]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
lu.shasha [Tue, 9 May 2017 07:05:03 +0000 (15:05 +0800)]
rgw: when create_bucket use the same num_shards with info.num_shards
pr #14388 only fix the num_shards in BucketInfo, "init_bucket_index" function still use local num_shards
Fixes: http://tracker.ceph.com/issues/19745
Signed-off-by: Shasha Lu <lu.shasha@eisoo.com>
Dan Mick [Tue, 9 May 2017 02:48:27 +0000 (19:48 -0700)]
Merge pull request #14984 from dmick/wip-osd-dup
test/osd/osd-dup.sh: lower wb fd throttle limits
Reviewed-by: Sage Weil <sage@redhat.com>
Yan, Zheng [Tue, 9 May 2017 02:34:00 +0000 (10:34 +0800)]
Merge pull request #14907 from ukernel/wip-19820
ceph-fuse: use user space permission check by default
Jason Dillaman [Mon, 8 May 2017 23:41:40 +0000 (19:41 -0400)]
Merge pull request #14976 from trociny/wip-19871
rbd-nbd: relax size check for newer kernel versions
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Mon, 8 May 2017 23:41:02 +0000 (19:41 -0400)]
Merge pull request #14656 from chardan/jfw-wip-halflife_atomic_t-rodan
rbd, librbd: migrate atomic_t to std::atomic
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Matt Benjamin [Mon, 8 May 2017 19:52:00 +0000 (15:52 -0400)]
Merge pull request #14925 from fangyuxiangGL/fix_unneccesary_write
rgw: don't do unneccesary write if buffer with zero length
Sage Weil [Mon, 8 May 2017 16:34:48 +0000 (11:34 -0500)]
Merge pull request #14990 from wjin/fix
osd: clean nonused work queue
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 8 May 2017 16:33:31 +0000 (11:33 -0500)]
Merge pull request #14962 from liewegas/wip-denc-dump
include/denc: support ENCODE_DUMP
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Kefu Chai [Mon, 8 May 2017 16:18:55 +0000 (00:18 +0800)]
Merge pull request #14995 from SUSE/wip-mgr-rest-exit
pybind/mgr/rest: completely terminate cherrypy in shutdown
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Mon, 8 May 2017 15:54:54 +0000 (11:54 -0400)]
include/denc: clean up ENCODE_DUMP a bit
- PATH_MAX for string
- ENCODE_DUMP -> ENCODE_DUMP_PATH
- some comments!
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 8 May 2017 14:22:38 +0000 (09:22 -0500)]
Merge pull request #14999 from ivancich/wip-mod-git-subtree-README
doc: Re-word the warnings about using git subtrees.
J. Eric Ivancich [Tue, 2 May 2017 20:31:11 +0000 (16:31 -0400)]
doc: Re-word the warnings about using git subtrees.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
Jesse Williamson [Wed, 19 Apr 2017 09:58:35 +0000 (02:58 -0700)]
rbd_mirror: migrate std::atomic<unsigned> to std::atomic<bool>
Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
Jesse Williamson [Sun, 16 Apr 2017 08:31:16 +0000 (01:31 -0700)]
librbd: migrate atomic_t to std::atomic<>
Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
Jesse Williamson [Mon, 24 Apr 2017 07:43:23 +0000 (00:43 -0700)]
tools (rbd*): migrate atomic_t to std::atomic<>
Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
Tim Serong [Mon, 8 May 2017 13:03:55 +0000 (23:03 +1000)]
pybind/mgr/rest: completely terminate cherrypy in shutdown
cherrypy.engine.stop() doesn't actually completely kill cherrypy,
which means cherrypy.engine.block() never returns, so this module's
thread never completes cleanly.
