Re: One source of constant annoyance identified

Поиск
Список
Период
Сортировка
От Tom Lane
Тема Re: One source of constant annoyance identified
Дата
Msg-id 25151.1025711036@sss.pgh.pa.us
обсуждение исходный текст
Ответ на Re: One source of constant annoyance identified  (Martijn van Oosterhout <kleptog@svana.org>)
Список pgsql-general
Martijn van Oosterhout <kleptog@svana.org> writes:
> My theory is that it's not using RAM at all, it's simply mapping the shared
> memory in, which inflates the RSS.

Interesting idea.  By rights the whole shared memory segment should be
charged against a backend's SIZE all the time, since it's certainly all
there in the address space.  But if for some reason a page of shmem
isn't charged until first touched, then indeed that could explain Markus'
observation --- and, perhaps, my inability to duplicate it on other
platforms.  (I tried on Red Hat 7.2, which you'd think would be fairly
close to his SuSE release, but maybe it's different on just this point.
HPUX seems to completely ignore shared segments in both SIZE and RSS,
but it's way out in left field on a number of fronts...)

            regards, tom lane



В списке pgsql-general по дате отправления:

Предыдущее
От: Robert Treat
Дата:
Сообщение: Re: README file for postgresql server upgrade
Следующее
От: Bruce Momjian
Дата:
Сообщение: Re: Suppressing postgres messages?