]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Samuel Just [Fri, 1 Jun 2012 16:58:42 +0000 (09:58 -0700)]
OSD: push_waiters is no longer used
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Mon, 7 May 2012 20:00:41 +0000 (13:00 -0700)]
OSD: do not lock osd during dequeue_op
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Mon, 7 May 2012 18:32:59 +0000 (11:32 -0700)]
OSD: don't assume pending pg removals have flushed
_create_lock_pg might encounter a preexisting pg collection simply
because the removal transaction had not yet completed.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Mon, 7 May 2012 18:00:52 +0000 (11:00 -0700)]
ReplicatedPG: change ReplicatedPG debug output to match PG
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Mon, 7 May 2012 17:33:59 +0000 (10:33 -0700)]
ReplicatedPG: do not eval_repop if aborted
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Fri, 4 May 2012 00:48:20 +0000 (17:48 -0700)]
OSD: remove superfluous pg get/put around enqueue_op
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 12 Jun 2012 00:05:40 +0000 (17:05 -0700)]
PG,OSD: fix op checking in pg, take_waiters during ActMap
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 3 May 2012 20:40:54 +0000 (13:40 -0700)]
PG,OSD: add OSD::queue_for_op, use in PG::queue_op
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Fri, 1 Jun 2012 16:50:10 +0000 (09:50 -0700)]
OSD: check for deleting in process_peering_event
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Fri, 1 Jun 2012 16:49:55 +0000 (09:49 -0700)]
PG: use osd->requeue_ops for ops, pg->queue_for_peering to requeue pg
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Wed, 13 Jun 2012 18:27:49 +0000 (11:27 -0700)]
PG: compound messages must carry epoch_sent for each part
Query and Notify messages include logical messages from multiple
pgs. Each logical message (pg_query_t and pg_notify_t) now
contains an epoch_sent.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Wed, 13 Jun 2012 04:25:39 +0000 (21:25 -0700)]
PG: CephPeeringEvents can now be descriptively printed
The CephPeeringEvt constructor is now templated to allow
storing a description string for debugging.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 31 May 2012 05:19:58 +0000 (21:19 -0800)]
OSD: initialize pgs in get_or_create_pg via handle_create
Previously, pgs were initialized via Info/Log/etc. Since the event
which triggered the pg creation may now be queued, map update events may
occur before the event is processed. Thus, get_or_create_pg now handles
the initialization prior to queuing the event.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 31 May 2012 05:19:48 +0000 (22:19 -0700)]
PG: include info and query by value in peering events
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 24 Apr 2012 23:00:49 +0000 (16:00 -0700)]
OSD,PG: handle pg map advance in process_peering_event
The pg map will now be advanced in process_peering_event (in advance_pg)
to allow handle_osd_map to not grab pg locks in-line. handle_osd_map
queues NullEvts to ensure that each pg is updated in a timely fashion.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 12 Jun 2012 23:01:05 +0000 (16:01 -0700)]
osd/: Make pg osdmap be independent of osd, other pg maps
This will allow handle_osd_map to not stop other work queues.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 24 Apr 2012 00:40:58 +0000 (17:40 -0700)]
OSD,PG: Move Op,SubOp queueing into PG
PG now handles delaying/discarding messages since pg map epoch may not
be the same as the OSD map.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 31 May 2012 04:51:29 +0000 (21:51 -0700)]
PG: process peering events in a queue
Peering events are now queued via queue_peering_event in the
peering_queue.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 31 May 2012 04:50:27 +0000 (21:50 -0700)]
PG: use intrusive_ptr in CephPeeringEvt
Properly disposing of the event_base member of CephPeeringEvt
requires use of intrusive_ptr.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Wed, 18 Apr 2012 22:39:46 +0000 (15:39 -0700)]
osd/: move history update from handle_pg_query into pg
Previously, replica history was updated in OSD::handle_pg_query.
Updating the history is now handled in the pg state machine.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Wed, 18 Apr 2012 22:20:02 +0000 (15:20 -0700)]
OSD,PG: push message checking to pg
old_peering_evt now checks CephPeeringEvts generically in
PG::handle_peering_event().
