Re: [squid-users] price/performance

From: Vivek Pai <>
Date: Wed, 14 Nov 2001 15:57:15 -0500

> According to these test results, Squid does worse than almost every other
> caching product on the market, including Microsoft's. This is in terms of
> both raw performance and cost comparison (hardware/software). Am I reading
> the test results wrong? Why is Squid such a poor performer?

You're not reading the results wrong - it's a "poor" performer
in absolute terms, but is often sufficient for the low
end of the market, especially if you're recycling unused
hardware for it and have people with spare time to handle it.

However, you have to put these things in context. The original
Harvest cache had good in-memory performance and really bad
disk-bound performance. So, from that time, what you see at
Squid has come a long way. It's just that the competitors have
often gone further.

With proxies, most of the performance work has been done in
the closed-source commercial arena - most of the Harvest team
ended up at a caching company, for example. Then, some people
from that company formed another one.

Many of the academics who figure out how to develop proxies
with much better performance than squid also tend to end up
in the commercial world - at least three caching companies
have roots in this area.

Again, disclaimer: I work for a caching company

Received on Wed Nov 14 2001 - 13:57:33 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:04:12 MST