]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
14 years agocephfs: remove unused variables
Sage Weil [Thu, 28 Oct 2010 20:14:03 +0000 (13:14 -0700)]
cephfs: remove unused variables

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoconfig: fix signal handler recursion
Sage Weil [Thu, 28 Oct 2010 19:10:29 +0000 (12:10 -0700)]
config: fix signal handler recursion

Avoid having old handler pointer match the new handler.

Avoid calling an old handler if it pointer is null.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoobjecter: refactor interface with object_locator_t
Sage Weil [Thu, 28 Oct 2010 18:53:38 +0000 (11:53 -0700)]
objecter: refactor interface with object_locator_t

This paves the way for a locator that lets the user specify an arbitrary
string to hash for placement (instead of the object name).  It also
captures everything that would affect placement (pool, preferred, etc.)
in a single type.

Just the client side; no server side or protocol changes yet.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agomds: pin NEEDSNAPFLUSH only when adding item
Sage Weil [Thu, 28 Oct 2010 18:02:26 +0000 (11:02 -0700)]
mds: pin NEEDSNAPFLUSH only when adding item

This is mainly paranoia.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agomds: store dir inode in separate object; fetch from both. incompat flag.
Sage Weil [Wed, 27 Oct 2010 21:43:43 +0000 (14:43 -0700)]
mds: store dir inode in separate object; fetch from both.  incompat flag.

This avoids setting large xattrs.  There's no reason the inode needs to be
on the same object as the dir(frag) data.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agofilestore: can force use of stale snaps
Yehuda Sadeh [Wed, 27 Oct 2010 20:21:11 +0000 (13:21 -0700)]
filestore: can force use of stale snaps

also, overwrite the commit_seq with the current version in case we
forced stale snaps.

14 years agofilestore: don't revert to old snapshots on startup
Yehuda Sadeh [Wed, 27 Oct 2010 18:38:11 +0000 (11:38 -0700)]
filestore: don't revert to old snapshots on startup

This should fix bug #55

14 years agofilestore: read commit_seq before mounting (btrfs ioctls)
Yehuda Sadeh [Tue, 26 Oct 2010 23:46:31 +0000 (16:46 -0700)]
filestore: read commit_seq before mounting (btrfs ioctls)

14 years agoceph.cc: delete deadcode
Colin Patrick McCabe [Wed, 27 Oct 2010 06:19:19 +0000 (23:19 -0700)]
ceph.cc: delete deadcode

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoMove ceph.cc to tools/
Colin Patrick McCabe [Wed, 27 Oct 2010 03:51:49 +0000 (20:51 -0700)]
Move ceph.cc to tools/

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoconfigure.ac: add ./configure option for gtk2
Colin Patrick McCabe [Tue, 26 Oct 2010 21:26:12 +0000 (14:26 -0700)]
configure.ac: add ./configure option for gtk2

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agomessenger: always unlock existing pipes, even if they're lossy
Greg Farnum [Tue, 26 Oct 2010 23:28:48 +0000 (16:28 -0700)]
messenger: always unlock existing pipes, even if they're lossy

14 years agoMerge remote branch 'origin/testing' into unstable
Sage Weil [Tue, 26 Oct 2010 19:04:17 +0000 (12:04 -0700)]
Merge remote branch 'origin/testing' into unstable

Conflicts:
configure.ac
src/rados.cc

14 years agofilestore: some cleanup
Yehuda Sadeh [Tue, 26 Oct 2010 18:05:55 +0000 (11:05 -0700)]
filestore: some cleanup

14 years agofilestore: escape the xattr chunk names
Yehuda Sadeh [Mon, 25 Oct 2010 23:35:48 +0000 (16:35 -0700)]
filestore: escape the xattr chunk names

14 years agoosd::Missing: const cleanup
Colin Patrick McCabe [Tue, 26 Oct 2010 17:51:52 +0000 (10:51 -0700)]
osd::Missing: const cleanup

