30 May, 2011
29 commits
-
* 'pnfs-submit' of git://git.open-osd.org/linux-open-osd: (32 commits)
pnfs-obj: pg_test check for max_io_size
NFSv4.1: define nfs_generic_pg_test
NFSv4.1: use pnfs_generic_pg_test directly by layout driver
NFSv4.1: change pg_test return type to bool
NFSv4.1: unify pnfs_pageio_init functions
pnfs-obj: objlayout_encode_layoutcommit implementation
pnfs: encode_layoutcommit
pnfs-obj: report errors and .encode_layoutreturn Implementation.
pnfs: encode_layoutreturn
pnfs: layoutret_on_setattr
pnfs: layoutreturn
pnfs-obj: osd raid engine read/write implementation
pnfs: support for non-rpc layout drivers
pnfs-obj: define per-inode private structure
pnfs: alloc and free layout_hdr layoutdriver methods
pnfs-obj: objio_osd device information retrieval and caching
pnfs-obj: decode layout, alloc/free lseg
pnfs-obj: pnfs_osd XDR client implementation
pnfs-obj: pnfs_osd XDR definitions
pnfs-obj: objlayoutdriver module skeleton
... -
* 'nfs-for-2.6.40' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
SUNRPC: Support for RPC over AF_LOCAL transports
SUNRPC: Remove obsolete comment
SUNRPC: Use AF_LOCAL for rpcbind upcalls
SUNRPC: Clean up use of curly braces in switch cases
NFS: Revert NFSROOT default mount options
SUNRPC: Rename xs_encode_tcp_fragment_header()
nfs,rcu: convert call_rcu(nfs_free_delegation_callback) to kfree_rcu()
nfs41: Correct offset for LAYOUTCOMMIT
NFS: nfs_update_inode: print current and new inode size in debug output
NFSv4.1: Fix the handling of NFS4ERR_SEQ_MISORDERED errors
NFSv4: Handle expired stateids when the lease is still valid
SUNRPC: Deal with the lack of a SYN_SENT sk->sk_state_change callback... -
Implement pg_test vector to test for max IO sizes. We calculate
a max_io_size member only once, and cache it in lseg so to not
do so on every page insert.Signed-off-by: Boaz Harrosh
[simplify logic]
Signed-off-by: Benny Halevy -
By default, unless pnfs is used coalesce pages until pg_bsize
(rsize or wsize) is reached.pnfs layout drivers define their own pg_test methods that use
pnfs_generic_pg_test and need to define their own I/O size
limits (e.g. based on the file stripe size).[Move a check from nfs_pageio_do_add_request to nfs_generic_pg_test]
Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
Signed-off-by: Benny Halevy
-
Signed-off-by: Benny Halevy
-
Use common code for pnfs_pageio_init_{read,write} and use
a common generic pg_test function.Note that this function always assumes the the layout driver's
pg_test method is implemented.[Fix BUG]
Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
* Define API for io-engines to report delta_space_used in IOs
* Encode the osd-layout specific information of the layoutcommit
XDR buffer.Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
Add a layout driver method to encode the layout type specific
opaque part of layout commit in-line in the xdr stream.Currently, the pnfs-objects layout driver uses it to encode metadata hints
to the MDS and the blocks layout driver to commit provisionally allocated
extents to the file.Signed-off-by: Benny Halevy
-
An io_state pre-allocates an error information structure for each
possible osd-device that might error during IO. When IO is done if all
was well the io_state is freed. (as today). If the I/O has ended with an
error, the io_state is queued on a per-layout err_list. When eventually
encode_layoutreturn() is called, each error is properly encoded on the
XDR buffer and only then the io_state is removed from err_list and
de-allocated.It is up to the io_engine to fill in the segment that fault and the type
of osd_error that occurred. By calling objlayout_io_set_result() for
each failing device.In objio_osd:
* Allocate io-error descriptors space as part of io_state
* Use generic objlayout error reporting at end of io.Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
Add a layout driver method to encode the layout type specific
opaque part of layout return in-line in the xdr stream.Currently the pnfs-objects layout driver uses it to encode i/o error
information on LAYOUTRETURN.Signed-off-by: Andy Adamson
[fixup layout header pointer for encode_layoutreturn]
Signed-off-by: Benny Halevy -
With the objects layout security model, we have object capabilities
that are associated with the layout and we anticipate that the server
will issue a cb_layoutrecall for any setattr that changes security
related attributes (user/group/mode/acl) or truncates the file.Therefore, the layout is returned before issuing the setattr to avoid
the anticipated cb_layoutrecall.Signed-off-by: Benny Halevy
-
NFSv4.1 LAYOUTRETURN implementation
Currently, does not support layout-type payload encoding.
