[e2e] Number of persistent connections per HTTP server?

[David P. Reed]

At 08:58 PM 10/10/2002 -0700, Greg Minshall wrote:
> > Besides, how is the client to know what a short request is vs. a long
> > one? Sometimes even the server doesn't know (when the reply is sent in
> > chunks)...
>
>i remember that Van Jacoboson's observation on all this once upon a time was
>*something like* the server should be in charge of what bits of what URL get
>sent when since only the server really knows the details (such as, i suppose,
>sizes, etc.).

The server knows very little.   Most servers synthesize pages on the fly, 
and the tendency is to do more of that, not less.

The dismal record of operating systems at "optimizing paging behavior" by 
requiring the application to predict its sequence of references should be 
instructive.

Or if you want a commercial example: What's Akamai's stock 
price?   Somewhere around Symbolics', it appears.   Optimizing an 
infrastructure for a narrowly defined set of applications, and requiring 
that the application fit itself into a tiny Procrustean bed to "get 
optimized"  always seems to be a winner, until yet again we see it is a loser.