> > Indeed I did forget such unbalanced indices could be useful. In this
> > case, the index is reasonably balanced. There is one value that is
> > contained by about 40%, the other 60% is roughly even split.
>
> Is the index useful? I mean: is it really faster to follow an index

and

> look up 40% (or 60%) of the records than just scanning the whole table?

That was probably a bit confusing, there are more than two values, in
this particular customer there are only 7, (but that is unusually
low). The value 1 is contained in about 60% of the table, 2 through 7
are around 6% - 7% each.

Adam