28 Sep, 2016
1 commit
-
current_fs_time() uses struct super_block* as an argument.
As per Linus's suggestion, this is changed to take struct
inode* as a parameter instead. This is because the function
is primarily meant for vfs inode timestamps.
Also the function was renamed as per Arnd's suggestion.Change all calls to current_fs_time() to use the new
current_time() function instead. current_fs_time() will be
deleted.Signed-off-by: Deepa Dinamani
Signed-off-by: Al Viro
05 Aug, 2016
1 commit
-
Pull nfsd updates from Bruce Fields:
"Highlights:- Trond made a change to the server's tcp logic that allows a fast
client to better take advantage of high bandwidth networks, but may
increase the risk that a single client could starve other clients;
a new sunrpc.svc_rpc_per_connection_limit parameter should help
mitigate this in the (hopefully unlikely) event this becomes a
problem in practice.- Tom Haynes added a minimal flex-layout pnfs server, which is of no
use in production for now--don't build it unless you're doing
client testing or further server development"* tag 'nfsd-4.8' of git://linux-nfs.org/~bfields/linux: (32 commits)
nfsd: remove some dead code in nfsd_create_locked()
nfsd: drop unnecessary MAY_EXEC check from create
nfsd: clean up bad-type check in nfsd_create_locked
nfsd: remove unnecessary positive-dentry check
nfsd: reorganize nfsd_create
nfsd: check d_can_lookup in fh_verify of directories
nfsd: remove redundant zero-length check from create
nfsd: Make creates return EEXIST instead of EACCES
SUNRPC: Detect immediate closure of accepted sockets
SUNRPC: accept() may return sockets that are still in SYN_RECV
nfsd: allow nfsd to advertise multiple layout types
nfsd: Close race between nfsd4_release_lockowner and nfsd4_lock
nfsd/blocklayout: Make sure calculate signature/designator length aligned
xfs: abstract block export operations from nfsd layouts
SUNRPC: Remove unused callback xpo_adjust_wspace()
SUNRPC: Change TCP socket space reservation
SUNRPC: Add a server side per-connection limit
SUNRPC: Micro optimisation for svc_data_ready
SUNRPC: Call the default socket callbacks instead of open coding
SUNRPC: lock the socket while detaching it
...
28 Jul, 2016
1 commit
-
Pull xfs updates from Dave Chinner:
"The major addition is the new iomap based block mapping
infrastructure. We've been kicking this about locally for years, but
there are other filesystems want to use it too (e.g. gfs2). Now it
is fully working, reviewed and ready for merge and be used by other
filesystems.There are a lot of other fixes and cleanups in the tree, but those are
XFS internal things and none are of the scale or visibility of the
iomap changes. See below for details.I am likely to send another pull request next week - we're just about
ready to merge some new functionality (on disk block->owner reverse
mapping infrastructure), but that's a huge chunk of code (74 files
changed, 7283 insertions(+), 1114 deletions(-)) so I'm keeping that
separate to all the "normal" pull request changes so they don't get
lost in the noise.Summary of changes in this update:
- generic iomap based IO path infrastructure
- generic iomap based fiemap implementation
- xfs iomap based Io path implementation
- buffer error handling fixes
- tracking of in flight buffer IO for unmount serialisation
- direct IO and DAX io path separation and simplification
- shortform directory format definition changes for wider platform
compatibility
- various buffer cache fixes
- cleanups in preparation for rmap merge
- error injection cleanups and fixes
- log item format buffer memory allocation restructuring to prevent
rare OOM reclaim deadlocks
- sparse inode chunks are now fully supported"* tag 'xfs-for-linus-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (53 commits)
xfs: remove EXPERIMENTAL tag from sparse inode feature
xfs: bufferhead chains are invalid after end_page_writeback
xfs: allocate log vector buffers outside CIL context lock
libxfs: directory node splitting does not have an extra block
xfs: remove dax code from object file when disabled
xfs: skip dirty pages in ->releasepage()
xfs: remove __arch_pack
xfs: kill xfs_dir2_inou_t
xfs: kill xfs_dir2_sf_off_t
xfs: split direct I/O and DAX path
xfs: direct calls in the direct I/O path
xfs: stop using generic_file_read_iter for direct I/O
xfs: split xfs_file_read_iter into buffered and direct I/O helpers
xfs: remove s_maxbytes enforcement in xfs_file_read_iter
xfs: kill ioflags
xfs: don't pass ioflags around in the ioctl path
xfs: track and serialize in-flight async buffers against unmount
xfs: exclude never-released buffers from buftarg I/O accounting
xfs: don't reset b_retries to 0 on every failure
xfs: remove extraneous buffer flag changes
...
