]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Sage Weil [Sat, 31 Dec 2011 00:44:53 +0000 (16:44 -0800)]
cmp: fix 5-uple operator==
Doh!
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Fri, 30 Dec 2011 23:51:45 +0000 (15:51 -0800)]
osd: do not backfill if any objects are missing on the primary
Someday we need to do something smarter so that a single unfound object
doesn't hold up replication of other objects. For now, this is the
simplest thing to do.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Fri, 30 Dec 2011 20:23:02 +0000 (12:23 -0800)]
osd: handle backfill_target for pick_newest_available
The it may not be missing on the backfill_target if it is after the
last_backfill marker.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Fri, 30 Dec 2011 20:19:32 +0000 (12:19 -0800)]
osd: return EINVAL if multi op specified with no src object name
This avoids crashing later in do_osd_ops() with something like
osd/ReplicatedPG.cc: In function 'int ReplicatedPG::do_osd_ops(ReplicatedPG::OpContext*, std::vector<OSDOp, std::allocator<OSDOp> >&, ceph::bufferlist&)', in thread '
7f27e2d7e700 '
osd/ReplicatedPG.cc: 1386: FAILED assert(src_obc)
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Fri, 30 Dec 2011 19:39:30 +0000 (11:39 -0800)]
hobject_t: fix operator==, !=
These weren't comparing key.
While we're at it, clean this up by using generic macros for writing
these operators, so we don't get it wrong half the time.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Fri, 30 Dec 2011 19:37:43 +0000 (11:37 -0800)]
cmp.h: define macros for creating comparison operators
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Fri, 30 Dec 2011 18:43:33 +0000 (10:43 -0800)]
Merge remote branch 'gh/master' into wip-backfill
Sage Weil [Fri, 30 Dec 2011 17:17:06 +0000 (09:17 -0800)]
.gitignore: src/ocf/ceph
Signed-off-by: Sage Weil <sage@newdream.net>
Florian Haas [Thu, 29 Dec 2011 19:58:02 +0000 (20:58 +0100)]
Spec: conditionally build ceph-resource-agents package
Put OCF resource agents in a separate subpackage,
to be enabled with a separate build conditional
(--with ocf).
Make the subpackage depend on the resource-agents
package, which provides the ocf-shellfuncs library
that the Ceph RAs use.
Signed-off-by: Florian Haas <florian@hastexo.com>
Florian Haas [Thu, 29 Dec 2011 19:58:01 +0000 (20:58 +0100)]
Add OCF-compliant resource agent for Ceph daemons
Add a wrapper around the ceph init script that makes
MDS, OSD and MON configurable as Open Cluster Framework
(OCF) compliant cluster resources. Allows Ceph
daemons to tie in with cluster resource managers that
support OCF, such as Pacemaker (http://www.clusterlabs.org).
Disabled by default, configure --with-ocf to enable.
Signed-off-by: Florian Haas <florian@hastexo.com>
Sage Weil [Fri, 30 Dec 2011 16:06:55 +0000 (08:06 -0800)]
mon: fix full ratio updates
- update them independently
- only if we are leader
- fix type for nearfull_ratio
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Fri, 30 Dec 2011 16:06:06 +0000 (08:06 -0800)]
mon: don't ignore first full ratio update callback
We get a callack on startup. Don't ignore it.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Fri, 30 Dec 2011 15:45:21 +0000 (07:45 -0800)]
mon: only update full_ratio if we're the leader
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Fri, 30 Dec 2011 15:42:20 +0000 (07:42 -0800)]
Merge remote branch 'gh/wip-cleanup'
Sage Weil [Fri, 30 Dec 2011 01:15:07 +0000 (17:15 -0800)]
mon: make full ratio config change callback safe
We can't propose_pending() from any context; do this in the tick() thread,
with the proper locking. Among other things, this fixes the crash on
startup that is now triggered due to
eba235f2 .
Signed-off-by: Sage Weil <sage@newdream.net>
Josh Durgin [Thu, 29 Dec 2011 23:43:55 +0000 (15:43 -0800)]
clitests: update for new error format
This was changed in
1f434da8a3ca4db830d1f3b0d87e5df941d85f2d
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Josh Durgin [Thu, 29 Dec 2011 23:28:16 +0000 (15:28 -0800)]
clitests: update monmaptool test
e93961c11119942eae3a4cd14a79f779a5a4d277 changed output format.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Florian Haas [Tue, 27 Dec 2011 10:43:47 +0000 (11:43 +0100)]
init script: be LSB compliant for exit code on status
An exit code of 1 on status is defined in LSB as
"program is dead, but pid file exists". Check for existence
of this pid file, and only set the exit status 1 if it's still there.
Set it to 3 ("program is not running") otherwise.
Reference: http://refspecs.linuxbase.org/LSB_3.1.0/LSB-Core-generic/LSB-Core-generic/iniscrptact.html
Signed-off-by: Florian Haas <florian@hastexo.com>
Sage Weil [Thu, 29 Dec 2011 19:58:28 +0000 (11:58 -0800)]
keyring: print more useful errors to log/err
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 19:57:55 +0000 (11:57 -0800)]
common: trigger all observers on startup
Among other things, this makes err-to-stderr and friends initialize
properly in the DoutStreamBuf.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 19:24:50 +0000 (11:24 -0800)]
common: make cpp_strerror output prettier
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 19:24:12 +0000 (11:24 -0800)]
librados: check for monclient::init() error
I think this fixes #1835.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 17:59:26 +0000 (09:59 -0800)]
qa: load-gen-mix-small.sh
Yehuda Sadeh [Thu, 29 Dec 2011 17:46:55 +0000 (09:46 -0800)]
rgw: turn on cache by default
Sage Weil [Thu, 29 Dec 2011 17:41:00 +0000 (09:41 -0800)]
osd: explicitly track leading edge of backfill
backfill_pos is the leading edge; last_backfill is the trailing edge.
Anything inbetween is either pushed, doesn't exist, or in
backfills_in_flight.
For operations on non-degraded (in-progress) objects in that window, book
the stats update in pending_backfill_updates so that it will get applied
when last_backfill is advanced.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Wed, 30 Nov 2011 01:18:48 +0000 (17:18 -0800)]
mds: assert if we get an EINVAL on our truncate
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 17:00:46 +0000 (09:00 -0800)]
osd: get fsid from monmap, not osdmap
We may not have a valid OSDMap in all of these cases (notably, during
boot). Always take the fsid from the monmap, which will be valid after
we've authenticated.
This fixes messages like
2011-12-29 08:53:44.530830
7ff3595e2700 mon.a@0(leader).pg v5 handle_statfs on fsid
00000000 -0000-0000-0000-
000000000000 !=
f8a6383d -5fbe-4f65-907e-
f8d09e1d540d
on the monitor from MPGStats messages with a bad fsid right after osd boot.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 16:59:00 +0000 (08:59 -0800)]
monc: get latest monmap during authentication
Tell the monitor which monmap version we have in our initial auth message.
Make the monitor send the latest monmap if it has something newer. This
ensures that once authentication completes the monclient has the latest
monmap and a valid fsid.
Fixes: #1848
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Thu, 29 Dec 2011 16:43:41 +0000 (08:43 -0800)]
osd: catch authenticate error on startup
Signed-off-by: Sage Weil <sage@newdream.net>
Greg Farnum [Fri, 23 Dec 2011 22:27:15 +0000 (14:27 -0800)]
osdmap: add const markers to some unfixed functions
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Yehuda Sadeh [Thu, 29 Dec 2011 01:00:19 +0000 (17:00 -0800)]
rgw: removing swift user index when removing user
Yehuda Sadeh [Thu, 29 Dec 2011 00:50:36 +0000 (16:50 -0800)]
rgw-admin: remove subuser index when required
Sage Weil [Thu, 29 Dec 2011 00:42:00 +0000 (16:42 -0800)]
osd: fix push completion check
Only check backfill if we pushed to the backfill target. And avoid teh hash
lookup in the general case.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Yehuda Sadeh [Thu, 29 Dec 2011 00:34:03 +0000 (16:34 -0800)]
rgw: clone operation should only update index for main category
Yehuda Sadeh [Thu, 29 Dec 2011 00:33:14 +0000 (16:33 -0800)]
rgw: fix cache interface (was not overloading method)
Yehuda Sadeh [Wed, 28 Dec 2011 23:10:10 +0000 (15:10 -0800)]
rgw: fix bucket creation
Yehuda Sadeh [Fri, 23 Dec 2011 20:46:05 +0000 (12:46 -0800)]
rgw: write bucket info in one operation
Greg Farnum [Fri, 23 Dec 2011 17:56:42 +0000 (09:56 -0800)]
Objecter: fix local reads one more time.
