On Aug 12, 2013, at 10:56 AM, Tim Ward <tdw@...> wrote:

> I believe the relevant part of the gstat output for the table in
> question to be as below, please let me know if I've got that wrong.
> (Names changed but otherwise unaltered.) My interpretation, which may be
> faulty, of
>
> Average version length: 0.00, total versions: 0, max versions: 0
>
> is that there are no versions of records lying around, so none of the
> explanations of the performance so far, all of which I think involve
> multiple versions in some way, is correct.

What does gstat show about the table before updates?

Best,

Ann