]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
11 years agomessages: MForward: fix compat version 2082/head
Joao Eduardo Luis [Tue, 8 Jul 2014 15:46:27 +0000 (16:46 +0100)]
messages: MForward: fix compat version

A while ago we bumped the head version and reset the compat version to 0.
Doing this so happens to make the messenger assume that the message does
not support the compat versioning and sets the compat version to the head
version -- thus making compat = 2 when it should have been 1.

The nasty side-effect of this is that upgrading from emperor to firefly
will have emperor-leaders being unable to decode forwarded messages from
firefly-peons.

Fixes: #8727
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
11 years agoMerge pull request #2037 from ceph/wip-async-log
Gregory Farnum [Mon, 7 Jul 2014 22:37:13 +0000 (15:37 -0700)]
Merge pull request #2037 from ceph/wip-async-log

MDS: Encode log events in a separate thread from main execution.

This is a first small step in multi-threading the MDS daemon.

Reviewed-by: Greg Farnum <greg@inktank.com>
11 years agoMerge pull request #2080 from ceph/wip-8306-rebase
Sage Weil [Mon, 7 Jul 2014 21:52:17 +0000 (14:52 -0700)]
Merge pull request #2080 from ceph/wip-8306-rebase

Wip 8306 rebase

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
11 years agoOSD: fix debug logging output
Greg Farnum [Mon, 7 Jul 2014 19:46:16 +0000 (12:46 -0700)]
OSD: fix debug logging output

The snapmapper and infos statements were backwards. Now they aren't.

Signed-off-by: Greg Farnum <greg@inktank.com>
11 years agoMerge pull request #2078 from ceph/wip-8751
Sage Weil [Mon, 7 Jul 2014 20:23:25 +0000 (13:23 -0700)]
Merge pull request #2078 from ceph/wip-8751

test: generalise default_pools in test_rados

Reviewed-by: Sage Weil <sage@redhat.com>
11 years agoceph.spec.in: add bash completion file for radosgw-admin 2080/head
Dan Mick [Thu, 3 Jul 2014 23:11:24 +0000 (16:11 -0700)]
ceph.spec.in: add bash completion file for radosgw-admin

Signed-off-by: Sandon Van Ness <sandon@inktank.com>
11 years agoceph.spec.in: rhel7-related changes:
Dan Mick [Thu, 3 Jul 2014 23:10:55 +0000 (16:10 -0700)]
ceph.spec.in: rhel7-related changes:

udev rules: /lib -> /usr/lib
/sbin binaries move to /usr/sbin or %{_sbindir}

Signed-off-by: Sandon Van Ness <sandon@inktank.com>
11 years agoFix/add missing dependencies:
Dan Mick [Thu, 3 Jul 2014 23:08:44 +0000 (16:08 -0700)]
Fix/add missing dependencies:

- rbd-fuse depends on librados2/librbd1
- ceph-devel depends on specific releases of libs and libcephfs_jni1
- librbd1 depends on librados2
- python-ceph does not depend on libcephfs1

Signed-off-by: Sandon Van Ness <sandon@inktank.com>
11 years agoceph.spec.in: whitespace fixes
Dan Mick [Thu, 3 Jul 2014 23:05:00 +0000 (16:05 -0700)]
ceph.spec.in: whitespace fixes

Signed-off-by: Sandon Van Ness <sandon@inktank.com>
11 years agoceph.spec.in: split out ceph-common as in Debian
Dan Mick [Thu, 3 Jul 2014 23:04:10 +0000 (16:04 -0700)]
ceph.spec.in: split out ceph-common as in Debian

Move files, postun scriptlet, and add dependencies on ceph-common
where appropriate

Signed-off-by: Sandon Van Ness <sandon@inktank.com>
11 years agotest: generalise default_pools in test_rados 2078/head
John Spray [Mon, 7 Jul 2014 17:18:28 +0000 (18:18 +0100)]
test: generalise default_pools in test_rados

Instead of fragile assumptions about what pools
do or do not exist by default, simply use what
exists at test setup time as a baseline.