Document it a little since we've gotten it wrong so often.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Samuel Just [Fri, 23 Dec 2011 01:41:40 +0000 (17:41 -0800)]
Merge remote branch 'upstream/master' into wip-backfill
Conflicts:
src/include/object.h
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Fri, 23 Dec 2011 01:38:39 +0000 (17:38 -0800)]
ReplicatedPG: objects currently begin backfilled are degraded
pending_stat_updates has also been renamed to pending_backfill_updates.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Fri, 23 Dec 2011 01:24:13 +0000 (17:24 -0800)]
ReplicatedPG: fill in backfill_peer in on_activate
Previously, there was a race between issue_repop/do_op and
start_recovery_ops.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Fri, 23 Dec 2011 01:17:40 +0000 (17:17 -0800)]
ReplicatedPG: only pull in one backfill peer at a time
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Thu, 22 Dec 2011 23:25:00 +0000 (15:25 -0800)]
filestore: fix config observer
Actually, I don't think this was fully implemented to begin with, so it's
not a 'fix' per se. This will let you use injectargs to adjust the
filestore config options during runtime.
Signed-off-by: Sage Weil <sage@newdream.net>
Samuel Just [Thu, 22 Dec 2011 23:17:22 +0000 (15:17 -0800)]
MOSDPGRepScrub: Fix typo in MOSDPGRepScrub
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Thu, 22 Dec 2011 22:32:15 +0000 (14:32 -0800)]
PG: update stats from master only if not backfilling
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Thu, 22 Dec 2011 20:44:38 +0000 (12:44 -0800)]
PG: backfill info should be cleared on recovery reset
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Thu, 22 Dec 2011 17:44:33 +0000 (09:44 -0800)]
ReplicatedPG: init backfill infos to last_backfill
We can scan starting from last_backfill to avoid rescanning portions
of the collection recovered by normal recovery. collection_list_partial
now includes begin if present. next will be <= the next object in the
collection. This way we can scan starting at last_backfill without
skipping last_backfill.
Signed-off-by: Samuel Just <rexludorum@gmail.com>
Samuel Just [Thu, 22 Dec 2011 02:10:44 +0000 (18:10 -0800)]
ReplicatedPG: update last_backfill when pushes complete
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Thu, 22 Dec 2011 00:45:11 +0000 (16:45 -0800)]
ReplicatedPG: simplify recover_backfill
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Thu, 22 Dec 2011 22:00:23 +0000 (14:00 -0800)]
Merge branch 'wip-signal'
Samuel Just [Thu, 22 Dec 2011 20:33:48 +0000 (12:33 -0800)]
MOSDRepScrub: use header.version for payload version
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Thu, 22 Dec 2011 20:16:06 +0000 (12:16 -0800)]
Merge branch 'stable'
Henry C Chang [Thu, 22 Dec 2011 10:48:29 +0000 (18:48 +0800)]
monmap: iterate over addr_name when printing summary
The rank is now ordered by IP address. We should iterate over
addr_name.
Signed-off-by: Henry C Chang <henry.cy.chang@gmail.com>
Henry C Chang [Thu, 22 Dec 2011 10:49:04 +0000 (18:49 +0800)]
monmap: clear addr_name map on calculating ranks
We should clear addr_name before filling it. Otherwise, the removed
mon will stay there and cause incorrect rank assignment.
Signed-off-by: Henry C Chang <henry.cy.chang@gmail.com>
Henry C Chang [Thu, 22 Dec 2011 10:47:25 +0000 (18:47 +0800)]
interval_set: fix truncation of _size
_size is type of int64_t. Use int to store the value of _size
will cause value truncation.
