]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Yan Jun [Fri, 30 Jun 2017 15:25:09 +0000 (23:25 +0800)]
mon/mgr: add detail error infomation
Signed-off-by: Yan Jun <yan.jun8@zte.com.cn>
Sage Weil [Fri, 30 Jun 2017 14:38:05 +0000 (09:38 -0500)]
Merge pull request #15963 from Songweibin/wip-release-notes
doc/release-notes: add Images creation timestamp note
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Sage Weil [Fri, 30 Jun 2017 14:11:56 +0000 (09:11 -0500)]
Merge pull request #15924 from jcsp/wip-log-last-filters
mon: Filter `log last` output by severity and channel
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Fri, 30 Jun 2017 14:10:39 +0000 (09:10 -0500)]
Merge pull request #15946 from Yan-waller/wip-waller-dumpwatcher0627
osd: dump the field name of object watchers and cleanups
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Sage Weil [Fri, 30 Jun 2017 14:09:53 +0000 (09:09 -0500)]
Merge pull request #15959 from smithfarm/wip-rgw-singleton-cleanup
tests: rgw/singleton: drop duplicate filestore-xfs.yaml
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Sage Weil [Fri, 30 Jun 2017 14:09:38 +0000 (09:09 -0500)]
Merge pull request #15961 from majianpeng/filestore-remove-redundant-judgement
os/filestore/FileStore.cc: remove a redundant judgement when get max latency
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Pan Liu <liupan1111@gmail.com>
Sage Weil [Fri, 30 Jun 2017 14:09:03 +0000 (09:09 -0500)]
Merge pull request #15999 from Yan-waller/wip-waller-0629message
msg/MOSDOpReply: fix missing trace decode
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Jos Collin [Fri, 30 Jun 2017 13:33:29 +0000 (13:33 +0000)]
Merge pull request #16037 from gmayyyha/monmapmonitor-use-func
mon/MonmapMonitor: use __func__ instead of hard code function name
Reviewed By: Joao Eduardo Luis <jecluis@gmail.com>
Yanhu Cao [Fri, 30 Jun 2017 08:44:01 +0000 (16:44 +0800)]
mon/MonmapMonitor: use __func__ instead of hard code function name
Signed-off-by: Yanhu Cao <gmayyyha@gmail.com>
Sage Weil [Fri, 30 Jun 2017 03:04:20 +0000 (22:04 -0500)]
Merge pull request #15927 from jcsp/wip-mgr-log-on-load-failed
mgr: cluster log message on plugin load error
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Fri, 30 Jun 2017 03:03:55 +0000 (22:03 -0500)]
Merge pull request #15951 from wido/issue-20430
osd: Execute crush_location_hook when configured in ceph.conf
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 30 Jun 2017 03:03:37 +0000 (22:03 -0500)]
Merge pull request #15954 from Liuchang0812/wip-osd-compact
mon: fix kvstore type in mon compact command
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 30 Jun 2017 03:03:20 +0000 (22:03 -0500)]
Merge pull request #15957 from liewegas/wip-rc
ceph_release: we are in the 'rc' phase (12.1.z)
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Fri, 30 Jun 2017 03:03:02 +0000 (22:03 -0500)]
Merge pull request #15968 from xiexingguo/wip-poolopts-fix
mon/OSDMonitor: two pool opts related fix
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 30 Jun 2017 03:02:47 +0000 (22:02 -0500)]
Merge pull request #15974 from liewegas/wip-require-osd-release-print
osd/OSDMap: print require_osd_release
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Sage Weil [Fri, 30 Jun 2017 03:02:08 +0000 (22:02 -0500)]
Merge pull request #15976 from liewegas/wip-bluestore-big-cache
os/bluestore: default cache size of 3gb
Kefu Chai [Fri, 30 Jun 2017 02:21:37 +0000 (10:21 +0800)]
Merge pull request #15489 from xxhdx1985126/master
librados: redirect balanced reads to acting primary when targeting object isn't recovered
Reviewed-by: Sage Weil <sage@redhat.com>
Kefu Chai [Fri, 30 Jun 2017 01:34:59 +0000 (09:34 +0800)]
Merge pull request #14678 from joscollin/wip-cleanup-storeget-return-check
mon: handle cases where store->get() may return error
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 30 Jun 2017 01:32:56 +0000 (09:32 +0800)]
Merge pull request #15926 from liewegas/wip-log-channel
librados: add log channel to rados_monitor_log2 callback
Reviewed-by: John Spray <john.spray@redhat.com>
Kefu Chai [Fri, 30 Jun 2017 01:31:02 +0000 (09:31 +0800)]
Merge pull request #15925 from jcsp/wip-fsstatus-cleanup
