X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org
Received: from localhost (unknown [200.46.204.144])
	by svr1.postgresql.org (Postfix) with ESMTP id 7EF5B52988
	for <pgsql-performance-postgresql.org@localhost.postgresql.org>;
	Tue, 19 Jul 2005 15:10:09 -0300 (ADT)
Received: from svr1.postgresql.org ([200.46.204.71])
	by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024)
	with ESMTP id 42519-04
	for <pgsql-performance-postgresql.org@localhost.postgresql.org>;
	Tue, 19 Jul 2005 18:10:08 +0000 (GMT)
Received: from sss.pgh.pa.us (sss.pgh.pa.us [66.207.139.130])
	by svr1.postgresql.org (Postfix) with ESMTP id ED5565298F
	for <pgsql-performance@postgresql.org>;
	Tue, 19 Jul 2005 15:10:04 -0300 (ADT)
Received: from sss2.sss.pgh.pa.us (tgl@localhost [127.0.0.1])
	by sss.pgh.pa.us (8.13.1/8.13.1) with ESMTP id j6JI9ueC007844;
	Tue, 19 Jul 2005 14:09:56 -0400 (EDT)
To: Christopher Petrilli <petrilli@gmail.com>
Cc: PFC <lists@boutiquenumerique.com>, Vivek Khera <vivek@khera.org>,
	pgsql-performance@postgresql.org
Subject: Re: Impact of checkpoint_segments under continual load conditions 
In-reply-to: <59d991c405071910133e28031a@mail.gmail.com> 
References: <59d991c4050717100874c08a86@mail.gmail.com>
	<16794.1121718743@sss.pgh.pa.us>
	<59d991c405071907482bb0689b@mail.gmail.com>
	<op.st52tvunth1vuj@localhost>
	<59d991c4050719084460b376f1@mail.gmail.com>
	<4541.1121788647@sss.pgh.pa.us>
	<59d991c40507190930244ba9bb@mail.gmail.com>
	<7224.1121791328@sss.pgh.pa.us>
	<59d991c4050719095440cd3de5@mail.gmail.com>
	<7436.1121792725@sss.pgh.pa.us>
	<59d991c405071910133e28031a@mail.gmail.com>
Comments: In-reply-to Christopher Petrilli <petrilli@gmail.com>
	message dated "Tue, 19 Jul 2005 13:13:05 -0400"
Date: Tue, 19 Jul 2005 14:09:56 -0400
Message-ID: <7843.1121796596@sss.pgh.pa.us>
From: Tom Lane <tgl@sss.pgh.pa.us>
X-Virus-Scanned: by amavisd-new at hub.org
X-Spam-Status: No, hits=0.006 tagged_above=0 required=5 tests=AWL
X-Spam-Level: 
X-Archive-Number: 200507/299
X-Sequence-Number: 13540

Christopher Petrilli <petrilli@gmail.com> writes:
>> Are you sure the backend is reading directly from the file, and not
>> through psql?  (\copy, or COPY FROM STDIN, would go through psql.)

> The exact command is:
> COPY test (columnlist...) FROM '/tmp/loadfile';

I tried to replicate this by putting a ton of COPY commands like that
into a file and doing "psql -f file ...".  I don't see more than about
0.3% CPU going to psql.  So there's something funny about your test
conditions.  How *exactly* are you invoking psql?

			regards, tom lane