Fixes: #8751
Signed-off-by: John Spray <john.spray@redhat.com>
11 years agoMerge pull request #2074 from onlyjob/docs
Sage Weil [Mon, 7 Jul 2014 16:07:04 +0000 (09:07 -0700)]
Merge pull request #2074 from onlyjob/docs

doc: mention kernel support for rbd format 2

Reviewed-by: Sage Weil <sage@redhat.com>
11 years agoMerge pull request #2077 from ceph/wip-8754
Sage Weil [Mon, 7 Jul 2014 16:04:57 +0000 (09:04 -0700)]
Merge pull request #2077 from ceph/wip-8754

tests: don't depend on 'data' pool in rbd test

Reviewed-by: Sage Weil <sage@redhat.com>
11 years agotests: don't depend on 'data' pool in rbd test 2077/head
John Spray [Mon, 7 Jul 2014 14:45:54 +0000 (15:45 +0100)]
tests: don't depend on 'data' pool in rbd test

Since we removed the default 'data' and 'metadata' pools,
tests which need a pool should create it themselves.

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agodoc/release-notes: clarify CRUSH notes about tunables
Sage Weil [Mon, 7 Jul 2014 14:05:38 +0000 (07:05 -0700)]
doc/release-notes: clarify CRUSH notes about tunables

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2075 from ceph/wip-8745
Sage Weil [Mon, 7 Jul 2014 13:54:49 +0000 (06:54 -0700)]
Merge pull request #2075 from ceph/wip-8745

mds: use client-provided time stamp for user-visible file metadata

Reviewed-by: Sage Weil <sage@redhat.com>
11 years agomds: use client-provided time stamp for user-visible file metadata 2075/head
Yan, Zheng [Mon, 7 Jul 2014 08:16:27 +0000 (16:16 +0800)]
mds: use client-provided time stamp for user-visible file metadata

Fixes: #8745
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
11 years agodoc: mention kernel support for rbd format 2 2074/head
Dmitry Smirnov [Sat, 5 Jul 2014 09:27:24 +0000 (19:27 +1000)]
doc: mention kernel support for rbd format 2

Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
11 years agoMerge remote-tracking branch 'gh/next'
Sage Weil [Sat, 5 Jul 2014 04:18:55 +0000 (21:18 -0700)]
Merge remote-tracking branch 'gh/next'

11 years agoMerge pull request #2072 from ceph/wip-8738-next
Sage Weil [Sat, 5 Jul 2014 01:35:24 +0000 (18:35 -0700)]
Merge pull request #2072 from ceph/wip-8738-next

Patch up the CRUSH map compatibility guards

Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@redhat.com>
11 years agodoc: Fix a typo regarding requiretty for RHEL based platforms
Wido den Hollander [Fri, 4 Jul 2014 12:28:03 +0000 (14:28 +0200)]
doc: Fix a typo regarding requiretty for RHEL based platforms

11 years agoMerge pull request #2058 from ceph/wip-refs
Sage Weil [Fri, 4 Jul 2014 00:36:48 +0000 (17:36 -0700)]
Merge pull request #2058 from ceph/wip-refs

refcount debugging for RefCountedObject

Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
11 years agomon: check changes to the whole CRUSH map and to tunables against cluster features 2072/head
Greg Farnum [Thu, 3 Jul 2014 23:30:49 +0000 (16:30 -0700)]
mon: check changes to the whole CRUSH map and to tunables against cluster features

When we change the tunables, or set a new CRUSH map, we need to make sure it's
supported by all the monitors and OSDs currently participating in the cluster.

Fixes: #8738
Signed-off-by: Greg Farnum <greg@inktank.com>
11 years agoOSDMonitor: fix quorum_features comparison in check_cluster_features
Greg Farnum [Thu, 3 Jul 2014 22:24:30 +0000 (15:24 -0700)]
OSDMonitor: fix quorum_features comparison in check_cluster_features

We need to see if there's a feature which is not in the quorum_features,
not if there are no features in common!

Signed-off-by: Greg Farnum <greg@inktank.com>
11 years agomsg: debug refs on incoming Messages 2058/head
Sage Weil [Tue, 1 Jul 2014 22:47:44 +0000 (15:47 -0700)]
msg: debug refs on incoming Messages

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agocommon/RefCountedObject: make nref, cct private
Sage Weil [Tue, 1 Jul 2014 22:51:30 +0000 (15:51 -0700)]
common/RefCountedObject: make nref, cct private

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agomsg/Message: use RefCountedObject ctor to set initial ref count
Sage Weil [Tue, 1 Jul 2014 22:50:33 +0000 (15:50 -0700)]
msg/Message: use RefCountedObject ctor to set initial ref count

Also, drop the useless assert in the dtor (the RefCountedObject dtor does
the same).

