]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Sage Weil [Fri, 15 Apr 2011 17:02:46 +0000 (10:02 -0700)]
mds: don't skip inodes in journal that may be trimmed during replay
During replay we trim non-auth inodes on EExport or EImportFinish abort.
Subtree trimming may be delayed, too.
Skip parents if the diri is in the same blob, or if it is journaled in the
current segment *and* it is in a subtree that is unambiguously auth. We can't
easily be more precise than that because the actual event we care about on
replay is EExport, but the migrator doesn't twiddle auth bits to false until
later.
Also, reset last_journaled on import.
This fixes replay bugs like
2011-04-13 18:15:18.064029
7f65588ef710 mds1.journal EImportStart.replay
10000000015 bounds []
2011-04-13 18:15:18.064034
7f65588ef710 mds1.journal EMetaBlob.replay 2 dirlumps by unknown0
2011-04-13 18:15:18.064040
7f65588ef710 mds1.journal EMetaBlob.replay dir
10000000010
2011-04-13 18:15:18.064046
7f65588ef710 mds1.journal EMetaBlob.replay missing dir ino
10000000010
mds/journal.cc: In function 'void EMetaBlob::replay(MDS*, LogSegment*)', in thread '0x7f65588ef710'
mds/journal.cc: 407: FAILED assert(0)
ceph version
0.25-683-g653580a (commit:
653580ae84c471c34872f14a0308c78af71f7243 )
1: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x53) [0xa53d26]
2: (EMetaBlob::replay(MDS*, LogSegment*)+0x7eb) [0x7a737d]
Fixes: #994
Signed-off-by: Sage Weil <sage@newdream.net>
Colin Patrick McCabe [Fri, 15 Apr 2011 22:21:36 +0000 (15:21 -0700)]
config: warn about old-style conf section names
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Greg Farnum [Fri, 15 Apr 2011 22:54:12 +0000 (15:54 -0700)]
man: Update cmds documentation.
You always need to specify a rank if you do journal-check.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Colin Patrick McCabe [Fri, 15 Apr 2011 21:45:56 +0000 (14:45 -0700)]
vstart.sh: use new-style section names in config
Use new-style section names in vstart.sh.
Also update sample.ceph.conf.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Fri, 15 Apr 2011 21:40:49 +0000 (14:40 -0700)]
mon:don't check for old-style monitor section name
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Fri, 15 Apr 2011 21:34:39 +0000 (14:34 -0700)]
cconf: update man page
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Sage Weil [Fri, 15 Apr 2011 21:03:40 +0000 (14:03 -0700)]
objecter: log when we defer a write because of FULL osdmap flag
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Fri, 15 Apr 2011 21:03:20 +0000 (14:03 -0700)]
mkcephfs, init-ceph: tolerate complete lack of a type
We were bailing out of mkcephfs with a config with no mds's defined
(because we set -e and grep returns an error here).
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Colin Patrick McCabe [Fri, 15 Apr 2011 20:59:57 +0000 (13:59 -0700)]
config: do not accept old-style section names
Stop accepting old-style section names of the form $type$id. Instead,
we want section names of the form $type.$id. So [osd0] will no longer
be a valid section name; instead, use [osd.0].
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Fri, 15 Apr 2011 20:49:55 +0000 (13:49 -0700)]
cconf: fix usage; clean up some code
cconf: fix obsolete usage message. Add --list-all-sections flag.
Use new ceph_argparse stuff. Update tests.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Fri, 15 Apr 2011 19:03:12 +0000 (12:03 -0700)]
config: normalize key names, cleanup
Normalize key names in md_config_t::get_val and md_config_t::set_val
Remove unused fields from struct config_option.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Yehuda Sadeh [Fri, 15 Apr 2011 18:15:11 +0000 (11:15 -0700)]
rgw: fix other err related issues
also remove the now redundant formatter->flush()
Yehuda Sadeh [Fri, 15 Apr 2011 17:52:14 +0000 (10:52 -0700)]
rgw: adjustments to error handling
fixing mixup between s3 error code and s3 error message
Colin Patrick McCabe [Fri, 15 Apr 2011 17:37:05 +0000 (10:37 -0700)]
libceph: implement ceph_conf_set and ceph_conf_get
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Sage Weil [Thu, 14 Apr 2011 01:59:14 +0000 (18:59 -0700)]
mds: init metablob MDLog* for EImportStart
This will initialize metablob.my_offset, which makes the parent inode
journaling logic work properly.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 14 Apr 2011 01:06:29 +0000 (18:06 -0700)]
init-ceph: no log_dir default
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 14 Apr 2011 02:01:15 +0000 (19:01 -0700)]
mds: fix journal offset types
Always uint64_t!
