Re: Q: Hit Rate calculation

From: Ross Wheeler <>
Date: Tue, 1 Jul 1997 21:08:24 +1000 (EST)

> I have a question about the calculation of the hit rate of a cache. Using
> different tools (i.e. Cache Manager, Squidstats, Squidtimes, spa,
> manual log analysis, etc.) I obtain wildly varying values for the hit
> rate of our cache. Which of these should be considered 'correct'? What I
> would like to know is what percentage of requests (TCP) to my proxy is
> actually being served from the cache. How do other people caculate this?

I asked a very similar question some time back, and it appears many
people worldwide are more interested in the ratio of requests made to
files furnished out of cache. I questioned that 50% of total hits was a
meaningless term if that 50% happened to be small files of say 1K in
size, while the 50% misses were images of 50Kb!

Some of us pay per megabyte, and are interested therefore in BYTES SAVED,
and I use seperate software to monitor that from another host. I watch
three items: traffic TO the proxy, traffic FROM the proxy and trafic
BYPASSING the proxy. These together tell me interesting and useful stats.

I would argue that since Squid is designed to reduce *traffic*,
everything should be a radio of bytes saved, not hits... but that's just
my viewpoint :-)

Regards, RossW
Received on Tue Jul 01 1997 - 04:14:55 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:35:39 MST