submission deadline, so
> we'll will be discussing tentative textual changes in the presentation
> tomorrow. However, since the text does exist, I thought I'd send it to
> the mailing list -- attached.



-- 
Stanislav Shalunov
BitTorrent Inc
shalunov@bittorrent.com

personal: http://shlang.com

From Joerg.Wagner@nw.neclab.eu  Tue Mar 23 05:06:41 2010
Return-Path: <Joerg.Wagner@nw.neclab.eu>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 4EA4C3A6A33 for <ledbat@core3.amsl.com>; Tue, 23 Mar 2010 05:06:41 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 1.131
X-Spam-Level: *
X-Spam-Status: No, score=1.131 tagged_above=-999 required=5 tests=[BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 6E-MrhIKTGD0 for <ledbat@core3.amsl.com>; Tue, 23 Mar 2010 05:06:40 -0700 (PDT)
Received: from smtp0.neclab.eu (smtp0.neclab.eu [195.37.70.41]) by core3.amsl.com (Postfix) with ESMTP id D0FFD3A6926 for <ledbat@ietf.org>; Tue, 23 Mar 2010 05:05:51 -0700 (PDT)
Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp0.neclab.eu (Postfix) with ESMTP id 128E92C020508; Tue, 23 Mar 2010 13:06:10 +0100 (CET)
X-Virus-Scanned: Amavisd on Debian GNU/Linux (atlas2.office)
Received: from smtp0.neclab.eu ([127.0.0.1]) by localhost (atlas2.office [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id E57vbX8PBGAt; Tue, 23 Mar 2010 13:06:10 +0100 (CET)
Received: from VENUS.office (mx2.office [192.168.24.15]) by smtp0.neclab.eu (Postfix) with ESMTP id ECA8F2C0204F9; Tue, 23 Mar 2010 13:05:59 +0100 (CET)
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Date: Tue, 23 Mar 2010 13:05:59 +0100
Message-ID: <B94940C43117794C9432FF5FF0CCB506012678CA@VENUS.office>
In-reply-to: <6c82d1361003221449n7c67c548s320082357a320344@mail.gmail.com>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [ledbat] draft-ietf-ledbat-congestion-01a.txt
Thread-Index: AcrKCaTmWLRIRCQMS0up8TbQ3CCJbQAbV57g
References: <6c82d1361003220355t420a42a9i3f6722b3727c5507@mail.gmail.com> <6c82d1361003221449n7c67c548s320082357a320344@mail.gmail.com>
From: "Joerg Wagner" <Joerg.Wagner@nw.neclab.eu>
To: "Stanislav Shalunov" <shalunov@bittorrent.com>, <ledbat@ietf.org>
Subject: Re: [ledbat] draft-ietf-ledbat-congestion-01a.txt
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Tue, 23 Mar 2010 12:06:41 -0000

Hello,

I cannot follow this statement:

> However, once the initial flow yields, the late comer immediately
>   measures the true base delay and the two flows operate from the same
>   (correct) inputs.

What we observed was that the decrease of the first flow and the =
increase of the second one resulted in a roughly constant amount of =
filling state in the modem's buffer. Even if the late comer eventually =
takes over the whole queue it was unable to correctly measure the base =
delay (self-measuring problem, same reason why the base delay gets wrong =
after 10 minutes free of cross-traffic).

If one extends this issue to more than 2 competing LEDBAT flows it =
becomes rather unlikely that the late comer will measure the correct =
base delay during the startup phase.

Joerg


> -----Original Message-----
> From: ledbat-bounces@ietf.org [mailto:ledbat-bounces@ietf.org] On
> Behalf Of Stanislav Shalunov
> Sent: Montag, 22. M=E4rz 2010 22:50
> To: ledbat@ietf.org
> Subject: Re: [ledbat] draft-ietf-ledbat-congestion-01a.txt
>=20
> The current draft version is now at
> http://tools.ietf.org/id/draft-ietf-ledbat-congestion-01.txt
>=20
>=20
> On Mon, Mar 22, 2010 at 3:55 AM, Stanislav Shalunov
> <shalunov@bittorrent.com> wrote:
> > draft-ietf-ledbat-congestion-01 missed the submission deadline, so
> > we'll will be discussing tentative textual changes in the
> presentation
> > tomorrow. However, since the text does exist, I thought I'd send it
> to
> > the mailing list -- attached.
>=20
>=20
>=20
> --
> Stanislav Shalunov
> BitTorrent Inc
> shalunov@bittorrent.com
>=20
> personal: http://shlang.com
> _______________________________________________
> ledbat mailing list
> ledbat@ietf.org
> https://www.ietf.org/mailman/listinfo/ledbat

