From mboxrd@z Thu Jan 1 00:00:00 1970 From: Boaz Harrosh Subject: Re: exofs_file_fsync Date: Tue, 01 Jun 2010 18:29:04 +0300 Message-ID: <4C052740.1070200@panasas.com> References: <20100531100927.GA11149@lst.de> <4C038E0D.3010400@panasas.com> <20100531102706.GA11961@lst.de> <4C038FE5.8000504@panasas.com> <20100531103349.GA12196@lst.de> <4C03BD14.5030004@panasas.com> <20100601100401.GB28762@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: linux-fsdevel@vger.kernel.org To: Christoph Hellwig Return-path: Received: from daytona.panasas.com ([67.152.220.89]:39393 "EHLO daytona.int.panasas.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755601Ab0FAP3J (ORCPT ); Tue, 1 Jun 2010 11:29:09 -0400 In-Reply-To: <20100601100401.GB28762@lst.de> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On 06/01/2010 01:04 PM, Christoph Hellwig wrote: > > The pages are written by vfs_fsync_range. You need to make sure > that the inode back, or if the datasync flag is set only changes > to the inode require to find that data are written back. That's > basically a messy wording for you can skip dirtiness of timestamp > updates if the datasync flag is set. > > Note that your patch below is very wrong for this, as it does > a lot of asynchronous activity if the datasync flag is not set. > Thank you Christoph. Me smack me on the head. Got two unrelated flags totally confused. I'll be posting a fix. For the best of my knowledge all I need is a synchronous call to sync_inode() which will in turn call exofs_write_inode. The later takes care of all metadata an exofs inode has. (No allocation bitmaps, no data nodes lists, etc...) In a next patch I'll also fix the super-block shit. Testing ... Boaz