Re: [Spud] Additional SPUD use-cases

David & I  approved the talk as a presentation of current research.

My own hopes are that this talk focusses on:

- the existing experiments and running code, showing how this handles
congestion-control.
- Actual gains of a L2-enhanced approach, such as this, compared to a
mechanism such as ECN.
- How to handle speed-increases, previous attempts at explicit signals for
speed increases at the IETF have all failed to progress. I am dubious that
this signal is useful for a shared capacity bearer.
- Explain the security requirements and model (which I do not understand).
- Help understand if this useful outside of a single-bottleneck radio
network.

To avoid any confusion: This is an individual submission expected to start
a discussion, this draft will not be considered as a candidate for
adoption at this meeting.

Gorry

> On Mon, Mar 16, 2015 at 5:02 PM, Black, David <david.black@emc.com> wrote:
>
>>  Here are four potentially related drafts:
>>
>>
>>
>> -- Rate Adaptation based on network feedback, and (to some extent) FCFS
>> (weak) admission control:
>>
>>
>>
>> This work is TCP based, but with similar goals:
>>
>>
>>
>>
>> https://datatracker.ietf.org/doc/draft-sprecher-mobile-tg-exposure-req-arch/
>>
>> https://datatracker.ietf.org/doc/draft-flinck-mobile-throughput-guidance/
>>
>>
>>
>> The latter draft is (IMHO) better viewed as a proof-of-concept
>> demonstration that this can work, as opposed to a specific protocol
>> design
>> for how to do it.  Design concerns have been raised about what was done
>> there (e.g., aggressive use of TCP options).
>>
>
> Hi David-
>
> Are the congestion control concerns being discussed within a working
> group?
>
> --aaron
> _______________________________________________
> Spud mailing list
> Spud@ietf.org
> https://www.ietf.org/mailman/listinfo/spud
>