Re: [tcpm] informal poll about initial cwnd

["SCHARF, Michael" <[e-mail]>]

I would allow (A) because of its simplicity, but the same I-D should
also mandate implementors to carefully monitor the impact and strongly
recommend to revert to IW3 if any harm is observed. As one potential
(recommended?) solution for this, it could propose a procedure somehow
along the lines of (C).

IMHO implementors MUST really carefully monitor the impact of an
increased IW, in particular for large-scale deployments. This can be
done by a procedure similar to draft-touch-tcpm-automatic-iw-00, but
probably also by other control loops, e. g., by regularly monitoring
transaction times at application level. The IETF should describe one
application-agnostic way of monitoring the impact of a larger IW, but
also allow implementors to come up with other solutions.

Michael


> -----Original Message-----
> From: [e-mail] [mailto:[e-mail]] On 
> Behalf Of Mark Allman
> Sent: Thursday, January 06, 2011 7:20 PM
> To: [e-mail]
> Subject: [tcpm] informal poll about initial cwnd
> 
> 
> Given that there are three proposals put down in I-D form in 
> some matter of baked-ness I am wondering if there is any sort 
> of clear WG preference on the *approach* to changing the 
> initial window.  So, putting aside the particulars for a 
> moment and just thinking about the approach I'd like to take 
> a quick, informal, absolutely non-binding in any way 
> (obviously) poll to take the WG's pulse.
> 
> So, do you prefer ...
> 
> (A) To increase the current static IW definition to a single updated
>     value.
> 
>     (Current proposal: draft-ietf-tcpm-initcwnd-00.txt, but I am
>     explicitly not asking about IW=10, just IW=some_X.)
> 
> (B) To increase the current static IW definition with a schedule of IW
>     updates to play out over some period of time.
> 
>     (Current proposal: 
> draft-allman-tcpm-bump-initcwnd-00.txt, but I am
>     explicitly not asking if you like the given schedule.)
> 
> (C) To define a procedure for hosts to figure out how to 
> adapt their IW
>     over time.
> 
>     (Current proposal: draft-touch-tcpm-automatic-iw-00.txt, but I am
>     explicitly not asking if you buy the particulars of this, just the
>     overall approach.)
> 
> (D) The current IW seems OK and I haven't seen a good reason 
> to think it
>     needs changed.
> 
> Thanks!
> 
> allman
> 
> 
> 
>