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agomsg/Pipe: debug Pipe refs
Sage Weil [Tue, 1 Jul 2014 23:44:02 +0000 (16:44 -0700)]
msg/Pipe: debug Pipe refs

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agomsg: debug Connection refs
Sage Weil [Tue, 1 Jul 2014 23:43:46 +0000 (16:43 -0700)]
msg: debug Connection refs

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoosd: debug Session refs
Sage Weil [Tue, 1 Jul 2014 22:44:11 +0000 (15:44 -0700)]
osd: debug Session refs

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agocommon/RefCountedObject: assert nref == 0 in dtor
Sage Weil [Tue, 1 Jul 2014 22:51:06 +0000 (15:51 -0700)]
common/RefCountedObject: assert nref == 0 in dtor

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agocommon/RefCountedObject: optionally take initial ref count to ctor
Sage Weil [Tue, 1 Jul 2014 22:49:58 +0000 (15:49 -0700)]
common/RefCountedObject: optionally take initial ref count to ctor

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agocommon/RefCountedObject: optionally debug
Sage Weil [Tue, 1 Jul 2014 22:43:47 +0000 (15:43 -0700)]
common/RefCountedObject: optionally debug

Introduce a 'refs' subsys for logging.  Print log ref count inc and dec
for any RefCountedObject that gets a cct passed to its ctor.

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2059 from ceph/wip-osd-dumpres
Sage Weil [Thu, 3 Jul 2014 21:27:42 +0000 (14:27 -0700)]
Merge pull request #2059 from ceph/wip-osd-dumpres

osd: allow dumping reservation state via asok

Reviewed-by: Samuel Just <sam.just@inktank.com>
11 years agoMerge pull request #2069 from thorstenb/thb-buildconvenience-1
Sage Weil [Thu, 3 Jul 2014 21:00:34 +0000 (14:00 -0700)]
Merge pull request #2069 from thorstenb/thb-buildconvenience-1

Automagically setup submodules on first run.

Reviewed-by: Sage Weil <sage@redhat.com>
11 years agoMerge pull request #2066 from thorstenb/wip-janitorial-clang-2
Sage Weil [Thu, 3 Jul 2014 20:56:01 +0000 (13:56 -0700)]
Merge pull request #2066 from thorstenb/wip-janitorial-clang-2

[werror] Fix c++11-compat-reserved-user-defined-literal

11 years agoMerge pull request #2062 from somnathr/wip-sd-replicated-pg
Samuel Just [Thu, 3 Jul 2014 20:36:50 +0000 (13:36 -0700)]
Merge pull request #2062 from somnathr/wip-sd-replicated-pg

ReplicatedPG: Removed the redundant register_snapset_context call

Reviewed-by: Samuel Just <sam.just@inktank.com>
11 years agoMerge pull request #2064 from somnathr/wip-sd-share-map
Samuel Just [Thu, 3 Jul 2014 20:36:27 +0000 (13:36 -0700)]
Merge pull request #2064 from somnathr/wip-sd-share-map

OSD: adjust share_map() to handle the case that the osd is down

Reviewed-by: Samuel Just <sam.just@inktank.com>
11 years agoMerge pull request #2065 from somnathr/wip-sd-optracker
Samuel Just [Thu, 3 Jul 2014 20:35:23 +0000 (13:35 -0700)]
Merge pull request #2065 from somnathr/wip-sd-optracker

Pull request for optracker changes

Reviewed-by: Samuel Just <sam.just@inktank.com>
11 years agoMerge pull request #2063 from athanatos/wip-8691
Samuel Just [Thu, 3 Jul 2014 20:34:19 +0000 (13:34 -0700)]
Merge pull request #2063 from athanatos/wip-8691

