From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay3.corp.sgi.com [198.149.34.15]) by oss.sgi.com (Postfix) with ESMTP id 3648F7F3F for ; Fri, 4 Jul 2014 09:09:18 -0500 (CDT) Received: from cuda.sgi.com (cuda2.sgi.com [192.48.176.25]) by relay3.corp.sgi.com (Postfix) with ESMTP id B87FCAC001 for ; Fri, 4 Jul 2014 07:09:14 -0700 (PDT) Received: from mail3.ks.pochta.ru (mail3.ks.pochta.ru [62.141.94.173]) by cuda.sgi.com with ESMTP id OHIybT8DqxuJyO6x (version=TLSv1 cipher=AES256-SHA bits=256 verify=NO) for ; Fri, 04 Jul 2014 07:09:12 -0700 (PDT) Message-ID: <53B6B581.5070801@hotbox.ru> Date: Fri, 04 Jul 2014 18:09:05 +0400 From: flux@hotbox.ru MIME-Version: 1.0 Subject: Re: XFS syncs References: <53B59B81.2030603@hotbox.ru> <20140703231730.GW4453@dastard> In-Reply-To: <20140703231730.GW4453@dastard> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="us-ascii"; Format="flowed" Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Dave Chinner Cc: xfs@oss.sgi.com Hello Dave, Thanks for the explanation and your suggestion to use wsync option. On 07/04/2014 03:17 AM, Dave Chinner wrote: > On Thu, Jul 03, 2014 at 10:05:53PM +0400, flux@hotbox.ru wrote: >> Hi, >> >> I issue 'mkdir abc' on my xfs partition the cut off the power. After >> reboot there's no 'abc' directoy. > > Because you didn't sync(1) the filesystem or fsync(2) the directory > before you cut the power. Hence the change never hit the disk. > >> However, when I do that on ext4 >> the 'abc' direcory is always created after reboots. > > That'll be pure fluke - ext4 delays journal writes on namespace > operations just like XFS does. > >> All the >> settings, about mount options are default for my distro. What am I >> missing or how do I change the things of the jounral or whatever? > > If you want directory operations to hitthe disk immediately, then > mount with the "-o wsync" option. Be aware, however, that this will > kill performance unless you have expensive storage with a large > amount of battery backed write cache in front of the disks. There's > a good chance it will also cause excessive wear on SSDs due to the > frequent journal writes. > > Cheers, > > Dave. > _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs