Re: [tcpm] New Version Notification for draft-you-tcpm-configuring-tcp-initial-window-00.txt

[Runa Barik <[e-mail]>]

Hi all,

On 2014-10-22 01:59, Joe Touch wrote:
> A few points on this thread:
>
> - 2140 includes both ensemble and temporal sharing
>       ensemble happens only when you have a concurrent
>       set of connections, at which point you subtract from
>       the window of the current ones to give to the new one
>
>       temporal includes going back to the same place - subnet
>       or specific IP - and can involve aging the window
>
> - we had a project here to look at whether the window could be
> predicted
> based on past behavior (e.g., time-based patterns, either time-of-day,
> day-of-week, etc.):
>       http://www.isi.edu/aln/
> The conclusion was that such patterns were not evident (at least when
> we
> did the experiment).
>

I agree with this points.

> - IW cannot be determined at the time of the connection per se
> The only way to do so would be to send IW segments into the net and
> see
> if they get there, which isn't so much a probe as just using that
> value
> as the initial window anyway.
>
> I continue to believe that IW can be adapted over loooong periods of
> time using information on past connections as network behavior evolves
> as per draft-touch-tcpm-automatic-iw-03.txt, but more experience is
> definitely needed.
>

In the draft ``draft-touch-tcpm-automatic-iw-03.txt", All the
connections at
a particular instance start with nearly same IW value --- a single
constant window for all flows.
My point is, why not to take a look on flow characteristics. I played
with a lot of simulations and experiments.
In my simulations in ns2, I considered a combination of flow types
based on sizes --- large flows from Pareto Distribution, and small flows
from Exponential Distribution. And we observed, large flows having a
small IW, and even randomly choosing a large IW for small flows gives
better performance than all the flows with IW10; and we considered my
network conditions --- multiple bottlenecks, underload, overload,
varying base RTT, Large delay path, and etc. I also tested with CAIDA
dataset in my experiments in a testbed network. A constant IW may not be
suitable.
Somewhere it is IW10 (currently set inside the Linux kernel), IW7
(checked by Youjianjie).
> Joe

- Runa Barik