mgr: clean up fsstatus module
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 30 Jun 2017 01:29:25 +0000 (09:29 +0800)]
Merge pull request #15932 from dillaman/wip-20421
pybind: restore original API for backwards compatibility
Reviewed-by: Kefu Chai <kchai@redhat.com>
Josh Durgin [Thu, 29 Jun 2017 21:00:18 +0000 (14:00 -0700)]
Merge pull request #14760 from dzafman/wip-19657
osd: On EIO from read recover the primary replica from another copy
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Yehuda Sadeh [Thu, 29 Jun 2017 19:54:28 +0000 (12:54 -0700)]
Merge pull request #15912 from cloudbau/wip-20107
rgw: Fix duplicate tag removal during GC
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Tested-by: Yuri Weinstein <yweinste@redhat.com>
Sage Weil [Thu, 29 Jun 2017 16:21:42 +0000 (11:21 -0500)]
Merge pull request #15894 from liewegas/wip-no-default-pool
mon,osd: do not create rbd pool by default
John Spray [Thu, 29 Jun 2017 15:59:53 +0000 (11:59 -0400)]
mon: make `log` command send messages to default channel
...rather than leaving channel blank. This means that
people watching the main "cluster" channel will see
the log messages sent using `log`.
Signed-off-by: John Spray <john.spray@redhat.com>
Yan Jun [Thu, 29 Jun 2017 06:11:26 +0000 (14:11 +0800)]
message: fix missing decode trace
Signed-off-by: Yan Jun <yan.jun8@zte.com.cn>
Kefu Chai [Thu, 29 Jun 2017 04:57:36 +0000 (12:57 +0800)]
Merge pull request #15471 from tchaikov/wip-radostriper-leak-on-fail
libradosstriper: fix MultiAioCompletion leaks on failure
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
David Zafman [Wed, 28 Jun 2017 22:19:43 +0000 (15:19 -0700)]
test: Fix osd-scrub-repair for movement of shards
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Wed, 28 Jun 2017 21:18:38 +0000 (14:18 -0700)]
test: Clean up extra json output from log
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Wed, 28 Jun 2017 21:16:04 +0000 (14:16 -0700)]
test: Give time for OSDs to see map with flag change
Signed-off-by: David Zafman <dzafman@redhat.com>
Sage Weil [Thu, 29 Jun 2017 02:31:11 +0000 (21:31 -0500)]
Merge pull request #15812 from dzafman/wip-cot-cleanup
tools: Cleanup dead code in ceph-objectstore-tool
Reviewed-by: Sage Weil <sage@redhat.com>
Casey Bodley [Wed, 28 Jun 2017 20:05:58 +0000 (16:05 -0400)]
Merge pull request #15983 from cbodley/wip-20386
rgw: fix infinite loop in rest api for log list
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Josh Durgin [Wed, 28 Jun 2017 19:32:04 +0000 (12:32 -0700)]
Merge pull request #15635 from dzafman/wip-13837
osd: Corrupt objects stop snaptrim and mark pg snaptrim_error
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Sage Weil [Wed, 28 Jun 2017 19:03:02 +0000 (14:03 -0500)]
Merge pull request #15987 from liewegas/wip-19994
doc/release-notes: fix ceph-deploy command
Sage Weil [Wed, 28 Jun 2017 19:02:34 +0000 (15:02 -0400)]
doc/release-notes: fix ceph-deploy command
Signed-off-by: Sage Weil <sage@redhat.com>
Casey Bodley [Wed, 28 Jun 2017 17:32:35 +0000 (13:32 -0400)]
rgw: rest handlers for mdlog and datalog list dont loop
the do-while loops are unnecessary, because cls_log_list() will already
give us the requested number of entries, unless truncated. and these
rest operations return the truncated flag and last_marker, which the
client side is already using to run the same loop
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Wed, 28 Jun 2017 16:19:52 +0000 (12:19 -0400)]
rgw: fix RGWMetadataLog::list_entries() for null last_marker
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley [Wed, 28 Jun 2017 16:18:33 +0000 (12:18 -0400)]
rgw: RGWMetadataLog::list_entries() no longer splices
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Yuri Weinstein [Wed, 28 Jun 2017 15:14:53 +0000 (08:14 -0700)]
Merge pull request #15850 from rzarzynski/wip-rgw-20384
rgw: fix wrong error code for expired Swift TempURL's links.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Jos Collin <jcollin@redhat.com>
Yuri Weinstein [Wed, 28 Jun 2017 15:13:02 +0000 (08:13 -0700)]
Merge pull request #15883 from rzarzynski/wip-rgw-20395
rgw: omit X-Account-Access-Control if there is no grant to serialize.