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 14 Apr 2011 02:08:05 +0000 (19:08 -0700)]
mds: show migration state names on cancel
Signed-off-by: Sage Weil <sage@newdream.net>
Colin Patrick McCabe [Thu, 14 Apr 2011 23:14:48 +0000 (16:14 -0700)]
rgw: rework error handling a bit
Rados Gateway: get rid of RGWOp::err. We already have req_state::err and
that represents the same thing.
Standardize nomenclature for errors. 'errno' is our internal
representation of the error. 'code' is what is returned by S3.
'message' is the message at the end. Improve rgw_err.
dump_errno shouldn't modify req_state, but just dump the error.
A new function set_req_state_err sets the error based on an 'errno'.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 14 Apr 2011 20:45:13 +0000 (13:45 -0700)]
config: add test for override ordering, comment
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 14 Apr 2011 22:26:20 +0000 (15:26 -0700)]
config: de-globalize reading config file
Reading a config file into any md_config_t structure except g_conf used
to be impossible. This is because the config_option code used to
contain explicit references to g_conf. Those have been removed, so now
any md_config_t should be able to read a configuration file.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 14 Apr 2011 22:18:31 +0000 (15:18 -0700)]
radosgw_admin: fix make check
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 14 Apr 2011 22:10:08 +0000 (15:10 -0700)]
config: make md_config_t.name a value, not ptr
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Yehuda Sadeh [Thu, 14 Apr 2011 21:59:09 +0000 (14:59 -0700)]
rgw: don't modify object owner when setting acls
Yehuda Sadeh [Thu, 14 Apr 2011 21:41:13 +0000 (14:41 -0700)]
rgw: allow changing acl using canned acl
Yehuda Sadeh [Thu, 14 Apr 2011 18:08:17 +0000 (11:08 -0700)]
radosgw_admin: add 'bucket unlink' option
Wido den Hollander [Thu, 31 Mar 2011 17:59:40 +0000 (19:59 +0200)]
mkcephfs: Actually do a mkfs.btrfs
Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Colin Patrick McCabe [Thu, 14 Apr 2011 00:40:02 +0000 (17:40 -0700)]
MonitorStore: use sync_filesystem when available
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Wed, 13 Apr 2011 21:43:21 +0000 (14:43 -0700)]
dout: log_per_instance should work with log_file
Now log_per_instance (the symlink dance) works with both log_file and
log_dir. This will facilitate gradually removing log_dir.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Samuel Just [Tue, 12 Apr 2011 19:02:22 +0000 (12:02 -0700)]
RadosModel: error handling fixes
ReadOp should read the recieve length to prevent buffer error.
Check error codes on WriteOp and ReadOp.
Signed-off-by: Samuel Just <rexludorum@gmail.com>
Colin Patrick McCabe [Wed, 13 Apr 2011 21:49:48 +0000 (14:49 -0700)]
filestore: fix do_getxattr check
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Wed, 13 Apr 2011 20:52:58 +0000 (13:52 -0700)]
FileStore: give better error message about xattrs
Fixes #952.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Sage Weil [Wed, 13 Apr 2011 19:03:31 +0000 (12:03 -0700)]
mds: fix dn unlocking on export_reverse
Triggered by mds_kill_import_at 5. We were clearing the export_locks
prior to calling export_unlock (der!).
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 13 Apr 2011 18:27:21 +0000 (11:27 -0700)]
mds: during export list target second
We need to maintain the invariant that (dir_auth.first==whoami) == is_auth.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 13 Apr 2011 18:26:15 +0000 (11:26 -0700)]
mds: do not start_new_segment on replay_start
We do not need to start a new segment after replay. And in fact must not
journal an ESubtreeMap prior to doing resolve!
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 13 Apr 2011 17:17:24 +0000 (10:17 -0700)]
mds: fix bad import_state check on handle_export_discover
This populates import_state[] with an bad value and leads to crashes like
mds/Migrator.h: In function 'static const char* Migrator::get_import_statename(int)', in thread '0x7f5ea8c97710'
mds/Migrator.h: 112: FAILED assert(0)
ceph version
0.25-670-g85bd67e (commit:
85bd67e0ab58876ad807b44ab2154e84b90a4f30 )
1: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x53) [0xa53ad6]
2: (Migrator::get_import_statename(int)+0x68) [0x91ea0f]
3: (Migrator::show_importing()+0x174) [0x90f640]
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 13 Apr 2011 17:06:34 +0000 (10:06 -0700)]
mds: queue rejoin_waiters on rejoin_ack survivor
For recovering nodes, we eventually open_snap_parents and much later
requeue these waiters. A surviving node wasn't requeueing them at all.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 13 Apr 2011 03:57:11 +0000 (20:57 -0700)]
mds: fix resolve
This was broken by
a01fba175b646f6 when an ambiguous import was changed
from CDIR_AUTH_UNKNOWN to <whoami,whoami> and disambiguate_imports wasn't
updated accordingly. The result was inconsistent results for subtree
ownership on different nodes.