OSD: wake_pg_waiters after dropping pg lock

Reviewed-by: Greg Farnum <greg@inktank.com>
11 years agoMerge pull request #2047 from dachary/wip-osd-config
Loic Dachary [Thu, 3 Jul 2014 14:00:56 +0000 (16:00 +0200)]
Merge pull request #2047 from dachary/wip-osd-config

osd: improve tests for configuration updates

Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.com>
11 years agoMerge pull request #2036 from ceph/wip-osd-map-cache-size
Loic Dachary [Thu, 3 Jul 2014 12:40:42 +0000 (14:40 +0200)]
Merge pull request #2036 from ceph/wip-osd-map-cache-size

osd: allow osd map cache size to be adjusted at runtime

Reviewed-by: Loic Dachary <loic@dachary.org>
11 years agoMerge pull request #2068 from thorstenb/wip-janitorial-clang-4
Loic Dachary [Thu, 3 Jul 2014 09:29:35 +0000 (11:29 +0200)]
Merge pull request #2068 from thorstenb/wip-janitorial-clang-4

ceph_argparse_flag has no regular 3rd parameter.

Reviewed-by: Loic Dachary <loic@dachary.org>
11 years agoqa: support running under non privileged user
Loic Dachary [Tue, 1 Jul 2014 06:42:58 +0000 (08:42 +0200)]
qa: support running under non privileged user

If the test is run against a cluster started with vstart.sh (which is
the case for make check), the --asok-does-not-need-root disables the use
of sudo and allows the test to run without requiring privileged user
permissions.

Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 522174b066044e51a7019bd6cad81117e83c394e)

11 years agoMerge pull request #2061 from ceph/wip-8728
Sage Weil [Thu, 3 Jul 2014 00:55:05 +0000 (17:55 -0700)]
Merge pull request #2061 from ceph/wip-8728

qa/workunits/rest/test.py: make osd create test idempotent

Reviewed-by: Dan Mick <dan.mick@inktank.com>
11 years agoMerge pull request #2046 from ceph/wip-8670
Sage Weil [Thu, 3 Jul 2014 00:44:56 +0000 (17:44 -0700)]
Merge pull request #2046 from ceph/wip-8670

mon: OSDMonitor: 'osd pool' - if we can set it, we must be able to get it

Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Sage Weil <sage@redhat.com>
11 years agoAutomagically setup submodules on first run. 2069/head
Thorsten Behrens [Mon, 2 Jun 2014 20:11:24 +0000 (22:11 +0200)]
Automagically setup submodules on first run.

I mean, who's reading the README, anyway?

Signed-off-by: Thorsten Behrens <tbehrens@suse.com>
11 years agoceph_argparse_flag has no regular 3rd parameter. 2068/head
Thorsten Behrens [Wed, 2 Jul 2014 22:15:03 +0000 (00:15 +0200)]
ceph_argparse_flag has no regular 3rd parameter.

With clang warning: 'va_start' has undefined behavior with reference
types, noticing copy-paste mistake on ceph_argparse_flag.

Signed-off-by: Thorsten Behrens <tbehrens@suse.com>
11 years ago[werror] Fix c++11-compat-reserved-user-defined-literal 2066/head
Thorsten Behrens [Tue, 24 Jun 2014 22:26:35 +0000 (00:26 +0200)]
[werror] Fix c++11-compat-reserved-user-defined-literal

c++11 readiness, avoid clash with
http://www.stroustrup.com/C++11FAQ.html#UD-literals

Signed-off-by: Thorsten Behrens <tbehrens@suse.com>
11 years agoOSD: adjust share_map() to handle the case that the osd is down 2064/head
Somnath Roy [Wed, 2 Jul 2014 18:51:38 +0000 (11:51 -0700)]
OSD: adjust share_map() to handle the case that the osd is down

The assert was hitting while OSd is waiting for becoming healthy
in handle_osd_map(). This can happen while io is going on and
OSDs are made down forcefully by say osd thrash command.
So, the fix could be instead of asserting just return from here.

Fixes: #8646
Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
11 years agomon: OSDMonitor: 'osd pool' - if we can set it, we must be able to get it 2046/head
Joao Eduardo Luis [Mon, 30 Jun 2014 16:51:47 +0000 (17:51 +0100)]
mon: OSDMonitor: 'osd pool' - if we can set it, we must be able to get it

Add support to get the values for the following variables:
 - target_max_objects
 - target_max_bytes
 - cache_target_dirty_ratio
 - cache_target_full_ratio
 - cache_min_flush_age
 - cache_min_evict_age

Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
11 years agoReplicatedPG: Removed the redundant register_snapset_context call 2062/head
Somnath Roy [Wed, 2 Jul 2014 18:20:29 +0000 (11:20 -0700)]
ReplicatedPG: Removed the redundant register_snapset_context call

In the get_object_context(), the get_snapset_context is been called
and the register_snapset_context is already been invoked from there.
This call seems to be redundant.

Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
11 years agoOpTracker: The optracker enabled/disabled check is added 2065/head
Somnath Roy [Wed, 2 Jul 2014 18:06:25 +0000 (11:06 -0700)]
OpTracker: The optracker enabled/disabled check is added

The optracker enabled/disabled check is now added in the
mark_event(const string&) interface.

Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
11 years agoOpTracker: use mark_event rather than _mark_event
Somnath Roy [Wed, 2 Jul 2014 18:01:55 +0000 (11:01 -0700)]
OpTracker: use mark_event rather than _mark_event

mark_event() interfaced changed to accept time and it is default
to 'now'. The mark_event is the wrapper function of _mark_event()
and it has the check for optracking enabled/disabled as well.
The _mark_event() is now a private function.

Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
11 years agoqa/workunits/rest/test.py: make osd create test idempotent 2061/head
Sage Weil [Wed, 2 Jul 2014 17:38:43 +0000 (10:38 -0700)]
qa/workunits/rest/test.py: make osd create test idempotent

Avoid possibility that we create multiple OSDs do to retries by passing in
the optional uuid arg.  (A stray osd id will make the osd tell tests a
few lines down fail.)

Fixes: #8728
Signed-off-by: Sage Weil <sage@inktank.com>
11 years agomds: defer encoding/submitting log events to separate thread 2037/head
Yan, Zheng [Fri, 27 Jun 2014 07:12:26 +0000 (15:12 +0800)]
mds: defer encoding/submitting log events to separate thread

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
11 years agomds: use mutex to protect log segment list
Yan, Zheng [Wed, 25 Jun 2014 08:09:15 +0000 (16:09 +0800)]
mds: use mutex to protect log segment list

prevent race between creating new log segment and trimming old
segment.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
11 years agomds: add thread to encode/submit log events
Yan, Zheng [Wed, 25 Jun 2014 07:09:33 +0000 (15:09 +0800)]
mds: add thread to encode/submit log events

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
11 years agoosd: add dump_reservations asok command 2059/head
Sage Weil [Wed, 2 Jul 2014 05:04:50 +0000 (22:04 -0700)]
osd: add dump_reservations asok command

Allow an admin to inspect pending and in-progress reservations.

Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com>
11 years agocommon/AsyncReserver: add dump()
Sage Weil [Wed, 2 Jul 2014 04:49:53 +0000 (21:49 -0700)]
common/AsyncReserver: add dump()

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2055 from ceph/wip-8692
Samuel Just [Tue, 1 Jul 2014 20:08:13 +0000 (13:08 -0700)]
Merge pull request #2055 from ceph/wip-8692

mon: clear osd request queue latency info on down or up

Reviewed-by: Samuel Just <sam.just@inktank.com>
11 years agomon: clear osd request queue latency info on down or up 2055/head
Sage Weil [Tue, 1 Jul 2014 19:42:19 +0000 (12:42 -0700)]
mon: clear osd request queue latency info on down or up

It doesn't make sense to warn about slow requests on OSDs that are down;
clear those stats in the monitor when we see an OSD go down (or up).

Fixes: #8692
Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2054 from ceph/wip-fs-cmds-oops
Gregory Farnum [Tue, 1 Jul 2014 18:49:21 +0000 (11:49 -0700)]
Merge pull request #2054 from ceph/wip-fs-cmds-oops

Apply some accidentally-dropped commits from the wip-fs-cmds branch to be a little friendlier and pass tests.

Reviewed-by: Greg Farnum <greg@inktank.com>
11 years agoOSD: wake_pg_waiters after dropping pg lock 2063/head
Samuel Just [Tue, 1 Jul 2014 18:04:51 +0000 (11:04 -0700)]
OSD: wake_pg_waiters after dropping pg lock

Otherwise, we dispatch_session_waiting while still holding the pg lock,
which is obviously wrong.  Unfortunately, this places an additional
burden on any user of _create_lock_pg, but I think it's unavoidable
since that method must atomically add the pg to the map and lock it.