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd: move PG::Missing implementation to PG.cc
Colin Patrick McCabe [Tue, 26 Oct 2010 17:42:15 +0000 (10:42 -0700)]
osd: move PG::Missing implementation to PG.cc

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agofilestore: some cleanup
Yehuda Sadeh [Tue, 26 Oct 2010 18:05:55 +0000 (11:05 -0700)]
filestore: some cleanup

14 years agoMerge branch 'btrfs_snap_ioctls' into unstable
Sage Weil [Tue, 26 Oct 2010 04:52:30 +0000 (21:52 -0700)]
Merge branch 'btrfs_snap_ioctls' into unstable

14 years agofilestore: warn if btrfs_snaps enabled but no async snap create ioctl
Sage Weil [Tue, 26 Oct 2010 04:52:07 +0000 (21:52 -0700)]
filestore: warn if btrfs_snaps enabled but no async snap create ioctl

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agomon: remove pg from deleted pools from pg_map
Sage Weil [Mon, 25 Oct 2010 23:44:10 +0000 (16:44 -0700)]
mon: remove pg from deleted pools from pg_map

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agomds: fix up mds_bal_frag options
Sage Weil [Mon, 25 Oct 2010 22:07:41 +0000 (15:07 -0700)]
mds: fix up mds_bal_frag options

Use the mds_bal_frag option to enable/disable.  Make checks consistent.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoadd cephfs to deb, rpm
Sage Weil [Mon, 25 Oct 2010 22:03:32 +0000 (15:03 -0700)]
add cephfs to deb, rpm

14 years agoMerge branch 'objectcacher' into unstable
Greg Farnum [Mon, 25 Oct 2010 23:51:38 +0000 (16:51 -0700)]
Merge branch 'objectcacher' into unstable

14 years agoclient: fix to handle new ObjectCacher pool requirements.
Greg Farnum [Mon, 25 Oct 2010 21:21:21 +0000 (14:21 -0700)]
client: fix to handle new ObjectCacher pool requirements.

14 years agoosdc: Add pool awareness to the ObjectCacher, to prevent unfortunate collisions.
Greg Farnum [Mon, 25 Oct 2010 21:18:02 +0000 (14:18 -0700)]
osdc: Add pool awareness to the ObjectCacher, to prevent unfortunate collisions.

14 years agoosdc: Fix release_all so it loops properly
Greg Farnum [Mon, 25 Oct 2010 18:38:41 +0000 (11:38 -0700)]
osdc: Fix release_all so it loops properly

14 years agofilestore: escape the xattr chunk names
Yehuda Sadeh [Mon, 25 Oct 2010 23:35:48 +0000 (16:35 -0700)]
filestore: escape the xattr chunk names

14 years agoPG::Log::Entry: remove unused snap_t field
Colin Patrick McCabe [Mon, 25 Oct 2010 22:22:34 +0000 (15:22 -0700)]
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>
14 years agomakefile: add cephfs
Greg Farnum [Mon, 25 Oct 2010 20:42:13 +0000 (13:42 -0700)]
makefile: add cephfs

14 years ago./ceph osd setcrushmap: validate crushmap
Colin Patrick McCabe [Mon, 25 Oct 2010 19:24:13 +0000 (12:24 -0700)]
./ceph osd setcrushmap: validate crushmap

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agocrush: improve error handling in map decoding
Colin Patrick McCabe [Mon, 25 Oct 2010 19:06:01 +0000 (12:06 -0700)]
crush: improve error handling in map decoding

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agocap_reconnect_t: ignore embedded NULLs in the path
Colin Patrick McCabe [Sun, 24 Oct 2010 21:22:00 +0000 (14:22 -0700)]
cap_reconnect_t: ignore embedded NULLs in the path

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agov0.22.1 v0.22.1
Sage Weil [Fri, 22 Oct 2010 23:51:27 +0000 (16:51 -0700)]
v0.22.1

