]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Yehuda Sadeh [Wed, 4 Mar 2009 00:03:57 +0000 (16:03 -0800)]
ceph_ver: add ceph_ver.h to list of .h files
Yehuda Sadeh [Wed, 4 Mar 2009 00:01:48 +0000 (16:01 -0800)]
kclient: write ceph git version when module loads
Yehuda Sadeh [Tue, 3 Mar 2009 23:46:06 +0000 (15:46 -0800)]
ceph_ver: add unconditional rule
Yehuda Sadeh [Tue, 3 Mar 2009 23:37:02 +0000 (15:37 -0800)]
ceph_ver: uncomment important line
Yehuda Sadeh [Tue, 3 Mar 2009 23:32:20 +0000 (15:32 -0800)]
ceph_ver: show the git sha1 version in the logs
Yehuda Sadeh [Tue, 3 Mar 2009 23:23:12 +0000 (15:23 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Yehuda Sadeh [Tue, 3 Mar 2009 22:35:56 +0000 (14:35 -0800)]
kclient: wakeup wq waiting on caps on write
Sage Weil [Tue, 3 Mar 2009 22:27:15 +0000 (14:27 -0800)]
kclient: some fmode cleanup
BUG instead of WARN. Rename field.
Sage Weil [Tue, 3 Mar 2009 22:26:28 +0000 (14:26 -0800)]
kclient: fix fmode ref count buf
We weren't taking an fmode reference on the root dir. This would
cause a WARN if our root caps were allowed to expire and we had
to ropen them. Duplicated wonky r_fmode conditional from later
fill_inode() call in fill_trace().
Sage Weil [Tue, 3 Mar 2009 20:28:11 +0000 (12:28 -0800)]
kclient: wake up i_cap_wq in ceph_add_cap
We could a thread blocked on caps when we are issued a new cap in
another thread. They need to be woken up.
Sage Weil [Tue, 3 Mar 2009 20:27:31 +0000 (12:27 -0800)]
kclient: check d_inode before clearing its COMPLETE flag.
Sage Weil [Tue, 3 Mar 2009 20:25:58 +0000 (12:25 -0800)]
mds: fix try_remove_unlinked_dn
Just because a dir is_complete() doesn't mean that we can safely
do away with a null dentry. What matters is if the dentry existed
before the last commit.. and having everything in our cache isn't
relevant at all there. If we are complete, a fetch() would be a
no-op, but since we can clear complete at any time, that's not
helpful.
Sage Weil [Tue, 3 Mar 2009 19:43:47 +0000 (11:43 -0800)]
kclient: do not return new null dentry from lookup
The VFS doesn't appear to like it when lookup returns a replacement
dentry that is null... it BUGs on unmount with a ref count that is
still 1.
So, if we get ENOENT and no trace, return ERR_PTR(-ENOENT) instead.
Sage Weil [Tue, 3 Mar 2009 19:33:42 +0000 (11:33 -0800)]
cfuse: fix startup
Yehuda Sadeh [Tue, 3 Mar 2009 18:43:35 +0000 (10:43 -0800)]
conf: some cleanup
Yehuda Sadeh [Tue, 3 Mar 2009 18:41:21 +0000 (10:41 -0800)]
conf: some more fixes (again)
Yehuda Sadeh [Tue, 3 Mar 2009 18:40:15 +0000 (10:40 -0800)]
conf: fix typo
Sage Weil [Tue, 3 Mar 2009 18:42:10 +0000 (10:42 -0800)]
mds: clean up auth_pin nesting code a bit
Sage Weil [Tue, 3 Mar 2009 18:32:50 +0000 (10:32 -0800)]
mkcephfs: take optional crush map on command line
Yehuda Sadeh [Tue, 3 Mar 2009 18:37:29 +0000 (10:37 -0800)]
conf: lockdep again
Yehuda Sadeh [Tue, 3 Mar 2009 18:17:13 +0000 (10:17 -0800)]
conf: fix some other errors
Yehuda Sadeh [Tue, 3 Mar 2009 18:14:17 +0000 (10:14 -0800)]
conf: the return of --lockdep, other fixes
Yehuda Sadeh [Tue, 3 Mar 2009 18:06:42 +0000 (10:06 -0800)]
config: some cleanup