Fixes: #8961
Introduced in:
  25466839589813047c975e44e67e14f34e32139e
  ecda2fef8ce982df3581a3b47ba74ae581d82479
Signed-off-by: Samuel Just <sam.just@inktank.com>
11 years agomds: Update default FS name 2054/head
John Spray [Fri, 13 Jun 2014 07:41:59 +0000 (08:41 +0100)]
mds: Update default FS name

From 'default' to 'cephfs' so that it looks
at least vaguely meaningful.

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agoqa: update cephtool EC pools test to respect IDs
John Spray [Tue, 1 Jul 2014 17:18:48 +0000 (18:18 +0100)]
qa: update cephtool EC pools test to respect IDs

...of data and metadata pools which are no longer
constant.

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agomon/MDSMonitor: EC check in 'fs new' like newfs
John Spray [Tue, 24 Jun 2014 21:49:54 +0000 (14:49 -0700)]
mon/MDSMonitor: EC check in 'fs new' like newfs

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agoqa: add a check for crash_replay_interval autoset
John Spray [Tue, 24 Jun 2014 21:14:03 +0000 (14:14 -0700)]
qa: add a check for crash_replay_interval autoset

... that after a fs new on fresh pools, crash_replay_interval
is set to the default on the data pool.

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agomon: Set crash_replay_interval automatically
John Spray [Mon, 23 Jun 2014 18:09:54 +0000 (11:09 -0700)]
mon: Set crash_replay_interval automatically

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agoqa: Update data pool ID for vxattrs test
John Spray [Fri, 20 Jun 2014 15:45:12 +0000 (11:45 -0400)]
qa: Update data pool ID for vxattrs test

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agoMerge pull request #2053 from dachary/wip-signed-warnings
Loic Dachary [Tue, 1 Jul 2014 15:05:34 +0000 (17:05 +0200)]
Merge pull request #2053 from dachary/wip-signed-warnings

test: use 0U with gtest to avoid spurious warnings

Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.com>
11 years agoMerge pull request #2052 from dachary/wip-vstart-wrapped
Loic Dachary [Tue, 1 Jul 2014 14:49:32 +0000 (16:49 +0200)]
Merge pull request #2052 from dachary/wip-vstart-wrapped

qa: support running under non privileged user

Reviewed-by: Florent Flament <florent.flament@cloudwatt.com>
11 years agotest: use 0U with gtest to avoid spurious warnings 2053/head
Loic Dachary [Tue, 1 Jul 2014 07:41:21 +0000 (09:41 +0200)]
test: use 0U with gtest to avoid spurious warnings

Signed-off-by: Loic Dachary <loic@dachary.org>
11 years agoqa: support running under non privileged user 2052/head
Loic Dachary [Tue, 1 Jul 2014 06:42:58 +0000 (08:42 +0200)]
qa: support running under non privileged user

If the test is run against a cluster started with vstart.sh (which is
the case for make check), the --asok-does-not-need-root disables the use
of sudo and allows the test to run without requiring privileged user
permissions.

Signed-off-by: Loic Dachary <loic@dachary.org>
11 years agoOSD: await_reserved_maps() prior to calling mark_down
Greg Farnum [Fri, 27 Jun 2014 21:59:23 +0000 (14:59 -0700)]
OSD: await_reserved_maps() prior to calling mark_down

send_message_osd_cluster() et al are *trying* to protect their Connection
lookups (and not re-open zapped Connections) via map reservations, but
that only works if we know that we haven't already called mark_down() on
the entities they might be looking up. So we need to await_reserved_maps
before we do any mark_down calls.
Since the waiting might take some time (fast dispatch in progress), only do
so if we are actually going to mark somebody down.

Fixes: #8512
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #1942 from ceph/wip-fs-cmds
Gregory Farnum [Tue, 1 Jul 2014 03:52:46 +0000 (20:52 -0700)]
Merge pull request #1942 from ceph/wip-fs-cmds

Wip fs cmds

Reviewed-by: Greg Farnum <greg@inktank.com>
11 years agoosd: allow osd map cache size to be adjusted at runtime 2036/head
Sage Weil [Tue, 1 Jul 2014 00:54:58 +0000 (17:54 -0700)]
osd: allow osd map cache size to be adjusted at runtime

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge remote-tracking branch 'gh/next'
Sage Weil [Mon, 30 Jun 2014 23:50:01 +0000 (16:50 -0700)]
Merge remote-tracking branch 'gh/next'