14 years agoMakefile: add errno.h
Sage Weil [Fri, 22 Oct 2010 23:33:03 +0000 (16:33 -0700)]
Makefile: add errno.h

14 years agomds: be quiet about snaprealm push/pop
Sage Weil [Sat, 23 Oct 2010 17:17:29 +0000 (10:17 -0700)]
mds: be quiet about snaprealm push/pop

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agofilestore: ignore ENOSPC on setxattr pending a better workaround
Sage Weil [Fri, 22 Oct 2010 23:06:19 +0000 (16:06 -0700)]
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>
14 years agofilestore: change xattr chunk size to 2048
Yehuda Sadeh [Fri, 22 Oct 2010 22:52:58 +0000 (15:52 -0700)]
filestore: change xattr chunk size to 2048

14 years agofilestore: split xattrs to multiple chunks
Yehuda Sadeh [Fri, 22 Oct 2010 17:09:32 +0000 (10:09 -0700)]
filestore: split xattrs to multiple chunks

14 years agorados: add getxattr, setxattr
Yehuda Sadeh [Thu, 21 Oct 2010 21:41:05 +0000 (14:41 -0700)]
rados: add getxattr, setxattr

14 years agofilestore: change xattr chunk size to 2048
Yehuda Sadeh [Fri, 22 Oct 2010 22:52:58 +0000 (15:52 -0700)]
filestore: change xattr chunk size to 2048

14 years agolibrados: add rmxattr
Yehuda Sadeh [Fri, 22 Oct 2010 21:32:55 +0000 (14:32 -0700)]
librados: add rmxattr

14 years agoRevert "messenger: Make sure to unlock existing->pipe_lock. There are a few cases...
Greg Farnum [Fri, 22 Oct 2010 20:36:30 +0000 (13:36 -0700)]
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 96692d24c8cdf0fe88260949b67f8580e0c70696.
This patch accidentally got merged into the tree twice, so
merging issues came up.

14 years agotest_lost.sh: put common functions in test_common
Colin Patrick McCabe [Fri, 22 Oct 2010 18:48:35 +0000 (11:48 -0700)]
test_lost.sh: put common functions in test_common

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoMerge branch 'msgr' into unstable
Greg Farnum [Fri, 22 Oct 2010 18:24:24 +0000 (11:24 -0700)]
Merge branch 'msgr' into unstable

14 years agomessenger: If we error out of accept() but have messages in our queue, save Pipe.
Greg Farnum [Fri, 22 Oct 2010 18:16:24 +0000 (11:16 -0700)]
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.

14 years agomessenger: If we're replacing an existing Pipe, steal queue when we kill it!
Greg Farnum [Fri, 22 Oct 2010 18:15:22 +0000 (11:15 -0700)]
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.

14 years agoPG::peer: introduce prior_set_build flag
Colin Patrick McCabe [Fri, 22 Oct 2010 18:01:15 +0000 (11:01 -0700)]
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>
14 years agofilestore: update btrfs_ioctl.h
Yehuda Sadeh [Wed, 20 Oct 2010 20:49:35 +0000 (13:49 -0700)]
filestore: update btrfs_ioctl.h

14 years agofilestore: use different encoding for snap async_create
Yehuda Sadeh [Mon, 18 Oct 2010 22:57:01 +0000 (15:57 -0700)]
filestore: use different encoding for snap async_create

14 years agofilestore: use SNAP_DESTROY_ASYNC ioctl if available
Sage Weil [Thu, 8 Apr 2010 17:34:50 +0000 (10:34 -0700)]
filestore: use SNAP_DESTROY_ASYNC ioctl if available

14 years agofilestore: remove stray async_snap_test if present
Sage Weil [Thu, 18 Mar 2010 18:33:32 +0000 (11:33 -0700)]
filestore: remove stray async_snap_test if present

This cleans up if a prior instance failed to delete its
async_snap_test subvol.

