From: Josh Berkus <josh@agliodbs.com>
Organization: Aglio Database Solutions
To: pgsql-performance@postgresql.org
Subject: Re: Benchmarking Function
Date: Sun, 21 May 2006 12:23:49 -0700
User-Agent: KMail/1.8.2
Cc: David Wheeler <david@kineticode.com>
References: <1D5FC47D-8D90-4856-8EB7-833476A37587@kineticode.com>
In-Reply-To: <1D5FC47D-8D90-4856-8EB7-833476A37587@kineticode.com>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Message-Id: <200605211223.49499.josh@agliodbs.com>

DW,

> The idea of the control is, of course, to subtract the overhead of =A0
> the benchmarking function from the code actually being tested. So I =A0
> guess my question is, how important is it to have the control there, =A0
> and, if it is important, how should it actually work?

Well, per our conversation the approach doesn't really work.   EXECUTE=20
'string' + generate_series seems to carry a substantial and somewhat random=
=20
overhead, between 100ms and 200ms -- enough to wipe out any differences=20
between queries.

=2D-=20
Josh Berkus
Aglio Database Solutions
San Francisco