From mirja.kuehlewind@ikr.uni-stuttgart.de  Tue Mar 23 09:54:24 2010
Return-Path: <mirja.kuehlewind@ikr.uni-stuttgart.de>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 0DA123A68CC for <ledbat@core3.amsl.com>; Tue, 23 Mar 2010 09:54:24 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 1.781
X-Spam-Level: *
X-Spam-Status: No, score=1.781 tagged_above=-999 required=5 tests=[BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, HELO_EQ_DE=0.35, MIME_8BIT_HEADER=0.3]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id vIhvKYjkJxtU for <ledbat@core3.amsl.com>; Tue, 23 Mar 2010 09:54:23 -0700 (PDT)
Received: from mailsrv.ikr.uni-stuttgart.de (mailsrv.ikr.uni-stuttgart.de [129.69.170.2]) by core3.amsl.com (Postfix) with ESMTP id 355273A68C8 for <ledbat@ietf.org>; Tue, 23 Mar 2010 09:54:23 -0700 (PDT)
Received: from netsrv1.ikr.uni-stuttgart.de (netsrv1-c [10.11.12.12]) by mailsrv.ikr.uni-stuttgart.de (Postfix) with ESMTP id 13366439F4 for <ledbat@ietf.org>; Tue, 23 Mar 2010 17:54:41 +0100 (CET)
Received: from vpn-1-cl15 (vpn-1-cl15 [10.88.11.25]) by netsrv1.ikr.uni-stuttgart.de (Postfix) with ESMTP id BB06DBC07E for <ledbat@ietf.org>; Tue, 23 Mar 2010 17:54:40 +0100 (CET)
From: Mirja =?iso-8859-1?q?K=FChlewind?= <mirja.kuehlewind@ikr.uni-stuttgart.de>
Date: Tue, 23 Mar 2010 17:54:37 +0100
User-Agent: KMail/1.9.10 (enterprise35 0.20090731.1005176)
MIME-Version: 1.0
Content-Disposition: inline
To: ledbat@ietf.org
Content-Type: Text/Plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Message-Id: <201003231754.37995.mkuehle@ikr.uni-stuttgart.de>
Subject: [ledbat] Seperating spec from implementation guidelines
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Tue, 23 Mar 2010 16:54:24 -0000

Hi,

I think I could not make my point clear in the wg meeting yesterday. So I try 
to phase my proposal again.
I suggest to make two documents out of the ledbat spec:

- one that really just describes the algorithm without making any assumption 
about the underlaying network (e.g. if acks could get lost) or the transport 
protocol (which is out of scope of the doc already) or any actual value for 
certain parameters (as these also might depend on an assumption about a 
specific scenario). If there is a logical reason for a upper or lower bound 
of a parameter (which maybe even calculable somehow), that should be in the 
document. But it needs to be explained.

- the other document will than have implementation recommendations/guidelines. 
That could be the place to put the pseudocode. But more important 
recommendations for all the parameters should be addressed here plus a 
description of the scenario (or various scenarios) those values have been 
approved in. 

I'm not sure if that is the proper way to handle it but it could help to set 
up a spec a soon as possible and than leave more space for the further 
evaluations.