Signed-off-by: Henry C Chang <henry.cy.chang@gmail.com>
Sage Weil [Wed, 21 Dec 2011 22:21:37 +0000 (14:21 -0800)]
osd: remove SIGTERM cruft
The default handler will exit(0). The got_sigterm stuff was dead code.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 21 Dec 2011 22:17:42 +0000 (14:17 -0800)]
mon: drop special SIGTERM handler
Default does exit(0).
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 21 Dec 2011 22:17:19 +0000 (14:17 -0800)]
mds: drop special SIGTERM handler
Default does exit(0).
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 21 Dec 2011 22:17:00 +0000 (14:17 -0800)]
exit(0) on SIGTERM by default
Signed-off-by: Sage Weil <sage@newdream.net>
Samuel Just [Wed, 21 Dec 2011 19:19:22 +0000 (11:19 -0800)]
ReplicatedPG: Initialize blocked_by in ObjectContext constructor
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Wed, 21 Dec 2011 04:11:51 +0000 (20:11 -0800)]
Merge pull request #7 from kylemarsh/wip-obsync-swift-metadata
obsync: pull object metadata from swift store
Samuel Just [Wed, 21 Dec 2011 01:35:55 +0000 (17:35 -0800)]
ReplicatedPG: take references for blocked_by and blocking
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Kyle Marsh [Wed, 21 Dec 2011 01:08:21 +0000 (17:08 -0800)]
obsync: pull object metadata from swift store
Obsync wasn't pulling object metadata from swift stores and thus wasn't
syncing metadata when reading from a swift store. This commit fixes that.
Samuel Just [Wed, 21 Dec 2011 01:05:29 +0000 (17:05 -0800)]
Merge remote branch 'upstream/wip-backfill-ordering' into wip-backfill
Samuel Just [Wed, 21 Dec 2011 00:52:38 +0000 (16:52 -0800)]
PG: add some documentation
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Wed, 21 Dec 2011 00:50:35 +0000 (16:50 -0800)]
ReplicatedPG: delay op while snapdir is missing/degraded
We cannot get/update a snapcontext if snapdir is missing/degraded.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Tue, 20 Dec 2011 23:28:11 +0000 (15:28 -0800)]
ReplicatedPG: don't manage waiting_on_backfill in start/finish_recovery_op
Set waiting_on_backfill in recover_backfill and clear in do_scan.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Yehuda Sadeh [Tue, 20 Dec 2011 19:39:32 +0000 (11:39 -0800)]
rgw: fix subuser key name when purging subuser keys
Yehuda Sadeh [Tue, 20 Dec 2011 19:00:39 +0000 (11:00 -0800)]
radosgw-admin: add --purge-keys option
Samuel Just [Tue, 20 Dec 2011 18:53:36 +0000 (10:53 -0800)]
ReplicatedPG: apply_repop: apply local_t before op_t
We create snap_collections in local_t and clone into them in op_t.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Josh Durgin [Tue, 20 Dec 2011 02:03:14 +0000 (18:03 -0800)]
librados: return -EROFS when trying to write to a snapshot
operate_read doesn't need this check because it does not write.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Josh Durgin [Tue, 20 Dec 2011 02:00:16 +0000 (18:00 -0800)]
librados: make getxattrs ENOMEM return negative
This is more consistent with the rest of librados.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Samuel Just [Tue, 20 Dec 2011 00:26:56 +0000 (16:26 -0800)]
PG: Do not update_snap_collections for log entries > last_backfill
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Tue, 20 Dec 2011 00:26:31 +0000 (16:26 -0800)]
PG: Fix stat debug output
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Sat, 17 Dec 2011 02:04:32 +0000 (18:04 -0800)]
calc_acting: Prefer up[0] as primary if possible
Previously, we could get into a state where although up[0] has been
fully backfilled, acting[0] could be selected as a primary if it is able
to pull another peer into the acting set. This also collects the logic
of choosing the best info into a helper function.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Yehuda Sadeh [Tue, 20 Dec 2011 00:00:27 +0000 (16:00 -0800)]
rgw: add timeout to init path
