Re: Cacheflow vs. Squid

Test driving one at the moment, having got it working right yet. Funny
thing, connected a monitor and keyboard to it and saw it probe
for fxp0 and fxp1 during bootup and the messages looked *incredibly*
familiar :-). Had an adaptec SCSI controller in it (and of course intel
NICS :-) ).

-

Barrett Richardson rabtter@orion.aye.net

On Tue, 28 Jul 1998, Dancer wrote:

> Fraser Campbell wrote:
> >
> > Someone has contacted me regarding a product called Cacheflow. He/they
> > claim their product is vastly superior to Squid. I'd like to know if
> > anyone here has any experience or comments with the product
> > (http://www.cacheflow.com/).
> >
> > The product apparently uses "active caching". This is it "by keeping
> > track of both user requests and content changes and by sending refresh
> > requests based on algorithms that calculate the probability that a refresh
> > will be needed. CacheFlow says this technique can boost hit rate to as
> > high as 75%, compared with 30% to 40% in most cache systems."
> >
> > I would say that this prefetching of a page (while it may slightly
> > increase response time) is going to use just as much bandwidth (possibly
> > more). What does everyone think? Has anyone here used Cachflow? Sorry,
> > if this is slightly off topic but I believe comparing alternative caching
> > systems to be relevant.
>
> Sounds like they're trading off bandwidth and spending it on speed.
>
> D
>
>
> --
> -----BEGIN GEEK CODE BLOCK-----
> Version: 3.1
> GAT d- s++: a C++++$ UL++++B+++S+++C++H++U++V+++$ P+++$ L+++ E-
> W+++(--)$ N++ w++$>--- t+ 5++ X+() R+ tv b++++ DI+++ e- h-@
> ------END GEEK CODE BLOCK------
>
>
Received on Tue Jul 28 1998 - 17:37:06 MDT