Re: [tcpm] TCP tuning

[Michael Welzl <[e-mail]>]

On Feb 3, 2010, at 7:41 PM, Joe Touch wrote:

>
>
> Michael Welzl wrote:
>>>> In other words, why not harness this knowledge somehow,
>>>> and develop a customized transport protocol, or ways of
>>>> customizing what we now have?
>>>
>>> That's been tried in various ways in various IETF efforts. Some  
>>> try to
>>> find the properties of the immediate link, which are expected for  
>>> some
>>> link types to dominate the path. Some try to detect path properties.
>>> Some reuse information from past connections.
>>
>> Really? I'd be curious about a few pointers, what exactly
>> do you have in mind? About reusing information etc., the
>> congestion manager and your TCB sharing stuff comes to
>> mind, but for the rest I'm curious
>
> Spencer Dawkins probably recalls better than I; I think there were
> numerous BOFs centered around "link indications", including:
> 	TRIGTRAN BOF
> 	"LinkUp"
> 	draft-dawkins-linkup-nevermind
> 	LCI BOF (Link Characteristic Information for Mobility)
> 	MPTCP WG
> 	LEDBAT WG
> 	RFC-4709

Thanks! I was aware about some (I liked trigtran and was sad to
see it fail) but definitely not all of these. At least LEDBAT doesn't
seem to fit in the list btw

Cheers,
Michael