Mirja


From shalunov@bittorrent.com  Tue Mar 23 18:41:55 2010
Return-Path: <shalunov@bittorrent.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 7D4EC3A6A2B for <ledbat@core3.amsl.com>; Tue, 23 Mar 2010 18:41:55 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 1.431
X-Spam-Level: *
X-Spam-Status: No, score=1.431 tagged_above=-999 required=5 tests=[BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, MIME_8BIT_HEADER=0.3]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id oF71rLd7b7OY for <ledbat@core3.amsl.com>; Tue, 23 Mar 2010 18:41:54 -0700 (PDT)
Received: from mail-vw0-f44.google.com (mail-vw0-f44.google.com [209.85.212.44]) by core3.amsl.com (Postfix) with ESMTP id A1A5C3A69C6 for <ledbat@ietf.org>; Tue, 23 Mar 2010 18:41:54 -0700 (PDT)
Received: by vws12 with SMTP id 12so624471vws.31 for <ledbat@ietf.org>; Tue, 23 Mar 2010 18:42:14 -0700 (PDT)
Received: by 10.220.122.28 with SMTP id j28mr4587112vcr.47.1269394933814; Tue, 23 Mar 2010 18:42:13 -0700 (PDT)
Received: from [130.129.25.133] ([130.129.25.133]) by mx.google.com with ESMTPS id 22sm37090638vws.3.2010.03.23.18.42.11 (version=TLSv1/SSLv3 cipher=RC4-MD5); Tue, 23 Mar 2010 18:42:12 -0700 (PDT)
References: <201003231754.37995.mkuehle@ikr.uni-stuttgart.de>
Message-Id: <8C1E2BC7-AD9A-450E-9FB5-E7521799AA5B@bittorrent.com>
From: Stanislav Shalunov <shalunov@bittorrent.com>
To: =?utf-8?Q?Mirja_K=C3=BChlewind?= <mirja.kuehlewind@ikr.uni-stuttgart.de>
In-Reply-To: <201003231754.37995.mkuehle@ikr.uni-stuttgart.de>
Content-Type: text/plain; charset=utf-8; format=flowed; delsp=yes
Content-Transfer-Encoding: quoted-printable
X-Mailer: iPhone Mail (7D11)
Mime-Version: 1.0 (iPhone Mail 7D11)
Date: Tue, 23 Mar 2010 18:42:03 -0700
Cc: "ledbat@ietf.org" <ledbat@ietf.org>
Subject: Re: [ledbat] Seperating spec from implementation guidelines
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 24 Mar 2010 01:41:55 -0000

The pseudocode is the meat of the spec. The rest of the document =20
explains why it is the way it is. If it is removed, it'd need to be =20
replaced with much more verbose text describing the same algorithmic =20
behavior in prose. It seems that pseudocode is not a bad way to =20
describe an algorithm because it is concise and unambiguous.

Are there any other parts of the spec you like to move out?


Stanislav Shalunov

On Mar 23, 2010, at 9:54 AM, Mirja K=C3=BChlewind =
<mirja.kuehlewind@ikr.uni-stuttgart.d=20
e> wrote:

> Hi,
>
> I think I could not make my point clear in the wg meeting yesterday. =20=

> So I try
> to phase my proposal again.
> I suggest to make two documents out of the ledbat spec:
>
> - one that really just describes the algorithm without making any =20
> assumption
> about the underlaying network (e.g. if acks could get lost) or the =20
> transport
> protocol (which is out of scope of the doc already) or any actual =20
> value for
> certain parameters (as these also might depend on an assumption =20
> about a
> specific scenario). If there is a logical reason for a upper or =20
> lower bound
> of a parameter (which maybe even calculable somehow), that should be =20=

> in the
> document. But it needs to be explained.
>
> - the other document will than have implementation recommendations/=20
> guidelines.
> That could be the place to put the pseudocode. But more important
> recommendations for all the parameters should be addressed here plus a
> description of the scenario (or various scenarios) those values have =20=

> been
> approved in.
>
> I'm not sure if that is the proper way to handle it but it could =20
> help to set
> up a spec a soon as possible and than leave more space for the further
> evaluations.
>
> Mirja
>
> _______________________________________________
> ledbat mailing list
> ledbat@ietf.org
> https://www.ietf.org/mailman/listinfo/ledbat

