RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-22 02:27:29 +00:00
Code Issues Packages Projects Releases Wiki Activity
73,026 Commits 216 Branches 395 Tags 1.4 GiB
fda6e16cf1
Commit Graph

73026 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Matt Benjamin
189ce0e5a6 Merge pull request #15293 from linuxbox2/wip-rgwfile-buckattr 
rgw_file: store bucket uxattrs on the bucket
 2017-05-26 09:48:09 -04:00
linbing
730781afec mon: it's no need to get pg action_primary osd twice in pg scrub 
Signed-off-by: linbing <linbing@t2cloud.net>
 2017-05-26 21:36:14 +08:00
Jason Dillaman
32bd33eb1b Merge pull request #15290 from idryomov/wip-krbd-unmap-straw 
qa/suites/krbd: unmap subsuite needs straw buckets

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-26 09:27:50 -04:00
Ken Dreyer
4274c91c28 doc: describe differences with "mds set" vs "fs set" 
Thanks to John Spray <jspray@redhat.com> on ceph-users for this
information.

Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
 2017-05-26 06:38:14 -06:00
Ken Dreyer
02753cdb91 doc: describe CephFS max_file_size 
Add a description of max_file_size to the CephFS admin docs.

Thanks to John Spray <jspray@redhat.com> on ceph-users for this
information.

Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
 2017-05-26 06:38:11 -06:00
Jianpeng Ma
910e58011d os/bluestore/BlueStore: Only call once notify_all. 
All txcs of deferred_running have the same osr, so only call once
notify_call.

Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
 2017-05-26 18:15:06 +08:00
Jianpeng Ma
45113968b8 os/bluestore/BlueStore: avoid iterating to get ios/cost in _kv_sync_thread. 
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
 2017-05-26 18:15:06 +08:00
Jianpeng Ma
6435c4a252 os/bluestore/BlueStore: batch handle Throttle.put. 
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
 2017-05-26 18:15:06 +08:00
Willem Jan Withagen
f28f4cbc20 ./qa/workunits/ceph-helpers.sh: Do not trace kill_daemon 
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
 2017-05-26 12:07:28 +02:00
Willem Jan Withagen
0f8972dd70 vstart:Suppress trivial logging info during devlopment 
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
 2017-05-26 12:07:14 +02:00
Willem Jan Withagen
f7e60bac5d src/ceph.in: Use env(CEPH_DEV) to suppress noise from ceph 
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
 2017-05-26 12:07:13 +02:00
linbing
5b468b641a Modify note error 
Signed-off-by: linbing linbing@t2cloud.net
 2017-05-26 17:45:43 +08:00
Piotr Dałek
9b5a1a4a32 inline_memory: optimized mem_is_zero for non-X64 
mem_is_zero is fast for X64 where 128-bit registers are available,
but it's very easy to optimze it for 32-bit Intel and ARM CPUs as
well, the speed won't be anywhere near the fastest one but still almost
7x faster than regular byte-by-byte check.
Now with extra test to check for corner cases that may pop with such
implementations.

Signed-off-by: Piotr Dałek <piotr.dalek@corp.ovh.com>
 2017-05-26 11:39:58 +02:00
liuchang0812
5284778e0e tool/ceph: support target mon in tell help subcommand 
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-05-26 17:39:22 +08:00
xie xingguo
9939d5a819 common/ceph_context: fix leak of registered commands on exit 
By unregister them properly.
Also rearrange commands order to keep pace with register process.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-05-26 17:28:55 +08:00
huanwen ren
fc54b831e4 client: fix display ino in the ldout 
Log need `ino`,not `address pointer`

Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
 2017-05-26 16:48:29 +08:00
Zhi Zhang
bd8c06de9a mds/MDBalancer: put heartbeat msg ref after using mantle balancer 
Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
 2017-05-26 14:58:27 +08:00
Zhi Zhang
a1214a702c Pass empty string to clear mantle balancer 
Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
 2017-05-26 14:54:32 +08:00
Greg Farnum
b0e9deeea8 osd: Reset() the snaptrimmer on shutdown 
We were failing to exit various wait states which held PGRefs. Error!

