Re: [tcpm] Request for feedback on WG adoption of draft-balasubramanian-tcpm-hystartplusplus-03

[Mark Allman <[e-mail]>]

> this work has been presented multiple time in tcpm which a bunch
> of measurement numbers of real deployments. I really don't think
> this material should end up in the draft. The draft provides the
> specification of the mechanism (preferably as comprehensive and
> short as possible). The IETF proceedings provide the record for
> results and background information.

I have never actually heard quite that framing before.

I am not looking for a research paper here.  But, some sketch of why
this has been found to be reasonable, that the draft is just
documenting existing practice, etc. would seem required to me.

And, incorporating a comprehensive set of references for more and
deeper information is fine.  The substantive reference in this draft
is from over a decade ago (yes, "the" because there is only one).  I
am not the sharpest knife in the drawer, but I would never think to
go dig through the IETF proceedings to try to find such.  Not that
it might not be there, just that that would be a long slog without a
reference.

I also bristle somewhat at this notion that our job is just to give
the "what" and not the "why".  I know we are much better at the
former.  And, I know I have been guilty of too little of the latter
at times.  I know this because I have seen new folks read these RFCs
and not understand why something was done.  Or, that something is
important for some unstated, but crucial reason.  Or, decide that we
do X because of Y and so if Y is different then X can be, too---even
though we did X because of Z and just didn't say it well.

I am clearly not consensus, but to me the adoption question is
completely premature when the document doesn't offer motivation that
it is reasonable (beyond an intuitive hand wave that we're
preventing slow start overshoot).  Neal's note does sketch out why
this might be an OK thing to do.  And, probably IETF talks have, as
well.  But, some of that motivation has to make it into the
document, it seems to me.

allman