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Yuri Weinstein [Wed, 28 Jun 2017 15:12:31 +0000 (08:12 -0700)]
Merge pull request #15884 from joscollin/wip-
1412617 -uninitialized-pointer-field
rgw: initialize non-static class members in ESQueryCompiler
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Yuri Weinstein [Wed, 28 Jun 2017 15:12:04 +0000 (08:12 -0700)]
Merge pull request #15886 from joscollin/wip-CID1412616-uninitialized-pointer-field
rgw: initialize Non-static class member worker in RGWReshard
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Yuri Weinstein [Wed, 28 Jun 2017 15:08:36 +0000 (08:08 -0700)]
Merge pull request #15888 from joscollin/wip-
1412615 -uninitialized-scalar-field
rgw: initialize Non-static class member val in ESQueryNodeLeafVal_Int
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Yuri Weinstein [Wed, 28 Jun 2017 15:07:54 +0000 (08:07 -0700)]
Merge pull request #15913 from smithfarm/wip-20417
tests: rgw.py: put client roles in a separate list
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Sage Weil [Mon, 26 Jun 2017 19:43:28 +0000 (15:43 -0400)]
test,qa/workunits: fix a zillion tests
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Sat, 24 Jun 2017 03:54:09 +0000 (23:54 -0400)]
mon/OSDMonitor: do not start mapping job on empty map
The Mapper doesn't do the completion. Just avoid it in the caller instead
of adding a Finisher or something similarly annoying for the completion.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 23 Jun 2017 20:02:26 +0000 (16:02 -0400)]
qa/tasks/ceph: create rbd pool after starting the osds
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 23 Jun 2017 19:42:45 +0000 (15:42 -0400)]
qa/workunits/ceph-helpers: shorten mon connect timeout
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 22 Jun 2017 17:46:25 +0000 (13:46 -0400)]
osdmaptool: do not create default pool without --with-default-pool
Signed-off-by: Sage Weil <sage@redhat.com>
Greg Farnum [Wed, 14 Jun 2017 20:05:46 +0000 (13:05 -0700)]
test: update TestPGLog's pool_id for the new world (no pool 0)
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Wed, 14 Jun 2017 20:05:19 +0000 (13:05 -0700)]
osdmap: maintain a pool-creating build_simple() for use in unit tests
Change the standard build_simple() so it no longer takes pg[p]_num -- these
params were unused. Add a new build_simple_with_pool() that can be called
when we want the rbd pool to be created by default. These are implemented
via a simple switched function (marked private).
Update the existing callers so they choose the right one for their needs.
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Wed, 14 Jun 2017 18:29:14 +0000 (11:29 -0700)]
osdmap: reference the correct value in debug output
Looks like we've been printing out the (possibly-still-default-initialized)
num_osd member variable instead of the given nosd value! Luckily
I don't see any other misuse and we fill out
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Tue, 6 Jun 2017 23:29:16 +0000 (16:29 -0700)]
cephtool/test: create an rbd pool since it's no longer automatic
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Tue, 6 Jun 2017 23:00:37 +0000 (16:00 -0700)]
TestOSDMap: provide more flexibility in the PrimaryAffinity check
Fix the margins for the primary affinity test.