From mirja.kuehlewind@ikr.uni-stuttgart.de  Wed Mar 24 09:33:33 2010
Return-Path: <mirja.kuehlewind@ikr.uni-stuttgart.de>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 4A94F3A6B91 for <ledbat@core3.amsl.com>; Wed, 24 Mar 2010 09:33:33 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: 1.631
X-Spam-Level: *
X-Spam-Status: No, score=1.631 tagged_above=-999 required=5 tests=[AWL=0.150,  BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, HELO_EQ_DE=0.35]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id oPTmOSuUSM5a for <ledbat@core3.amsl.com>; Wed, 24 Mar 2010 09:33:32 -0700 (PDT)
Received: from mailsrv.ikr.uni-stuttgart.de (mailsrv.ikr.uni-stuttgart.de [129.69.170.2]) by core3.amsl.com (Postfix) with ESMTP id CC0CB3A6920 for <ledbat@ietf.org>; Wed, 24 Mar 2010 09:33:31 -0700 (PDT)
Received: from netsrv1.ikr.uni-stuttgart.de (netsrv1-c [10.11.12.12]) by mailsrv.ikr.uni-stuttgart.de (Postfix) with ESMTP id A53D6439F4; Wed, 24 Mar 2010 17:33:51 +0100 (CET)
Received: from vpn-1-cl15 (vpn-1-cl15 [10.88.11.25]) by netsrv1.ikr.uni-stuttgart.de (Postfix) with ESMTP id 3741FBC07E; Wed, 24 Mar 2010 17:33:51 +0100 (CET)
From: Mirja Kuehlewind <mirja.kuehlewind@ikr.uni-stuttgart.de>
Organization: University of Stuttgart (Germany), IKR
To: Stanislav Shalunov <shalunov@bittorrent.com>
Date: Wed, 24 Mar 2010 17:33:48 +0100
User-Agent: KMail/1.9.10 (enterprise35 0.20090731.1005176)
References: <201003231754.37995.mkuehle@ikr.uni-stuttgart.de> <8C1E2BC7-AD9A-450E-9FB5-E7521799AA5B@bittorrent.com>
In-Reply-To: <8C1E2BC7-AD9A-450E-9FB5-E7521799AA5B@bittorrent.com>
X-KMail-QuotePrefix: > 
MIME-Version: 1.0
Content-Type: Text/Plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Message-Id: <201003241733.49006.mirja.kuehlewind@ikr.uni-stuttgart.de>
Cc: "ledbat@ietf.org" <ledbat@ietf.org>
Subject: Re: [ledbat] Seperating spec from implementation guidelines
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 24 Mar 2010 16:33:33 -0000

I'm not saying to remove anything. I not even saying that there is anything=
=20
wrong about the way it is now. I'm just suggesting another way of documenti=
ng=20
it. Don't know if this might be the better way...

The only thing I'm concerned about are those parameter values in the spec,=
=20
which are there without any explanation where there are coming from. I woul=
d=20
like to see some evaluation results and maybe even more important I would=20
like to know in which scenarios you actually evaluated the algorithm.=20
But to get the spec finished as soon as possible, maybe move this part to a=
=20
different doc...?

If one of your goals is to write a short and handy spec which makes it easy=
 to=20
implement the algorithm, it might just be more appropriate to have a separa=
te=20
doc. In such a doc, which gives implementation guidelines, the pseudocode=20
would be probably really helpful.

The pseudocode is a good way to describe the algorithm but anyway I would l=
ike=20
to have some more text there as well. If you don't get all of the pseudocod=
e=20
at the first look I guess some text is really helpful. If you get everythin=
g=20
from the pseudocode just don't read the text.
Moreover, I was wondering if the pseudocode is maybe implying some=20
implementation assumptions - like e.g. define a certain order to do things =
=2D=20
I don't know; you have to tell...

Another point is I think it would be helpful to have an implementation=20
guideline doc to describe scenarios in which LEDBAT should be use. I guess=
=20
your motivation to use LEDBAT with Bittorrent is right now that the=20
bottleneck link is in the access network and so Bittorrent traffic might=20
block other transmission of the same user.
There might be different scenarios e.g. within a private network where you=
=20
just have a different use case and therefore different parameter value shou=
ld=20
be selected.
The parameter values might also depend on the application you use LEDBAT wi=
th. =20
E.g. I was thinking about having also something like a lower bound of the=20
congestion windows which could be helpful for video streaming application=20
(which do some buffering). Just a thought...

