From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from fransum.emea.sgi.com (fransum.emea.sgi.com [144.253.208.10]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id n6OCq12m128707 for ; Fri, 24 Jul 2009 07:52:01 -0500 Subject: Re: umount xfs filesystem References: <4A66C5E7.7050408@readytec.it> From: Olaf Weber Date: Fri, 24 Jul 2009 14:52:42 +0200 In-Reply-To: <4A66C5E7.7050408@readytec.it> (Daniele Nuzzo's message of "Wed, 22 Jul 2009 09:55:19 +0200") Message-ID: MIME-Version: 1.0 List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: Daniele Nuzzo - Readytec SPA Cc: xfs@oss.sgi.com Daniele Nuzzo writes: > hi, > I think I need your advice-opinion ... > I set up a system like CentOS 5.3, lvm, drbd 8.2, various systems raid > (Adaptec aacraid or LSI MegaRAID with or without write back cache) > after some time of work (a few hours or days) do the umount is > slow... even a few minutes ... why? > I have already disabled barrier and write cache on drbd, but not on > the controller or the sas drives... ideas? > thanks a lot. > p.s. > drbd partitions formatted with the default options. On unmount the system has flush all dirty data to disk. Depending on the amount of data in memory, this might take a while. I'm not claiming this is definitely the case here, but it is an obvious candidate. -- Olaf Weber SGI Phone: +31(0)30-6696752 Veldzigt 2b Fax: +31(0)30-6696799 Technical Lead 3454 PW de Meern Vnet: 955-7151 Storage Software The Netherlands Email: olaf@sgi.com _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs