linux-stable.git/fs/ceph, branch v3.12

ceph: use d_invalidate() to invalidate aliases

2013-09-06T19:55:29+00:00

d_invalidate() is the standard VFS method to invalidate dentry.
compare to d_delete(), it also try shrinking children dentries.

Signed-off-by: Yan, Zheng 
Reviewed-by: Sage Weil

ceph: remove ceph_lookup_inode()

2013-09-06T19:55:09+00:00

commit 6f60f889 (ceph: fix freeing inode vs removing session caps race)
introduced ceph_lookup_inode(). But there is already a ceph_find_inode()
which provides similar function. So remove ceph_lookup_inode(), use
ceph_find_inode() instead.

Signed-off-by: Yan, Zheng 
Reviewed-by: Alex Elder 
Reviewed-by: Sage Weil

ceph: trivial buildbot warnings fix

2013-09-06T16:50:12+00:00

The linux-next build bot found a three of warnings, this addresses all of them.

 * non-ANSI function declaration of function 'ceph_fscache_register' and
   'ceph_fscache_unregister'
 * symbol 'ceph_cache_netfs' was not declared, now it's extern in the header.
 * warning: "pr_fmt" redefined

Signed-off-by: Milosz Tanski

ceph: Do not do invalidate if the filesystem is mounted nofsc

2013-09-06T16:50:12+00:00

Previously we would always try to enqueue work even if the filesystem is not
mounted with fscache enabled (or the file has no cookie). In the case of the
filesystem mouned nofsc (but with fscache compiled in) this would lead to a
crash.

Signed-off-by: Milosz Tanski

ceph: page still marked private_2

2013-09-06T16:50:12+00:00

Previous patch that allowed us to cleanup most of the issues with pages marked
as private_2 when calling ceph_readpages. However, there seams to be a case in
the error case clean up in start read that still trigers this from time to
time. I've only seen this one a couple times.

BUG: Bad page state in process petabucket  pfn:335b82
page:ffffea000cd6e080 count:0 mapcount:0 mapping:          (null) index:0x0
page flags: 0x200000000001000(private_2)
Call Trace:
 [] dump_stack+0x46/0x58
 [] bad_page+0xc7/0x120
 [] free_pages_prepare+0x10e/0x120
 [] free_hot_cold_page+0x40/0x160
 [] __put_single_page+0x27/0x30
 [] put_page+0x25/0x40
 [] ceph_readpages+0x2e9/0x6f0 [ceph]
 [] __do_page_cache_readahead+0x1af/0x260

Signed-off-by: Milosz Tanski 
Signed-off-by: Sage Weil

ceph: ceph_readpage_to_fscache didn't check if marked

2013-09-06T16:50:12+00:00

Previously ceph_readpage_to_fscache did not call if page was marked as cached
before calling fscache_write_page resulting in a BUG inside of fscache.

FS-Cache: Assertion failed
------------[ cut here ]------------
kernel BUG at fs/fscache/page.c:874!
invalid opcode: 0000 [#1] SMP
Call Trace:
 [] __ceph_readpage_to_fscache+0x66/0x80 [ceph]
 [] readpage_nounlock+0x124/0x210 [ceph]
 [] ceph_readpage+0x1d/0x40 [ceph]
 [] generic_file_aio_read+0x1f6/0x700
 [] ceph_aio_read+0x5fc/0xab0 [ceph]

Signed-off-by: Milosz Tanski 
Signed-off-by: Sage Weil

ceph: clean PgPrivate2 on returning from readpages

2013-09-06T16:50:11+00:00

In some cases the ceph readapages code code bails without filling all the pages
already marked by fscache. When we return back to readahead code this causes
a BUG.

Signed-off-by: Milosz Tanski

ceph: use fscache as a local presisent cache

2013-09-06T16:50:11+00:00

Adding support for fscache to the Ceph filesystem. This would bring it to on
par with some of the other network filesystems in Linux (like NFS, AFS, etc...)

In order to mount the filesystem with fscache the 'fsc' mount option must be
passed.

Signed-off-by: Milosz Tanski 
Signed-off-by: Sage Weil

ceph: use vfs __set_page_dirty_nobuffers interface instead of doing it inside filesystem

2013-08-27T23:29:44+00:00

Following we will begin to add memcg dirty page accounting around
__set_page_dirty_{buffers,nobuffers} in vfs layer, so we'd better use vfs interface to
avoid exporting those details to filesystems.

Since vfs set_page_dirty() should be called under page lock, here we don't need elaborate
codes to handle racy anymore, and two WARN_ON() are added to detect such exceptions.
Thanks very much for Sage and Yan Zheng's coaching!

I tested it in a two server's ceph environment that one is client and the other is
mds/osd/mon, and run the following fsx test from xfstests:

  ./fsx   1MB -N 50000 -p 10000 -l 1048576
  ./fsx  10MB -N 50000 -p 10000 -l 10485760
  ./fsx 100MB -N 50000 -p 10000 -l 104857600

The fsx does lots of mmap-read/mmap-write/truncate operations and the tests completed
successfully without triggering any of WARN_ON.

Signed-off-by: Sha Zhengju 
Reviewed-by: Sage Weil

ceph: allow sync_read/write return partial successed size of read/write.

2013-08-27T19:28:46+00:00

For sync_read/write, it may do multi stripe operations.If one of those
met erro, we return the former successed size rather than a error value.
There is a exception for write-operation met -EOLDSNAPC.If this occur,we
retry the whole write again.

Signed-off-by: Jianpeng Ma