Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance

Поиск
Список
Период
Сортировка
От Kevin Grittner
Тема Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance
Дата
Msg-id 4CADBB410200002500036644@gw.wicourts.gov
обсуждение исходный текст
Ответ на Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance  (Robert Haas <robertmhaas@gmail.com>)
Ответы Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance  (Stephen Frost <sfrost@snowman.net>)
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance  (Robert Haas <robertmhaas@gmail.com>)
Список pgsql-performance
Robert Haas <robertmhaas@gmail.com> wrote:

> perhaps it would be possible by, say, increasing the number of
> lock partitions by 8x.  It would be nice to segregate these issues
> though, because using pread/pwrite is probably a lot less work
> than rewriting our lock manager.

You mean easier than changing this 4 to a 7?:

#define LOG2_NUM_LOCK_PARTITIONS  4

Or am I missing something?

-Kevin

В списке pgsql-performance по дате отправления:

Предыдущее
От: Merlin Moncure
Дата:
Сообщение: Re: Runtime dependency from size of a bytea field
Следующее
От: Aaron Turner
Дата:
Сообщение: large dataset with write vs read clients