14 years agofilestore: use new async btrfs ioctls
Sage Weil [Tue, 23 Feb 2010 00:03:09 +0000 (16:03 -0800)]
filestore: use new async btrfs ioctls

14 years agoosd: fix deadlock in map handler
Sage Weil [Fri, 22 Oct 2010 17:11:21 +0000 (10:11 -0700)]
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>
14 years agofilestore: split xattrs to multiple chunks
Yehuda Sadeh [Fri, 22 Oct 2010 17:09:32 +0000 (10:09 -0700)]
filestore: split xattrs to multiple chunks

14 years agorados: add getxattr, setxattr
Yehuda Sadeh [Thu, 21 Oct 2010 21:41:05 +0000 (14:41 -0700)]
rados: add getxattr, setxattr

14 years agomds: implement 'fragment_dir path frag by' command
Sage Weil [Fri, 22 Oct 2010 04:45:27 +0000 (21:45 -0700)]
mds: implement 'fragment_dir path frag by' command

For testing dir fragmentation.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoMerge branch 'testing' into unstable
Sage Weil [Fri, 22 Oct 2010 04:38:21 +0000 (21:38 -0700)]
Merge branch 'testing' into unstable

14 years agoPG::recover_master_log: replace count with find
Colin Patrick McCabe [Fri, 22 Oct 2010 00:20:40 +0000 (17:20 -0700)]
PG::recover_master_log: replace count with find

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoprior_set_affected: log msg when we see a lost osd
Colin Patrick McCabe [Thu, 21 Oct 2010 23:23:21 +0000 (16:23 -0700)]
prior_set_affected: log msg when we see a lost osd

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd: build_prior: clean up started_since_joining
Colin Patrick McCabe [Thu, 21 Oct 2010 23:12:31 +0000 (16:12 -0700)]
osd: build_prior: clean up started_since_joining

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd: PG::prior_set_affected: fix lost OSD detection
Colin Patrick McCabe [Thu, 21 Oct 2010 22:17:29 +0000 (15:17 -0700)]
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>
14 years agotest_lost.sh: ensure that recovery doesn't start.
Colin Patrick McCabe [Thu, 21 Oct 2010 20:59:15 +0000 (13:59 -0700)]
test_lost.sh: ensure that recovery doesn't start.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoinclude/utime.h: should include include/types.h
Colin Patrick McCabe [Thu, 21 Oct 2010 17:54:08 +0000 (10:54 -0700)]
include/utime.h: should include include/types.h

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoerrno: add missing common/errno.h
Sage Weil [Thu, 21 Oct 2010 00:30:10 +0000 (17:30 -0700)]
errno: add missing common/errno.h

14 years agoCreate cpp_strerror to make error reporting easier
Colin Patrick McCabe [Wed, 20 Oct 2010 22:40:07 +0000 (15:40 -0700)]
Create cpp_strerror to make error reporting easier

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoFileJournal: fix journal size calculation
Colin Patrick McCabe [Wed, 20 Oct 2010 20:19:49 +0000 (13:19 -0700)]
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 ad12d5d5be41ce.

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>
14 years agomakefile: simplify cdebugpack install rule
Sage Weil [Wed, 20 Oct 2010 20:47:16 +0000 (13:47 -0700)]
makefile: simplify cdebugpack install rule

14 years agodebian: 0.22-4
Sage Weil [Tue, 19 Oct 2010 16:11:25 +0000 (09:11 -0700)]
debian: 0.22-4

14 years agoTestTimers: test SafeTimer as well as Timer
Colin Patrick McCabe [Wed, 20 Oct 2010 00:38:32 +0000 (17:38 -0700)]
TestTimers: test SafeTimer as well as Timer

Test SafeTimer as well as Timer. Test timer shutdown.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoTimer.cc: add testtimers
Colin Patrick McCabe [Wed, 20 Oct 2010 00:02:15 +0000 (17:02 -0700)]
Timer.cc: add testtimers

