RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-01-11 13:41:02 +00:00
Code Issues Packages Projects Releases Wiki Activity
10,449 Commits 214 Branches 394 Tags 1.3 GiB
775506e9ac
Commit Graph

10449 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Fred Ar
775506e9ac debian: include cclass 2010-06-19 08:41:21 -07:00
Fred Ar
d4173fa717 initscript: fix for dash 
Signed-off-by: Fred Ar <ar.fred@yahoo.com>
 2010-06-19 08:40:00 -07:00
Fred Ar
1f2725bc04 cclass: fix for dash 
Signed-off-by: Fred Ar <ar.fred@yahoo.com>
 2010-06-19 08:39:37 -07:00
Sage Weil
6d8334759f initscript: remove class loading for now 
- only need to do it once, by connecting to a random monitor, not for
  each monitor
- not sure we should try it every time we start the monitor for all time,
  as opposed to once after mkfs, or whenever the admin chooses to load
  new classes
 2010-06-18 21:26:41 -07:00
Sage Weil
b3dc5ecf65 vstart: only need to load classes once, not for each monitor 2010-06-18 19:12:01 -07:00
Sage Weil
c626ac3846 Merge branch 'rbd-class' into unstable 2010-06-18 16:32:10 -07:00
Sage Weil
3a2c9169b8 Revert "class: able to add classes when doing mkfs" 
This reverts commit 65371482dd.
 2010-06-18 16:31:38 -07:00
Sage Weil
fb1ad6e746 filestore: op_start when op is _queued_, so that q is drained on commit 
We need the store in a consistent state on commit, which means flushing
transactions such that we have all ops <= a given seq applied.  That is
handled by the commit_start()/commit_started() pair, but will only include
ops in the FileStore queue if we op_start when it is initially queued.
Which is exactly what we want, because the queue can reorder things, so
stopping just currently-being-applied updates will only keep transactions
atomic but not ordered.

Yup!
 2010-06-18 15:59:36 -07:00
Sage Weil
6a261eb1cc journal: maintain applied_seq, use that value during the commit. 
Track which seq's have successfully applied.

This fixes writeahead mode.  Parallel mode is still broken...
 2010-06-18 15:09:05 -07:00
Sage Weil
ed768c9ae0 buffer: fix includes for writev/iovec stuff in write_fd() 2010-06-18 14:30:02 -07:00
Sage Weil
a3e906e3e7 filestore: make sync() and friends actually sync! 2010-06-18 14:09:15 -07:00
Sage Weil
ae90ba1828 initscripts: fix verbose output for root commands 2010-06-18 13:56:24 -07:00
Sage Weil
10d41d2cb4 filejournal: only pad to align for data segments above 64 KB 2010-06-18 13:06:13 -07:00
Sage Weil
f98c0b4f65 filejournal: make alignment optional (<0 == no preferred alignment) 2010-06-18 13:00:23 -07:00
Sage Weil
2be1480a5b Merge branch 'unstable' of ceph.newdream.net:git/ceph into unstable 2010-06-18 12:49:55 -07:00
Sage Weil
3fbc2a2a0a buffer: remove debug cruft 2010-06-18 12:48:01 -07:00
Sage Weil
d1626090b7 filejournal: pad entries on disk based on preferred alignment 
Adjust pre/post padding to align entry payload with it's preferred
alignment.
 2010-06-18 12:47:13 -07:00
Sage Weil
f59d77be82 objectstore: track offset, alignment of largest data segment [encoding change] 2010-06-18 12:46:23 -07:00
Sage Weil
0995f28fe2 buffer: list::rebuild_page_aligned() 
Rebuild bufferlist such that all segments/ptrs are page sized/aligned.
(Avoids copying/reallocating segments that are already aligned.)
 2010-06-18 12:44:57 -07:00
Greg Farnum
25116b2738 client: if checking caps on a snap, return, don't assert 2010-06-18 11:38:45 -07:00
Sage Weil
bd4188a02a filejournal: use buffer::write_fd() instead of open coding 
Avoid dup code, and also handle short writes.
 2010-06-18 10:10:53 -07:00
Sage Weil
ca9b756399 osd: implement bench command 
'bench [bsize] [total bytes]'

Result is reported via logclient.
 2010-06-18 09:40:01 -07:00
Sage Weil
e4b9dd4bba msgr: avoid calculating data crc is peer didn't either 
Otherwise we're just wasting CPU cycles!
 2010-06-18 09:19:20 -07:00
Simone Gotti
2bb94b3626 msgr: Fix crash in policy.throttler->get(message_size) when message_size == 0 
Signed-off-by: Simone Gotti <simone.gotti@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-06-18 08:34:14 -07:00
Sage Weil
35095434d9 qa: another mds test fix... wait long enough for the previous death to trigger 2010-06-17 13:44:12 -07:00
Sage Weil
c6067131bd msgr: ref count Pipe to avoid use after free 
The Connection has a Pipe pointer to facilitate
 send_message(Message, Connection)
but the reaper() clears that pointer when tearing down old pipes.  This
leads to a race in which submit_message dereferences the old Pipe pointer.

