Re: XLog size reductions: Reduced XLog record header size for PG17

Поиск
Список
Период
Сортировка
От Andrey M. Borodin
Тема Re: XLog size reductions: Reduced XLog record header size for PG17
Дата
Msg-id C27A10AC-C97E-4786-8CDC-9754523D1C7D@yandex-team.ru
обсуждение исходный текст
Ответ на Re: XLog size reductions: Reduced XLog record header size for PG17  (Pavel Borisov <pashkin.elfe@gmail.com>)
Список pgsql-hackers

> On 3 Jan 2024, at 15:15, Pavel Borisov <pashkin.elfe@gmail.com> wrote:
>
> Hi and Happy New Year!
>
> I've looked through the patches and the change seems quite small and justified. But at the second round, some doubt
ariseson whether this long patchset indeed introduces enough performance gain? I may be wrong, but it saves only
severalbytes and the performance gain would be only in some specific artificial workload.  Did you do some
measurements?Do we have several percent performance-wise? 
>
> Kind regards,
> Pavel Borisov

Hi Matthias!

This is a kind reminder that the thread is waiting for your reply. Are you interesting in CF entry [0]?

Thanks!


Best regards, Andrey Borodin.
[0] https://commitfest.postgresql.org/47/4386/


В списке pgsql-hackers по дате отправления:

Предыдущее
От: "Andrey M. Borodin"
Дата:
Сообщение: Re: Change prefetch and read strategies to use range in pg_prewarm ... and raise a question about posix_fadvise WILLNEED
Следующее
От: Andres Freund
Дата:
Сообщение: Re: Improve heapgetpage() performance, overhead from serializable