Re: Improve heapgetpage() performance, overhead from serializable
| От | John Naylor |
|---|---|
| Тема | Re: Improve heapgetpage() performance, overhead from serializable |
| Дата | |
| Msg-id | CAFBsxsF+q7x6r+_Qoo48SqWZ8T2wSYRH48Qdrc+UsLvv6fbzkw@mail.gmail.com обсуждение исходный текст |
| Ответ на | Re: Improve heapgetpage() performance, overhead from serializable (Andres Freund <andres@anarazel.de>) |
| Ответы |
Re: Improve heapgetpage() performance, overhead from serializable
Re: Improve heapgetpage() performance, overhead from serializable |
| Список | pgsql-hackers |
On Mon, Jul 17, 2023 at 9:58 PM Andres Freund <andres@anarazel.de> wrote:
> FWIW, there's more we can do, with some hacky changes I got the time down to
> 273.261, but the tradeoffs start to be a bit more complicated. And 397->320ms
> for something as core as this, is imo worth considering on its own.
> 273.261, but the tradeoffs start to be a bit more complicated. And 397->320ms
> for something as core as this, is imo worth considering on its own.
Nice!
> On 2023-07-17 09:55:07 +0800, Zhang Mingli wrote:
> > Does it make sense to combine if else condition and put it to the incline function’s param?
> >
> > Like:
> > scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
> > block, lines, all_visible, check_serializable);
>
> I think that makes it less likely that the compiler actually generates a
> constant-folded version for each of the branches. Perhaps worth some
> experimentation.
Combining this way doesn't do so for me.
> >
> > Like:
> > scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
> > block, lines, all_visible, check_serializable);
>
> I think that makes it less likely that the compiler actually generates a
> constant-folded version for each of the branches. Perhaps worth some
> experimentation.
Combining this way doesn't do so for me.
Minor style nit:
+ scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
+ block, lines, 0, 1);
I believe we prefer true/false rather than numbers.
+ block, lines, 0, 1);
I believe we prefer true/false rather than numbers.
В списке pgsql-hackers по дате отправления: