From: Ross Zwisler Subject: Re: [PATCH v2 0/9] re-enable DAX PMD support Date: Wed, 31 Aug 2016 15:36:07 -0600 Message-ID: <20160831213607.GA6921@linux.intel.com> References: <20160823220419.11717-1-ross.zwisler@linux.intel.com> <20160830230150.GA12173@linux.intel.com> <1472674799.2092.19.camel@hpe.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Cc: "tytso-3s7WtUTddSA@public.gmane.org" , "akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org" , "mawilcox-0li6OtcxBFHby3iVrkZq2A@public.gmane.org" , "linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org" , "david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org" , "linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , "linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org" , "adilger.kernel-m1MBpc4rdrD3fQ9qLvQP4Q@public.gmane.org" , "viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org" , "jack-IBi9RG/b67k@public.gmane.org" , "linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , "linux-ext4-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" To: "Kani, Toshimitsu" Return-path: Content-Disposition: inline In-Reply-To: <1472674799.2092.19.camel-ZPxbGqLxI0U@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: linux-nvdimm-bounces-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org Sender: "Linux-nvdimm" List-Id: linux-ext4.vger.kernel.org On Wed, Aug 31, 2016 at 08:20:48PM +0000, Kani, Toshimitsu wrote: > On Tue, 2016-08-30 at 17:01 -0600, Ross Zwisler wrote: > > On Tue, Aug 23, 2016 at 04:04:10PM -0600, Ross Zwisler wrote: > > > = > > > DAX PMDs have been disabled since Jan Kara introduced DAX radix > > > tree based locking.=A0=A0This series allows DAX PMDs to participate in > > > the DAX radix tree based locking scheme so that they can be re- > > > enabled. > > > = > > > Changes since v1: > > > =A0- PMD entry locking is now done based on the starting offset of > > > the PMD entry, rather than on the radix tree slot which was > > > unreliable. (Jan) > > > =A0- Fixed the one issue I could find with hole punch.=A0=A0As far as= I > > > can tell hole punch now works correctly for both PMD and PTE DAX > > > entries, 4k zero pages and huge zero pages. > > > =A0- Fixed the way that ext2 returns the size of holes in > > > ext2_get_block(). (Jan) > > > =A0- Made the 'wait_table' global variable static in respnse to a > > > sparse warning. > > > =A0- Fixed some more inconsitent usage between the names 'ret' and > > > 'entry' for radix tree entry variables. > > > = > > > Ross Zwisler (9): > > > =A0 ext4: allow DAX writeback for hole punch > > > =A0 ext2: tell DAX the size of allocation holes > > > =A0 ext4: tell DAX the size of allocation holes > > > =A0 dax: remove buffer_size_valid() > > > =A0 dax: make 'wait_table' global variable static > > > =A0 dax: consistent variable naming for DAX entries > > > =A0 dax: coordinate locking for offsets in PMD range > > > =A0 dax: re-enable DAX PMD support > > > =A0 dax: remove "depends on BROKEN" from FS_DAX_PMD > > > = > > > =A0fs/Kconfig=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0|=A0=A0=A01 - > > > =A0fs/dax.c=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0| 297 ++++++++++++++++= +++++++++++++----------- > > > ------------ > > > =A0fs/ext2/inode.c=A0=A0=A0=A0=A0|=A0=A0=A03 + > > > =A0fs/ext4/inode.c=A0=A0=A0=A0=A0|=A0=A0=A07 +- > > > =A0include/linux/dax.h |=A0=A029 ++++- > > > =A0mm/filemap.c=A0=A0=A0=A0=A0=A0=A0=A0|=A0=A0=A06 +- > > > =A06 files changed, 201 insertions(+), 142 deletions(-) > > > = > > > --=A0 > > > 2.9.0 > > = > > Ping on this series?=A0=A0Any objections or comments? > = > Hi Ross, > = > I am seeing a major performance loss in fio mmap test with this patch- > set applied. =A0This happens with or without my patches [1] applied on > top of yours. =A0Without my patches,=A0dax_pmd_fault() falls back to the > pte handler since an mmap'ed address is not 2MB-aligned. > = > I have attached three test results. > =A0o rc4.log - 4.8.0-rc4 (base) > =A0o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte) > =A0o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps) > = > My test steps are as follows. > = > mkfs.ext4 -O bigalloc -C 2M /dev/pmem0 > mount -o dax /dev/pmem0 /mnt/pmem0 > numactl --preferred block:pmem0 --cpunodebind block:pmem0 fio test.fio > = > "test.fio" > --- > [global] > bs=3D4k > size=3D2G > directory=3D/mnt/pmem0 > ioengine=3Dmmap > [randrw] > rw=3Drandrw > --- > = > Can you please take a look? Yep, thanks for the report.