11 years agoMerge pull request #2050 from ceph/wip-cephtool
Dan Mick [Mon, 30 Jun 2014 23:48:29 +0000 (16:48 -0700)]
Merge pull request #2050 from ceph/wip-cephtool

qa/workunits/cephtool/test.sh: sudo ceph daemon

11 years agoqa/workunits/cephtool/test.sh: sudo ceph daemon 2050/head
Sage Weil [Mon, 30 Jun 2014 23:38:10 +0000 (16:38 -0700)]
qa/workunits/cephtool/test.sh: sudo ceph daemon

Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2049 from ceph/wip-fix-pglog-unittest
Sage Weil [Mon, 30 Jun 2014 22:31:10 +0000 (15:31 -0700)]
Merge pull request #2049 from ceph/wip-fix-pglog-unittest

PGLog: fix clear() to avoid the IndexLog::zero() asserts

Reviewed-by: Sage Weil <sage@redhat.com>
11 years agoPGLog: fix clear() to avoid the IndexLog::zero() asserts 2049/head
Samuel Just [Mon, 30 Jun 2014 20:40:07 +0000 (13:40 -0700)]
PGLog: fix clear() to avoid the IndexLog::zero() asserts

Introduced in:
  c5b8d8105d965da852c79add607b69d5ae79a4d4
  ac11ca40b4f4525cbe9b1778b1c5d9472ecb9efa
Signed-off-by: Samuel Just <sam.just@inktank.com>
11 years agoMerge pull request #2003 from ferustigris/hotfix/rgw_memory_leaks
Josh Durgin [Mon, 30 Jun 2014 20:13:52 +0000 (13:13 -0700)]
Merge pull request #2003 from ferustigris/hotfix/rgw_memory_leaks

RGW memory leaks have been fixed

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
11 years agoMerge pull request #2041 from ceph/wip-map-unmap
Josh Durgin [Mon, 30 Jun 2014 20:11:46 +0000 (13:11 -0700)]
Merge pull request #2041 from ceph/wip-map-unmap

Wip map unmap

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
11 years agoMerge pull request #2040 from ceph/wip-krbd-settle
Josh Durgin [Mon, 30 Jun 2014 20:09:21 +0000 (13:09 -0700)]
Merge pull request #2040 from ceph/wip-krbd-settle

krbd: rework the unmap retry loop

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
11 years agoMerge pull request #2038 from ceph/wip-fsx-random-ctx
Josh Durgin [Mon, 30 Jun 2014 20:08:14 +0000 (13:08 -0700)]
Merge pull request #2038 from ceph/wip-fsx-random-ctx

test_librbd_fsx: use private RNG context

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
11 years agoMerge pull request #2048 from ceph/wip-8699
Josh Durgin [Mon, 30 Jun 2014 20:02:17 +0000 (13:02 -0700)]
Merge pull request #2048 from ceph/wip-8699

rgw: fix uninit ofs in RGWObjManifect::obj_iterator

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
11 years agorgw: fix uninit ofs in RGWObjManifect::obj_iterator 2048/head
Sage Weil [Mon, 30 Jun 2014 19:55:45 +0000 (12:55 -0700)]
rgw: fix uninit ofs in RGWObjManifect::obj_iterator

Valgrind picked this up:

  <kind>UninitCondition</kind>
  <what>Conditional jump or move depends on uninitialised value(s)</what>
  <stack>
    <frame>
      <ip>0x5145B8</ip>
      <obj>/usr/bin/radosgw</obj>
      <fn>RGWObjManifest::obj_iterator::seek(unsigned long)</fn>
      <dir>/srv/autobuild-ceph/gitbuilder.git/build/out~/ceph-0.82-354-g62027ec/src/rgw</dir>
      <file>rgw_rados.cc</file>
      <line>562</line>
    </frame>
    <frame>
      <ip>0x5672A4</ip>
      <obj>/usr/bin/radosgw</obj>
      <fn>list_multipart_parts(RGWRados*, req_state*, std::string const&amp;, std::string&amp;, int, int, std::map&lt;unsigned int, RGWUploadPartInfo, std::less&lt;unsigned int&gt;, std::allocator&lt;std::pair&lt;unsigned int const, RGWUploadPartInfo&gt; &gt; &gt;&amp;, int*, bool*, bool)</fn>
      <dir>/srv/autobuild-ceph/gitbuilder.git/build/out~/ceph-0.82-354-g62027ec/src/rgw</dir>
      <file>rgw_rados.h</file>
      <line>217</line>
    </frame>
    <frame>
      <ip>0x5688EE</ip>
      <obj>/usr/bin/radosgw</obj>
      <fn>RGWListMultipart::execute()</fn>
      <dir>/srv/autobuild-ceph/gitbuilder.git/build/out~/ceph-0.82-354-g62027ec/src/rgw</dir>
      <file>rgw_op.cc</file>
      <line>2956</line>
    </frame>
...

