On 6/19/09, Andrew Dunstan <andrew@dunslane.net> wrote:
> Kevin Grittner wrote:
> > 8.3.7
> > real 0m24.249s
> > real 0m24.054s
> > real 0m24.361s
> > 8.4rc1
> > real 0m33.503s
> > real 0m34.198s
> > real 0m33.931s
>
> Ugh. This looks like a poster child case for a benchfarm ...
>
> Is there any chance you guys could triangulate this a bit? Good initial
> triangulation points might be the end of each commitfest. (I have a vested
> interest in making sure COPY performance doesn't regress, since it will
> affect parallel restore's speed in spades.)
git bisect?
--
marko