Mirja


On Wednesday 24 March 2010 02:42:03 Stanislav Shalunov wrote:
> The pseudocode is the meat of the spec. The rest of the document
> explains why it is the way it is. If it is removed, it'd need to be
> replaced with much more verbose text describing the same algorithmic
> behavior in prose. It seems that pseudocode is not a bad way to
> describe an algorithm because it is concise and unambiguous.
>
> Are there any other parts of the spec you like to move out?
>
>
> Stanislav Shalunov
>
> On Mar 23, 2010, at 9:54 AM, Mirja K=C3=BChlewind
> <mirja.kuehlewind@ikr.uni-stuttgart.d
>
> e> wrote:
> > Hi,
> >
> > I think I could not make my point clear in the wg meeting yesterday.
> > So I try
> > to phase my proposal again.
> > I suggest to make two documents out of the ledbat spec:
> >
> > - one that really just describes the algorithm without making any
> > assumption
> > about the underlaying network (e.g. if acks could get lost) or the
> > transport
> > protocol (which is out of scope of the doc already) or any actual
> > value for
> > certain parameters (as these also might depend on an assumption
> > about a
> > specific scenario). If there is a logical reason for a upper or
> > lower bound
> > of a parameter (which maybe even calculable somehow), that should be
> > in the
> > document. But it needs to be explained.
> >
> > - the other document will than have implementation recommendations/
> > guidelines.
> > That could be the place to put the pseudocode. But more important
> > recommendations for all the parameters should be addressed here plus a
> > description of the scenario (or various scenarios) those values have
> > been
> > approved in.
> >
> > I'm not sure if that is the proper way to handle it but it could
> > help to set
> > up a spec a soon as possible and than leave more space for the further
> > evaluations.
> >
> > Mirja
> >
> > _______________________________________________
> > ledbat mailing list
> > ledbat@ietf.org
> > https://www.ietf.org/mailman/listinfo/ledbat



=2D-=20
=2D------------------------------------------------------------------
Dipl.-Ing. Mirja K=C3=BChlewind
Institute of Communication Networks and Computer Engineering (IKR)
University of Stuttgart, Germany
Pfaffenwaldring 47, D-70569 Stuttgart

web: www.ikr.uni-stuttgart.de
email: mirja.kuehlewind@ikr.uni-stuttgart.de
tel: +49(0)711/685-67973
=2D------------------------------------------------------------------

From muraris@microsoft.com  Tue Mar 30 10:45:16 2010
Return-Path: <muraris@microsoft.com>
X-Original-To: ledbat@core3.amsl.com
Delivered-To: ledbat@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 157663A683A for <ledbat@core3.amsl.com>; Tue, 30 Mar 2010 10:45:16 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -7.463
X-Spam-Level: 
X-Spam-Status: No, score=-7.463 tagged_above=-999 required=5 tests=[AWL=-0.594, BAYES_50=0.001, DNS_FROM_OPENWHOIS=1.13, RCVD_IN_DNSWL_HI=-8]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id C7TPpBOtjgdY for <ledbat@core3.amsl.com>; Tue, 30 Mar 2010 10:45:14 -0700 (PDT)
Received: from smtp.microsoft.com (mailb.microsoft.com [131.107.115.215]) by core3.amsl.com (Postfix) with ESMTP id EF0BB3A67CF for <ledbat@ietf.org>; Tue, 30 Mar 2010 10:45:13 -0700 (PDT)
Received: from TK5EX14MLTC102.redmond.corp.microsoft.com (157.54.79.180) by TK5-EXGWY-E802.partners.extranet.microsoft.com (10.251.56.168) with Microsoft SMTP Server (TLS) id 8.2.176.0; Tue, 30 Mar 2010 10:45:43 -0700
Received: from TK5EX14MBXC128.redmond.corp.microsoft.com ([169.254.7.2]) by TK5EX14MLTC102.redmond.corp.microsoft.com ([157.54.79.180]) with mapi; Tue, 30 Mar 2010 10:45:42 -0700
From: Murari Sridharan <muraris@microsoft.com>
To: "ledbat@ietf.org" <ledbat@ietf.org>
Thread-Topic: Draft IETF 77- LEDBAT Meeting Notes
Thread-Index: AcrJ7MaDG3GF6T4uQkeypVO5fA9KBAGQ/J0Q
Date: Tue, 30 Mar 2010 17:45:35 +0000
Message-ID: <03520536067DF14395EA93FE7ECFDCF0292E70E3@TK5EX14MBXC128.redmond.corp.microsoft.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Subject: [ledbat] FW: Draft IETF 77- LEDBAT Meeting Notes
X-BeenThere: ledbat@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Mailing list of the LEDBAT WG <ledbat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/ledbat>
List-Post: <mailto:ledbat@ietf.org>
List-Help: <mailto:ledbat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ledbat>, <mailto:ledbat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Tue, 30 Mar 2010 17:45:16 -0000

