It seems I overlooked this answer, sorry - some answers below, but also cutting stuff to keep it to the point:
Despite the undebatable importance of bufferbloat and its impact on e2e packet latency, this is only one of the factors playing into the "latency" that I perceive when I click on the link as I surf the Internet.
Doing a breakdown of that latency - most of that seems solved...Background prefetchDNS lookupSSL connection negotiationThe actual transfer.Screen draw....I'm still missing your point. Is looking for "sparseness" part of aCCN-like effort?
No, it’s just about flow completion time (“The actual transfer”) above being a function not only of the queue length, but also of the capacity the flow gets to use. Hence the push for a larger initial window.
Flow completion time has to do with saturation as well.
FCT was not a subject of that draft.
Right - sorry for side-tracking.
My (admittedly ranty) points were:
I read them - I didn’t want to get into this debate, it was only a side comment about not all flows being limited, and there being some value in better capacity usage too.
Cheers,