Add testtimers to test the timer code.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agotest_lost.sh: update timeout, fix payload
Colin Patrick McCabe [Tue, 19 Oct 2010 21:45:14 +0000 (14:45 -0700)]
test_lost.sh: update timeout, fix payload

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoOSDMap: const cleanup
Colin Patrick McCabe [Tue, 19 Oct 2010 17:20:21 +0000 (10:20 -0700)]
OSDMap: const cleanup

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoPG::build_prior: update comment
Colin Patrick McCabe [Tue, 19 Oct 2010 17:09:29 +0000 (10:09 -0700)]
PG::build_prior: update comment

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd: track prior_set_lost
Colin Patrick McCabe [Mon, 18 Oct 2010 20:44:51 +0000 (13:44 -0700)]
osd: track prior_set_lost

In the placement group code, track prior_set_lost. This fixes a bug
where a new OSDMap updates an OSD's lost_at time, but the PG code does
not update the PG data structures.

When clearing the peering state, call clear_prior() rather than manually
clearing every prior set.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd: fix spacing in OSDMap::print
Colin Patrick McCabe [Mon, 18 Oct 2010 17:31:25 +0000 (10:31 -0700)]
osd: fix spacing in OSDMap::print

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoOSDMap::print: print osd_info_t using ostream op
Colin Patrick McCabe [Fri, 15 Oct 2010 19:16:41 +0000 (12:16 -0700)]
OSDMap::print: print osd_info_t using ostream op

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd mon: validate arguments before marking lost
Colin Patrick McCabe [Fri, 15 Oct 2010 19:16:41 +0000 (12:16 -0700)]
osd mon: validate arguments before marking lost

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoosd: test: Add script to test LOST state
Colin Patrick McCabe [Fri, 15 Oct 2010 01:14:27 +0000 (18:14 -0700)]
osd: test: Add script to test LOST state

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agomessenger: Make sure to unlock existing->pipe_lock. There are a few cases in the...
Greg Farnum [Mon, 18 Oct 2010 18:23:50 +0000 (11:23 -0700)]
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.

14 years agomds: show readdir frag
Sage Weil [Thu, 21 Oct 2010 23:16:34 +0000 (16:16 -0700)]
mds: show readdir frag

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoclient: reset fg after _readdir_get_frag
Sage Weil [Thu, 21 Oct 2010 23:16:20 +0000 (16:16 -0700)]
client: reset fg after _readdir_get_frag

The _readdir_get_frag may remap our frag; update the local variable
accordingly.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoclient: fix skipped dentry on readdir chunk boundaries
Sage Weil [Thu, 21 Oct 2010 23:15:52 +0000 (16:15 -0700)]
client: fix skipped dentry on readdir chunk boundaries

The at_cache_name is the last name successfully passed to the caller.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoclient: fix dcache removal during multiple frags
Sage Weil [Thu, 21 Oct 2010 23:15:03 +0000 (16:15 -0700)]
client: fix dcache removal during multiple frags

We remove unexpected dentries from our cache while processing mds results.
Results are ordered within a frag, but not between them.  Since we can
have multiple frags, only remove results for the current frag, to avoid
removing items from earlier frags.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoclient: show file offsets in hex
Sage Weil [Thu, 21 Oct 2010 23:13:35 +0000 (16:13 -0700)]
client: show file offsets in hex

This makes it easy to pick out frags and offsets.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agomessenger: a 0 timeout on ::poll really means don't wait
Greg Farnum [Thu, 21 Oct 2010 20:27:35 +0000 (13:27 -0700)]
messenger: a 0 timeout on ::poll really means don't wait
(as opposed to -1, which waits until an event occurs).

So, set the default timeout to -1, and convert ms_tcp_read_timeout
to -1 if it's set at 0.

