On 2016-02-11 12:50:58 -0500, Robert Haas wrote:
> On Thu, Feb 11, 2016 at 12:48 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
> > Robert Haas <robertmhaas@gmail.com> writes:
> >> I think we should either get this fixed RSN or revert the problematic
> >> commit until we get it fixed. I'd be rather disappointed about the
> >> latter because I think this was a very good thing on the merits, but
> >> probably not good enough to justify taking the performance hit over
> >> the long term.
> >
> > Since it's only in HEAD, I'm not seeing the urgency of reverting it.
> > However, it'd be a good idea to put this on the 9.6 open items list
> > (have we got such a page yet?) to make sure it gets addressed before
> > beta.
>
> One problem is that it makes for misleading results if you try to
> benchmark 9.5 against 9.6.
You need a really beefy box to show the problem. On a large/new 2 socket
machine the performance regression in in the 1-3% range for a pgbench of
SELECT 1. So it's not like it's immediately showing up for everyone.
Putting it on the open items list sounds good to me.
Regards,
Andres