[9391] in www-talk@info.cern.ch
Re: two ideas...
daemon@ATHENA.MIT.EDU (touch@ISI.EDU)
Fri Dec 1 18:07:57 1995
From: touch@ISI.EDU
Date: Fri, 1 Dec 1995 14:50:20 -0800
To: ses@tipper.oit.unc.edu, mogul@pa.dec.com
Cc: touch@ISI.EDU, marc@ckm.ucsf.edu, www-talk@www0.cern.ch,
www-speed@tipper.oit.unc.edu
Resent-From: www-talk@w3.org
> From: Jeffrey Mogul <mogul@pa.dec.com>
>
> I grabbed a copy of the Touch and Farber paper cited earlier in
> this thread, which seemed to deal with FTP. This described a
> pre-send selection algorithm of sending everything in the currently
> selected directory. The Boston University system used a simple
> 1-level probablistic model to pick the best candidates for
> pre-send, and used fare less extra bandwidth, though with a higher
> probablity of a cache-miss. There's lots of stuff to tune with
> speculation.
>
> The model that Venkata Padmanabhan and I had been working on is
> a little different from the BU and Touch/Farber models (as far as
> I have been able to learn).
>
> We started from these principles:
I liked the idea of Jeff's summaries, so I put abbreviated versions of
my own on the Related works page of the LowLat pages:
http://www.isi.edu/lowlat/related-work.html
This is a summary of ALL latency reduction techniques, with pointers,
and some brief summaries. It is a work-in-progress; feedback would be
appreciated.
Thanks!
Joe