Signed-off-by: Tim Serong <tserong@suse.com>
Haomai Wang [Mon, 8 May 2017 12:14:31 +0000 (20:14 +0800)]
Merge pull request #14956 from liewegas/wip-bdev-ioc-lock
os/bluestore: fix use after free race with aio_wait
Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Jianpeng Ma <jianpeng@intel.com>
Wei Jin [Mon, 8 May 2017 07:17:40 +0000 (15:17 +0800)]
osd: clean nonused work queue
it was restructured by
3cc48278bf0ee5c9535d04b60a661f988c50063b
Signed-off-by: Wei Jin <wjin.cn@gmail.com>
Sage Weil [Mon, 8 May 2017 03:26:03 +0000 (22:26 -0500)]
Merge pull request #14919 from tchaikov/wip-19825
mon: check is_shutdown() in timer callbacks
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 8 May 2017 03:23:55 +0000 (22:23 -0500)]
Merge pull request #14968 from TsaiJin/wip-lock-pg-when-scrub-available
osd: sched_scrub() lock pg only if all scrubbing conditions are fulfilled
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Pan Liu <liupan1111@gmail.com>
Loic Dachary [Sat, 6 May 2017 06:09:03 +0000 (08:09 +0200)]
Merge pull request #14970 from dachary/wip-crush-documentation
crush: update documentation for negative choose step
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Sage Weil [Fri, 5 May 2017 22:42:38 +0000 (17:42 -0500)]
Merge pull request #14979 from liewegas/wip-19874
mon: fix prime_pg_temp overrun
common/Finisher: fix uninitialized variable warning
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Fri, 5 May 2017 22:42:26 +0000 (17:42 -0500)]
Merge pull request #14958 from ovh/bp-fix-finisher-warning
common/Finisher: fix uninitialized variable warning
common/Finisher: fix uninitialized variable warning
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Fri, 5 May 2017 22:41:55 +0000 (17:41 -0500)]
Merge pull request #14793 from dmick/wip-prio-and-daemonperf
ceph: perfcounter priorities and daemonperf updates to use them
Sage Weil [Fri, 5 May 2017 22:41:22 +0000 (17:41 -0500)]
Merge pull request #14510 from liewegas/wip-bluefs-sync-write
os/bluestore/BlueFS: add bluefs_sync_write option
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Sage Weil [Fri, 5 May 2017 22:40:58 +0000 (17:40 -0500)]
Merge pull request #14305 from liewegas/wip-zipkin-partial
osd: zipkin tracing
Sage Weil [Fri, 5 May 2017 20:48:25 +0000 (16:48 -0400)]
messages/MCommand: fix type on decode
Wow, this has been broken since v0.38, but apparently
the message never made it into the object corpus so
we never noticed!
In reality the bug is harmless: decode_message() will
set_header which clobbers whatever version the default
ctor fills in, so this only affects ceph-dencoder's
test.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 5 May 2017 20:36:05 +0000 (16:36 -0400)]
ceph-object-corpus: kraken objects
Signed-off-by: Sage Weil <sage@redhat.com>
Dan Mick [Fri, 5 May 2017 21:47:14 +0000 (14:47 -0700)]
test/osd/osd-dup.sh: lower wb fd throttle limits
osd-dup.sh was losing OSDs to EMFILE, mostly on arm64 (not clear why).
