prairiedechien wrote:

> The execution plan informs that the index is not used (Ok, not really
> an issue in this case). But the response time is always different and
> deos not seem to follow any rule (I expected it will decrease and
> take advantage of cached data).

There was a really good talk about this by Ivan Prenosil at the Firebird
Conference. He also gave few alternatives that can give really quick
record counts.

Perhaps you should take a look at his paper when it gets published.

--
Milan Babuskov
http://njam.sourceforge.net
http://www.flamerobin.org