Re: Seqscan rather than Index

On Fri, Dec 17, 2004 at 22:56:27 +0100,
  "Steinar H. Gunderson" <sgunderson@bigfoot.com> wrote:
>
> I'm a bit unsure -- should counting ~3 million rows (no OIDs, PG 7.4,
> everything in cache, 32-byte rows) take ~3500ms on an Athlon 64 2800+?

It doesn't seem totally out of wack. You will be limited by the memory
bandwidth and it looks like you get something on the order of a few
hundred references to memory per row. That may be a little high, but
it doesn't seem ridiculously high.