Sage Weil [Tue, 3 Mar 2009 17:32:01 +0000 (09:32 -0800)]
debian: fix dependencies
Yehuda Sadeh [Tue, 3 Mar 2009 01:19:47 +0000 (17:19 -0800)]
conf: fix erronous scoping
Yehuda Sadeh [Tue, 3 Mar 2009 01:12:35 +0000 (17:12 -0800)]
conf: moved options to the preparse section
Yehuda Sadeh [Tue, 3 Mar 2009 01:05:23 +0000 (17:05 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Yehuda Sadeh [Tue, 3 Mar 2009 01:05:08 +0000 (17:05 -0800)]
conf: added old remarks
Sage Weil [Tue, 3 Mar 2009 00:56:45 +0000 (16:56 -0800)]
config: remove 'debug_after' cruft
Yehuda Sadeh [Tue, 3 Mar 2009 00:40:11 +0000 (16:40 -0800)]
conf: removed some more old stuff
Yehuda Sadeh [Tue, 3 Mar 2009 00:37:56 +0000 (16:37 -0800)]
conf: remove old stuff
Sage Weil [Tue, 3 Mar 2009 00:38:11 +0000 (16:38 -0800)]
kclient: revamp async truncation
We can learn about truncations from an mds reply or from a TRUNC
cap message. Set up the async truncation in the generic
ceph_fill_file_size helper. Remove old crufty async trunc code
(that assumed TRUNC would come before an ltruncate reply).
Sage Weil [Tue, 3 Mar 2009 00:30:10 +0000 (16:30 -0800)]
mds: flush log on wrlock_start if lock isn't stable
Sage Weil [Tue, 3 Mar 2009 00:29:55 +0000 (16:29 -0800)]
mds: flush mdlog on max_size increase
Presumably a writer is waiting for it.
Sage Weil [Tue, 3 Mar 2009 00:29:30 +0000 (16:29 -0800)]
mds: only issue cap TRUNC if truncating smaller
Sage Weil [Tue, 3 Mar 2009 00:10:30 +0000 (16:10 -0800)]
filestore: more helpful error message with xattrs don't work
Sage Weil [Mon, 2 Mar 2009 23:35:20 +0000 (15:35 -0800)]
sample.cluster.conf: fix mon path/osd dev option names
Sage Weil [Mon, 2 Mar 2009 23:19:20 +0000 (15:19 -0800)]
mds: fix truncate bug
Use consistent conditional value to determine whether it is a
forward truncation or not. Otherwise we get out of sync before vs
after journaling...
Yehuda Sadeh [Tue, 3 Mar 2009 00:26:29 +0000 (16:26 -0800)]
conf: fixed issue with deleted conf options
Yehuda Sadeh [Tue, 3 Mar 2009 00:26:14 +0000 (16:26 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Yehuda Sadeh [Tue, 3 Mar 2009 00:20:28 +0000 (16:20 -0800)]
conf: added all the conf options
Yehuda Sadeh [Mon, 2 Mar 2009 22:38:57 +0000 (14:38 -0800)]
conf: revised cmd line parsing and conf reading
still need to set all the default initialization
Sage Weil [Mon, 2 Mar 2009 22:16:46 +0000 (14:16 -0800)]
kclient: make sure we cleanup in all error paths
Sage Weil [Mon, 2 Mar 2009 22:14:48 +0000 (14:14 -0800)]
kclient: make statfs() cleanup when interrupted
Statfs() needs to remove itself from the request tree when
completed or canceled. Otherwise, we end up with request
pointers to bad locations on the stack. Fixes crash from
dbench after control-c.
Sage Weil [Mon, 2 Mar 2009 21:48:58 +0000 (13:48 -0800)]
kclient: remove /proc cruft
Sage Weil [Mon, 2 Mar 2009 21:48:40 +0000 (13:48 -0800)]
kclient: remove old client_list cruft
Sage Weil [Mon, 2 Mar 2009 21:45:40 +0000 (13:45 -0800)]
Revert "kclient: fix __grab_cache_page #if"
This reverts commit
220b116bfdc0ede84da93f296d42706fc0fc23f4 .
Linux commit
54566b2c1594c2326a645a3551f9d989f7ba3c5e falls between
v2.6.28 and v2.6.29-rc1, so this #if should be 2.6.29.
