From: Trond Myklebust Subject: Re: [ltt-dev] [PATCH] nfs: add support for splice writes Date: Tue, 21 Apr 2009 13:35:02 -0400 Message-ID: <1240335302.5390.20.camel@heimdal.trondhjem.org> References: <49D45974.2060202@suse.de> <20090402063235.GB24846@Krystal> <49D45E42.3050502@suse.de> <91e0b5050904020542l6b38d7a6hab6d7ef8b4593425@mail.gmail.com> <49EC0A83.8060802@suse.de> <1240230224.8073.6.camel@heimdal.trondhjem.org> <49EC6CB3.8080800@suse.de> <1240237274.13636.9.camel@heimdal.trondhjem.org> <49EC990B.1030007@suse.de> <20090421144810.GA7036@infradead.org> Mime-Version: 1.0 Content-Type: text/plain Cc: Suresh Jayaraman , Masahiro Tamori , Mathieu Desnoyers , linux-nfs@vger.kernel.org, ltt-dev-33AaDErTWvBVxDZ2/Zk0YoryAYyacSEB@public.gmane.org, LKML , linux-embedded@vger.kernel.org, Peter Zijlstra To: Christoph Hellwig Return-path: Received: from mail-out2.uio.no ([129.240.10.58]:39686 "EHLO mail-out2.uio.no" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752330AbZDURfP (ORCPT ); Tue, 21 Apr 2009 13:35:15 -0400 In-Reply-To: <20090421144810.GA7036@infradead.org> Sender: linux-nfs-owner@vger.kernel.org List-ID: On Tue, 2009-04-21 at 10:48 -0400, Christoph Hellwig wrote: > On Mon, Apr 20, 2009 at 09:17:23PM +0530, Suresh Jayaraman wrote: > > +static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, > > + struct file *filp, loff_t *ppos, > > + size_t count, unsigned int flags) > > +{ > > + struct dentry *dentry = filp->f_path.dentry; > > + > > + dprintk("NFS splice_write(%s/%s, %lu@%Lu)\n", > > + dentry->d_parent->d_name.name, dentry->d_name.name, > > + (unsigned long) count, (unsigned long long) *ppos); > > + > > + return generic_file_splice_write(pipe, filp, ppos, count, flags); > > +} > > + > > You need all calls from nfs_file_write, too: > > - most importantly the nfs_revalidate_file_size for O_APPEND Isn't O_APPEND illegal for splice_write()? It looks like it is from a quick perusal of do_splice_from(). > - the nfs_do_fsync for sync writes generic_file_splice_write() calls generic_osync_inode(), which should ensure sync writes even with NFS. The one thing it won't do is propagate NFS write errors back to the caller. If we do care about this, then we should certainly test for nfs_need_sync_write() and then call nfs_do_fsync() (see nfs_file_write()). > - probably the stats increment We should talk to Chuck about this. Cheers Trond