14 Jul, 2016
1 commit
-
Signed-off-by: Tom Haynes
Reviewed-by: Christoph Hellwig
Reviewed-by: Jeff Layton
Signed-off-by: J. Bruce Fields
21 Jun, 2016
1 commit
-
Signed-off-by: Christoph Hellwig
Reviewed-by: Bob Peterson
Signed-off-by: Dave Chinner
14 Jun, 2016
1 commit
-
On 32-bit:
fs/nfsd/blocklayout.c: In function ‘nfsd4_block_get_device_info_scsi’:
fs/nfsd/blocklayout.c:337: warning: integer constant is too large for ‘long’ type
fs/nfsd/blocklayout.c:344: warning: integer constant is too large for ‘long’ type
fs/nfsd/blocklayout.c: In function ‘nfsd4_scsi_fence_client’:
fs/nfsd/blocklayout.c:385: warning: integer constant is too large for ‘long’ typeAdd the missing "ULL" postfix to 64-bit constant NFSD_MDS_PR_KEY to fix
this.Fixes: f99d4fbdae6765d0 ("nfsd: add SCSI layout support")
Signed-off-by: Geert Uytterhoeven
Reviewed-by: Christoph Hellwig
Signed-off-by: J. Bruce Fields
18 Mar, 2016
2 commits
-
This is a simple extension to the block layout driver to use SCSI
persistent reservations for access control and fencing, as well as
SCSI VPD pages for device identification.For this we need to pass the nfs4_client to the proc_getdeviceinfo method
to generate the reservation key, and add a new fence_client method
to allow for fence actions in the layout driver.Signed-off-by: Christoph Hellwig
Signed-off-by: J. Bruce Fields -
Trivial reorganization, no change in behavior. Move some code around,
pull some code out of block layoutcommit that will be useful for the
scsi layout.[bfields@redhat.com: split off from "nfsd: add SCSI layout support"]
Signed-off-by: J. Bruce Fields
10 Oct, 2015
1 commit
-
Recent Linux clients have started to send GETLAYOUT requests with
minlength less than blocksize.Servers aren't really allowed to impose this kind of restriction on
layouts; see RFC 5661 section 18.43.3 for details.This has been observed to cause indefinite hangs on fsx runs on some
clients.Cc: stable@vger.kernel.org
Signed-off-by: Christoph Hellwig
Signed-off-by: J. Bruce Fields
05 May, 2015
1 commit
-
Commit df52699e4fcef ("NFSv4.1: Don't cache deviceids that have no
notifications") causes the Linux NFS client to stop caching deviceid's
unless a server pretends to support deviceid notifications. While this
behavior is stupid and the language around this area in rfc5661 is a
mess carified by an errata that I submittted, Trond insists on this
behavior. Not caching deviceids degrades block layout performance
massively as a GETDEVICEINFO is fairly expensive.So add this hack to make the Linux client happy again.
Cc: stable@vger.kernel.org
Signed-off-by: Christoph Hellwig
Signed-off-by: J. Bruce Fields
26 Mar, 2015
1 commit
-
When testing pnfs with nfsd_debug on, nfsd print a negative number
of layout length and foff in nfsd4_block_proc_layoutget as,
"GET: -xxxx:-xxx 2"Signed-off-by: Kinglong Mee
Reviewed-by: Christoph Hellwig
Signed-off-by: J. Bruce Fields
05 Feb, 2015
1 commit
-
Add a small shim between core nfsd and filesystems to translate the
somewhat cumbersome pNFS data structures and semantics to something
more palatable for Linux filesystems.Thanks to Rick McNeal for the old prototype pNFS blocklayout server
code, which gave a lot of inspiration to this version even if no
code is left from it.Signed-off-by: Christoph Hellwig