Re: [conex] Fwd: New Version Notification for draft-ietf-conex-tcp-modifications-02.txt

[Ingemar Johansson S <[e-mail]>]

Hi

Thanks for a great effort to get this in order.

Some comments, even though I haven't had the time to follow all the details in ConEx I still hope they can be of some value. 

I have not scrutinized the computation of CEG and LEG  in detail but I follow the discussion and it makes sense. Question, has anybody done any simulation experiments on this ?

Comments/questions:
Section 4.1, last sentence: First I did not understand it at all but I believe that I get it now.. Maybe not important but perhaps one can rewrite it like
The CEG and LEG counters SHOULD be reset if any of these conditions occur:
1) One RTT since they was last decreased
2) One RTT after (loss?) recovery if no further congestion
Not sure if this makes things more simple... 

Section 4.2:
This is IMHO the most complicated part. I fail to understand why it is sufficient with a number of credits which is half the number of packet in flight. Is this some kind of educated estimate ?. Probably I need to get this explained better but there is a chance that other need it too.
As regards to the statement that credit marks are only needed in slow start. Cubic's cubic function may make it necessary to add extra credit marks to avoid the flows being penalized in the audit functions or?

Section 4.3:
One complicating matter in e.g LTE is that the audit function needs to be in the eNodeB, at handover the audit state will be lost unless it is communicated to the other eNodeB via the X2 interface. Nothing that needs mention in this document but it is worth mention anyway.

Section 5:
"The sender MUST NOT delay the ConEx signal more than one RTT" : This has implications for instance for WebRTC as it puts a strict requirement to feedback the actual congestion information in a timely manner. As of today the discussion in WebRTC is around feedback of rate request information rather than congetsion information. Again, nothing that needs to be mentioned in this doc but should probably be considered if the congetsion control WG for WebRTC is formed.

/Ingemar


Nits:
Page 8: "No congestion feedback information are available" --> "No congestion feedback information is available"

Page 9: " Thus these packet.."  --> " Thus these packets.."
"These packet" --> "These packets"
"unset" --> "reset" ?

Page 11: "contributed with this.." --> "contributed with his" ? 


 

> -----Original Message-----
> From: Mirja Kühlewind [mailto:[e-mail]] 
> Sent: den 10 maj 2012 19:32
> To: Matt Mathis; Janardhan Iyengar
> Cc: [e-mail]
> Subject: [conex] Fwd: New Version Notification for 
> draft-ietf-conex-tcp-modifications-02.txt
> 
> Hi Matt, hi Jana,
> 
> I submitted a new version of the ConEx TCP Mod Draft. I 
> believe you volunteered to review the document.
> 
> There are currently two ToDos left. One is about a more 
> generic description how set the right number of credits 
> regarding the congestion control that is used. I think, Matt, 
> you had some idea here already. Maybe you can provide some 
> feedback here as well.
> The other one is the question if further action needs to be 
> take if ConEx markings got lost. I guess I will post this 
> question separately on the mailing list.
> 
> Thanks in advance,
> Mirja
> 
> 
> ----------  Forwarded Message  ----------
> 
> Subject: New Version Notification for
> draft-ietf-conex-tcp-modifications-02.txt
> Date: Thursday 10 May 2012, 19:26:08
> From: [e-mail]
> To: [e-mail]
> CC: [e-mail]
> 
> A new version of I-D, 
> draft-ietf-conex-tcp-modifications-02.txt has been 
> successfully submitted by Mirja Kuehlewind and posted to the 
> IETF repository.
> 
> Filename:	 draft-ietf-conex-tcp-modifications
> Revision:	 02
> Title:		 TCP modifications for Congestion Exposure
> Creation date:	 2012-05-10
> WG ID:		 conex
> Number of pages: 14
> 
> Abstract:
>    Congestion Exposure (ConEx) is a mechanism by which senders inform
>    the network about the congestion encountered by previous packets on
>    the same flow.  This document describes the necessary modifications
>    to use ConEx with the Transmission Control Protocol (TCP).
> 
>                                                               
>                     
> 
> 
> The IETF Secretariat
> 
> -------------------------------------------------------
> 
>