From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: MIME-Version: 1.0 In-Reply-To: <20151116144130.GD3443@quack.suse.cz> References: <1447459610-14259-1-git-send-email-ross.zwisler@linux.intel.com> <20151116144130.GD3443@quack.suse.cz> Date: Mon, 16 Nov 2015 08:58:11 -0800 Message-ID: Subject: Re: [PATCH v2 00/11] DAX fsynx/msync support From: Dan Williams Content-Type: text/plain; charset=UTF-8 Sender: owner-linux-mm@kvack.org To: Jan Kara Cc: Ross Zwisler , "linux-kernel@vger.kernel.org" , "H. Peter Anvin" , "J. Bruce Fields" , Theodore Ts'o , Alexander Viro , Andreas Dilger , Dave Chinner , Ingo Molnar , Jan Kara , Jeff Layton , Matthew Wilcox , Thomas Gleixner , linux-ext4 , linux-fsdevel , Linux MM , "linux-nvdimm@lists.01.org" , X86 ML , XFS Developers , Andrew Morton , Matthew Wilcox , Dave Hansen List-ID: On Mon, Nov 16, 2015 at 6:41 AM, Jan Kara wrote: > On Fri 13-11-15 17:06:39, Ross Zwisler wrote: >> This patch series adds support for fsync/msync to DAX. >> >> Patches 1 through 7 add various utilities that the DAX code will eventually >> need, and the DAX code itself is added by patch 8. Patches 9-11 update the >> three filesystems that currently support DAX, ext2, ext4 and XFS, to use >> the new DAX fsync/msync code. >> >> These patches build on the recent DAX locking changes from Dave Chinner, >> Jan Kara and myself. Dave's changes for XFS and my changes for ext2 have >> been merged in the v4.4 window, but Jan's are still unmerged. You can grab >> them here: >> >> http://www.spinics.net/lists/linux-ext4/msg49951.html > > I had a quick look and the patches look sane to me. I'll try to give them > more detailed look later this week. When thinking about the general design > I was wondering: When we have this infrastructure to track data potentially > lingering in CPU caches, would not it be a performance win to use standard > cached stores in dax_io() and mark corresponding pages as dirty in page > cache the same way as this patch set does it for mmaped writes? I have no > idea how costly are non-temporal stores compared to cached ones and how > would this compare to the cost of dirty tracking so this may be just > completely bogus... Keep in mind that this approach will flush every virtual address that may be dirty. For example, if you touch 1byte in a 2MB page we'll end up looping through the entire 2MB range. At some point the dirty size becomes large enough that is cheaper to flush the entire cache, we have not measured where that crossover point is. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752838AbbKPQ6P (ORCPT ); Mon, 16 Nov 2015 11:58:15 -0500 Received: from mail-wm0-f51.google.com ([74.125.82.51]:34977 "EHLO mail-wm0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752399AbbKPQ6M (ORCPT ); Mon, 16 Nov 2015 11:58:12 -0500 MIME-Version: 1.0 In-Reply-To: <20151116144130.GD3443@quack.suse.cz> References: <1447459610-14259-1-git-send-email-ross.zwisler@linux.intel.com> <20151116144130.GD3443@quack.suse.cz> Date: Mon, 16 Nov 2015 08:58:11 -0800 Message-ID: Subject: Re: [PATCH v2 00/11] DAX fsynx/msync support From: Dan Williams To: Jan Kara Cc: Ross Zwisler , "linux-kernel@vger.kernel.org" , "H. Peter Anvin" , "J. Bruce Fields" , "Theodore Ts'o" , Alexander Viro , Andreas Dilger , Dave Chinner , Ingo Molnar , Jan Kara , Jeff Layton , Matthew Wilcox , Thomas Gleixner , linux-ext4 , linux-fsdevel , Linux MM , "linux-nvdimm@lists.01.org" , X86 ML , XFS Developers , Andrew Morton , Matthew Wilcox , Dave Hansen Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Nov 16, 2015 at 6:41 AM, Jan Kara wrote: > On Fri 13-11-15 17:06:39, Ross Zwisler wrote: >> This patch series adds support for fsync/msync to DAX. >> >> Patches 1 through 7 add various utilities that the DAX code will eventually >> need, and the DAX code itself is added by patch 8. Patches 9-11 update the >> three filesystems that currently support DAX, ext2, ext4 and XFS, to use >> the new DAX fsync/msync code. >> >> These patches build on the recent DAX locking changes from Dave Chinner, >> Jan Kara and myself. Dave's changes for XFS and my changes for ext2 have >> been merged in the v4.4 window, but Jan's are still unmerged. You can grab >> them here: >> >> http://www.spinics.net/lists/linux-ext4/msg49951.html > > I had a quick look and the patches look sane to me. I'll try to give them > more detailed look later this week. When thinking about the general design > I was wondering: When we have this infrastructure to track data potentially > lingering in CPU caches, would not it be a performance win to use standard > cached stores in dax_io() and mark corresponding pages as dirty in page > cache the same way as this patch set does it for mmaped writes? I have no > idea how costly are non-temporal stores compared to cached ones and how > would this compare to the cost of dirty tracking so this may be just > completely bogus... Keep in mind that this approach will flush every virtual address that may be dirty. For example, if you touch 1byte in a 2MB page we'll end up looping through the entire 2MB range. At some point the dirty size becomes large enough that is cheaper to flush the entire cache, we have not measured where that crossover point is. From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dan Williams Subject: Re: [PATCH v2 00/11] DAX fsynx/msync support Date: Mon, 16 Nov 2015 08:58:11 -0800 Message-ID: References: <1447459610-14259-1-git-send-email-ross.zwisler@linux.intel.com> <20151116144130.GD3443@quack.suse.