RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-01-10 13:10:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
10,925 Commits 213 Branches 394 Tags 1.2 GiB
810ff49974
Commit Graph

10925 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sage Weil
6aa32f8c26 Merge remote branch 'origin/debian' into unstable 2010-07-21 13:30:02 -07:00
Yehuda Sadeh
93a2ba8ea2 rgw: fix calls to finish_get_obj() with uninitialized handle 2010-07-21 11:03:36 -07:00
Sage Weil
0bd671f734 debian: drop unused *.modules.in 2010-07-21 09:31:57 -07:00
Sage Weil
68fc3fc884 debian: no more ceph-kclient-soruce 2010-07-21 09:27:49 -07:00
Sage Weil
dd9d23b3a1 debian: cleanup from Clint Byrum <clint@ubuntu.com> 
With a few changes by me (changelog, copyright clarification)
 2010-07-21 09:27:49 -07:00
Sage Weil
ef2ecdab6c fuse.cc: make license GPL 
Originally based on Miklos' fusexmp.c, which is GPL.  Keep that license.
LGPL makes no sense here anyway.
 2010-07-21 09:27:49 -07:00
Sage Weil
6cb3ea762b mon: specify default new pool size/rule/pg_num in conf 2010-07-20 15:07:12 -07:00
Sage Weil
24c7516700 clean up new pool crush rule values [backward compatible protocol change] 
Default to -1 (not 0!), which means 'server default'.
 2010-07-20 15:07:12 -07:00
Sage Weil
9ddb6ab27d osd: infer missing map is empty when last_complete==last_update 2010-07-20 13:24:38 -07:00
Sage Weil
e8eec86c98 mon: set/clear pause{rd,wr} osdmap flags 2010-07-20 13:24:38 -07:00
Sage Weil
856999eda4 osd: clear failure_queue when marked down 
This prevents bleed through of failures (due to not getting hearbeats, due
to us being marked down) so they don't get sent after we are marked back
up again.

This fixes one possible source of up/down flapping...
 2010-07-20 13:24:38 -07:00
Sage Weil
618f7f25db osd: clean up pulling first/complete business 2010-07-20 12:39:42 -07:00
Sage Weil
462476404d osd: push in chunks 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-20 12:30:53 -07:00
Yehuda Sadeh
f3eb96457b rgw: fix content-length reporting 
and also some other various issues that came up while at it
 2010-07-20 12:13:27 -07:00
Sage Weil
190df1c66f debug: fix log append 
ios::ate does not work as advertised!