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Wed, 18 Apr 2012 22:19:31 +0000 (15:19 -0700)]
OSD: Remove handle_pg_missing, MOSDPGMissing no longer used
Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Samuel Just [Wed, 18 Apr 2012 21:11:26 +0000 (14:11 -0700)]
PG: Move handle_* methods to PG
PG now calls handle_event in RecoveryState.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Apr 2012 23:54:06 +0000 (16:54 -0700)]
PG: CephPeeringEvt
CephPeeringEvt is now the supertype for all peering state machine
events. This will allow us to generalize checking for stale peering
events and delaying events for future maps.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 3 Jul 2012 20:58:56 +0000 (13:58 -0700)]
OSD,PG::scrub() move pg->put() into queue process
This clarifies ownership of the pg reference.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Wed, 4 Jul 2012 20:59:04 +0000 (13:59 -0700)]
osd: add missing formatter close_section() to scrub status
Also add braces to make the open/close matchups easier to see. Broken
by
f36617392710f9b3538bfd59d45fd72265993d57 .
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Wed, 4 Jul 2012 16:30:21 +0000 (09:30 -0700)]
Merge branch 'stable'
Conflicts:
src/test/cli/radosgw-admin/help.t
Wido den Hollander [Wed, 4 Jul 2012 13:46:04 +0000 (15:46 +0200)]
librados: Bump the version to 0.48
Signed-off-by: Wido den Hollander <wido@widodh.nl>
Signed-off-by: Sage Weil <sage@inktank.com>
Samuel Just [Tue, 3 Jul 2012 19:00:32 +0000 (12:00 -0700)]
librados: add assert_version as an operation on an ObjectOperation
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 3 Jul 2012 22:35:29 +0000 (15:35 -0700)]
ReplicatedPG: do not set reply version to last_update
The version should be oi.user_version as set above.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Wed, 4 Jul 2012 01:51:02 +0000 (18:51 -0700)]
rgw: initialize fields of RGWObjEnt
This fixes various valgrind warnings triggered by the s3test
test_object_create_unreadable.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 23:49:29 +0000 (16:49 -0700)]
Merge remote-tracking branch 'gh/wip-crush'
Yehuda Sadeh [Wed, 27 Jun 2012 00:28:51 +0000 (17:28 -0700)]
rgw-admin: use correct modifier with strptime
Bug #2658: used %I (12h) instead of %H (24h)
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh [Thu, 21 Jun 2012 22:40:27 +0000 (15:40 -0700)]
rgw: send both swift x-storage-token and x-auth-token
older clients need x-storage-token, newer x-auth-token
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh [Thu, 21 Jun 2012 22:17:19 +0000 (15:17 -0700)]
rgw: radosgw-admin date params now also accept time
The date format now is "YYYY-MM-DD[ hh:mm:ss]". Got rid of
the --time param for the old ops log stuff.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Conflicts:
src/test/cli/radosgw-admin/help.t
Yehuda Sadeh [Thu, 21 Jun 2012 20:14:47 +0000 (13:14 -0700)]
rgw-admin: fix usage help
s/show/trim
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Tommi Virtanen [Tue, 3 Jul 2012 22:24:26 +0000 (15:24 -0700)]
ceph-disk-prepare: Partition and format OSD data disks automatically.
Uses gdisk, as it seems to be the only tool that can automate GPT uuid
changes. Needs to run as root.
Adds Recommends: gdisk to ceph.deb.
Closes: #2547
Signed-off-by: Tommi Virtanen <tv@inktank.com>
John Wilkins [Tue, 3 Jul 2012 21:20:34 +0000 (14:20 -0700)]
doc: removed /srv/osd.$id.journal from ceph.conf example.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
caleb miles [Tue, 3 Jul 2012 20:05:48 +0000 (13:05 -0700)]
CrushTester.cc: remove BOOST dependencies.
remove calls to BOOST libraries for computing Chi-squared statistics and
producing discrete random variables with a given probability distribution.
Signed-off-by: caleb miles <caleb.miles@inktank.com>
John Wilkins [Tue, 3 Jul 2012 21:14:42 +0000 (14:14 -0700)]
doc: Updates to 5-minute quick start.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Sage Weil [Tue, 3 Jul 2012 21:07:16 +0000 (14:07 -0700)]
radosgw-admin: fix clit test
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 20:04:36 +0000 (13:04 -0700)]
Merge branch 'wip-config'
Sage Weil [Tue, 3 Jul 2012 20:04:28 +0000 (13:04 -0700)]
lockdep: increase max locks
Hit this limit with the rados api tests.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 19:07:28 +0000 (12:07 -0700)]
config: add unlocked version of get_my_sections; use it internally
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 18:32:57 +0000 (11:32 -0700)]
ceph: fix cli help test
Signed-off-by: Sage Weil <sage@inktank.com>
John Wilkins [Tue, 3 Jul 2012 18:48:31 +0000 (11:48 -0700)]
Merge branch 'master' of github.com:ceph/ceph
John Wilkins [Tue, 3 Jul 2012 18:48:15 +0000 (11:48 -0700)]
doc: Clean up of 5-minute quick start.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Samuel Just [Tue, 3 Jul 2012 18:23:16 +0000 (11:23 -0700)]
ReplicatedPG: remove faulty scrub assert in sub_op_modify_applied
This assert assumed that all ops submitted before MOSDRepScrub was
submitted were processed by the time that MOSDRepScrub was
processed. In fact, MOSDRepScrub's scrub_to may refer to a
last_update yet to be seen by the replica.
Bug #2693
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 3 Jul 2012 18:23:16 +0000 (11:23 -0700)]
ReplicatedPG: remove faulty scrub assert in sub_op_modify_applied
This assert assumed that all ops submitted before MOSDRepScrub was
submitted were processed by the time that MOSDRepScrub was
processed. In fact, MOSDRepScrub's scrub_to may refer to a
last_update yet to be seen by the replica.
Bug #2693
Signed-off-by: Samuel Just <sam.just@inktank.com>
John Wilkins [Tue, 3 Jul 2012 18:21:43 +0000 (11:21 -0700)]
doc: Updating Getting Started with 5-minute quick start.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Kyle Bader [Tue, 3 Jul 2012 18:20:38 +0000 (11:20 -0700)]
ceph: better usage
Signed-off-by: Kyle Bader <kyle.bader@dreamhost.com>
John Wilkins [Tue, 3 Jul 2012 18:18:11 +0000 (11:18 -0700)]
Merge branch 'master' of github.com:ceph/ceph
John Wilkins [Tue, 3 Jul 2012 18:17:50 +0000 (11:17 -0700)]
doc: restructuring quick start section.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Samuel Just [Tue, 3 Jul 2012 18:10:54 +0000 (11:10 -0700)]
IoCtxImpl: pass objver pointer to aio_operate_read
Signed-off-by: Samuel Just <sam.just@inktank.com>
Tommi Virtanen [Tue, 3 Jul 2012 16:22:28 +0000 (09:22 -0700)]
ceph-disk-prepare: Take fsid from config file.
Closes: #2546.
Signed-off-by: Tommi Virtanen <tv@inktank.com>
Sage Weil [Tue, 3 Jul 2012 13:46:10 +0000 (06:46 -0700)]
config: remove bad argparse_flag argument in parse_option()
This is wrong, and thankfully valgrind picks it up.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 16:20:35 +0000 (09:20 -0700)]
debian: strip new ceph-mds package
Reported-by: Amon Ott <a.ott@m-privacy.de>
Signed-off-by: Sage Weil <sage@inktank.com>
John Wilkins [Tue, 3 Jul 2012 15:46:14 +0000 (08:46 -0700)]
doc: Cleaned up rbd snapshots.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Sage Weil [Tue, 3 Jul 2012 15:20:06 +0000 (08:20 -0700)]
config: fix lock recursion in get_val_from_conf_file()
Introduce a private, already-locked version.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 15:15:08 +0000 (08:15 -0700)]
config: fix recursive lock in parse_config_files()
The _impl() helper is only called from parse_config_files(); don't retake
the lock.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 13:46:10 +0000 (06:46 -0700)]
config: remove bad argparse_flag argument in parse_option()
This is wrong, and thankfully valgrind picks it up.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 04:08:27 +0000 (21:08 -0700)]
client: improve dump_cache output
Hunting #1737.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 03:13:51 +0000 (20:13 -0700)]
doc: release notes for 0.48
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 01:03:02 +0000 (18:03 -0700)]
doc: 'Configuring a Storage Cluster' -> 'Configuration'
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Tue, 3 Jul 2012 04:24:56 +0000 (21:24 -0700)]
Merge tag 'v0.48argonaut'
v0.48argonaut
Sage Weil [Tue, 3 Jul 2012 00:54:35 +0000 (17:54 -0700)]
Merge branch 'wip-msgr'
Sage Weil [Thu, 28 Jun 2012 23:23:30 +0000 (16:23 -0700)]
lockdep: enable in common_init
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Mon, 2 Jul 2012 00:23:28 +0000 (17:23 -0700)]
msgr: restart_queue when replacing existing pipe and taking over the queue
The queue may have been previously stopped (by discard_queue()), and needs
to be restarted.
