X-Original-To: pgsql-performance-postgresql.org@postgresql.org Received: from localhost (wm.hub.org [200.46.204.128]) by postgresql.org (Postfix) with ESMTP id A3ED29FB2E5 for ; Thu, 21 Sep 2006 04:31:30 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.128]) (amavisd-new, port 10024) with ESMTP id 97178-05 for ; Thu, 21 Sep 2006 07:31:17 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey- Received: from mail.tacotec.de (mail.tacotec.de [83.137.101.41]) by postgresql.org (Postfix) with ESMTP id B835C9FB2D2 for ; Thu, 21 Sep 2006 04:31:17 -0300 (ADT) Received: from localhost (localhost [127.0.0.1]) by mail.tacotec.de (Postfix) with ESMTP id 8B36211D5AA; Thu, 21 Sep 2006 09:31:15 +0200 (CEST) Received: from mail.tacotec.de ([83.137.101.41]) by localhost (hera.tacotec.de [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 23967-09; Thu, 21 Sep 2006 09:31:15 +0200 (CEST) Received: from lunix.schabi.de (p549D1A66.dip0.t-ipconnect.de [84.157.26.102]) by mail.tacotec.de (Postfix) with ESMTP id 8BF9611D538; Thu, 21 Sep 2006 09:31:14 +0200 (CEST) Received: from [127.0.0.1] (localhost [127.0.0.1]) by lunix.schabi.de (Postfix) with ESMTP id 6E4211975FC; Thu, 21 Sep 2006 09:31:13 +0200 (CEST) Message-ID: <45123FC0.9060100@logix-tt.com> Date: Thu, 21 Sep 2006 09:31:12 +0200 From: Markus Schaber User-Agent: Thunderbird 1.5.0.5 (X11/20060812) MIME-Version: 1.0 To: Luke Lonergan Cc: pgsql-performance@postgresql.org Subject: Re: Large tables (was: RAID 0 not as fast as References: In-Reply-To: X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at mail.tacotec.de X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0.134 tagged_above=0 required=5 tests=FORGED_RCVD_HELO, SPF_HELO_PASS X-Spam-Level: X-Archive-Number: 200609/276 X-Sequence-Number: 20962 Hi, Luke, Luke Lonergan wrote: >> I thought that posix_fadvise() with POSIX_FADV_WILLNEED was exactly >> meant for this purpose? > > This is a good idea - I wasn't aware that this was possible. This possibility was the reason for me to propose it. :-) > We'll do some testing and see if it works as advertised on Linux and > Solaris. Fine, I'm looking forward to the results. According to my small test, it works at least on linux 2.6.17.4. Btw, posix_fadvise() could even give a small improvement for multi-threaded backends, given that the I/O subsystem is smart enough to cope intelligently to cope with large bunches of outstanding requests. HTH, Markus