Re: One source of constant annoyance identified

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: Martijn van Oosterhout <kleptog(at)svana(dot)org>
Cc: Markus Wollny <Markus(dot)Wollny(at)computec(dot)de>, pgsql-general(at)postgresql(dot)org
Subject: Re: One source of constant annoyance identified
Date: 2002-07-03 15:43:56
Message-ID: 25151.1025711036@sss.pgh.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-general

Martijn van Oosterhout <kleptog(at)svana(dot)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

In response to

Browse pgsql-general by date

  From Date Subject
Next Message Bruce Momjian 2002-07-03 15:44:34 Re: Suppressing postgres messages?
Previous Message Robert Treat 2002-07-03 15:41:32 Re: README file for postgresql server upgrade