Fixes consistent failures from the mon_recovery.py integration tests.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sun, 1 Jul 2012 22:37:31 +0000 (15:37 -0700)]
msgr: choose incoming connection if ours is STANDBY
If the connect_seq matches, but our existing connection is in STANDBY, take
the incoming one. Otherwise, the other end will wait indefinitely for us
to connect but we won't.
Alternatively, we could "win" the race and trigger a connection by sending
a keepalive (or similar), but that is more work; we may as well accept the
incoming connection we have now.
This removes STANDBY from the acceptable WAIT case states. It also keeps
responsibility squarely on the shoulders of the peer with something to
deliver.
Without this patch, a 3-osd vstart cluster with
'ms inject socket failures = 100' and rados bench write -b 4096 would start
generating slow request warnings after a few minutes due to the osds
failing to connect to each other. With the patch, I complete a 10 minute
run without problems.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 00:50:47 +0000 (17:50 -0700)]
msgr: preserve incoming message queue when replacing pipes
If we replace an existing pipe with a new one, move the incoming queue
of messages that have not yet been dispatched over to the new Pipe so that
they are not lost. This prevents messages from being lost.
Alternatively, we could set in_seq = existing->in_seq - existing->in_qlen,
but that would make the other end resend those messages, which is a waste
of bandwidth.
Very easy to reproduce the original bug with 'ms inject socket failures'.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 00:45:24 +0000 (17:45 -0700)]
msgr: move dispatch_entry into DispatchQueue class
A bit cleaner.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 00:38:34 +0000 (17:38 -0700)]
msgr: move incoming queue to separate class
This extricates the incoming queue and its funky relationship with
DispatchQueue from Pipe and moves it into IncomingQueue. There is now a
single IncomingQueue attached to each Pipe. DispatchQueue is now no
longer tied to Pipe.
This modularizes the code a bit better (tho that is still a work in
progress) and (more importantly) will make it possible to move the
incoming messages from one pipe to another in accept().
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 28 Jun 2012 00:06:40 +0000 (17:06 -0700)]
msgr: make D_CONNECT constant non-zero, fix ms_handle_connect() callback
A while ago we inadvertantly broke ms_handle_connect() callbacks because
of a check for m being non-zero in the dispatch_entry() thread. Adjust the
enums so that they get delivered again.
This fixes hangs when, for example, the ceph tool sends a command, gets a
connection reset, and doesn't get the connect callback to resend after
reconnecting to a new monitor.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Wed, 27 Jun 2012 00:10:40 +0000 (17:10 -0700)]
msgr: fix pipe replacement assert
We may replace an existing pipe in the STANDBY state if the previous
attempt failed during accept() (see previous patches).
This might fix #1378.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Wed, 27 Jun 2012 00:07:31 +0000 (17:07 -0700)]
msgr: do not try to reconnect con with CLOSED pipe
If we have a con with a closed pipe, drop the message. For lossless
sessions, the state will be STANDBY if we should reconnect. For lossy
sessions, we will end up with CLOSED and we *should* drop the message.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Wed, 27 Jun 2012 00:06:41 +0000 (17:06 -0700)]
msgr: move to STANDBY if we replace during accept and then fail
If we replace an existing pipe during accept() and then fail, move to
STANDBY so that our connection state (connect_seq, etc.) is preserved.
Otherwise, we will throw out that information and falsely trigger a
RESETSESSION on the next connection attempt.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sat, 30 Jun 2012 21:50:20 +0000 (14:50 -0700)]
v0.48argonaut
Holger Macht [Mon, 2 Jul 2012 20:54:48 +0000 (13:54 -0700)]
ceph.spec.in: Change license of base package to GPL and use SPDX format
LGPLv2 in spec file is not correct, because some of the included
packages/binaries are GPLv2. For example:
src/mount/mtab.c -> package ceph, binary mount.ceph
src/common/fiemap.cc -> package ceph, binary rbd
Also use SPDX format (http://www.spdx.org/licenses) for the sub-package
licenses.
