Re: computational model of transactions

Anne & Lynn Wheeler wrote:
> ...
> for a little drift ... recent post about performance management
> http://www.garlic.com/~lynn/2006o.html#23 Strobe equivalents
> ...

(quote from above, I think):

Remembering the science center experience from the early 70s (nearly 35 years earlier), i wondered if multiple regression analysis could identify opportunities; in fact it turned up something accounting for over 20% of total usage. The issue has been that things like instruction sampling and event modeling tend to turn up things at the micro level ... while multiple regression analysis frequently can highlight more macro level issues. The identified feature was a complex, spaghetti combination of low-level stuff ... which turned out could be optimized (at the macro level) and resulted in 14% total system savings.

(end quote).

I can believe it. At one time, I used to require app writers, as well as system programmers, to count IO's. Later, I advanced to making them count server messages and logical rows using some casual 'r-o-t' about 1000 logical rows costing the same as 100 IO's, blah blah. Still it was amazing how many times the developer said, "wow, that many? that's not in the requirement!" and the change got re-thought.

p Received on Tue Aug 01 2006 - 22:06:24 CEST