To: Mike Rylander <mrylander@gmail.com>
Cc: Mark Rinaudo <mark@bowmansystems.com>,
	pgsql-performance@postgresql.org
Subject: Re: Postgresql on an AMD64 machine 
In-reply-to: <b918cf3d05060613593a73a18a@mail.gmail.com> 
References: <1118080420.1644.23.camel@penguin1>
	<b918cf3d05060613593a73a18a@mail.gmail.com>
Comments: In-reply-to Mike Rylander <mrylander@gmail.com>
	message dated "Mon, 06 Jun 2005 16:59:21 -0400"
Date: Mon, 06 Jun 2005 17:15:21 -0400
Message-ID: <22887.1118092521@sss.pgh.pa.us>
From: Tom Lane <tgl@sss.pgh.pa.us>

Mike Rylander <mrylander@gmail.com> writes:
> On 06 Jun 2005 12:53:40 -0500, Mark Rinaudo <mark@bowmansystems.com> wrote:
>> I'm not sure if this is the appropriate list to post this question to
>> but i'm starting with this one because it is related to the performance
>> of Postgresql server.  I have a Penguin Computing dual AMD 64 bit
>> opteron machine with 8 Gigs of memory.  In my attempt to increase the
>> number of shared_buffers from the default to 65000 i was running into a
>> semget error when trying to start Postgresql.

> Did you perhaps disable spinlocks when compiling PG?

That sure looks like it must be the issue --- in a normal build the
number of semaphores needed does not vary with shared_buffers, but
it will if Postgres is falling back to semaphore-based spinlocks.
Which is a really bad idea from a performance standpoint, so you
want to fix the build.

Which PG version is this exactly, and what configure options did
you use?  What compiler was used?

			regards, tom lane