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 182B69FB2AA for ; Mon, 7 Aug 2006 08:51:18 -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 10758-06 for ; Mon, 7 Aug 2006 11:51:14 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey- Received: from mail.logix-tt.com (mail.logix-tt.com [212.211.145.186]) by postgresql.org (Postfix) with ESMTP id 036579FB25D for ; Mon, 7 Aug 2006 08:51:13 -0300 (ADT) Received: from kingfisher.intern.logix-tt.com (p549D25A1.dip0.t-ipconnect.de [84.157.37.161]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.logix-tt.com (Postfix) with ESMTP id 34BF9656B8; Mon, 7 Aug 2006 13:53:09 +0200 (CEST) Received: from [127.0.0.1] (localhost [127.0.0.1]) by kingfisher.intern.logix-tt.com (Postfix) with ESMTP id E3623185CD0DC; Mon, 7 Aug 2006 13:51:23 +0200 (CEST) Message-ID: <44D7293B.20702@logix-tt.com> Date: Mon, 07 Aug 2006 13:51:23 +0200 From: Markus Schaber Organization: Logical Tracking and Tracing International AG, Switzerland User-Agent: Thunderbird 1.5.0.4 (X11/20060713) MIME-Version: 1.0 To: carlosreimer Cc: pgsql-performance Subject: Re: Disk writes References: In-Reply-To: X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0.135 tagged_above=0 required=5 tests=FORGED_RCVD_HELO X-Spam-Level: X-Archive-Number: 200608/65 X-Sequence-Number: 20250 Hi, Reimer, carlosreimer wrote: > There is some performance problems with the server and I discovered with > vmstat tool that there is some process writing a lot of information in > the disk subsystem. [..] > I could I discover who is sending so many data to the disks? It could be something triggered by your crontab (updatedb comes in my mind, or texpire from leafnode etc.). Another idea would be that you have statement logging on, or something else that produces lots of kernel or syslog messages[1], and your syslogd is configured to sync() after every line... HTH, Markus [1] We once had such a problem because an ill-compiled kernel having USB verbose logging on... -- Markus Schaber | Logical Tracking&Tracing International AG Dipl. Inf. | Software Development GIS Fight against software patents in EU! www.ffii.org www.nosoftwarepatents.org