Thanks David for the meeting notes. Let me know if you have comments before=
 I post it up.=20

Thanks

-----Original Message-----
From: Mcdysan, David E [mailto:dave.mcdysan@verizon.com]=20
Sent: Monday, March 22, 2010 11:24 AM
To: shalunov@bittorrent.com; Murari Sridharan; lars.eggert@nokia.com
Subject: Draft IETF 77- LEDBAT Meeting Notes

LEDBAT IETF 77 Meeting Agenda=20

Chairs:  S. Shalunov
         M. Sridharan
Monday, March 22, 2010 0900-1130  Manhattan

Preliminaries (10 minutes)
Note well
Blue Sheets
Minute Takers
- Dave McDysan
Jabber Scribe
- No volunteers?
Agenda bashing
- No commments
Document Status - Murari summarized slides, no comments
See http://www.ietf.org/proceedings/10mar/slides/ledbat-1.pdf=20

9:10 - 9:40 LEDBAT Practices and Recommendations, R. Penno (30 minutes)
http://tools.ietf.org/id/draft-penno-ledbat-app-practices-recommendation
s-01.txt=20

Renaldo presented:
http://www.ietf.org/proceedings/10mar/slides/ledbat-0.pdf =20
Murari Q: Is recommendation of less than 6 connections needed if window
scale implemented?

REC-3: Applications in general should not open more than 6 connections
to download the same
object.

A: Yes, but another issue is server bandwidth limit per connection.
Murari Q: How would client know about this server restriction?
Stuart Chesire (Apple): Guidelines apply to http but not necessarily
appropriate for other applications. Easier for server to send as fast as
possible and let TCP flow control work. Opening 6 connections will
create more load on the server than one.
Mathis: Institutionalizing workarounds (such as this) for a problem is a
dangerous road.
Renaldo: Proposed rewording recommendation for "purposes of throughput"
Murari: Capture disucssion in document.
Chesire: Why 6 instead of 5 or 7. Recommending that this be one.
Stan: Focus should be on the reason for multiple connections (e.g.,
control/ data is OK), or for throughput (probably not OK).=20
Janai (sp?) Franklin/ Marshall College: Is any number needed? Discussion
of pros/cons should be in document.
Joe Touch: Proposed wording: "Apps should not open multiple connections
for the sole purpose of increasing throughput." Emphasis on "sole"
Dave McDysan: Suggested adding the impact on NAT, especially IPv6
Carrier Grade NAT which would be impacted by multiple TCP connections.
Renaldo: More materia
Matthew Kaufmann (Adobe): Agree with "sole." Other protocols do not have
this problem.=20
Stan: Only TCP, other protocols out of scope.

REC-4: HTTP based applications should use HTTP/1.1 pipelining when
transferring multiple small objects from the same server.

Joe Touch: Differentiate between persistent connections (OK) and
pipelining (possibly not OK in some situations).
Chesire: Is the draft mixing up http and TCP? What is the focus: server
developers, application developers, robust clients.=20
Polly (Apple): Need to tolerate buggy servers (e.g., transparent
proxies).
Lars Eggert: Recommend the good thing to do and what is realistic (i.e.,
under what conditions environments can it be used). Similar to ECN and
other Diffserv marking in this sense.=20

REC-5: Application developers should provide users with a way to
configure the number of
concurrent TCP connections used to transfer a single object.

