On Mon, 2003-11-03 at 10:01, Tom Lane wrote:
> Neil Conway <neilc(at)samurai(dot)com> writes:
> > POSIX_FADV_RANDOM doesn't effect the page cache, it just determines how
> > aggressive the kernel is when doing readahead (at least on Linux, but
> > I'd expect to see other kernels implement similar behavior).
> 
> I would expect POSIX_FADV_SEQUENTIAL to reduce the chance that a page
> will be kept in buffer cache after it's been used.

I don't think that can be reasonably implied from the POSIX text, which
is merely:

POSIX_FADV_SEQUENTIAL
        Specifies that the application expects to access the specified
        data sequentially from lower offsets to higher offsets.

The present Linux implementation doesn't do this, AFAICS -- all it does
it increase the readahead for this file:

	http://lxr.linux.no/source/mm/fadvise.c?v=2.6.0-test7

-Neil

In response to

• Re: adding support for posix_fadvise() at 2003-11-03 15:01:55 from Tom Lane

Responses

• Re: adding support for posix_fadvise() at 2003-11-03 16:11:36 from Tom Lane
• Re: adding support for posix_fadvise() at 2003-11-03 19:24:59 from Manfred Spraul

pgsql-hackers by date

Next:	From: Tom Lane	Date: 2003-11-03 15:47:04
	Subject: Re: Experimental patch for inter-page delay in VACUUM
Previous:	From: Jan Wieck	Date: 2003-11-03 15:33:21
	Subject: Experimental ARC implementation