From mboxrd@z Thu Jan 1 00:00:00 1970 From: Zach Brown Subject: Re: [RFC] fs io with struct page instead of iovecs Date: Wed, 07 Nov 2007 09:02:05 -0800 Message-ID: <4731EF8D.5090701@oracle.com> References: <11943998113245-git-send-email-zach.brown@oracle.com> <1194454245.26782.32.camel@dyn9047017100.beaverton.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: linux-fsdevel , Christoph Hellwig , David Chinner To: Badari Pulavarty Return-path: Received: from tetsuo.zabbo.net ([207.173.201.20]:37410 "EHLO tetsuo.zabbo.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758431AbXKGRCH (ORCPT ); Wed, 7 Nov 2007 12:02:07 -0500 In-Reply-To: <1194454245.26782.32.camel@dyn9047017100.beaverton.ibm.com> Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org Badari Pulavarty wrote: > On Tue, 2007-11-06 at 17:43 -0800, Zach Brown wrote: >> At the FS meeting at LCE there was some talk of doing O_DIRECT writes from the >> kernel with pages instead of with iovecs. T > > Why ? Whats the use case ? Well, I think there's a few: There are existing callers which hold a kmap() across ->write, which isn't great. ecryptfs() does this. That's mentioned in the patch series. Arguably loopback should be using this instead of copying some fs paths and trying to call aop methods directly. I seem to remember Christoph and David having stories of knfsd folks in SGI wanting to do O_DIRECT writes from knfsd? (If not, *I* kind of want to, after rolling some patches to align net rx descriptors :)). Lustre shows us that there is a point at which you can't saturate your network and storage if your cpu is copying all the data. I'll be the first to admit that the community might not feel a pressing need to address this for in-kernel file system writers, but the observation remains. - z