Signed-off-by: Dan Mick <dan.mick@redhat.com>
Orit Wasserman [Fri, 5 May 2017 21:04:11 +0000 (00:04 +0300)]
Merge pull request #14981 from cbodley/wip-rgw-bi-list-plain
cls/rgw: list_plain_entries() stops before bi_log entries
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Sage Weil [Fri, 5 May 2017 20:31:02 +0000 (16:31 -0400)]
test/encoding/generate-corpus-objects: fix typo
Signed-off-by: Sage Weil <sage@redhat.com>
Casey Bodley [Fri, 5 May 2017 18:56:40 +0000 (14:56 -0400)]
cls/rgw: list_plain_entries() stops before bi_log entries
list_plain_entries() was using encode_obj_versioned_data_key() to set
its end_key, which gives a prefix of BI_BUCKET_OBJ_INSTANCE_INDEX[=2]
that range between start_key and end_key would not only span the
BI_BUCKET_OBJS_INDEX[=0] prefixes, but BI_BUCKET_LOG_INDEX[=1] prefixes
as well. this can result in list_plain_entries() trying and failing to
decode a rgw_bi_log_entry as a rgw_bucket_dir_entry
Fixes: http://tracker.ceph.com/issues/19876
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Sage Weil [Fri, 5 May 2017 13:19:23 +0000 (09:19 -0400)]
test/encoding/generate-corpus-objects.sh: simplify object corpus population
Script that generates corpus objects.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 5 May 2017 19:19:05 +0000 (15:19 -0400)]
qa/workunits/rgw/run-s3tests.sh: run s3-tests
This works out of the box with a vstart environment and
RGW=1 ../src/vstart.sh -n -l
PATH=bin:$PATH ../qa/workunits/rgw/run-s3tests.sh
Signed-off-by: Sage Weil <sage@redhat.com>
Jason Dillaman [Fri, 5 May 2017 18:40:55 +0000 (14:40 -0400)]
Merge pull request #14051 from SpandanKumarSahu/bug#17195
rbd: stop indefinite thread waiting in krbd udev handling
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Sage Weil [Fri, 5 May 2017 18:39:18 +0000 (14:39 -0400)]
os/bluestore: remove useless IOContext::num_reading
If we are a syncrhonous read, we don't need this: we don't aio_wait for
sync reads. If we are an aio_read, we are in the aio_running count anyway,
and there is also no purpose for this counter.
I'm a bit unsure about the NVME use of this counter; I switched it to use
num_running (pretty sure we aren't mixing reads and writes on a single
IOContext) *but* it might make more sense to switch to a private counter.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 5 May 2017 18:11:31 +0000 (14:11 -0400)]
os/bluestore/BlockDevice: fix racy aio_{wake,wait}() on IOContext
Thread 1 (_do_read) Thread 2 (_aio_thread)
queues aio
ioc->aio_wait()
locks ioc->lock
num_waiting++
finishes aios
ioc->aio_wake
if (num_waiting)
lock ioc->lock (blocks)
num_running == 0, continue
ioc->unlock
ioc->lock taken
do_read destroys ioc
use after free, may block forever
The last bit of the race may vary; the key thing is that thread 2 is
taking a lock that thread 1 can destroy; thread 2 doesn't have it pinned
in memory.
Fix this by simplifying the aio_wake, aio_wait. Since it is mutually
exclusive with a callback completion, we can avoid calling it at all when
a callback in present, and focus on keeping it simple.
Avoid use-after-free by making sure the last decrement happens under
the lock in the aio_wake/wait case.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 5 May 2017 18:35:07 +0000 (14:35 -0400)]
os/bluestore/KernelDevice: remove weird aio_wake from sync read()
I'm not entirely sure why we were ever signaling the cond here; the read
is synchronous!
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 5 May 2017 17:59:35 +0000 (13:59 -0400)]
CMakeLists.txt: WITH_BLKIN off for now
We are unconditionally linking lttng-ust, which make selinux complain. We
should either
- fix selinux rules and unconditionally link
- dlopen at runtime based on an option (like we do for the current
tracepoints)
- ???
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 21 Apr 2017 16:01:54 +0000 (12:01 -0400)]
blkin: fix test
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 18 Apr 2017 16:35:11 +0000 (12:35 -0400)]
blkin: fix cmake compile options
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 14 Apr 2017 17:27:44 +0000 (13:27 -0400)]
blkin: remove installed files
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 12 Apr 2017 15:34:03 +0000 (11:34 -0400)]
blkin: fix -fPIC option
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 10 Apr 2017 20:03:13 +0000 (16:03 -0400)]
blkin: drop boost dependency
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 7 Apr 2017 19:50:25 +0000 (15:50 -0400)]
common/zipkin_trace: fix blkin_trace_info encoding
- encode the same regardless of whether it is compiled in (!)