Lars: Specifying the conditions under which such a number/knob should be
used.
Stanislav: Majority of users will not use such configuration options,
and those who do may not forsee consequences of such configuration.
Fraction who can do something useful is small, but they are vocal.
Murari: Make specific to applications.=20
Lars: Should list specific applications in the draft. Suggest stating as
configure the upper limit.
KK Ramakrishnan: Goals: improve thruput, separate control/data, HOL
blocking versus increase in state. Is an aspect that of different remote
end points?
Herbert Koogle: Since most web objects are small is goal to eliminate
slow start.
Renaldo: Yes, but also avoidance of HOL blocking.
Joe Touch: Pipelining as a general concept is OK, but HTTP 1.1 version
has issues and that is why it is turned off.=20

* Bi-directional HTTP - HyBi working group effort at IETF
Lars: Seems to be outside of charter (http specific) and may be out of
scope.

Mark Polly: http is fundamental impedance mismatch with modern web
browsing. Originally, http pulled down one object while now http
retrieves a page with multiple objects.
Joe Touch: Can cite publications that describe this mismatch.
Stanislav: True, but this seems out of scope.=20
Joe: Recommends pointing to papers.=20
Lars: http is good example that uses multiple TCP connections. OK to use
http and ftp as examples, but DON't make recommendations about the
applications.
Chesire: HOL blocking is an issue if browser wants to display page
before all objects are received; however, other apps (e.g.,
audio/video.program) everything needs to be downloaded.=20
Joe: Pieplining for a single object can impact other objects. Amazon
example given.
Chesire: Scope was a single object.
Mark Polly: Webdav has a similar issue.

Renaldo recap: Reword following:
- sole purpose of multiple connections is to increase=20
- Summarize why pipelining is broken, what is needed
- REC-5 configuration reworded based upon Lars' comments

9:40 - 10:10 LEDBAT Congestion Architecture, M. Arumaithurai (30
minutes)
http://tools.ietf.org/html/draft-mayutan-ledbat-congestionarchitecture-0
0
Mayutan presented
http://www.ietf.org/proceedings/10mar/slides/ledbat-2.pdf

Murari: Appears more appropriate for iccrg. Context could be
architectural framework. Not sure decoupling is such a good idea, way
that everything works together is more important.=20
KK Ramakrishnan: Proposing a framework as useful to think about the
components of the protocol and how they fit together and interact with
other mechanisms.=20
Stanislav: Specific comments on the wg spec and any suggestions as to
what should be changed?
KK: If/when network supports explicit congestion notification, how could
this be plugged in. Better estimate of fair share as a target for
exploration instead of a delay based scheme.=20
Murari: ECN is TCP-based, ledbat is striving to be more general.
Arami (sp?) Cisco: No mention of RED? Why not?=20
Murari: Not clear if RED is available in cable modems.
Stan: From charter, AQM is a more generic term that includes RED.

Janai: One use is a clear separation of constants in the congestion
draft (e.g., the max latency of 25 ms). Introduce more flexibility into
the experimental solution in terms of configurable constants.=20
Stan: Inconsistent with wg comments from last meeting where feedback was
to pick specific values.
Jana: Don't use MUST, but move to recommendations.
Stan: MUST is needed for interoperability.=20
Lars: Use specified value for interoperability, but does not preclude
experimentation with other values.=20

KK: Specific feedback requested on draft.
Murari: Could use bandwidth estimate, feedback instead of or in
complementary way with delay estimation.
Stanislav: Provide specific text changes on congestion.
Bob Briscoe: Add specific text to describe how ledbat congestion
interacts with ECN.=20

10:10 - 10:40 Low Extra Delay Background Transport (LEDBAT), S. Shalunov
(30 minutes)
http://tools.ietf.org/html/draft-ietf-ledbat-congestion-00
Stanislav presented
http://www.ietf.org/proceedings/10mar/slides/ledbat-3.pdf

Lars: This draft missed the cutoff and was noted in the meeting.
Stanislav: Tentative proposed text changes, premilinary version sent to
mailing list, will follow up with a version -01 based upon feedback
received.

