Re: [PATCH] Use optimized single-datum tuplesort in ExecSort - Mailing list pgsql-hackers

From James Coleman
Subject Re: [PATCH] Use optimized single-datum tuplesort in ExecSort
Date
Msg-id CAAaqYe8=rw2_RYr6xrFq6u-f-S4OryCg1OPJfxi-_JPeSmtQVg@mail.gmail.com
Whole thread Raw
In response to Re: [PATCH] Use optimized single-datum tuplesort in ExecSort  (David Rowley <dgrowleyml@gmail.com>)
Responses Re: [PATCH] Use optimized single-datum tuplesort in ExecSort  (David Rowley <dgrowleyml@gmail.com>)
List pgsql-hackers
On Wed, Jul 14, 2021 at 9:22 PM David Rowley <dgrowleyml@gmail.com> wrote:
>
> On Thu, 15 Jul 2021 at 12:30, Ranier Vilela <ranier.vf@gmail.com> wrote:
> >
> > Em qua., 14 de jul. de 2021 às 21:21, David Rowley <dgrowleyml@gmail.com> escreveu:
> >> But, in v8 there is no additional branch, so no branch to mispredict.
> >> I don't really see how your explanation fits.
> >
> > In v8 the branch occurs at :
> > + if (ExecGetResultType(outerPlanState(sortstate))->natts == 1)
>
> You do know that branch is in a function that's only executed once
> during executor initialization, right?

This is why I have a hard time believing there's a "real" change here
and not the result of either noise or something not really
controllable like executable layout changing.

James



pgsql-hackers by date:

Previous
From: Ibrar Ahmed
Date:
Subject: Re: SQL:2011 PERIODS vs Postgres Ranges?
Next
From: gkokolatos@pm.me
Date:
Subject: Re: Introduce pg_receivewal gzip compression tests