- encode in endian- and struct alignment-safe way.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 7 Apr 2017 19:40:21 +0000 (15:40 -0400)]
msg/Message: make {encode,decode}_trace unconditional
These are protocol features and cannot vary based on our compilation.
Encode and decode unconditionally. The callers have already guarded these
field additions with a message version bump and are conditionally calling
decode_trace.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 7 Apr 2017 19:26:57 +0000 (15:26 -0400)]
CMakeLists.txt: fix libcommon link to blkin
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 7 Apr 2017 19:14:56 +0000 (15:14 -0400)]
CMakeLists.txt: default WITH_BLKIN=ON
Signed-off-by: Sage Weil <sage@redhat.com>
Casey Bodley [Wed, 17 Aug 2016 18:15:14 +0000 (14:15 -0400)]
cmake: build blkin instead of using find_package
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Sage Weil [Fri, 7 Apr 2017 18:15:35 +0000 (14:15 -0400)]
src/blkin: add blkin submodule
Signed-off-by: Sage Weil <sage@redhat.com>
Victor Araujo [Thu, 18 Aug 2016 11:25:33 +0000 (13:25 +0200)]
librados: Overload aio_operate with blkin trace info parameter
This will enable passing trace information from rbd to librados for
aio_reads and aio_writes.
Signed-off-by: Victor Araujo <ve.ar91@gmail.com>
vears91 [Sat, 25 Jun 2016 18:21:24 +0000 (21:21 +0300)]
cmake: Add blkin libs to target_link_libraries
Signed-off-by: Victor Araujo <ve.ar91@gmail.com>
Casey Bodley [Thu, 12 Nov 2015 21:33:04 +0000 (16:33 -0500)]
blkin: add config variable osdc_blkin_trace_all
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Fri, 23 Oct 2015 13:33:36 +0000 (09:33 -0400)]
blkin: add traces to librados and Objecter
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Tue, 27 Oct 2015 16:18:33 +0000 (12:18 -0400)]
blkin: add config variable osd_blkin_trace_all
when set, Message::decode_trace() will always create a trace for
incoming messages, even if they didn't pass trace information
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Victor Araujo [Mon, 5 Sep 2016 12:15:03 +0000 (14:15 +0200)]
filestore: Initialize Zipkin traces when there is a store trace
Avoids creating orphaned traces.
Signed-off-by: Victor Araujo <ve.ar91@gmail.com>
Casey Bodley [Fri, 28 Aug 2015 14:32:40 +0000 (10:32 -0400)]
blkin: add traces to FileStore/Journal
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Sage Weil [Wed, 15 Feb 2017 23:17:33 +0000 (18:17 -0500)]
blkin: add traces to ECBackend
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Fri, 28 Aug 2015 19:33:46 +0000 (15:33 -0400)]
blkin: add traces to ReplicatedBackend
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Fri, 28 Aug 2015 20:22:06 +0000 (16:22 -0400)]
blkin: set up tracing in PGs
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Fri, 28 Aug 2015 16:08:14 +0000 (12:08 -0400)]
blkin: set up tracing in the OSD
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Tue, 25 Aug 2015 19:26:03 +0000 (15:26 -0400)]
blkin: osd op messages carry trace information
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Tue, 25 Aug 2015 18:40:48 +0000 (14:40 -0400)]
blkin: add traces to AsyncMessenger
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Tue, 25 Aug 2015 18:18:07 +0000 (14:18 -0400)]
blkin: add traces to XioMessenger
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Tue, 25 Aug 2015 16:49:50 +0000 (12:49 -0400)]
blkin: add traces to SimpleMessenger
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Mon, 17 Aug 2015 20:31:10 +0000 (16:31 -0400)]
blkin: Messenger integration
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Tue, 27 Oct 2015 13:59:46 +0000 (09:59 -0400)]
