Sage Weil
f48ed5f2e1
todos
2008-11-06 10:56:51 -08:00
Sage Weil
616dcd1e27
vstart.sh
2008-11-05 14:55:08 -08:00
Sage Weil
b592adae31
crush todos
2008-10-31 14:09:51 -07:00
Sage Weil
656e92e3b1
crush todo
2008-10-31 12:49:46 -07:00
Sage Weil
3ec5dce2e7
Merge commit 'origin/unstable' into recovery
2008-10-27 10:03:30 -07:00
Sage Weil
44c9462b2d
kclient: flush cap_snaps on session close
2008-10-22 12:35:43 -07:00
Sage Weil
2997c91f32
mds todo
2008-10-20 15:37:49 -07:00
Sage Weil
5424a3375a
kclient: messenger.c cleanup, reorganization, comments
2008-10-17 20:47:07 -07:00
Sage Weil
57709b27a1
osd todos
2008-10-17 13:36:15 -07:00
Sage Weil
8f92c35e4f
mds: only check osdmap against snap table while active
2008-10-17 13:30:33 -07:00
Sage Weil
0f03831792
kclient: addr.c comments, cleanup
...
I'm leaving the ability to redirty a page within a given
snapc in ceph_set_page_dirty (even though it isn't used)
because I'm not sure about the failure paths.. I suspect
we will need it later.
2008-10-16 16:34:44 -07:00
Sage Weil
be2927058d
kclient: more mds_client comments, cleanup
2008-10-16 12:14:25 -07:00
Sage Weil
000defc5c2
kclient: caps.c comments, cleanup
2008-10-15 16:38:03 -07:00
Sage Weil
1ed5520657
use flags for mds chown requests
...
This avoids colliding with uids of -1 (with the old, lame method).
Clean up client's utimes() code while we're at it to explicitly specify
a mask.
2008-10-15 12:13:35 -07:00
Sage Weil
e683417565
kclient: inode.c comments, cleanup
2008-10-15 12:13:35 -07:00
Sage Weil
81bfddd2f7
kclient: remove static caps from inode
...
Since most inodes will never have a capability, there is no point in embedding them
in the ceph_inode_info and paying the memory overhead in the general case.
2008-10-14 16:18:24 -07:00
Sage Weil
5d184bd6ad
kclient: super.h comments, cleanup, some minor cruft removed
2008-10-14 16:15:54 -07:00
Sage Weil
ae0daf01c4
kclient: resend osd requests if osd resets the connection
2008-10-13 17:19:30 -07:00
Sage Weil
ab9054d812
Merge commit 'origin/unstable' into recovery
2008-10-13 12:03:49 -07:00
Sage Weil
c4d2160635
msgr: track lossy mode independently for self, peer
...
The policy will be asymmetrical for the OSDs, so we need to
track it independently.
The various assertions aren't all worked out yet. Notably,
connection races aren't quite right. But the basic bits
are there.
2008-10-13 12:02:27 -07:00
Sage Weil
cbe084d77d
todos
2008-10-08 16:45:31 -07:00
Sage Weil
c3a68d7424
msgr: include priority in msg header, make dispatch a priority queue
...
Generalizes previous hack that put messages from the monitor at the front of the
dispatch queue. Monitor now just sets a (non-default) default_send_priority
of CEPH_MSG_PRIO_HIGH. That value is used only if the message priority isn't
set explicitly by set_priority() before being queued for send.
2008-10-08 10:49:12 -07:00
Sage Weil
3e5266f968
Merge branch 'unstable' into recovery
...
Conflicts:
src/osd/ReplicatedPG.cc
2008-10-07 14:08:24 -07:00
Sage Weil
403f64341d
todos
2008-10-02 22:21:50 -07:00
Sage Weil
cefdb4e540
todos
2008-10-02 11:15:27 -07:00
Sage Weil
d05dfe81a7
kclient: mds reset stub
...
Get rid of compile warning. Add todo.
2008-10-02 11:15:26 -07:00
Sage Weil
2909ef79ce
v0.4, todos
2008-10-01 11:53:38 -07:00
Sage Weil
b01d902b3c
Merge branch 'unstable' into recovery
2008-09-30 13:20:04 -07:00
Sage Weil
750c94411e
todos
2008-09-29 13:52:28 -07:00
Sage Weil
9bae2a4b92
osd: include old version in missing map
...
The primary will need to know the existing (old) version of objects on replicas to efficiently deal with clones or partial pushes..
2008-09-20 16:57:58 -07:00
Sage Weil
2111e5ec2a
Merge branch 'unstable' into recovery
2008-09-20 15:13:17 -07:00
Sage Weil
8ecd757767
kclient: time out mds session close on umount. messily.
...
This at least won't hang, but it will leave inodes pinned after umount, so it still needs some real work.
2008-09-20 13:51:12 -07:00
Sage Weil
17128988e1
kclient: unify mount timeouts
...
Make both mon map and mount messages and mds session, root inode open time out. Previously the mon interaction would time out but we could hang on a non-responsive (e.g., not active) mds.
2008-09-20 13:34:11 -07:00
Sage Weil
c95f010a1e
todos
2008-09-20 12:37:46 -07:00
Sage Weil
a0eb5e7d91
todos
2008-09-18 15:39:54 -07:00
Sage Weil
fb8cf71e27
todo
2008-09-17 15:05:35 -07:00
Sage Weil
1cc73c210a
fixes
2008-09-16 16:36:12 -07:00
Sage Weil
43e7e39972
osd: push/pull data_subset, clone_subsets
2008-09-16 14:44:47 -07:00
Sage Weil
07c3f0138f
kclient: fill in kstatfs f_fsid
2008-09-12 12:46:43 -07:00
Sage Weil
37c3ad36d4
journal: journal rewrite
2008-09-11 16:58:27 -07:00
Sage Weil
bfb5b8d9bd
osd: some snap_trimmer fixes
2008-09-10 15:53:00 -07:00
Sage Weil
d4fad4c867
kclient: some todos
2008-09-10 13:01:36 -07:00
Sage Weil
60965364e5
mds: recover file size for all affected snapshots, not just the head
2008-09-10 12:16:46 -07:00
Sage Weil
32906d5dfb
todos
2008-09-09 11:32:57 -07:00
Sage Weil
0629e502ec
todos
2008-09-08 14:38:58 -07:00
Sage Weil
6aeb28804a
kclient: no short read in ceph_osdc_sync_read
2008-09-08 14:38:58 -07:00
Sage Weil
b1da940952
kclient: some writepage cleanup
2008-08-22 15:33:24 -07:00
Sage Weil
3a3c48f54f
kclient: page_mkwrite, improved dirty page accounting
2008-08-22 14:07:41 -07:00
Sage Weil
7e66635361
kclient: mmap/page_mkwrite shell
2008-08-22 11:15:35 -07:00
Sage Weil
9258ee9f9c
todos
2008-08-21 09:40:16 -07:00