Samuel Just [Mon, 19 Dec 2011 22:50:17 +0000 (14:50 -0800)]
MOSDRepScrub,ReplicatedPG: Add scrub_to to MOSDRepScrub
When scrub_from is set, also set scrub_to to the primary's
last_update_applied (which will also be the official last_update before
finalizing scrub began). The replica instead of waiting for
last_update_applied to catch up to last_update will wait for
last_update_applied to catch up to active_rep_scrub->scrub_to. This
avoids a race where the replica scrub is requeued before all of the
currently queued sub-ops have been processed.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Sage Weil [Mon, 19 Dec 2011 21:47:43 +0000 (13:47 -0800)]
mon: update man page to document --mkfs stuff
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 30 Nov 2011 01:21:42 +0000 (17:21 -0800)]
mds: misc assertions about truncation
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 30 Nov 2011 01:17:25 +0000 (17:17 -0800)]
osd: EINVAL on truncate to huge object size
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Mon, 19 Dec 2011 22:00:59 +0000 (14:00 -0800)]
Merge pull request #6 from kylemarsh/wip-obsync-swift
Wip obsync swift
Yehuda Sadeh [Mon, 19 Dec 2011 21:54:04 +0000 (13:54 -0800)]
rgw: remove temp context in prepare_get_obj
Yehuda Sadeh [Mon, 19 Dec 2011 21:38:58 +0000 (13:38 -0800)]
rgw: fix xml parser internal structure leak
Yehuda Sadeh [Mon, 19 Dec 2011 21:38:40 +0000 (13:38 -0800)]
rgw: fix a leak of acl structure (in req_state)
Yehuda Sadeh [Mon, 19 Dec 2011 21:54:04 +0000 (13:54 -0800)]
rgw: remove temp context in prepare_get_obj
Yehuda Sadeh [Mon, 19 Dec 2011 21:38:58 +0000 (13:38 -0800)]
rgw: fix xml parser internal structure leak
Yehuda Sadeh [Mon, 19 Dec 2011 21:38:40 +0000 (13:38 -0800)]
rgw: fix a leak of acl structure (in req_state)
Greg Farnum [Mon, 19 Dec 2011 21:25:27 +0000 (13:25 -0800)]
Merge branch 'wip-osd-maybe-created'
Sage Weil [Mon, 19 Dec 2011 21:24:46 +0000 (13:24 -0800)]
Merge branch 'wip-osd-fsid'
Sage Weil [Mon, 19 Dec 2011 21:24:31 +0000 (13:24 -0800)]
doc: fix typo
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 30 Nov 2011 22:13:47 +0000 (14:13 -0800)]
osd: --get-journal-fsid
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 30 Nov 2011 22:13:14 +0000 (14:13 -0800)]
filejournal: uuid for fsid
Decode old header struct, but encode new class using more normal encoding
style. Embed in a bufferlist for later extensibility. Use the first
64 bits of the uuid for the per-entry magic, as before.
When we load an old fsid, we mirror the 64-bits.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Wed, 30 Nov 2011 05:49:49 +0000 (21:49 -0800)]
filestore: make fsid uuid_d instead of uint64_t
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Wed, 30 Nov 2011 05:06:29 +0000 (21:06 -0800)]
osd: --get-osd-fsid and --get-cluster-fsid
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Wed, 30 Nov 2011 05:06:10 +0000 (21:06 -0800)]
osd: store osd_fsid as text in osd_data dir
along with ceph_fsid (the cluster fsid) and a few other things.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Wed, 30 Nov 2011 05:05:20 +0000 (21:05 -0800)]
osd: include osd_fsid in OSDSuperblock
Generated during mkfs.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Wed, 30 Nov 2011 04:46:42 +0000 (20:46 -0800)]
osd: rename OSDSuperblock::fsid -> cluster_fsid
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Sage Weil [Mon, 19 Dec 2011 16:04:53 +0000 (08:04 -0800)]
doc: fix mon cluster expansion docs
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Mon, 19 Dec 2011 16:03:59 +0000 (08:03 -0800)]
mon: pull addr from ceph.conf, mon_host as needed when joining mon cluster
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Mon, 19 Dec 2011 15:57:45 +0000 (07:57 -0800)]
mon: fix setting of mon addr when joining a cluster
Signed-off-by: Sage Weil <sage@newdream.net>