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-20 10:38:26 -07:00
Sage Weil
538ceedcc8 debug: say 'append' or 'new' when opening log 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-20 10:36:35 -07:00
Sage Weil
2483096e66 osd: wait for non-existant pools (w/o crashing); clean up handle_op() 
Make sure the pool exists before calling OSDMap::raw_pg_to_pg().  Fixes
crash on operations shortly after pg pools are created.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-20 10:25:34 -07:00
Yehuda Sadeh
a0cd80cfbf rgw: fix copy 2010-07-19 17:20:53 -07:00
Yehuda Sadeh
925e209248 rgw: get/put read and write by chunks 2010-07-19 16:50:43 -07:00
Sage Weil
1e30deaaa1 osd: refactor push code 
- send_push_op() does a push, nothing else
- push_start() starts a primary->replica push, tracks state
- push_to_replica() ensures we push head first, calculates cloning, etc.
 2010-07-19 16:22:52 -07:00
Yehuda Sadeh
eed7f726c5 rgw: lay groundwork for chunky read/write 2010-07-19 16:20:54 -07:00
Sage Weil
1d2018320d osd: recover degraded objects _before_ modifying it 
This will slow down writes to degraded objects because we will wait for it
to recover before applying the write.  OTOH it will be robust in the case
of large objects.  We can optimize the small object update (and overwrite)
cases later.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-19 14:44:09 -07:00
Sage Weil
2e521b82cc osd: make client op version actual at_version 
I.e. this should take into account any cloning.  So set it after we call
prepare_transaction, not before.
 2010-07-19 13:42:31 -07:00
Sage Weil
f7cc6e8f9d osd: fix subop version in snaptrimmer 
The at_version should end equal to last_update, not +1.
 2010-07-19 13:42:30 -07:00
Sage Weil
71ff557f32 osd: observe osd_recovery_max_chunk when pulling objects to primary 2010-07-19 13:08:10 -07:00
Sage Weil
be8359ad22 intervalset: implement span_of() 2010-07-19 13:06:48 -07:00
Sage Weil
2e137c9a0f osd: clean out temp pg on startup 2010-07-19 10:48:48 -07:00
Sage Weil
e0b6255750 osd: create temp collection during mkfs 2010-07-19 10:44:11 -07:00
Sage Weil
a108774e03 osd: give coll_t an explicit type in {meta,temp,pg} 2010-07-19 10:40:12 -07:00
Sage Weil
b4b6a82432 osd: add osd_recovery_max_chunk 2010-07-19 10:15:04 -07:00
Sage Weil
0b366744ae mon: check command length on osdmon 
Fixes crash on 'ceph osd tell'.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-19 10:13:36 -07:00
Yehuda Sadeh
bf8aa18d48 rbd: add removal of snapshots 2010-07-19 10:20:43 -07:00
Greg Farnum
9810f7eab7 librados: don't read attributes until the callback is done! 2010-07-16 16:18:44 -07:00
Greg Farnum
7315f4fc84 rgw: rgw_rest: Properly return the content-length. 
From wido.
 2010-07-16 16:18:44 -07:00
Greg Farnum
344c43184c rgw: rgw_rados: initialize the position in list_buckets_init! 2010-07-16 16:18:44 -07:00
Sage Weil
bee69c8802 monc: be quiet about 'continuing hunt' too 2010-07-16 14:03:47 -07:00
Yehuda Sadeh
f00992c9c7 librados: librados.hpp should be standalone 
removed references to object_t, declared librados::SnapContext
 2010-07-16 14:05:59 -07:00
Sage Weil
0656d0f0a4 mds: small EMetablob fixup 
Push to the back, update the back.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 12:03:26 -07:00
Sage Weil
fdd79de60b osd: always set snapset context if can_create 
The most common code paths loaded it, but not the case where the obc was
already loaded.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 12:02:25 -07:00
Sage Weil
8ea9cd5956 mds: journal dirty items in order 
There was some weird thing where dirty items were added to the front of
the list in the EMetaBlob, dating from 2007.  I have no idea why.  But it
was breaking rename, which dirties the same inode twice in some cases
(same src and dst dir).  Since it would replay in reverse, the inode would
end up with an older state.  If that happened to be the last time the inode
was modified in the journal prior to an mds restart+replay, we'd get bad
dirstat/rstat metadata.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 11:43:42 -07:00
Sage Weil
1ac265f8b3 mds: helpful journal replay debug output 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 11:43:42 -07:00
Sage Weil
63642224df client: drop unnecessary #include 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 11:43:42 -07:00
Sage Weil
74e3d79681 mds: simplify rstat/dirstat debug printing 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 11:43:42 -07:00
Sage Weil
00fae3a258 mds: remove bogus 'oldest snap' floor on lssnap result 
I suspect the intent was to exclude snaps from parents from before we
existed.  However, get_snap_info() already does that intelligently.  And
get_oldest_snap() was wrong: this dirs snaps have little to do with
the nested snaprealms, old_inodes isn't a good indicator of birth time,
etc.

This fixes a bug where we couldn't see a snap in .snaps, but after the mds
restart could (because old_inodes included more old versions after
replay).

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-16 11:43:42 -07:00
Christian Brunner
eb1738703d lower loglevel for successfull mon hunting 
I'm receving log output on every rados_initialize (... found mon0).
Since this makes the qemu-iotests fail, I'd suggest to lower the loglevel.

Christian
 2010-07-16 11:38:19 -07:00
Greg Farnum
cf02db4288 messages: fix MClientRequest::is_write(), rename to may_write(). 
Also remove unused can_forward(), auth_is_best().
 2010-07-16 09:56:40 -07:00
Sage Weil
2d358a4c4c msgr: use in6addr_any extern for is_blank_addr() 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-15 14:51:29 -07:00
Sage Weil
0d9b998d18 msgr: put brackets around ipv6 addrs 
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-15 14:51:29 -07:00
Sage Weil
5f6d077abb mds: throw std::bad_alloc on boost:pool<> depletion 
A bit more informative than a segfault from this=NULL in the constructor.

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-07-15 14:51:29 -07:00
Yehuda Sadeh
1f7e11aaf0 rbd: fix usage 2010-07-15 14:50:33 -07:00