Signed-off-by: Alexandros Batsakis
Signed-off-by: Andy Adamson
Signed-off-by: Andy Adamson
Signed-off-by: Dean Hildebrand
Signed-off-by: Fred Isaman
Signed-off-by: Fred Isaman
Signed-off-by: Marc Eshel
Signed-off-by: Zhang Jingwang
[call pnfs_return_layout right before pnfs_destroy_layout]
[remove assert_spin_locked from pnfs_clear_lseg_list]
[remove wait parameter from the layoutreturn path.]
[remove return_type field from nfs4_layoutreturn_args]
[remove range from nfs4_layoutreturn_args]
[no need to send layoutcommit from _pnfs_return_layout]
[don't wait on sync layoutreturn]
[fix layout stateid in layoutreturn args]
[fixed NULL deref in _pnfs_return_layout]
[removed recaim member of nfs4_layoutreturn_args]
Signed-off-by: Benny Halevy -
With the use of the in-kernel osd library. Implement read/write
of data from/to osd-objects according to information specified
in the objects-layout.Support for stripping over mirrors with a received stripe_unit.
There are however a few constrains which are not supported:
1. Stripe Unit must be a multiple of PAGE_SIZE
2. stripe length (stripe_unit * number_of_stripes) can not be
bigger then 32bit.Also support raid-groups and partial-layout. Partial-layout is
when not all the groups are received on the line, addressing
only a partial range of the file.TODO:
Only raid0! raid 4/5/6 support will come at later stageA none supported layout will send IO through the MDS
[Important fallout from the last rebase]
Signed-off-by: Boaz Harrosh
[gfp_flags]
Signed-off-by: Benny Halevy -
Non-rpc layout driver such as for objects and blocks
implement their own I/O path and error handling logic.
Therefore bypass NFS-based error handling for these layout drivers.[fix lseg ref-count bugs, and null de-refs]
[Fall out from: non-rpc layout drivers]
Signed-off-by: Boaz Harrosh
[get rid of PNFS_USE_RPC_CODE]
[get rid of __nfs4_write_done_cb]
[revert useless change in nfs4_write_done_cb]
Signed-off-by: Benny Halevy -
allocate and deallocate per-inode private pnfs_layout_hdr
in preparation for I/O implementation.Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
[gfp_flags]
Signed-off-by: Benny Halevy -
When a new layout is received in objio_alloc_lseg all device_ids
referenced are retrieved. The device information is queried for from MDS
and then the osd_device is looked-up from the osd-initiator library. The
devices are cached in a per-mount-point list, for later use. At unmount
all devices are "put" back to the library.objlayout_get_deviceinfo(), objlayout_put_deviceinfo() middleware
API for retrieving device information given a device_id.TODO: The device cache can get big. Cap its size. Keep an LRU and start
to return devices which were not used, when list gets to big, or
when new entries allocation fail.[pnfs-obj: Bugs in new global-device-cache code]
Signed-off-by: Boaz Harrosh
[gfp_flags]
[use global device cache]
[use layout driver in global device cache]
Signed-off-by: Benny Halevy -
objlayout_alloc_lseg prepares an xdr_stream and calls the
raid engins objio_alloc_lseg() to allocate a private
pnfs_layout_segment.objio_osd.c::objio_alloc_lseg() uses passed xdr_stream to
decode and store the layout_segment information in an
objio_segment struct, using the pnfs_osd_xdr.h API for
the actual parsing the layout xdr.objlayout_free_lseg calls objio_free_lseg() to free the
allocated space.Signed-off-by: Boaz Harrosh
[gfp_flags]
[removed "extern" from function definitions]
Signed-off-by: Benny Halevy -
* Add the fs/nfs/objlayout/pnfs_osd_xdr_cli.c file, which will
include the XDR encode/decode implementations for the pNFS
client objlayout driver.[Wrong type in comments]
Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
* Define the PNFS_OBJLAYOUT Kconfig option in the nfs
master Kconfig file.
* Add the objlayout driver to the Kernel's Kbuild system.