msg: pass Connection to decode_message
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Thu, 20 Aug 2015 18:03:00 +0000 (14:03 -0400)]
blkin: add header and initialization
zipkin_trace.h is a wrapper around ztracer.hpp, which provides a stub
implementation when WITH_BLKIN is not defined
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Mon, 17 Aug 2015 18:17:23 +0000 (14:17 -0400)]
cmake: add module and WITH_BLKIN option for blkin
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Andrew Shewmaker [Wed, 11 Mar 2015 02:43:26 +0000 (19:43 -0700)]
Build support for BlkKin (LTTng + Zipkin) tracing
* Adds --with-blkin to autoconf (default without)
* Adds BLKIN_LIBS to necessary automake files
* Adds documentation for testing BlkKin tracing
Signed-off-by: Andrew Shewmaker <agshew@gmail.com>
Signed-off-by: Marios-Evaggelos Kogias <marioskogias@gmail.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Jason Dillaman [Fri, 5 May 2017 17:16:48 +0000 (13:16 -0400)]
Merge pull request #14834 from runsisi/wip-fix-double-free
librbd: minor fixes for image trash move
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Fri, 5 May 2017 17:16:35 +0000 (13:16 -0400)]
Merge pull request #14830 from runsisi/wip-open-cleanup
librbd: remove redundant check for image id emptiness
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Kefu Chai [Fri, 5 May 2017 16:31:33 +0000 (00:31 +0800)]
Merge pull request #14927 from tchaikov/wip-19427
logclient: use the seq id of the 1st log entry when resetting session
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Kefu Chai [Fri, 5 May 2017 16:29:12 +0000 (00:29 +0800)]
Merge pull request #14920 from tchaikov/wip-14579
mgr: add machinery for python modules to send MCommands to daemons
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 5 May 2017 16:27:58 +0000 (00:27 +0800)]
Merge pull request #13681 from liewegas/wip-epochs
osd: tag fast dispatch messages with min_epoch
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Fri, 5 May 2017 15:47:03 +0000 (11:47 -0400)]
osd/OSDMapMapping: add assert
This is easier to debug than walking off into memory we don't own!
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 5 May 2017 15:43:59 +0000 (11:43 -0400)]
mon/OSDMonitor: fix prime_pg_temp condition
We have to make sure the *pg* exists, not just the pool, in the previous
map, or else we'll get a funky overrun in OSDMapMapping::get().
Signed-off-by: Sage Weil <sage@redhat.com>
Casey Bodley [Fri, 5 May 2017 15:38:54 +0000 (11:38 -0400)]
Merge pull request #14273 from cbodley/wip-rgw-beast-new-parser
rgw: update Beast for streaming reads in asio frontend
Reviewed-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
Mykola Golub [Fri, 5 May 2017 13:59:44 +0000 (15:59 +0200)]
rbd-nbd: relax size check for newer kernel versions
Fixes: http://tracker.ceph.com/issues/19871
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Casey Bodley [Fri, 28 Apr 2017 13:56:06 +0000 (09:56 -0400)]
rgw: rename frontend from asio to beast
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Sat, 18 Feb 2017 23:00:05 +0000 (18:00 -0500)]
rgw: update Beast for streaming reads in asio frontend
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Fri, 28 Apr 2017 14:23:40 +0000 (10:23 -0400)]
rgw: update Beast submodule
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Sage Weil [Fri, 5 May 2017 13:53:38 +0000 (08:53 -0500)]
Merge pull request #14931 from tchaikov/wip-19771
qa/tasks/ceph_manager: always fix pgp_num when done with thrashosd task
Reviewed-by: Sage Weil <sage@redhat.com>
Loic Dachary [Fri, 5 May 2017 09:38:32 +0000 (11:38 +0200)]
crush: update documentation for negative choose step
And remove an obsolete comment.
