Squid performance on the bake-off

From: Durval Menezes <durval@dont-contact.us>
Date: Sun, 11 Apr 1999 22:45:24 -0300 (EST)


I've just read the 1st Bake-off report, and I must confess I'm somewhat
surprised that Squid scored so low, less than 25% the rate of the second
worst competitor, the Novell/Dell-S combo.

Comparing the hardware used, specially between Squid and Peregrine
(which scored a wooping 545% better than Squid, and with much more
gracious degradation to boot), I see that they are on the same order
of magnitude for everything but RAM (35% more CPU and disks 38% faster,
compared to 100% more RAM on the Peregrine hardware).

Ok, there's the Unix FS handicap to account for, but we are talking
about _more_than_six_times_ the performance, and in any case the tradition
says that a well-tuned FFS (as is the case with FreeBSD) approaches 50%
of the hardware maximum transfer rate.

Based on my experience with Squid, neither that CPU nor the disks can
explain a 545% diference, but just maybe (depending on the total size
and distribution of the cacheable data), perhaps 100% more RAM can
explain at least a part of it. And the cost for twice (or even four
times more) the RAM would be negligible, specially if compared to other
alternatives (more/faster disks, etc). I'm ignorant enough about the
Polygraph benchmark to be unable to elaborate further.

Will anyone more knowledgeable care to comment?

Best Regards,

   Durval Menezes (durval@tmp.com.br, http://www.amcham.com.br/~durval)
Received on Sun Apr 11 1999 - 19:34:50 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:45:47 MST