Re: data on devel code perf dip

On Sun, 2005-08-21 at 20:37 -0400, Tom Lane wrote:
> The whole thing's pretty bizarre.

I hate to sound obvious, but does the missing performance return if you
back the patch out?  It seemed to have been decided on Tue, 16 Aug 2005
15:45:30 -0700 that the performance was the same before and after.
However, there also seems to be version confusion, as maryedie@osdl.org
also claimed to be testing a tree from the future.

Basically I think there's more confusion here than evidence.  On an
admittedly smaller x86 configuration, source trees with this patch are
faster than without, not slower.

And finally, not to start a flamewar, but the initial report was on a
machine running gentoo, the distribution that should be renamed
Irreproduceable Benchmarks Linux.

-jwb