On Mon, Nov 9, 2020 at 3:49 PM Tom Lane <tgl@sss.pgh.pa.us> wrote:
> Alvaro Herrera <alvherre@alvh.no-ip.org> writes:
> > Are you taking into account the possibility that generated machine code
> > is a small percent slower out of mere bad luck? I remember someone
> > suggesting that they can make code 2% faster or so by inserting random
> > no-op instructions in the binary, or something like that. So if the
> > difference between v8 and v9 is that small, then it might be due to this
> > kind of effect.
>
> Yeah. I believe what this arises from is good or bad luck about relevant
> tight loops falling within or across cache lines, and that sort of thing.
> We've definitely seen performance changes up to a couple percent with
> no apparent change to the relevant code.
That was Andrew Gierth. And it was 5% IIRC.
In theory it should be possible to control for this using a tool like
stabilizer:
https://github.com/ccurtsinger/stabilizer
I am not aware of anybody having actually used the tool with Postgres,
though. It looks rather inconvenient.
--
Peter Geoghegan