* Add the fs/nfs/objlayout/Kbuild file for building the
objlayoutdriver.ko driver
* Define fs/nfs/objlayout/objio_osd.c, register the driver on module
initialization and unregister on exit.[pnfs-obj: remove of CONFIG_PNFS fallout]
Signed-off-by: Boaz Harrosh
[added "unsure" clause]
[depend on NFS_V4_1]
Signed-off-by: Benny Halevy -
A pNFS client auto-negotiates a lot of features (minorversion level,
pNFS layout type, etc.). This is convenient, but makes certain kinds of
failures hard for a user to detect.For example, if the client falls back on 4.0, or falls back to MDS IO
because the user didn't connect to the right iscsi disks before
mounting, the only symptoms may be reduced performance, which may not be
noticed till long after the actual failure, and may be difficult for a
user to diagnose.However, such "failures" may also be perfectly normal in some cases, so
we don't want to spam the system logs with them.One approach would be to put some more information into
/proc/self/mountstats.Signed-off-by: J. Bruce Fields
Signed-off-by: Benny Halevy
[pnfs: add commit client stats]
[fixup data types for "ret" variables in pnfs_try_to* inline funcs.]
Signed-off-by: Benny Halevy
[fix definition of show_pnfs for !CONFIG_PNFS]
Signed-off-by: Benny Halevy
[nfs41: Fix show_sessions in the not CONFIG_NFS_V4_1 case]
There is a build error when CONFIG_NFS_V4 is set but
CONFIG_NFS_V4_1 is *not* set. show_sessions() prototype
was unbalanced between the two cases.
Signed-off-by: Boaz Harrosh
[pnfs: super.c remove CONFIG_PNFS]
Signed-off-by: Andy Adamson
Signed-off-by: Benny Halevy -
Use recalled range to invalidate particular layout segments in the layout cache.
Signed-off-by: Benny Halevy
-
Signed-off-by: Benny Halevy
-
Add offset and count parameters to pnfs_update_layout and use them to get
the layout in the pageio path.Order cache layout segments in the following order:
* offset (ascending)
* length (descending)
* iomode (RW before READ)Test byte range against the layout segment in use in pnfs_{read,write}_pg_test
so not to coalesce pages not using the same layout segment.[fix lseg ordering]
[clean up pnfs_find_lseg lseg arg]
[remove unnecessary FIXME]
[fix ordering in pnfs_insert_layout]
[clean up pnfs_insert_layout]
Signed-off-by: Benny Halevy -
Initialize xdr_stream and xdr_buf using an array of page pointers
and length of buffer.Signed-off-by: Benny Halevy
-
pnfs deviceids are unique per server, per layout type.
struct nfs_client is currently used to distinguish deviceids from
different nfs servers, yet these may clash between different layout
types on the same server. Therefore, use the layout driver associated
with each deviceid at insertion time to look it up, unhash, or
delete it.Signed-off-by: Benny Halevy
-
Note: This functionlaity is incomplete as all layout segments referring to
the 'to be removed device id' need to be reaped, and all in flight I/O drained.[use be32 res in nfs4_callback_devicenotify]
[use nfs_client to qualify deviceid for cb_notify_deviceid]
[use global deviceid cache for CB_NOTIFY_DEVICEID]
[refactor device cache _lookup_deviceid]
[refactor device cache _find_get_deviceid]
Signed-off-by: Benny Halevy
[Bug in new global-device-cache code]
[layout_driver MUST set free_deviceid_node if using dev-cache]
Signed-off-by: Boaz Harrosh
Signed-off-by: Benny Halevy -
Use the pnfs_layoutdriver_type both as a qualifier for the deviceid,
distinguishing deviceid from different layout types on the server,
and for freeing the layout-driver allocated structure containing the
nfs4_deviceid_node.[BUG in _deviceid_purge_client]
[layout_driver MUST set free_deviceid_node if using dev-cache]
[let ver < 4.1 compile]
Signed-off-by: Boaz Harrosh
[removed EXPORT_SYMBOL_GPL(nfs4_deviceid_purge_client)]
Signed-off-by: Benny Halevy
29 May, 2011
4 commits
-
Move deviceid cache from the pnfs files layout driver to the
generic layer in preparation for the objects layout driver.Signed-off-by: Benny Halevy
-
Some definitions in the header file depend on nfs_fs.h so pnfs.h can't
be included independently.Signed-off-by: Benny Halevy
-
deviceids are unique per server, per layout type.