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Signed-off-by: Sage Weil <sage@redhat.com>
Greg Farnum [Mon, 5 Jun 2017 19:27:46 +0000 (12:27 -0700)]
osdmap: do not automatically create an rbd pool on cluster creation; skip pool 0
We don't use pool ID 0 any more because CephFS can't handle it.
Update the user quick-start to include it, and add some links to support that process.
Fix the tests to handle the new state of life.
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Tue, 6 Jun 2017 22:29:15 +0000 (15:29 -0700)]
TestOSDMap: actually loop through the pools as intended
Looks like this was meant to be a loop but (unlike the other tests)
just referred to a constant pool 0. Whoops!
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Tue, 6 Jun 2017 00:56:31 +0000 (17:56 -0700)]
pgmap: extend mon_pg_warn_min_objects to cover the PG-per-OSD warnings too
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Wed, 14 Jun 2017 20:13:47 +0000 (13:13 -0700)]
src/jobs: remove these definitely-broken old testing scripts
They haven't been touched in 6 years and were considered broken then.
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Sage Weil [Wed, 28 Jun 2017 14:48:45 +0000 (10:48 -0400)]
os/bluestore: default cache size of 3gb
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 28 Jun 2017 14:29:56 +0000 (10:29 -0400)]
osd/OSDMap: print require_osd_release
Signed-off-by: Sage Weil <sage@redhat.com>
Haomai Wang [Wed, 28 Jun 2017 14:22:14 +0000 (22:22 +0800)]
Merge pull request #15967 from Adirl/continous
msg/async/rdma: register buffer as continuous
Reviewed-by: Haomai Wang <haomai@xsky.com>
Xie Rui [Thu, 22 Jun 2017 09:12:30 +0000 (17:12 +0800)]
fix infinite loop in rest api for log list
as max_entries_str is empty, it will be infinite loop when log is more than MAX_ENTRIES(1000) from marker.
and max_entries maybe overflow if use it to count the left entries.
Fixes: http://tracker.ceph.com/issues/20386
Signed-off-by: xierui <jerry.xr86@gmail.com>
Joao Eduardo Luis [Wed, 28 Jun 2017 12:36:02 +0000 (14:36 +0200)]
Merge pull request #14102 from renhwztetecs/renhw-wip-moninit-cleanup
mon: clean up in ceph_mon.cc
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Jos Collin <jcollin@redhat.com>
xie xingguo [Wed, 28 Jun 2017 10:10:32 +0000 (18:10 +0800)]
os/bluestore: allow user to unset pool compression_mode[algorithm] properly
A string-typed pool option requires user pass in a empty string to do a valid cancellation,
but the "osd pool set " command won't allow it. E.g.:
./bin/ceph osd pool set rbd compression_mode
Invalid command: missing required parameter val(<string>)
Since we already use the "unset" keyword to cancel the csum_type setting,
we could simply extends the above mechanism for compression_mode
and compression_algorithm too.
E.g.:
./bin/ceph osd pool set rbd compression_algorithm zlib
set pool 0 compression_algorithm to zlib
./bin/ceph osd pool set rbd compression_algorithm unset
unset pool 0 compression_algorithm
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Jianpeng Ma [Wed, 28 Jun 2017 12:05:08 +0000 (20:05 +0800)]
os/filestore/FileStore.cc: remove a redundant judgement when get max latency.
