RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-16 07:17:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,814 Commits 216 Branches 0 Tags 1.2 GiB
5eb8ef7f11
Commit Graph

11814 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Greg Farnum
7bb31f75a3 osdc: Fix release_all so it loops properly 2010-10-25 16:45:56 -07:00
Yehuda Sadeh
e27f0b1e62 filestore: escape the xattr chunk names 2010-10-25 16:36:24 -07:00
Colin Patrick McCabe
961d3bc4d9 PG::Log::Entry: remove unused snap_t field 
The snap_t information is stored in the sobject_t field now.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-25 15:24:33 -07:00
Greg Farnum
61b3fc354c makefile: add cephfs 2010-10-25 13:42:24 -07:00
Colin Patrick McCabe
d4bbde5ab1 ./ceph osd setcrushmap: validate crushmap 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-25 12:31:49 -07:00
Colin Patrick McCabe
394b0712bc crush: improve error handling in map decoding 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-25 12:08:30 -07:00
Colin Patrick McCabe
a869b35abd cap_reconnect_t: ignore embedded NULLs in the path 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-24 14:28:14 -07:00
Sage Weil
e912e686de v0.22.1 2010-10-23 10:49:50 -07:00
Sage Weil
96d467377c Makefile: add errno.h 2010-10-23 10:17:44 -07:00
Sage Weil
a974cfda90 mds: be quiet about snaprealm push/pop 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-10-23 10:17:29 -07:00
Sage Weil
6907894671 filestore: ignore ENOSPC on setxattr pending a better workaround 
This effectively reverts to old behavior (we weren't checking for ENOSPC
errors at all before).  Log which object it happened on.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-10-22 16:06:19 -07:00
Yehuda Sadeh
6826ce4a8e filestore: change xattr chunk size to 2048 2010-10-22 15:55:32 -07:00
Yehuda Sadeh
76157d91ab filestore: split xattrs to multiple chunks 2010-10-22 15:55:24 -07:00
Yehuda Sadeh
3ee37ee730 rados: add getxattr, setxattr 2010-10-22 15:55:14 -07:00
Yehuda Sadeh
22bb21188d filestore: change xattr chunk size to 2048 2010-10-22 15:52:58 -07:00
Greg Farnum
b4fd986a2e mds: Remove scatter_pins. 
We used these to prevent freezing a tree during gather-scatter ops,
but now we can just go stale on data when a scatter finishes.
Hurray simpler code that goes into try-undo loops less often!
 2010-10-22 15:51:23 -07:00
Greg Farnum
db6759fe0a mds: use set_stale() as appropriate: 
1) When we update a lock but can't write its new data,
2) We load potentially-stale data off disk (ie, in restart).
 2010-10-22 15:51:23 -07:00
Greg Farnum
47a5fc95f3 mds: Whenever we set locks to state LOCK_MIX, check is_stale() 
and set to state LOCK_MIX_STALE instead, if necessary.
 2010-10-22 15:51:23 -07:00
Greg Farnum
372e8b3ecf mds: Add bool "dirty" to ScatterLock, plus manipulation functions. 
Also add is_dirty() to SimpleLock so we don't need typing in these checks.

This lets us set that a dirfrag's accounting data is dirty and we
have to enter LOCK_MIX_STALE instead of LOCK_MIX.
 2010-10-22 15:51:23 -07:00
Greg Farnum
f893a63b06 mds: rename Locker::file_mixed to scatter_mix 2010-10-22 15:51:23 -07:00
Greg Farnum
512a1da9af mds: Check for LOCK_MIX_STALE along with LOCK_MIX 
LOCK_MIX_STALE precludes writing to the protected data, but
in general cases it's an acceptable state whenever LOCK_MIX is.

