Re: [squid-users] fourth cache off??

On Thu, 20 Dec 2001, Vivek Sadananda Pai wrote:

> b) Is this approach scalable? The three entries with better hit times
> had throughputs roughly 4-20 times as high. So, if your system can
> only hold 4GB of memory, the RAM disk approach has less than a
> factor of 2 from its current numbers before one would expect some
> degradation.

Linear math may not apply here because of the skew in object access
pattern. When you double the request rate, you do not necessarily need
to double RAM cache to get the same utilization (hits/byte),
especially if the proxy is smart regarding what goes into the RAM
cache. Just a correction; I am not arguing that RAM caches are bad or
good.

Alex.

P.S. No standard disclaimers apply.
Received on Thu Dec 20 2001 - 09:21:42 MST