Date: Thu, 14 Dec 2006 10:26:27 -0500
From: Michael Stone <mstone+postgres@mathom.us>
Subject: Re: New to PostgreSQL, performance considerations
In-reply-to: <E1GuYSE-000378-Sk@elasmtp-spurfowl.atl.sa.earthlink.net>
To: Postgresql Performance list <pgsql-performance@postgresql.org>
Mail-followup-to: Postgresql Performance list
	<pgsql-performance@postgresql.org>
Message-id: <20061214152623.GD29167@mathom.us>
MIME-version: 1.0
Content-type: text/plain; charset=us-ascii; format=flowed
Content-disposition: inline
References: <C1A31C39.15548%llonergan@greenplum.com>
	<457EA39E.1020207@streppone.it> <20061212124803.GA29167@mathom.us>
	<4580264F.8030109@streppone.it>
	<E1GuYSE-000378-Sk@elasmtp-spurfowl.atl.sa.earthlink.net>
User-Agent: Mutt/1.5.13 (2006-08-11)

On Wed, Dec 13, 2006 at 01:03:04PM -0500, Ron wrote:
>What I find interesting is that so far Guido's C2D Mac laptop has 
>gotten the highest values by far in this set of experiments, and no 
>one else is even close.
>The slowest results, Michael's, are on the system with what appears 
>to be the slowest CPU of the bunch; and the ranking of the rest of 
>the results seem to similarly depend on relative CPU 
>performance.  This is not what one would naively expect when benching 
>a IO intensive app like a DBMS.

Note that I ran with fsync off, that the data set is <300M, and that all 
of the systems (IIRC) have at least 1G RAM. This is exactly the 
distribution I would expect since we're configuring the benchmark to 
determine whether cpu-specific optimizations affect the results.

Mike Stone