Hi Ingemar,

Thank you very much for reviewing the draft and for your suggestions. Your
feedback is timely and very welcome.

Based on your comments, in the last revision of our document (-08) we have
added a new subsection (subsection 4.3.3) that discusses the Initial
Window setting in the context of CNNs.

Cheers,

Carles (on behalf of all authors)


> Hi
>
> I hope that I am not too late with the review.
>
> Perhaps this has been brought up earlier, and it that is the case then
> sorry
> for kicking in open doors.
>
>
>
> I have read but to not seen any mention of the initial congestion window
> size. Today the initial window in most TCP stacks is set to 10*MSS and
> this
> may well be used by Nb-IoT implementers that are unaware of default
> settings.
>
> While this is likely not an issue if he applications transmit small
> objects
> that fit in a few segments, it can become an issue with larger object
> transfers and if a burst of 14600 bytes overflows a tiny network buffer.
>
> Should this be addressed, possibly with a recommendation to adjust the
> initial window based on network constraints ?
>
>
>
> /Ingemar
>
> ==================================
>
> Ingemar Johansson  M.Sc.
>
> Master Researcher
>
>
>
> Ericsson Research
>
> Network Protocols & E2E Performance
>
> Labratoriegränd 11
>
> 971 28, Luleå, Sweden
>
> Phone +46-1071 43042
>
> SMS/MMS +46-73 078 3289
>
> [email protected]
>
> www.ericsson.com
>
>
>
>                 Nothing to stop this
>
>              being the best day ever
>
>                             U2
>
> ==================================
>
>
>
> _______________________________________________
> Lwip mailing list
> [email protected]
> https://www.ietf.org/mailman/listinfo/lwip
>


_______________________________________________
Lwip mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/lwip

Reply via email to