At 11:08 AM 11/14/2000 -0500, Dalton Calford wrote:

>I have a question (please don't shoot me for asking)
>
>Why don't we think about a larger page size?
>16k, 32k, 64k (these are all natural page read/write sizes on hardware
>RAID devices and some software RAID systems - the larger block sizes are
>also supported by various file systems)
>
>This would allow for larger key sizes per page and perhaps in certain
>instances, increase performance as the interbase page size would more
>closely fit the underlying structures.
>
>What would be involved in this?

Not much. My concern is that testing showed a performance
improvement going to 4K from 1 or 2, but almost none going
from 4 to 8. We may need to improve the efficiency of some
page search algorithms.

How many of you consider that your applications are I/O bound?

Regards,

Ann