Signed-off-by: Holger Macht <hmacht@suse.de>
Sage Weil [Mon, 2 Jul 2012 23:05:16 +0000 (16:05 -0700)]
mon: initialize quorum_features
This could cause us to incorrectly encode new features into the monstore
that an old mon won't understand.
This is overly conservative; we probably need to persist the set of quorum
features that are supported and use those.
Signed-off-by: Sage Weil <sage@inktank.com>
John Wilkins [Mon, 2 Jul 2012 20:05:26 +0000 (13:05 -0700)]
doc: fixed --cap error and a few additional bits of cleanup.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Samuel Just [Mon, 2 Jul 2012 16:51:37 +0000 (09:51 -0700)]
OSD::do_command: unlock pg only if we had it
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Mon, 2 Jul 2012 16:49:52 +0000 (09:49 -0700)]
MOSDSubOp: set hobject_incorrect_pool in decode_payload
Signed-off-by: Samuel Just <sam.just@inktank.com>
John Wilkins [Mon, 2 Jul 2012 15:55:36 +0000 (08:55 -0700)]
doc: Added sudo and cleaner instruction for unmap.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Mon, 2 Jul 2012 15:35:10 +0000 (08:35 -0700)]
doc: updated usage on RBD kernel object commands.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Mon, 2 Jul 2012 15:07:23 +0000 (08:07 -0700)]
Merge pull request #15 from fghaas/wip-rgw-doc
radosgw documentation improvements
Sage Weil [Mon, 2 Jul 2012 15:03:33 +0000 (08:03 -0700)]
Merge pull request #17 from fghaas/rgw-manpage
doc: drop mention of MDS capabilities from radosgw man page
Florian Haas [Mon, 2 Jul 2012 14:54:08 +0000 (16:54 +0200)]
doc: drop mention of MDS capabilities from radosgw man page
Signed-off-by: Florian Haas <florian@hastexo.com>
Sage Weil [Mon, 2 Jul 2012 14:10:33 +0000 (07:10 -0700)]
filestore: initialize m_filestore_do_dump
Signed-off-by: Sage Weil <sage@inktank.com>
Josh Durgin [Sat, 30 Jun 2012 02:20:33 +0000 (19:20 -0700)]
doc: add design doc for rbd layering
I'm still not sure about the names for the command line
operations, but they can be changed later if better ones
come up.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Sage Weil [Mon, 7 May 2012 21:37:38 +0000 (14:37 -0700)]
filestore: set min flush size
If a write is smaller than some threshold, do not bother to flush it; let
the fs do that (efficiently, we hope) at commit time. Focus on the big
writes.
Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Sat, 30 Jun 2012 02:56:07 +0000 (19:56 -0700)]
osdmap: check new pool name on rename
Ensure the new pool name doesn't already exist, both in the current and
project map.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sat, 30 Jun 2012 02:54:35 +0000 (19:54 -0700)]
osd: handle pool name changes properly
* Remove the old name from the name->id map.
Fixes: #2676
Signed-off-by: Sage Weil <sage@inktank.com>
caleb miles [Fri, 29 Jun 2012 23:38:16 +0000 (16:38 -0700)]
CrushTester: add Monte Carlo generator to more accurately simulate a
CRUSH mapping using a RNG
Signed-off-by: caleb miles <caleb.miles@inktank.com>
caleb miles [Fri, 29 Jun 2012 23:37:37 +0000 (16:37 -0700)]
crush: style changes
Signed-off-by: caleb miles <caleb.miles@inktank.com>
Samuel Just [Fri, 29 Jun 2012 22:49:41 +0000 (15:49 -0700)]
PG: reset_recovery_pointers in activate if missing is empty
Signed-off-by: Samuel Just <sam.just@inktank.com>
Dan Mick [Fri, 29 Jun 2012 22:25:52 +0000 (15:25 -0700)]
vstart.sh: don't clobber keyring if not -n
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 21:51:32 +0000 (14:51 -0700)]
mon: 'osd pool rename <oldname> <newname>'
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 21:22:14 +0000 (14:22 -0700)]
doc: document new 'osd crush move ...' command
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 21:16:05 +0000 (14:16 -0700)]
mon: fix 'osd crush move <item> <loc ...>'
- fix arg count check
- avoid updating crush map if it is already correct
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 29 Jun 2012 19:34:13 +0000 (12:34 -0700)]
Merge branch 'wip-crushwrapper2'
Reviewed-by: Sage Weil <sage@inktank.com>