From owner-freebsd-questions Sun Apr 2 19:40:56 2000 Delivered-To: freebsd-questions@freebsd.org Received: from TK147108.tuwien.teleweb.at (TK147108.tuwien.teleweb.at [195.34.147.108]) by hub.freebsd.org (Postfix) with ESMTP id B7F8937BD19 for ; Sun, 2 Apr 2000 19:40:51 -0700 (PDT) (envelope-from satyr@TK147108.tuwien.teleweb.at) Received: from satyr by TK147108.tuwien.teleweb.at with local (Exim 2.12 #1) id 12bwpj-0001TN-00; Mon, 3 Apr 2000 04:43:19 +0200 Date: Mon, 3 Apr 2000 04:43:19 +0200 From: "Marinos J . Yannikos" To: David Greenman Cc: questions@freebsd.org Subject: Re: tuning the vm system / disk cache Message-ID: <20000403044319.V31173@TK147108.telekabel.at> Reply-To: nino@inode.at References: <20000403025556.S31173@TK147108.telekabel.at> <200004030209.TAA07259@implode.root.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.95.5i In-Reply-To: <200004030209.TAA07259@implode.root.com>; from David Greenman on Sun, Apr 02, 2000 at 07:09:52PM -0700 Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Sun, Apr 02, 2000 at 07:09:52PM -0700, David Greenman wrote: > I'm sure the system is already caching the entire file - evidence of this > is the 438M of free memory, which the system would directly allocate from in > order to cache the file. The only way I can explain the disk I/O is that there > must be some writes taking place for some reason. You're right (of course). I checked Postgres' data directory and, surprisingly, it writes temporary files for every query. Their filenames begin with "pg_sorttemp", so the GROUP BY clause seems to be the culprit. Shouldn't it be possible to get rid of those disk accesses somehow? These are very short-lived files, softupdates are enabled. -mjy -- ***==> Marinos J. Yannikos ***==> http://pobox.com/~mjy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message