Message-ID: <4382E9A2.5080102@openwide.fr>
Date: Tue, 22 Nov 2005 10:49:22 +0100
From: Guillaume Smet <guillaume.smet@openwide.fr>
User-Agent: Mozilla Thunderbird 1.0.7-1.1.fc3 (X11/20050929)
MIME-Version: 1.0
To: Andrew Sullivan <ajs@crankycanuck.ca>
CC: pgsql-performance@postgresql.org
Subject: Re: weird performances problem
References: <437CC21D.8070402@openwide.fr>
	<20051117221314.GC26696@phlogiston.dyndns.org>
	<437D13AA.4010309@openwide.fr>
	<20051118161312.GC28967@phlogiston.dyndns.org>
In-Reply-To: <20051118161312.GC28967@phlogiston.dyndns.org>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit

Andrew,

> I would be very suspicious of that much memory for sort.  Please see
> the docs for what that does.  That is the amount that _each sort_ can
> allocate before spilling to disk.
> If some set of your users are
> causing complicated queries with, say, four sorts apiece, then each
> user is potentially allocating 4x that much memory.  That's going to
> wreak havoc on your disk buffers (which are tricky to monitor on most
> systems, and impossible on some).

Yes, we have effectively complicated queries. That's why we put the 
sort_mem so high. I'll see if we can put it lower for the next few days 
to see if it improves our performances.

Thanks for your help.

--
Guillaume