This updates disambiguate_imports to match that EImportStart::replay
change.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 23:08:46 +0000 (16:08 -0700)]
mds: don't check_rstats on non-auth or frozen dirs
If we are, say, auth but frozen (mid-import) the dir content isn't valid
and check_rstats will likely fail.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 22:32:17 +0000 (15:32 -0700)]
mds: fix _freeze_dir assert for refragment case
The is_freezeable_dir() is true at freeze time but not forever after over
the lifetime of the freeze. We split later on and _freeze_dir on the new
fragments, so this assertion isn't necessarily true then.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 22:10:54 +0000 (15:10 -0700)]
mds: fix choose_lock_state() on xlocked object
This crops up on inodes during clientreplay when we reconnect the cap
on the newly created (and still xlocked) object.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Colin Patrick McCabe [Wed, 13 Apr 2011 20:28:52 +0000 (13:28 -0700)]
osd: Use syncfs when available
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Yehuda Sadeh [Wed, 13 Apr 2011 20:29:24 +0000 (13:29 -0700)]
rgw: create bucket with empty name should return a valid error
Yehuda Sadeh [Wed, 13 Apr 2011 17:38:11 +0000 (10:38 -0700)]
rgw: recreation of bucket returns success
unless it was owned by a different user, at which case it
returns -EEXIST.
Greg Farnum [Wed, 13 Apr 2011 17:36:05 +0000 (10:36 -0700)]
mds: update rstats on stray dir when you rename over existing inode.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Colin Patrick McCabe [Wed, 13 Apr 2011 17:02:25 +0000 (10:02 -0700)]
sample.ceph.conf: add log file and pid file
These really should be included in a sample...
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Wed, 13 Apr 2011 16:59:16 +0000 (09:59 -0700)]
vstart.sh: use "log file" instead of "log dir"
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Yehuda Sadeh [Wed, 13 Apr 2011 15:45:43 +0000 (08:45 -0700)]
rgw: listing non existent bucket returns NoSuchBucket
Sage Weil [Wed, 13 Apr 2011 02:57:18 +0000 (19:57 -0700)]
Merge remote branch 'origin/mon_mds'
Colin Patrick McCabe [Wed, 13 Apr 2011 00:20:21 +0000 (17:20 -0700)]
osd: move MAX_CEPH_OBJECT_NAME_LEN into object.h
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Tue, 12 Apr 2011 23:41:06 +0000 (16:41 -0700)]
osd: check obj name length to avoid ENAMETOOLONG
Since the object store is ultimately based on ext3, ext4, or btrfs, and
object names ultimately get translated into file names, we need to
impose a corresponding limit on the length of ceph object names.
Otherwise, the "writeback" thread in the FileStore gets ENAMETOOLONG,
and the transaction does not succeed, even though we journalled it.
Perhaps we will extend or eliminate MAX_CEPH_OBJECT_NAME_LEN at some
point by using prehashing or some other technique. Until then, we need
to be sure to check for this.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Josh Durgin [Tue, 12 Apr 2011 23:39:48 +0000 (16:39 -0700)]
librbd: don't write to stdout
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Colin Patrick McCabe [Tue, 12 Apr 2011 21:05:21 +0000 (14:05 -0700)]
Add test_mutate
Add test_mutate, in an effort to track down an objecter bug.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 21:00:24 +0000 (14:00 -0700)]
mdsmap: initialize standby_for_rank
This is initialized in MDSMonitor anyway; do so where for completeness.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 21:13:56 +0000 (14:13 -0700)]
mon: simplify mds follow checks
Instead of assigning followers in the last_beacon laggy check loop, do it
at the end, the same way we let standby nodes take over.
This also fixes a bug where a non-standby node (say, up:replay) that used
to be up:standby-replay and has standby_for_rank set gets reset back to
up:standby-replay.
