Re: Squid 1.2 Release Date & Effectiveness of Proxies

Tim Brody wrote:
>
> ( ) -- ( )
> ( ) / o \ ( )
> ( )__ \ / ( )__
> (____) --- (____)
>
> More seriously, I need some ammunition. I want to install a proxy at my
> local ISP (I'm sure the enthusiasm should be the other way round), but they
> think it's a waste of time..."it's just another machine for the request to
> go through".
>
> Can anybody give me some _general_ information on the benefits of Proxies,
> like do Proxies (squid1.2) slow down requests, how effective is a proxy on a
> low bandwidth connection, i.e. ISDN? Do proxies pose any security risk,
> assuming that ACLs block external access to the proxy. Most information on
> proxies seem to cover T1/T3 type load ... I'm not really in that ball-park!
>

Yes, it works _well_ over ISDN connections. Impressively so, except (of
course) that ICP tends to get lost when things get busy...so you can't
really use ICP between multiple parents. Squid loses sight of them when
things busy up.

I've got a bunch of clients now all using squid over ISDN. Think: '40%
more delivered data to customers for the same cost as before.' The
percentage varies on setup, but any piece of software that will do that
for you is a win, IMO.

Also, two shorter data-paths (or three, even) between two widely
separated points are less likely to break from congestion than a single
link between the endpoints, and much liklier to show higher data rates:
The effects of RTT on end-to-end bandwidth. Even if there's a little
postage-and-handling at each proxy in the chain, or slightly increased
times in starting the fetch of an object, the delivery time tends to be
much improved and the delivery itself tends to be more reliable.

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------