Fairness
Lars: Measurements in Trilogy project is not enough, minutes may be
needed to determine baseline delay measurement. Explicit randomization
should help.=20
Rolf Winter NEC:  An issue is one minute slots for base delay, with
history of ten minutes. A long delay in a one minute slot will not be
aged out until ten minutes.=20
Stanislav: Clarification, inserts small random (zero mean) values to
delay which changes amount of capacity that is distributed to other
flows. Paramter should be related to the target.=20

Prameter Values:
Dave McDysan: Question on clarification of interoperability related to
different implementations achieving similar performance.
Stanislav: Stronger than that, is a distributed algorithm where the
implementations interact. For example, in a shared bottleneck two
implementations with similar demand should get a fair share of the
bottleneck bandwidth.

Covers all issues?
Rolf: DSL case in rural areas has a lower rate. More than 25 ms can
occur at lower rates. Should segment size be reduced for these lower
speed links.=20
Stanislav: Preliminary algorithm for adapting segment size has been
developed, but not as well baked as other work. It adds considerable
complications.=20
Rolf: Agrees that this is not trivial, and recommends saying something
about this in the draft.
Stan: If serialization exceeds the target, then ledbat should work.=20
Rolf: But does not do what was specified. Home Gateways do more than
FIFO/ drop tail for European market. For example, multiple queues voice,
BE, Lower Effort. P2P can be classified as Worse than Best Effort, which
is in a different queue and hence delay measurements don't work.=20
Stanislav: Requested more info on this.=20
Murari: Requested a formal presentation at the next meeting on
measurements performed.
Cheshire: This may not be an issue, putting lower effort in another
queue has been done by the home gateway.

Lars: These are points for discussion on applicability of draft. Also,
extension on packet (segment) size is problematic. Nothing stops wg from
moving current draft for stable baseline to experimental and then make
other extensions, such as variable segment size as future experimental
drafts.=20
Lars: Confirmation of stability to be done on mailing list, then run
last call on the mailing list. =20

Lars/KK: State underlying assumptions in draft (e.g., ledbat traffic
shares bottleneck queue with foreground traffic).=20

Detailed Text slides are in the distributed deck, and are also on the
mailing list.=20

Jana: Doesn't seem to address issue if off_Target is high then Ceiling
could increase due to a long cumulative ACK (e.g., due to prior ACKs
being lost), back-back ACKs and bursty behavior could result.=20
Stan: Increases in ceiling are bounded and are no more than TCP.=20
Murari: Reframed question as to how acknowledgements are received and
the packets are "released" and not necessarily how congestion window
(ceiling in Jana's question) increases. Such behavior will cause
measured delay to increase.
Stan: Pseudocode on slide 16=20
	cwnd +=3D GAIN * off_target / cwnd
is increase once per RTT=20
Pseudocode applies to one ACK per packet (for exposition purposes).=20
Lars: Summarize the issue in the draft and consider this as a possible
future extension.=20

Mathis: Number of TCP implementations behave this way and result in
"stretch ACKs."  Consequence is that measured delay momentarily
increases and throughput decreases.=20
Stanislav: Ultimate solution is rate-based instead of window-based.
However, straightforward port to rate-based does not work as well as
window-based.

Jana: State assumption that ACKs must be sent (and received) frequently
for the spec to work.
Stan: Will add this to framing considerations.

??: Separate specification from implementation recommendations in
separate documents
Stan: Could be a later document when to not use SHOULD in original spec
for a particular environment.=20
Murari: Asking for experimental data?
Cheshire: Supports having one clear document. Avoid making things too
general.
Reggisio (??): Recommend assuming ACK per data packet.=20
Stan: However, doesn't address case of multiple lost ACKs.

KK: Suggested trying to understand to burst release of data from one or
more sources that could cause impact on other flows.=20

A Survey of Lower-than-Best-Effort Transport Protocols (No Presentation,
updated document)
http://tools.ietf.org/html/draft-ietf-ledbat-survey-00


Next Steps and Wrapup (20 minutes)