Fixes: #1001
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 20:54:53 +0000 (13:54 -0700)]
mon: simplify mds laggy check
We should never have a laggy standby, so technically this doesn't change
any behavior, but it makes the flow less confusing.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 20:33:32 +0000 (13:33 -0700)]
mon: don't take over for a standby-replay
If a standby-replay is laggy we shouldn't "take over" for them (they're
not part of the cluster yet). They should be removed like a regular
standby.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Colin Patrick McCabe [Tue, 12 Apr 2011 21:04:06 +0000 (14:04 -0700)]
rados-tool: use init_with_config interface
Programs that use both librados and common_init should use
init_with_config.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Sage Weil [Mon, 11 Apr 2011 21:54:59 +0000 (14:54 -0700)]
mds: improve scatterlog debug msg
Sage Weil [Wed, 6 Apr 2011 22:12:57 +0000 (15:12 -0700)]
mds: clear flush state on rejoin ack
If we sent scatterlock state during rejoin, the auth will send us an inode
base. Clear scatterlock flush state if that happens.
Fixes: #637
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 6 Apr 2011 22:09:39 +0000 (15:09 -0700)]
mds: send any dirty scatterlock state on rejoin
Not just inodes for auth dirfrags, but for any inode with dirty scatterlock
state. Include the root inode.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 6 Apr 2011 20:29:38 +0000 (13:29 -0700)]
mds: reset dirty->flushing on rejoin scatterflush
Reset dirty/flushing state during rejoin.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Tue, 12 Apr 2011 18:08:43 +0000 (11:08 -0700)]
mds: drop debugging cruft
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 18:08:39 +0000 (11:08 -0700)]
mds: make _create_system_file dirty dentries properly
Properly dirty the new dentries so they get written to the directory
objects later on.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Tue, 12 Apr 2011 18:07:54 +0000 (11:07 -0700)]
mds: fix create_mydir_hierarchy to save dir
Mark the dentries dirty so they get saved to disk (they're not journaled!).
This fixes rstat problems on startup, where populate_mydir was recreating
the entries and munging rstats accordingly.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Colin Patrick McCabe [Tue, 12 Apr 2011 17:55:25 +0000 (10:55 -0700)]
radosacl: read Ceph configuration file
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Tue, 12 Apr 2011 16:38:50 +0000 (09:38 -0700)]
cephtool: don't print anything on SIGTERM, SIGINT
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Sage Weil [Mon, 11 Apr 2011 17:18:26 +0000 (10:18 -0700)]
mds: don't crash on bad export_dir command
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Mon, 11 Apr 2011 17:14:21 +0000 (10:14 -0700)]
mds: fix file_eval on subtree roots
We were going from mix->sync when we shouldn't. Fix mis-coded filelock
and look at _lock_ state, not inode's!
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Mon, 11 Apr 2011 23:30:10 +0000 (16:30 -0700)]
Merge remote branch 'origin/dead-code'
Sage Weil [Mon, 11 Apr 2011 23:22:11 +0000 (16:22 -0700)]
osd: fix ref leak on pg when queueing
op_wq.queue() takes a ref; don't take one here too. We were leaking like
crazy.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Mon, 11 Apr 2011 23:21:41 +0000 (16:21 -0700)]
osd: take reference for RepModify
We put in the completions on done; take the matching reference.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Mon, 11 Apr 2011 23:18:39 +0000 (16:18 -0700)]
osd: fix race in op enqueuing
This is never really exposed except when op_threads == 0.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Mon, 11 Apr 2011 16:43:25 +0000 (09:43 -0700)]
mon: simplify osd health output
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Mon, 11 Apr 2011 16:36:25 +0000 (09:36 -0700)]
osd: only log scrub errors (not ok's)
Otherwise we fill up the error log with "foo is ok!" messages.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Samuel Just [Mon, 11 Apr 2011 16:45:57 +0000 (09:45 -0700)]
TestSnaps: Fix compile error
Introduced in
0e371de79e4047b92317dee353f6d75c2aba4260 .
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Colin Patrick McCabe [Sat, 9 Apr 2011 01:14:13 +0000 (18:14 -0700)]
cfuse: pass through SIGTERM, SIGINT to FUSE
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Fri, 8 Apr 2011 22:52:40 +0000 (15:52 -0700)]
ceph_fuse_ll_main: restructure error handling
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Josh Durgin [Sat, 9 Apr 2011 00:39:04 +0000 (17:39 -0700)]
librbdtest: check for error on out of bounds I/O
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Josh Durgin [Sat, 9 Apr 2011 00:38:07 +0000 (17:38 -0700)]
librbd: check for out of bounds I/O in all forms of read/write
This was found by qemu-io tests, which tried to read and write past
the end of an rbd image. The test hung waiting for a completion that
was never scheduled, since it did not check the return value of
rbd_aio_write.