Sage Weil [Mon, 2 Mar 2009 21:36:01 +0000 (13:36 -0800)]
vstart: fix conf, use -d on startup, etc.
Sage Weil [Mon, 2 Mar 2009 21:25:00 +0000 (13:25 -0800)]
debian: restructure packages
Consolidate. Fix dependencies.
Sage Weil [Mon, 2 Mar 2009 20:37:49 +0000 (12:37 -0800)]
todos, changelog
Sage Weil [Fri, 27 Feb 2009 21:14:09 +0000 (13:14 -0800)]
kclient: fix __grab_cache_page #if
2.6.28, not .29
Sage Weil [Mon, 2 Mar 2009 19:09:04 +0000 (11:09 -0800)]
initscripts: clean out old scripts
Sage Weil [Mon, 2 Mar 2009 19:11:20 +0000 (11:11 -0800)]
initscripts: rename ceph-daemons init-ceph
My real motivation is just to be able to type './i<tab>' instead of
'./ce<tab>-<tab>'.
Sage Weil [Mon, 2 Mar 2009 18:11:14 +0000 (10:11 -0800)]
initscripts: add 'killall' command
Sage Weil [Mon, 2 Mar 2009 18:07:35 +0000 (10:07 -0800)]
cosd: rename conf file
Sage Weil [Mon, 2 Mar 2009 18:05:57 +0000 (10:05 -0800)]
initscripts: fix stop_daemon; add 'forcestop' command
Sage Weil [Mon, 2 Mar 2009 17:59:01 +0000 (09:59 -0800)]
initscripts: add 'cleanlogs' and 'cleanalllogs' options
Sage Weil [Mon, 2 Mar 2009 17:51:13 +0000 (09:51 -0800)]
initscripts: ensure cluster.conf exists
Sage Weil [Mon, 2 Mar 2009 17:29:08 +0000 (09:29 -0800)]
debian: missing files
Sage Weil [Mon, 2 Mar 2009 17:34:07 +0000 (09:34 -0800)]
config: remove osd_rep
We always use primary copy replication mode.
Sage Weil [Mon, 2 Mar 2009 17:31:21 +0000 (09:31 -0800)]
config: remove obsolete ms_* fields
Used to be used for startup via mpi or similar.
Sage Weil [Mon, 2 Mar 2009 17:28:34 +0000 (09:28 -0800)]
config: remove some debug cruft
mkfs, tick, osd_remount_at. rename some stuff.
Sage Weil [Mon, 2 Mar 2009 05:31:10 +0000 (21:31 -0800)]
makefile: cleanup, some sample conf files
They're in /etc/conf/sample.*.conf, when technically they should probably
be in /usr/doc/ceph or something? Not sure.
Sage Weil [Sun, 1 Mar 2009 05:58:34 +0000 (21:58 -0800)]
config: rename logger/dout config fields to make more sense
'logger' is the common/Logger.cc stats/instrumentation. 'log' is the
dout() log business.
Sage Weil [Sun, 1 Mar 2009 05:50:19 +0000 (21:50 -0800)]
makefile: put sample conf files in /etc/ceph
Sage Weil [Sun, 1 Mar 2009 05:37:16 +0000 (21:37 -0800)]
initial sample.ceph.conf (incomplete)
Sage Weil [Sun, 1 Mar 2009 00:25:29 +0000 (16:25 -0800)]
fix pid file removal
Sage Weil [Sun, 1 Mar 2009 00:12:20 +0000 (16:12 -0800)]
initscript: include all monitor addrs on command line
Sage Weil [Sun, 1 Mar 2009 00:06:27 +0000 (16:06 -0800)]
initscripts: make mkcephfs and initscript behave on cosd*
Sage Weil [Sun, 1 Mar 2009 00:00:40 +0000 (16:00 -0800)]
config: parse 'monmap file' from conf files
Sage Weil [Sat, 28 Feb 2009 23:52:46 +0000 (15:52 -0800)]
cosd: don't screw up stdout with NULL string
Sage Weil [Sat, 28 Feb 2009 23:52:18 +0000 (15:52 -0800)]
config: chdir_root on by default
Sage Weil [Sat, 28 Feb 2009 23:48:09 +0000 (15:48 -0800)]
config: use daemon() call; rename use_abspath to chdir_root
Sage Weil [Sat, 28 Feb 2009 05:19:52 +0000 (21:19 -0800)]
config: fix conf metaoption parsing
Remove from args[] so that caller doesn't get confused by them.