Instead, make Pipe ref counted, and only submit_message() if we get a
valid Pipe reference.  This fixes races between send_message() and
reaper() (as well as any use of the Connection after the pipe is closed).

Signed-off-by: Sage Weil <sage@newdream.net>
 2010-06-17 13:37:34 -07:00
Sage Weil
920b2d8974 qa: fix mdstable failure tests 2010-06-17 13:09:22 -07:00
Sage Weil
4d66a72a5a ceph: fix straggler header ifdef guards 2010-06-17 10:51:40 -07:00
Markus Elfring
f4b9d9d847 Bug #98: Unique names for include guards 
A couple of preprocessor symbols for include guards tampered with the reserved namespace.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-06-17 10:47:37 -07:00
Sage Weil
6de2dde762 ceph: remove leading _ from macro 
Reported-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-06-17 10:36:39 -07:00
Markus Elfring
9013832c5d Bug #98: Movement of an underscore for a data structure identifier 
A leading underscore was moved to the back of a data structure identifier.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
 2010-06-17 10:34:11 -07:00
Sage Weil
f6501564a9 Merge branch 'unstable' of ssh://ceph.newdream.net/home/sage/ceph.newdream.net/git/ceph into unstable 2010-06-17 10:04:20 -07:00
Sage Weil
57d79aaa5f Revert "mkcephfs: cosd mkfs as root, then chown" 
This reverts commit 0383878c4f.
 2010-06-17 10:13:04 -07:00
Sage Weil
081bbe15a5 mds: fix cdir head/snap items/null accounting 
We were mixing up primary vs remote, partly due to the weird placement of
the counter adjustments.  Make those sane and clean things up a bit.
 2010-06-17 10:13:04 -07:00
Sage Weil
e6b033acbc osd: make clean_up_local remove hardlinks from collection dirs 2010-06-17 10:13:04 -07:00
Sage Weil
af2d023caa osd: don't requeue null OSDOp on apply_and_flush_repops 
(this triggers during snap trimming)
 2010-06-17 10:13:04 -07:00
Sage Weil
8c5ee65b21 osd: fix snap_trimmer AccessMode interaction 
Recheck access mode every time we retake the pg lock (each object). Sleep
if necessary.
 2010-06-17 10:13:04 -07:00
Sage Weil
f976bbdcf7 filejournal: journal write cache is safe on >= 2.6.33 2010-06-17 09:29:36 -07:00
Sage Weil
583f9f4296 mkcephfs: error out of journal dev is included in btrfs devs 2010-06-17 09:29:36 -07:00
Sage Weil
b472722940 osd: optionally periodically check pglog for corruption 
...at least until we find this bug, periodically check pglog for corruption
and log it to the monitor when it happens.

Off by default.
 2010-06-17 09:29:36 -07:00
Sage Weil
b30ff1710a logclient: clean up interaction with monclient, monitor 
Use monclient where available.  Otherwise, we are a monitor, so send to
ourselves.

Conflicts:

	src/mon/MonmapMonitor.cc
 2010-06-17 09:29:36 -07:00
Sage Weil
d7b9f39d9a filejournal: log if journal item is larger than journal 2010-06-16 14:15:10 -07:00
Yehuda Sadeh
5dfc4119fc osd: warn when failing to mount journal on ENOTTY 
suggest that the problem was due to journal size not configured
 2010-06-16 10:53:08 -07:00
Yehuda Sadeh
5c001f4e5c conf: can specify environment variables for substitution 2010-06-16 10:14:20 -07:00
Yehuda Sadeh
d5995661ea conf: fix buffer initalization 
This fixes a bug where we didn't initialize the variable
post processing buffer, which would sometimes lead to
garbage data.
 2010-06-16 10:14:20 -07:00
Yehuda Sadeh
ce909c2c31 osd: error out when failing to read journal header 
This fixes bug #201.
 2010-06-16 10:13:59 -07:00
Yehuda Sadeh
d971bb06f5 osd: mkfs failures are colored red 2010-06-14 12:22:54 -07:00
Sage Weil
658d51dae1 mon: make send_reply always consume reply ref (even if not sent); fix caller hackery 2010-06-11 10:12:24 -07:00
Sage Weil
e5ff518946 mds: add force_wrlock to lock states; use for filemax changes 
This lets us write out a max_size change when we revoke caps from a client
(thus excl->sync) and the client releases dirty caps.
 2010-06-11 10:12:24 -07:00
Yehuda Sadeh
3336d9d0fa rgw: put_obj uses write_full 2010-06-10 16:01:34 -07:00