Reported-by: Stefan Hajnoczi <stefanha@gmail.com>
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Brian Chrisman [Fri, 8 Apr 2011 22:42:16 +0000 (15:42 -0700)]
cfuse recognizing same xattr subset as kernel client
Hopefully this patch is formatted/signed off correctly.
Signed-off-by: Brian Chrisman <brchrisman@gmail.com>
Samuel Just [Fri, 8 Apr 2011 23:13:14 +0000 (16:13 -0700)]
TestSnaps.cc: allow client id to be overridden
CEPH_CLIENT_ID environment variable if set now overrides the rados
client id for testsnaps
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Fri, 8 Apr 2011 20:11:45 +0000 (13:11 -0700)]
rgw: utility, not daemon
- we don't want to open a log file
- we don't want to print a stability warning
- we don't want to fork (not that we do, but anyway!)
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Greg Farnum [Fri, 8 Apr 2011 18:17:48 +0000 (11:17 -0700)]
CDir: check_rstats will now print out dir stats whenever there's a bug.
Previously it only printed out dir stats at high debug levels, which
meant you could get output of the dentries without seeing what the
totals were supposed to be!
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Colin Patrick McCabe [Fri, 8 Apr 2011 00:03:11 +0000 (17:03 -0700)]
obsync: preserve ACLs
Preserve ACLs by default. Also add --no-preserve-acls option to disable
this behavior.
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 7 Apr 2011 22:16:15 +0000 (15:16 -0700)]
obsync: escape obj names between S3 and local FS
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Greg Farnum [Thu, 7 Apr 2011 23:17:20 +0000 (16:17 -0700)]
osd: futz with stat again.
We really need to fill in the result, even if it's that the object
doesn't exist!
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Samuel Just [Tue, 5 Apr 2011 19:04:45 +0000 (12:04 -0700)]
test/osd: Add latency stat collection to TestSnaps.cc/RadosModel.h
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Thu, 7 Apr 2011 21:38:48 +0000 (14:38 -0700)]
ReplicatedPG: fix error in snap_trimmer
newsnaps continued to be used after it was swapped with coi.snaps.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Tommi Virtanen [Thu, 7 Apr 2011 22:05:02 +0000 (15:05 -0700)]
crush, clitest: Port old test_crushtool.sh to clitest.
Also test --help, while we're at it.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Sage Weil [Thu, 7 Apr 2011 21:57:41 +0000 (14:57 -0700)]
osd: more futzing with stat
We can get here when the object doesn't exist if the client specifies
may read and may write (in this case, Filer::probe). Look at the exists
bit in the object context. If the object is supposed to exist, we should never get ENOENT from stat.
Signed-off-by: Sage Weil <sage@newdream.net>
Tommi Virtanen [Thu, 7 Apr 2011 18:47:35 +0000 (11:47 -0700)]
libceph: Make header usable from plain old C.
Fixes: #986
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Tommi Virtanen [Thu, 7 Apr 2011 21:42:05 +0000 (14:42 -0700)]
crush: Remove dead code.
The Makefile never integrated with the surrounding automake
setup, and is unused.
The test helper has failed to compile for quite a long time.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Tommi Virtanen [Thu, 7 Apr 2011 21:34:37 +0000 (14:34 -0700)]
crush: Remove dead code.
Looks like these never went anywhere.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Wido den Hollander [Thu, 7 Apr 2011 10:23:34 +0000 (12:23 +0200)]
radosgw: Remove PHP setting from VirtualHost documentation
Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Sage Weil <sage@newdream.net>
Tommi Virtanen [Thu, 7 Apr 2011 21:25:12 +0000 (14:25 -0700)]
osd: Remove dead code.
RAID4PG has been "temporarily ripped out" for 3.5 years.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Tommi Virtanen [Thu, 7 Apr 2011 21:22:39 +0000 (14:22 -0700)]
msg, os: Remove dead code.
Looks like these never went anywhere.
Signed-off-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
Colin Patrick McCabe [Thu, 7 Apr 2011 21:22:15 +0000 (14:22 -0700)]
test-obsync.py: add test for --follow-symlinks
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 7 Apr 2011 21:10:29 +0000 (14:10 -0700)]
test-obsync: some fixes, be more verbose
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>
Colin Patrick McCabe [Thu, 7 Apr 2011 17:53:37 +0000 (10:53 -0700)]
boto_tool.py: fix rmbucket
Signed-off-by: Colin McCabe <colin.mccabe@dreamhost.com>