In fact, utime_t default is utime_t(). So we can remove this judgement.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Adir Lev [Mon, 5 Jun 2017 12:19:55 +0000 (12:19 +0000)]
msg/async/rdma: register buffer as continuous
Change-Id: I1a715de28ace3ff8ae077ca783ad5060e7966d54
Signed-off-by: Adir Lev <adirl@mellanox.com>
liuchang0812 [Tue, 27 Jun 2017 15:49:29 +0000 (23:49 +0800)]
mon: fix kvstore type in mon compact command
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
xie xingguo [Wed, 28 Jun 2017 03:43:32 +0000 (11:43 +0800)]
mon/OSDMonitor: fix error handling if we fail to set some pool opts
Returning a positive error code is generally not the preferred option
and can not be handled properly by caller here.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
clove [Wed, 28 Jun 2017 04:59:06 +0000 (12:59 +0800)]
doc/release-notes: add Images creation timestamp note
Signed-off-by: songweibin song.weibin@zte.com.cn
Kefu Chai [Wed, 28 Jun 2017 02:04:50 +0000 (10:04 +0800)]
Merge pull request #15907 from tchaikov/wip-with-zfs
cmake: fix the build with -DWITH_ZFS=ON
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Haomai Wang [Wed, 28 Jun 2017 01:55:39 +0000 (09:55 +0800)]
Merge pull request #15908 from Adirl/twice
msg/async/rdma: use lists properly
Reviewed-by: Haomai Wang <haomai@xsky.com>
John Spray [Tue, 27 Jun 2017 21:59:32 +0000 (17:59 -0400)]
Merge pull request #15521 from dillaman/wip-rbd-dashboard
pybind/mgr/dashboard: initial block integration
Reviewed-by: John Spray <john.spray@redhat.com>
Nathan Cutler [Tue, 27 Jun 2017 21:14:43 +0000 (23:14 +0200)]
tests: rgw/singleton: drop duplicate filestore-xfs.yaml
This yaml is now included in the objectstore/ directory. It makes no sense to
duplicate it here.
Signed-off-by: Nathan Cutler <ncutler@suse.com>
Sage Weil [Tue, 27 Jun 2017 19:13:53 +0000 (14:13 -0500)]
Merge pull request #15853 from liewegas/wip-simpler-ceph
qa/tasks/ceph: simplify ceph deployment slightly
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 16:52:35 +0000 (12:52 -0400)]
qa/tasks/ceph: explicitly add osds to crush map for upgrades
Before kraken, ceph-osd didn't add itself to crush... ceph-osd-prestart.sh
did it. And ceph.py doesn't use that.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 27 Jun 2017 16:49:24 +0000 (12:49 -0400)]
ceph_release: we are in the 'rc' phase (12.1.z)
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 27 Jun 2017 16:36:38 +0000 (11:36 -0500)]
Merge pull request #15955 from liewegas/wip-20431
qa/tasks/dump_stuck: fix for active+clean+remapped
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Sage Weil [Tue, 27 Jun 2017 16:01:07 +0000 (12:01 -0400)]
qa/tasks/dump_stuck: fix for active+clean+remapped
In
d24a8886658c2d8882275d69c6409717a62701be we made remapped a clean
state but didn't fix this test.
Fixes: http://tracker.ceph.com/issues/20431
Signed-off-by: Sage Weil <sage@redhat.com>
Kefu Chai [Mon, 26 Jun 2017 03:58:28 +0000 (11:58 +0800)]
cmake: compile libzfs backend conditionally
* do not REQUIRE libzfs if it is enabled, this follows the way how we
handle `WITH_XFS` option.
* also refactor the cmake script related to libxfs backend support a
little bit.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:22:42 +0000 (10:22 -0500)]
Merge pull request #15874 from elliswuuuuuuuu/remove_unuse_config
common/config_opt: remove unused config
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:22:26 +0000 (10:22 -0500)]
Merge pull request #15864 from joscollin/wip-CID1412839-uninitialized-pointer-field
common: initialize array in struct BackTrace
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:22:03 +0000 (10:22 -0500)]
Merge pull request #15881 from joscollin/wip-
1412776 -explicit-null-dereferenced
common: Passing null pointer option_name to operator << in md_config_t::parse_option()
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:21:46 +0000 (10:21 -0500)]
Merge pull request #15896 from Yan-waller/wip-waller-mgrcleanup0624
mgr: drop repeated log info. and unnecessary write permission
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:21:15 +0000 (10:21 -0500)]
Merge pull request #15910 from wido/cest-api-fork
ceph-rest-api: Various REST API fixes
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:19:59 +0000 (10:19 -0500)]
Merge pull request #15915 from liupan1111/wip-add-perfs
src/OSD: add more useful perf counters for performance tuning.