Fixes: #8699
Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2045 from ceph/wip-8542
Sage Weil [Mon, 30 Jun 2014 19:35:46 +0000 (12:35 -0700)]
Merge pull request #2045 from ceph/wip-8542

qa/workunits/suites/fsx.sh: don't use zero range

Reviewed-by: Greg Farnum <greg@inktank.com>
11 years agoosd: improve tests for configuration updates 2047/head
Loic Dachary [Mon, 30 Jun 2014 19:10:41 +0000 (21:10 +0200)]
osd: improve tests for configuration updates

Extract the default values from the actual configuration instead of
having them hardcoded. Also check that lowering the osd_map_cache_size
triggers the expected warning.

Signed-off-by: Loic Dachary <loic@dachary.org>
11 years agoMerge pull request #2026 from athanatos/wip-8438-master
Samuel Just [Mon, 30 Jun 2014 18:12:03 +0000 (11:12 -0700)]
Merge pull request #2026 from athanatos/wip-8438-master

Wip 8438 master

Fixes: #8438
Backport: Firefly
Reviewed-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2027 from athanatos/wip-7999-master
Samuel Just [Mon, 30 Jun 2014 18:11:16 +0000 (11:11 -0700)]
Merge pull request #2027 from athanatos/wip-7999-master

Wip 7999 master

Fixes: #7999
Backport: Firefly
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
11 years agoqa/workunits/suites/fsx.sh: don't use zero range 2045/head
Sage Weil [Mon, 30 Jun 2014 14:05:04 +0000 (07:05 -0700)]
qa/workunits/suites/fsx.sh: don't use zero range

Zero range is not supported by cephfs.

Fixes: #8542
Signed-off-by: Sage Weil <sage@inktank.com>
11 years agoMerge pull request #2039 from dachary/wip-erasure-code-doc
Loic Dachary [Mon, 30 Jun 2014 09:40:30 +0000 (11:40 +0200)]
Merge pull request #2039 from dachary/wip-erasure-code-doc

erasure-code: add definitions to the glossary

Reviewed-by: Florent Flament <florent.flament@cloudwatt.com>
11 years agomon/MDSMonitor: log warning while MDS up but no FS 1942/head
John Spray [Thu, 12 Jun 2014 11:54:35 +0000 (12:54 +0100)]
mon/MDSMonitor: log warning while MDS up but no FS

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agomon/MDSMonitor: fix incorrect comment
John Spray [Thu, 12 Jun 2014 11:30:35 +0000 (12:30 +0100)]
mon/MDSMonitor: fix incorrect comment

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agomon/MDSMonitor: s/enabled/get_enabled()/
John Spray [Thu, 12 Jun 2014 11:24:03 +0000 (12:24 +0100)]
mon/MDSMonitor: s/enabled/get_enabled()/

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agomds: Handle setting 'enabled' in upgrades
John Spray [Thu, 12 Jun 2014 11:22:33 +0000 (12:22 +0100)]
mds: Handle setting 'enabled' in upgrades

Previously was always defaulting to disabled,
should be enabled if MDS map epoch is >1 (i.e.
if an MDS was ever started).

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agomds: journal-related debug messages
John Spray [Mon, 9 Jun 2014 11:37:03 +0000 (12:37 +0100)]
mds: journal-related debug messages

Signed-off-by: John Spray <john.spray@redhat.com>
11 years agotest/qa: update for MDSMonitor changes
John Spray [Tue, 27 May 2014 10:04:43 +0000 (11:04 +0100)]
test/qa: update for MDSMonitor changes

Accomodate changes:
 * data and metadata pools no longer exist by default
 * filesystem-using tests must use `fs new` to create
   the filesystem first.

Signed-off-by: John Spray <john.spray@inktank.com>