Signed-off-by: Loic Dachary <loic@dachary.org>
Sage Weil [Fri, 5 May 2017 13:20:35 +0000 (08:20 -0500)]
Merge pull request #14973 from ifed01/wip-bluestore-kvsync-cond
os/bluestore: remove unused condition variable
Reviewed-by: Sage Weil <sage@redhat.com>
Igor Fedotov [Fri, 5 May 2017 12:33:01 +0000 (15:33 +0300)]
os/bluestore: remove unused condition variable
Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
Mykola Golub [Fri, 5 May 2017 12:27:07 +0000 (15:27 +0300)]
Merge pull request #14963 from dillaman/wip-19858
rbd-mirror: failover and failback of unmodified image results in split-brain
Reviewed-by: Mykola Golub <mgolub@mirantis.com>
Jason Dillaman [Fri, 5 May 2017 11:30:52 +0000 (07:30 -0400)]
Merge pull request #14965 from dmick/wip-19865
test/librbd/test_librbd.cc: set *features even if RBD_FEATURES is unset
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Mykola Golub [Fri, 5 May 2017 11:12:53 +0000 (14:12 +0300)]
Merge pull request #14465 from dillaman/wip-librbd-devstack-tempest
qa/workunits: switch to OpenStack Ocata release for RBD testing
Reviewed-by: Mykola Golub <mgolub@mirantis.com>
Jin Cai [Fri, 5 May 2017 08:29:25 +0000 (16:29 +0800)]
osd/OSD.cc: lock the pg only when all conditional checks are passed when
scheduling a scrub
Signed-off-by: Jin Cai <caijin.caij@alibaba-inc.com>
Kefu Chai [Fri, 5 May 2017 04:02:05 +0000 (12:02 +0800)]
mon: check is_shutdown() in timer callbacks
introduce a helper class: C_MonContext, and initialize all timer events
using it, to ensure that they do check is_shutdown() before doing their
work.
Fixes: http://tracker.ceph.com/issues/19825
Signed-off-by: Kefu Chai <kchai@redhat.com>
Dan Mick [Fri, 5 May 2017 03:15:58 +0000 (20:15 -0700)]
test/librbd/test_librbd.cc: set *features even if RBD_FEATURES is unset
If RBD_FEATURES is not in the environment, set *features to 0 in
get_features(); callers rely on a valid return value. (This was
breaking on arm64.)
Fixes: http://tracker.ceph.com/issues/19865
Signed-off-by: Dan Mick <dan.mick@redhat.com>
Kefu Chai [Thu, 4 May 2017 14:49:04 +0000 (22:49 +0800)]
mon/Elector: call cancel_timer() in shutdown()
instead of doing it manually.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Jason Dillaman [Thu, 4 May 2017 21:56:22 +0000 (17:56 -0400)]
librbd: add no-op event when promoting an image
The rbd-mirror process needs an event in the journal
to properly detect the transition between primary and
non-primary state between peers.
Fixes: http://tracker.ceph.com/issues/19858
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Thu, 4 May 2017 23:47:01 +0000 (19:47 -0400)]
librbd: do not delay propagation of demote events
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Sage Weil [Thu, 4 May 2017 22:33:21 +0000 (18:33 -0400)]
include/denc: support ENCODE_DUMP
Signed-off-by: Sage Weil <sage@redhat.com>
Jason Dillaman [Thu, 4 May 2017 21:57:34 +0000 (17:57 -0400)]
rbd-mirror: prevent infinite loop when computing replay status
If the image had a non-primary predecessor epoch whose tag tid
duplicates an epoch within its own journal, an infinite loop
would result.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Yehuda Sadeh [Thu, 4 May 2017 18:25:50 +0000 (11:25 -0700)]
Merge pull request #14373 from rzarzynski/wip-rgw-19520
rgw: fix broken /crossdomain.xml, /info and /healthcheck of Swift API.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Casey Bodley [Thu, 4 May 2017 18:13:01 +0000 (14:13 -0400)]
Merge pull request #9950 from weiqiaomiao/wqm-wip-fetchobj-req
rgw: should delete in_stream_req if conn->get_obj(...) return not zero value
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Thu, 4 May 2017 18:01:35 +0000 (14:01 -0400)]
Merge pull request #14601 from Jing-Scott/fix-bulkupload-multisite
rgw: fix forward request for bulkupload to be applied in multisite
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>