Re: HTCP versus ICP

George Michaelson wrote:
>
>
> Regardless of HTCP status, _if_ most of us consider small false hit ratio
> acceptable, Cache Digests is the way to go. They do not introduce any
> query/response delays and, thus, scale well with the number of peers. The
> price is more RAM, but with less than a 1MB digest per 16GB peer and cheap
> memory, it's not a big deal.
>
>
> Can you make a first-order guess at the size of the false-hit levels? small
> is very relative to the eye of the beholder.
>
> The LBL proposals for cache-mesh with multicast backend sharing still look the
> most innovative work in this area. They are due to report on ns simulations
> soon I believe..

From my experience, the curve is a touch non-linear. One of my clients
(~10000 requests/day) shows less than 0.05% false hits with ICP.

Another, (with approximately ~1000000/day) shows around 0.7%.

Larger caches, you might get up to around %5 or so. It depends largely
on what resources the users access as well.

D

>
> -George
> --
> George Michaelson | DSTC Pty Ltd
> Email: ggm@dstc.edu.au | University of Qld 4072
> Phone: +61 7 3365 4310 | Australia
> Fax: +61 7 3365 4311 | http://www.dstc.edu.au

-- 
-----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------