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:19:41 +0000 (10:19 -0500)]
Merge pull request #15917 from xiexingguo/wip-upmap-fixes
mon/OSDMonitor: a couple of upmap and other fixes
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 27 Jun 2017 15:19:22 +0000 (10:19 -0500)]
Merge pull request #15935 from zphj1987/master
ceph-conf: fix typo in usage: 'mon add' should be 'mon addr'
Reviewed-by: Kefu Chai <kchai@redhat.com>
Yuri Weinstein [Tue, 27 Jun 2017 15:03:12 +0000 (08:03 -0700)]
Merge pull request #15885 from liewegas/wip-radosbench-timeout
qa/tasks/radosbench: increase timeout
Reviewed-by: Yuri Weinstein <yweins@redhat.com>
Yuri Weinstein [Tue, 27 Jun 2017 15:01:02 +0000 (08:01 -0700)]
Merge pull request #15882 from rzarzynski/wip-20372
rgw: fixes for AWSBrowserUploadAbstractor auth
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Yuri Weinstein [Tue, 27 Jun 2017 15:00:12 +0000 (08:00 -0700)]
Merge pull request #15931 from cbodley/wip-rgw-slo-compression
rgw: use uncompressed size for range_to_ofs() in slo/dlo
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Casey Bodley [Tue, 27 Jun 2017 14:30:02 +0000 (10:30 -0400)]
Merge pull request #15928 from liewegas/wip-rgw-warning
rgw/rgw_op: fix whitespace and indentation warning
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Jos Collin [Thu, 20 Apr 2017 11:50:24 +0000 (17:20 +0530)]
mon: handle cases where store->get() may return error
Handled cases where store->get() may return error. Fixed the review comments too in this commit.
Fixes: http://tracker.ceph.com/issues/19601
Signed-off-by: Jos Collin <jcollin@redhat.com>
Wido den Hollander [Tue, 27 Jun 2017 14:17:58 +0000 (16:17 +0200)]
osd: Execute crush_location_hook when configured in ceph.conf
CrushLocation only invoked update_from_conf() which meant that
update_from_hook() was never executed.
By called init_on_startup() both functions are executed so that
the hook is called when configured.
Signed-off-by: Wido den Hollander <wido@42on.com>
John Spray [Tue, 27 Jun 2017 14:09:40 +0000 (15:09 +0100)]
qa: call into `status` module from cephtool test
Signed-off-by: John Spray <john.spray@redhat.com>
Sage Weil [Tue, 27 Jun 2017 14:04:34 +0000 (09:04 -0500)]
Merge pull request #15920 from wido/docs-mgr-dashboard
docs: mgr dashboard
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: John Spray <jspray@redhat.com>
Adir Lev [Sun, 28 May 2017 13:11:54 +0000 (13:11 +0000)]
msg/async/rdma: avoid adding worker twice to pending_workers
Change-Id: I4dda9040a055bdb8787ffd23a6928925d0a69d83
Signed-off-by: Adir Lev <adirl@mellanox.com>
Adir lev [Sun, 28 May 2017 10:56:29 +0000 (13:56 +0300)]
msg/async/rdma: avoid adding csi twice to pending_list
Change-Id: Id76ffbfebc54c2da339e0e7f063c5420042fbe7c
Signed-off-by: Adir lev <adirl@mellanox.com>
Wido den Hollander [Mon, 26 Jun 2017 12:49:28 +0000 (14:49 +0200)]
doc: Mgr Dashboard docs update
More instructions on how to deploy the dashboard using ceph-mgr
Signed-off-by: Wido den Hollander <wido@42on.com>
Yan Jun [Tue, 27 Jun 2017 12:07:35 +0000 (20:07 +0800)]
osd: use object section to dump watchers titles
Signed-off-by: Yan Jun <yan.jun8@zte.com.cn>
Nathan Cutler [Mon, 26 Jun 2017 08:42:08 +0000 (10:42 +0200)]
tests: rgw.py: put client roles in a separate list
Fixes: http://tracker.ceph.com/issues/20417
Signed-off-by: Nathan Cutler <ncutler@suse.com>