Yehuda Sadeh [Sat, 28 Feb 2009 01:20:10 +0000 (17:20 -0800)]
ceph-daemons: some more fixes
Yehuda Sadeh [Sat, 28 Feb 2009 01:11:22 +0000 (17:11 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Yehuda Sadeh [Sat, 28 Feb 2009 01:11:10 +0000 (17:11 -0800)]
ceph-daemons: some more fixes
Sage Weil [Sat, 28 Feb 2009 00:41:07 +0000 (16:41 -0800)]
rename sample.startup.conf
Sage Weil [Sat, 28 Feb 2009 00:39:40 +0000 (16:39 -0800)]
more cleanup
Sage Weil [Sat, 28 Feb 2009 00:39:09 +0000 (16:39 -0800)]
makefile: cleanup
Sage Weil [Sat, 28 Feb 2009 00:17:40 +0000 (16:17 -0800)]
ceph-daemons: generate list of items to stop/start in ceph_common.sh
nothing -> everything
mon -> all monitors (mon*)
mds0 -> just mds0
Sage Weil [Sat, 28 Feb 2009 00:04:34 +0000 (16:04 -0800)]
ceph-daemons: simplify crun/valgrind logic
Yehuda Sadeh [Sat, 28 Feb 2009 00:04:20 +0000 (16:04 -0800)]
ceph-daemons: fixed merge
Yehuda Sadeh [Sat, 28 Feb 2009 00:02:09 +0000 (16:02 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Yehuda Sadeh [Sat, 28 Feb 2009 00:01:53 +0000 (16:01 -0800)]
ceph-daemons: minor changes
Sage Weil [Fri, 27 Feb 2009 23:51:55 +0000 (15:51 -0800)]
ceph-daemons: 'stop' works
Yehuda Sadeh [Fri, 27 Feb 2009 23:49:01 +0000 (15:49 -0800)]
Merge branch 'unstable' of ssh://ceph.newdream.net/git/ceph into unstable
Conflicts:
src/ceph-daemons
Yehuda Sadeh [Fri, 27 Feb 2009 23:46:10 +0000 (15:46 -0800)]
ceph-daemons: works partially
Sage Weil [Fri, 27 Feb 2009 23:44:14 +0000 (15:44 -0800)]
vstart: some changes
no more crun wrapper; rename ceph_stop back to stop.sh
Sage Weil [Fri, 27 Feb 2009 23:15:11 +0000 (15:15 -0800)]
vstart: no more crun
Sage Weil [Fri, 27 Feb 2009 23:11:19 +0000 (15:11 -0800)]
mkcephfs
Still need to add optional mkbtrfs + mount stuff.
Sage Weil [Fri, 27 Feb 2009 22:23:49 +0000 (14:23 -0800)]
debian: update packages
Sage Weil [Fri, 27 Feb 2009 22:23:40 +0000 (14:23 -0800)]
makefile, todo
Sage Weil [Fri, 27 Feb 2009 22:19:21 +0000 (14:19 -0800)]
config: specify --monmap_file on command line
Still defaults to .ceph_monmap.
Sage Weil [Fri, 27 Feb 2009 21:12:25 +0000 (13:12 -0800)]
client: fix warning
Sage Weil [Fri, 27 Feb 2009 21:12:15 +0000 (13:12 -0800)]
ceph-daemon: some comments
Yehuda Sadeh [Fri, 27 Feb 2009 22:33:15 +0000 (14:33 -0800)]
ceph-daemons: no norestart any more
Yehuda Sadeh [Fri, 27 Feb 2009 22:30:09 +0000 (14:30 -0800)]
ceph-daemons: read config for different entities
Yehuda Sadeh [Fri, 27 Feb 2009 20:55:41 +0000 (12:55 -0800)]
crun: replace $* with "$@"
Yehuda Sadeh [Fri, 27 Feb 2009 20:51:51 +0000 (12:51 -0800)]
ceph-daemons: replace $* with "$@"