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 53C4D3A2B3C for ; Fri, 5 Nov 2004 04:29:07 +0000 (GMT) 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 42832-05 for ; Fri, 5 Nov 2004 04:29:02 +0000 (GMT) Received: from sue.samurai.com (sue.samurai.com [205.207.28.74]) by svr1.postgresql.org (Postfix) with ESMTP id 301093A1D92 for ; Fri, 5 Nov 2004 04:29:02 +0000 (GMT) Received: from localhost (localhost [127.0.0.1]) by sue.samurai.com (Postfix) with ESMTP id A3EF419861; Thu, 4 Nov 2004 23:29:01 -0500 (EST) Received: from sue.samurai.com ([127.0.0.1]) by localhost (sue.samurai.com [127.0.0.1]) (amavisd-new, port 10024) with LMTP id 64966-01-9; Thu, 4 Nov 2004 23:29:00 -0500 (EST) Received: from [61.88.101.19] (unknown [61.88.101.19]) by sue.samurai.com (Postfix) with ESMTP id 973921985B; Thu, 4 Nov 2004 23:28:59 -0500 (EST) Subject: Re: Anything to be gained from a 'Postgres Filesystem'? From: Neil Conway To: "Steinar H. Gunderson" Cc: pgsql-performance@postgresql.org In-Reply-To: <20041104192004.GA18793@uio.no> References: <20041104120047.62810c8f@kingfisher.intern.logi-track.com> <60bred39bg.fsf@dba2.int.libertyrms.com> <20041104192004.GA18793@uio.no> Content-Type: text/plain Message-Id: <1099628919.10449.39.camel@localhost.localdomain> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.6 Date: Fri, 05 Nov 2004 15:28:39 +1100 Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at mailbox.samurai.com X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.0 tagged_above=0.0 required=5.0 tests= X-Spam-Level: X-Archive-Number: 200411/82 X-Sequence-Number: 9036 On Fri, 2004-11-05 at 06:20, Steinar H. Gunderson wrote: > You mean, like, open(filename, O_DIRECT)? :-) This disables readahead (at least on Linux), which is certainly not we want: for the very case where we don't want to keep the data in cache for a while (sequential scans, VACUUM), we also want aggressive readahead. -Neil