Therefore, in the global cache in the files layout driver
deviceids from different servers may clash so we need
to qualify them with a struct nfs_client that represents
the nfs server that returned the deviceid.Introduced in 2.6.39 commit ea8eecdd
"NFSv4.1 move deviceid cache to filelayout driver"Signed-off-by: Benny Halevy
-
Signed-off-by: Jim Rees
Signed-off-by: Benny Halevy
28 May, 2011
6 commits
-
Marek Belisko reports that recent attempts
to fix regressions in NFSROOT have broken his configuration:> After update from 2.6.38-rc8 to 2.6.38 is mounting rootfs over nfs not possible.
> Log:
> VFS: Mounted root (nfs filesystem) on device 0:14.
> Freeing init memory: 132K
> nfs: server 10.146.1.21 not responding, still trying
> nfs: server 10.146.1.21 not responding, still trying
>
> This is never ending. I make short bisect (not too much commits
> between versions)
> and bad commit was reported: 53d4737580535e073963b91ce87d4216e434fab5
>
> NFS: NFSROOT should default to "proto=udp"
>
> I've tested on mini2440 board (DM9000, static IP).
> Is there some missing option or something else to be checked?An examination of a network trace captured during the failure shows
that the mount is actually succeeding, but that the client is not
seeing READ replies larger than 16KB. This could be a local packet
filtering issue on the client, but we didn't troubleshoot this
further because of the reported "git bisect" result.Last fall we removed the ad hoc mount option parser in
fs/nfs/nfsroot.c in favor of using the main parser in fs/nfs/super.c
(see commit 56463e50 "NFS: Use super.c for NFSROOT mount option
parsing"). That commit changed the default NFSROOT mount options to
be the same as those employed by user space mounts.As it turns out, these new default mount options are not tolerated by
many embedded systems. So far these problems have been due to
specific behavior of certain embedded NICs. The NFS community does
not have such hardware on hand for running tests.Commit 53d47375 recently introduced a clean way to specify default
mount options for NFSROOT, so we can now easily restore the
traditional defaults for NFSROOT:vers=2,udp,rsize=4096,wsize=4096
This should revert the new default NFSROOT mount options introduced
with commit 56463e50.Tested-by: Marek Belisto
Signed-off-by: Chuck Lever
Signed-off-by: Trond Myklebust -
The rcu callback nfs_free_delegation_callback() just calls a kfree(),
so we use kfree_rcu() instead of the call_rcu(nfs_free_delegation_callback).Signed-off-by: Lai Jiangshan
Signed-off-by: Paul E. McKenney
Cc: Trond Myklebust
Signed-off-by: Trond Myklebust -
A client sends offset to MDS as it was seen by DS. As result,
file size after copy is only half of original file size in case
of 2 DS.Signed-off-by: Vitaliy Gusev
Cc: stable@kernel.org [2.6.39]
Signed-off-by: Trond Myklebust -
Hi Trond,
In nfs_update_inode debug output, print the current and new inode
size when the file size changes on the NFS server.Signed-off-by: Harshula Jayasuriya
Reviewed-by: Jeff Layton
Signed-off-by: Trond Myklebust -
Currently, the call to nfs4_schedule_session_recovery() will actually just
result in a test of the lease when what we really want is to force a
session reset.Signed-off-by: Trond Myklebust
Cc: stable@kernel.org -
Currently, if the server returns NFS4ERR_EXPIRED in reply to a READ or
WRITE, but the RENEW test determines that the lease is still active, we
fail to recover and end up looping forever in a READ/WRITE + RENEW death
spiral.Signed-off-by: Trond Myklebust
Cc: stable@kernel.org
25 May, 2011
1 commit
-
Change each shrinker's API by consolidating the existing parameters into
shrink_control struct. This will simplify any further features added w/o
touching each file of shrinker.[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: fix warning]
[kosaki.motohiro@jp.fujitsu.com: fix up new shrinker API]
[akpm@linux-foundation.org: fix xfs warning]
[akpm@linux-foundation.org: update gfs2]
Signed-off-by: Ying Han
Cc: KOSAKI Motohiro
Cc: Minchan Kim
Acked-by: Pavel Emelyanov
Cc: KAMEZAWA Hiroyuki
Cc: Mel Gorman
Acked-by: Rik van Riel
Cc: Johannes Weiner
Cc: Hugh Dickins
Cc: Dave Hansen
Cc: Steven Whitehouse
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
