X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id BEFA9D1BAC8; Thu, 18 Mar 2004 20:04:07 +0000 (GMT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (neptune.hub.org [200.46.204.2]) (amavisd-new, port 10024) with ESMTP id 87755-10; Thu, 18 Mar 2004 16:04:06 -0400 (AST) Received: from adicia.telenet-ops.be (adicia.telenet-ops.be [195.130.132.56]) by svr1.postgresql.org (Postfix) with ESMTP id D8FDAD1C9EA; Thu, 18 Mar 2004 16:03:55 -0400 (AST) Received: from localhost (localhost.localdomain [127.0.0.1]) by adicia.telenet-ops.be (Postfix) with SMTP id 4B9121F7282; Thu, 18 Mar 2004 21:04:01 +0100 (MET) Received: from kabel.telenet.be (D5767DEE.kabel.telenet.be [213.118.125.238]) by adicia.telenet-ops.be (Postfix) with ESMTP id 83E1B1F71EE; Thu, 18 Mar 2004 21:04:00 +0100 (MET) Received: by kabel.telenet.be (Postfix, from userid 501) id A9AFA158AD5; Thu, 18 Mar 2004 21:03:59 +0100 (CET) Date: Thu, 18 Mar 2004 21:03:59 +0100 From: Kurt Roeckx To: Bruce Momjian Cc: Tom Lane , Mark Kirkwood , pgsql-performance@postgresql.org, PostgreSQL-development Subject: Re: [HACKERS] fsync method checking Message-ID: <20040318200359.GA8330@ping.be> References: <20040318191840.GA7088@ping.be> <200403181922.i2IJMAd16258@candle.pha.pa.us> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200403181922.i2IJMAd16258@candle.pha.pa.us> User-Agent: Mutt/1.4.2.1i X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200403/287 X-Sequence-Number: 6143 On Thu, Mar 18, 2004 at 02:22:10PM -0500, Bruce Momjian wrote: > > OK, what better test do you suggest? Right now, there has been no > testing of these. I suggest you start by doing atleast preallocating a 16 MB file and do the tests on that, to atleast be somewhat simular to what WAL does. I have no idea what the access pattern is for normal WAL operations or how many times it gets synched. Does it only do f(data)sync() at commit time, or for every block it writes? I think if you write more data you'll see more differences between O_(D)SYNC and f(data)sync(). I guess it can depend on if you have lots of small transactions, or more big ones. Atleast try to make something that covers different access patterns. Kurt