Add checks for LOCK_MIX_STALE to asserts and if statements that
match those for LOCK_MIX.
 2010-10-22 15:51:23 -07:00
Greg Farnum
557e7e34af mds: Add new LOCK_MIX_STALE state to lock structs. 2010-10-22 15:51:23 -07:00
Yehuda Sadeh
9d4f7b8e77 librados: add rmxattr 2010-10-22 14:33:17 -07:00
Greg Farnum
429b2d9954 Revert "messenger: Make sure to unlock existing->pipe_lock. There are a few cases in the "open" section where we can go to fail_unlocked while still holding existing->pipe_lock. So unlock it." 
This reverts commit 96692d24c8.
This patch accidentally got merged into the tree twice, so
merging issues came up.
 2010-10-22 13:36:30 -07:00
Colin Patrick McCabe
242b5992f3 test_lost.sh: put common functions in test_common 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-22 11:50:25 -07:00
Greg Farnum
55fcbc649c Merge branch 'msgr' into unstable 2010-10-22 11:24:24 -07:00
Greg Farnum
696da81588 messenger: If we error out of accept() but have messages in our queue, save Pipe. 
This can occur if we're replacing another Pipe and hit an error
in the process.
 2010-10-22 11:16:24 -07:00
Greg Farnum
49d8fd8a21 messenger: If we're replacing an existing Pipe, steal queue when we kill it! 
Previously we could fail out after killing existing but before
splicing its queue into our own, which lost messages.
 2010-10-22 11:15:22 -07:00
Colin Patrick McCabe
bf0d347d43 PG::peer: introduce prior_set_build flag 
Just because we have prior_set.empty() doesn't mean that the prior set
wasn't built. Create a flag to represent this concept.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-22 11:01:15 -07:00
Yehuda Sadeh
b8c0d3dfea filestore: update btrfs_ioctl.h 2010-10-22 10:16:29 -07:00
Yehuda Sadeh
1a7a341dab filestore: use different encoding for snap async_create 2010-10-22 10:16:25 -07:00
Sage Weil
bb451d202b filestore: use SNAP_DESTROY_ASYNC ioctl if available 2010-10-22 10:16:20 -07:00
Sage Weil
a3d8c1ffd1 filestore: remove stray async_snap_test if present 
This cleans up if a prior instance failed to delete its
async_snap_test subvol.
 2010-10-22 10:16:17 -07:00
Sage Weil
953ef1da8a filestore: use new async btrfs ioctls 2010-10-22 10:16:13 -07:00
Sage Weil
78352b32cd osd: fix deadlock in map handler 
To avoid deadlock,
- we need to drop osd_lock while we flush.
- we need to take map_lock _after_ we flush.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-10-22 10:11:21 -07:00
Yehuda Sadeh
f96eb80522 filestore: split xattrs to multiple chunks 2010-10-22 10:10:20 -07:00
Yehuda Sadeh
515efd5a2f rados: add getxattr, setxattr 2010-10-22 10:10:20 -07:00
Sage Weil
6a88d572f2 mds: implement 'fragment_dir path frag by' command 
For testing dir fragmentation.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-10-21 21:45:27 -07:00
Sage Weil
b4f8232878 Merge branch 'testing' into unstable 2010-10-21 21:38:21 -07:00
Colin Patrick McCabe
7207476e00 PG::recover_master_log: replace count with find 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
3cbeaa1479 prior_set_affected: log msg when we see a lost osd 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
17c615c003 osd: build_prior: clean up started_since_joining 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
831075c4e1 osd: PG::prior_set_affected: fix lost OSD detection 
When looking for newly-lost OSDs, we should check prior_set_lost rather
than prior_set. Down OSDs often are in PG::prior_set_down and NOT in
PG::prior_set.

Also update comment for prior_set_down. Sometimes OSDs are in both
PG::prior_set and PG::prior_set_down.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
399d31fa1d test_lost.sh: ensure that recovery doesn't start. 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
881bf02dd1 include/utime.h: should include include/types.h 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Sage Weil
dec5b787c7 errno: add missing common/errno.h 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
ce050ef67a Create cpp_strerror to make error reporting easier 
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:59 -07:00
Colin Patrick McCabe
3d94b6afb5 FileJournal: fix journal size calculation 
If the journal is a raw block device, the user shouldn't need to give a
journal size argument most of the time-- it should default to using the
entire block device. This was the old default but it got changed
erroneously by commit ad12d5d5be.

Along the way, I split the FileJournal::_open code into multiple
functions, and added some additional checks. We no longer try block
device ioctls on regular files. We now check for block devices that are
too small.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
 2010-10-21 17:31:58 -07:00
Sage Weil
4d1b9e6960 makefile: simplify cdebugpack install rule 2010-10-21 17:31:58 -07:00
Sage Weil
9c59a6aab5 debian: 0.22-4 2010-10-21 17:31:58 -07:00