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Cc: Ross Zwisler , "linux-kernel@vger.kernel.org" , "H. Peter Anvin" , "J. Bruce Fields" , "Theodore Ts'o" , Alexander Viro , Andreas Dilger , Dave Chinner , Ingo Molnar , Jan Kara , Jeff Layton , Matthew Wilcox , Thomas Gleixner , linux-ext4 , linux-fsdevel , Linux MM , "linux-nvdimm@lists.01.org" , X86 ML , XFS Developers , Andrew Morton , Matthew Wilcox , Dave Hansen Return-path: In-Reply-To: <20151116144130.GD3443@quack.suse.cz> Sender: owner-linux-mm@kvack.org List-Id: linux-ext4.vger.kernel.org On Mon, Nov 16, 2015 at 6:41 AM, Jan Kara wrote: > On Fri 13-11-15 17:06:39, Ross Zwisler wrote: >> This patch series adds support for fsync/msync to DAX. >> >> Patches 1 through 7 add various utilities that the DAX code will eventually >> need, and the DAX code itself is added by patch 8. Patches 9-11 update the >> three filesystems that currently support DAX, ext2, ext4 and XFS, to use >> the new DAX fsync/msync code. >> >> These patches build on the recent DAX locking changes from Dave Chinner, >> Jan Kara and myself. Dave's changes for XFS and my changes for ext2 have >> been merged in the v4.4 window, but Jan's are still unmerged. You can grab >> them here: >> >> http://www.spinics.net/lists/linux-ext4/msg49951.html > > I had a quick look and the patches look sane to me. I'll try to give them > more detailed look later this week. When thinking about the general design > I was wondering: When we have this infrastructure to track data potentially > lingering in CPU caches, would not it be a performance win to use standard > cached stores in dax_io() and mark corresponding pages as dirty in page > cache the same way as this patch set does it for mmaped writes? I have no > idea how costly are non-temporal stores compared to cached ones and how > would this compare to the cost of dirty tracking so this may be just > completely bogus... Keep in mind that this approach will flush every virtual address that may be dirty. For example, if you touch 1byte in a 2MB page we'll end up looping through the entire 2MB range. At some point the dirty size becomes large enough that is cheaper to flush the entire cache, we have not measured where that crossover point is. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay1.corp.sgi.com [137.38.102.111]) by oss.sgi.com (Postfix) with ESMTP id 71F8A7CBF for ; Mon, 16 Nov 2015 10:58:17 -0600 (CST) Received: from cuda.sgi.com (cuda2.sgi.com [192.48.176.25]) by relay1.corp.sgi.com (Postfix) with ESMTP id 2FF108F8049 for ; Mon, 16 Nov 2015 08:58:17 -0800 (PST) Received: from mail-wm0-f48.google.com (mail-wm0-f48.google.com [74.125.82.48]) by cuda.sgi.com with ESMTP id 0lxdxjph1qA2Jdin (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NO) for ; Mon, 16 Nov 2015 08:58:12 -0800 (PST) Received: by wmww144 with SMTP id w144so128172141wmw.0 for ; Mon, 16 Nov 2015 08:58:11 -0800 (PST) MIME-Version: 1.0 In-Reply-To: <20151116144130.GD3443@quack.suse.cz> References: <1447459610-14259-1-git-send-email-ross.zwisler@linux.intel.com> <20151116144130.GD3443@quack.suse.cz> Date: Mon, 16 Nov 2015 08:58:11 -0800 Message-ID: Subject: Re: [PATCH v2 00/11] DAX fsynx/msync support From: Dan Williams 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 Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Jan Kara Cc: Dave Hansen , "J. Bruce Fields" , Linux MM , Andreas Dilger , "H. Peter Anvin" , Jeff Layton , "linux-nvdimm@lists.01.org" , X86 ML , Ingo Molnar , Matthew Wilcox , Ross Zwisler , linux-ext4 , XFS Developers , Alexander Viro , Thomas Gleixner , Theodore Ts'o , "linux-kernel@vger.kernel.org" , Jan Kara , linux-fsdevel , Andrew Morton , Matthew Wilcox On Mon, Nov 16, 2015 at 6:41 AM, Jan Kara wrote: > On Fri 13-11-15 17:06:39, Ross Zwisler wrote: >> This patch series adds support for fsync/msync to DAX. >> >> Patches 1 through 7 add various utilities that the DAX code will eventually >> need, and the DAX code itself is added by patch 8. Patches 9-11 update the >> three filesystems that currently support DAX, ext2, ext4 and XFS, to use >> the new DAX fsync/msync code. >> >> These patches build on the recent DAX locking changes from Dave Chinner, >> Jan Kara and myself. Dave's changes for XFS and my changes for ext2 have >> been merged in the v4.4 window, but Jan's are still unmerged. You can grab >> them here: >> >> http://www.spinics.net/lists/linux-ext4/msg49951.html > > I had a quick look and the patches look sane to me. I'll try to give them > more detailed look later this week. When thinking about the general design > I was wondering: When we have this infrastructure to track data potentially > lingering in CPU caches, would not it be a performance win to use standard > cached stores in dax_io() and mark corresponding pages as dirty in page > cache the same way as this patch set does it for mmaped writes? I have no > idea how costly are non-temporal stores compared to cached ones and how > would this compare to the cost of dirty tracking so this may be just > completely bogus... Keep in mind that this approach will flush every virtual address that may be dirty. For example, if you touch 1byte in a 2MB page we'll end up looping through the entire 2MB range. At some point the dirty size becomes large enough that is cheaper to flush the entire cache, we have not measured where that crossover point is. _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs