[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <150389211501.25151.6477753201827914462.stgit@dwillia2-desk3.amr.corp.intel.com>
Date: Sun, 27 Aug 2017 20:48:35 -0700
From: Dan Williams <dan.j.williams@...el.com>
To: linux-fsdevel@...r.kernel.org
Cc: jack@...e.cz, "Darrick J. Wong" <darrick.wong@...cle.com>,
linux-nvdimm@...ts.01.org, linux-xfs@...r.kernel.org,
Andreas Dilger <adilger.kernel@...ger.ca>,
Jan Kara <jack@...e.com>, Theodore Ts'o <tytso@....edu>,
linux-ext4@...r.kernel.org, hch@....de
Subject: [PATCH v2 0/2] fs, dax: lookup dax_device at mount time
Changes since v1:
* Move the lookup to mount time. (Christoph)
---
Christoph notes:
I just noticed that we now do a fs_dax_get_by_host in every
iomap_begin call for DAX. This function iterates a list, does a
string compared and igrab. I really think we need to cache this in
the superblock (possible even the fs superblock) similar to what we
do for the block device.
This passes the libnvdimm unit tests.
---
Dan Williams (2):
fs, xfs: perform dax_device lookup at mount
ext2, ext4: use the super_block dax_device
drivers/dax/super.c | 10 ++++++++++
fs/ext2/inode.c | 10 ++--------
fs/ext4/inode.c | 10 ++--------
fs/super.c | 26 +++++++++++++++++++++++---
fs/xfs/xfs_aops.c | 13 +++++++++++++
fs/xfs/xfs_aops.h | 1 +
fs/xfs/xfs_buf.c | 4 +++-
fs/xfs/xfs_buf.h | 3 ++-
fs/xfs/xfs_iomap.c | 10 +---------
fs/xfs/xfs_super.c | 21 +++++++++++++++++----
include/linux/dax.h | 6 ++++++
include/linux/fs.h | 1 +
12 files changed, 81 insertions(+), 34 deletions(-)
Powered by blists - more mailing lists