On 12 May 2003 at 13:51, fabiano_bonin wrote:

> Let's supose i have a table with a pk and two more fields, field1
> and field2, where field1 has almost always the same value for all
> records and field2 has more variations.
>
> Is there some performance difference if i create an index using
> (field2, field1) against (field1, field2), supposing i will make a
> query using these two fields in the criteria?

It the order of keys doesn't make difference when your filter condition
contains expressions on all fields in key. It make difference when you DO
NOT use all fields in where condition.

Best regards
Pavel Cisar

See you at the First European Firebird Conference in May in Fulda,
Germany
http://www.firebird-conference.com

http://www.ibphoenix.com
For all your upto date Firebird and
InterBase information