X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 441FD9DCBE7 for ; Sat, 11 Mar 2006 10:26:14 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 69593-08 for ; Sat, 11 Mar 2006 10:26:18 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from obelix.askesis.nl (laudanum.demon.nl [82.161.125.16]) by postgresql.org (Postfix) with ESMTP id B13DA9DCBE4 for ; Sat, 11 Mar 2006 10:26:11 -0400 (AST) Received: obelix 172.31.0.1 from 172.31.1.4 172.31.1.4 via HTTP with MS-WebStorage 6.0.6249 Received: from panoramix by obelix; 11 Mar 2006 15:26:14 +0100 Subject: Re: x206-x225 From: Joost Kraaijeveld To: PFC Cc: David Lang , Richard Huxton , pgsql-performance@postgresql.org In-Reply-To: References: <441181C6.3040401@archonet.com> <1142063378.6634.13.camel@localhost> <1142065029.6634.23.camel@localhost> Content-Type: text/plain Content-Transfer-Encoding: 7bit Date: Sat, 11 Mar 2006 15:26:14 +0100 Message-Id: <1142087174.6634.32.camel@localhost> Mime-Version: 1.0 X-Mailer: Evolution 2.4.2.1 X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.093 required=5 tests=[AWL=0.092, UNPARSEABLE_RELAY=0.001] X-Spam-Score: 0.093 X-Spam-Level: X-Archive-Number: 200603/151 X-Sequence-Number: 17588 On Sat, 2006-03-11 at 12:33 +0100, PFC wrote: > >> each transaction requires a sync to the disk, a sync requires a real > >> write (which you then wait for), so you can only do one transaction per > >> rotation. > > Not according to a conversation I had with Western Digital about the > > > It depends if you consider that "written to the disk" means "data is > somewhere between the OS cache and the platter" or "data is writter on the > platter and will survive a power loss". > > Postgres wants the second option, of course. I assume that for PostgreSQL "written to disk" is after fsync returned successfully. In practice that could very well mean that the data is still in a cache somewhere (controller or harddisk, not in the OS anymore, see also man page of fsync) -- Groeten, Joost Kraaijeveld Askesis B.V. Molukkenstraat 14 6524NB Nijmegen tel: 024-3888063 / 06-51855277 fax: 024-3608416 e-mail: J.Kraaijeveld@Askesis.nl web: www.askesis.nl