Dear Mark,

> Quite simple: with a field of VARCHAR(10000) on 8K pages it needs to read
> at least two pages if the VARCHAR is filled for over 80%, for smaller
> VARCHARs there is still a relatively high chance it will need to read 2
> pages. For page sizes of 16K this is less, but still relatively high
> (especially if the field is filled for a large percentage). If there are
> multiple record versions that need to be processed even more pages need to
> be read. Reading more pages => more IO => more time.

YEs this i understand, but what i don't understand is that in my select (select IDObj From DESCRIPTION where ID='ID_NOT_EXIST') the speed is the same ! :( here normally no data page must be read (because no row was found), only page used by the index must be read ?

I also try with blob, unfortunatly nothing change, just a little little (around 10%) more faster with blob :(

>
> BTW: Try to use BLOBs instead of VARCHAR(10000), it might reduces this
> problem
>
> Mark
>