Testing memcache vs db

[David B]

Curious if any of you have some metrics of using memcache with a
db…performance numbers before and after?
If not what would be a good way of testing?

I can imagine a simplistic loop that runs the same query a million
times but the db would cache it itself after the first select * from
customer where customerid = 1
And so the db will be faster on subsequent queries.

By the same token if I query where customerid = N and loop through n
from 1-1million I will not find hits in db or in cache.

As a quick test I wrote a program that queried where cust = 1 for
1million passes.
Memcache was 4times faster... I was expecting more like 50-100x...but
I suspect it was because of the db caching result (all running on same
box).

Thank you for any ideas or suggestions or pointers to existing results…