Re: Features

From: Gregory Maxwell <>
Date: Mon, 24 Nov 1997 08:57:54 -0500 (EST)

On Mon, 24 Nov 1997, Umar Goldeli wrote:

> > There is a major problem here though when you are running a large cache and
> > have run into the maximum your hardware allows, which I would definately
> > believe is out there when you are referring to the Intel Architecture
> > (mainly ram).
> NOVM? :)
> > As for CPU hit, the only way I can see of truely avoiding this, is allowing
> > some use of a plug in compression card. The problems here of course are
> > that the few that are available most likely have very little support,
> > and/or example code, and would have to vary for platform to platform, if
> > some platforms have them at all!
> In regards to CPU problems -> a p166mmx on a lightly loaded cache
> (3000 requests/hour max), 25gb cache_swap, running NOVM eats only 1% CPU
> .. considering that a PPro200 or something along those lines can be bought
> for peanuts(1) and the average pro board will take 1Gb of RAM anyway... I
> don't see a problem with RAM or CPU..

Quite true..
> Have a flag in the cache_host directive for "compression support" on a
> particular host and everything is happy... perhaps more options for
> sending "compression_detect" requests etc for clients could be added
> too... (hey, the next version of navigator could even be squid-compression
> enabled too! *grin* => considering that most people use Squid as their
> proxy, this isn't as insane as it sounds... :)
> 1. compared to bandwidth pricing..

Yes.. The client should be able to suggest the compression mode and the
server should be able to decide.. I'm certian that if this get's
implimented then some W3 browser will support it..
Received on Mon Nov 24 1997 - 06:19:53 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:37:43 MST