On Mon, 14 Nov 2011, Andrew Daviel wrote:

>> This is not true. The RTT is not really a factor for a single uni-direction
>> stream in modern TCP since they introduced the ability to set large windows
>> (>16 bit size), many years ago. If you believe otherwise, then please
>> provide details.
>
> I recall that the concept of "jumbo frames" was introduced, which I presume
> is the same thing. I believe that that requires the large frames to be
> supported end-to-end across all links, something that is not guaranteed on
> the regular internet.

No, that is completely bogus and false. Jumbo frames are for Ethernet and you
probably need to read up on this: http://en.wikipedia.org/wiki/Jumbo_frame

> I haven't looked at the numbers, but I presume that as data size and
> bandwidth increase the current large windows will become less effective. I
> recall some kind of practical limit, but that may have been for a current
> generation of backbone router.

I don't understand what you base this talk on and I don't see how it matters
here.

> I haven't worked the numbers or tested that for real, only the principle.

...

> I guess I was thinking about adding it to the curl tool. I'm just floating
> balloons, really, so not too bothered if they get legitimately shot down.

I think you need to get back and study the actual network protocol details and
bottle necks first, then try to think about what can and should be done about
them.

But again: there are reasons and times when multiple parallel transfers of the
same URL makes sense. And it could be fun to have curl support that. If you
want to work on that, please take that topic over and continue this discussion
on the curl-users list.

-- 
  / daniel.haxx.se
-------------------------------------------------------------------
List admin: http://cool.haxx.se/list/listinfo/curl-library
Etiquette:  http://curl.haxx.se/mail/etiquette.html