Re: Planner chooses multi-column index in 9.2 when maybe it should not

On Wed, Oct 10, 2012 at 09:24:32PM -0400, Tom Lane wrote:
> I'd not been thinking of that change as something we'd risk
> back-patching, but maybe we should consider putting it into 9.2. It
> seems like the index-only scan support has put a new level of premium on
> the quality of the planner's rowcount estimates.

Yes, please do! It's that or we globally disable index-only scans,
which I'd prefer not to do. Let me know if you'd like me to test
a patch, I can apply it and see if it fixes our issue at hand.

> Meanwhile, that range condition in itself looks a tad, er, klugy.
> Do you really need that, or is this a crummy way of stating
> foobar.id = m.id?

No, it's really needed. That's merely the tip of the kluginess;
don't get me started! The dangers of an organically grown schema. :)
This thing has been growing since Postgres v6.

(Looking back at how far Postgres has come from 6.x to 9.2
is truly awe-inspiring)

--
Greg Sabino Mullane greg(at)endpoint(dot)com
End Point Corporation
PGP Key: 0x14964AC8