14 years agomds: fix inodestat encoding when frags are present
Sage Weil [Thu, 21 Oct 2010 20:07:38 +0000 (13:07 -0700)]
mds: fix inodestat encoding when frags are present

Also simplify the max_size check calculation.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agomds: do not finish_scatter_gather_update_accounted on dirfraglock
Sage Weil [Thu, 21 Oct 2010 19:48:07 +0000 (12:48 -0700)]
mds: do not finish_scatter_gather_update_accounted on dirfraglock

This needs to match finish_scatter_gather_update, and we don't
update/project the dirfrag there.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoobjecter: reconnect on osd disconnect
Sage Weil [Thu, 21 Oct 2010 18:37:45 +0000 (11:37 -0700)]
objecter: reconnect on osd disconnect

If the connection closes to an OSD, we need to reconnect and resubmit our
ops.  Otherwise we just hang.  This is problematic if it is a transient
error, since we'll only retry if the OSDMap reflects a change, and that
won't happen for transient network/socket errors and such.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agorgw: return 204 on successful removal of bucket/object
Yehuda Sadeh [Thu, 21 Oct 2010 16:53:37 +0000 (09:53 -0700)]
rgw: return 204 on successful removal of bucket/object

14 years agoinit-ceph: Make sure daemon_is_running() checks the correct instance
Jim Schutt [Thu, 21 Oct 2010 16:32:09 +0000 (10:32 -0600)]
init-ceph: Make sure daemon_is_running() checks the correct instance

When starting multiple instances of a daemon on a single host,
for unknown reasons /var/run/ceph/$type.$id.pid can hold a pid
for which /proc/$pid/cmdline identifies the right type of daemon,
but the wrong instance.  When this happens, all the configured
instances of a daemon are not running, but repeated invocations
of "init-ceph start" do not start the missing instances.

So, check for the correct daemon instance id as well as type when
testing if the daemon is up.

Signed-off-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoobjecter: pause writes when FULL flag is set
Sage Weil [Thu, 21 Oct 2010 17:59:49 +0000 (10:59 -0700)]
objecter: pause writes when FULL flag is set

Also, subscribe to all osdmap updates while FULL flag is set, so that we
discover when it is unset.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoobjecter: always set READ or WRITE flag
Sage Weil [Thu, 21 Oct 2010 18:05:55 +0000 (11:05 -0700)]
objecter: always set READ or WRITE flag

We should set either (or both).  Assert if we don't.

Signed-off-by: Sage Weil <sage@newdream.net>
14 years agoinclude/utime.h: should include include/types.h
Colin Patrick McCabe [Thu, 21 Oct 2010 17:54:08 +0000 (10:54 -0700)]
include/utime.h: should include include/types.h

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agorgw: return 204 on successful removal of bucket/object
Yehuda Sadeh [Thu, 21 Oct 2010 16:53:37 +0000 (09:53 -0700)]
rgw: return 204 on successful removal of bucket/object

14 years agoerrno: add missing common/errno.h
Sage Weil [Thu, 21 Oct 2010 00:30:10 +0000 (17:30 -0700)]
errno: add missing common/errno.h

14 years agoCreate cpp_strerror to make error reporting easier
Colin Patrick McCabe [Wed, 20 Oct 2010 22:40:07 +0000 (15:40 -0700)]
Create cpp_strerror to make error reporting easier

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
14 years agoFileJournal: fix journal size calculation
Colin Patrick McCabe [Wed, 20 Oct 2010 20:19:49 +0000 (13:19 -0700)]
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 ad12d5d5be41ce.

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>
14 years agomakefile: simplify cdebugpack install rule
Sage Weil [Wed, 20 Oct 2010 20:47:16 +0000 (13:47 -0700)]
makefile: simplify cdebugpack install rule

14 years agodebian: 0.22-4
Sage Weil [Tue, 19 Oct 2010 16:11:25 +0000 (09:11 -0700)]
debian: 0.22-4