Fixes: http://tracker.ceph.com/issues/19931

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
 2017-05-25 21:52:49 -07:00
Yan, Zheng
e901d7fe97 mds: properly create aux subtrees for pinned directory 
Fixes: http://tracker.ceph.com/issues/20083
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
 2017-05-26 11:46:42 +08:00
Sage Weil
6b6c14f8c7 Merge pull request #14658 from chardan/jfw-wip-halflife_atomic_t-baragon 
librados,libradosstriper,test: migrate atomic_t to std::atomic (baragon)

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:29:19 -05:00
Sage Weil
0f01014ba5 Merge pull request #15227 from tchaikov/wip-20051 
mon/MonClient: cancel pending commands on shutdown

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-25 22:28:47 -05:00
Sage Weil
6650a18e59 Merge pull request #15249 from Alessandro-Barbieri/patch-2 
yasm-wrapper: filter -pthread

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:27:57 -05:00
Sage Weil
dcebdf4ff0 Merge pull request #15268 from ifed01/wip-bluestore-false-assert 
os/bluestore: fix false assert in IOContext::aio_wake

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:27:23 -05:00
Sage Weil
94c834ab9b Merge pull request #15272 from tchaikov/wip-mon-cleanups 
mon: cleanups

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:27:11 -05:00
Sage Weil
855955e58e osd: reduce size of osdmap cache, messages 
On large clusters, these large caches can be problematic (as maps get big).
We've seen good results with extremely small caches (10s of maps).  Make
a more modest reduction.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 23:13:37 -04:00
Sage Weil
c1b92cdcbb test/osd/osd-config.sh: fix test to isolate cases 
The third test (increasing osd_map_max_advance)
was triggering a warning from the 4th case (which
it didn't before).

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 23:13:37 -04:00
Sage Weil
c489d45113 osd: fadvise hint WILL_NEED when reading encoded osdmaps 
This way will ensure we cache data for recent osdmaps if we need to for
the benefit of laggy clients... even if (in bluestore's case)
bluestore_default_buffered_reads = false (it's true by default).  This
should mitigate any tail latency/work even if the osdmap cache size is too
small.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:52:33 -04:00
Sage Weil
73985a5b10 osd: instrument osdmap bl cache hits and misses 
Add perfcounters so we can see whether we are missing osdmaps in the
cache.  This will let us tell whether, given a workload or environment,
our osdmap cache might be too small.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:52:33 -04:00
Sage Weil
0ff3d4291c osd: do not bother with misdirected op diagnosis by default 
We enable osd_debug_misdirected_ops in QA, but this is wasted effort on
a production cluster.  In particular, it means that a idle client that
sends an op to the wrong OSD based on an old map will require that OSD to
load that old map into memory to decide whether to print a warning... all
on the off-chance that the client is buggy.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:29:22 -04:00
Sage Weil
c150cba817 osd: remove osd_enxio_on_misdirected_op option 
There is no good reason anyone would want this turned on.

Introduced 923e7f5ce5 (post-kraken), but
backported to kraken and jewel (10.2.6).

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 22:29:22 -04:00
liuchang0812
b2fcb62b7a tool/ceph: remove old mon support and verbose support 
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-05-26 10:27:26 +08:00
liuchang0812
9753a0065d tool/ceph: validate target in tell subcommand 
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-05-26 10:27:26 +08:00
liuchang0812
b0af39713b test/cephtool: convert FS_NAME to local variable 
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-05-26 10:27:26 +08:00
liuchang0812
a1cf9ae766 doc/tool: introduce "ceph tell x help" command in man 
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-05-26 10:27:26 +08:00
liuchang0812
5680936878 tool/ceph: create "tell x help" command 
Fixes: http://tracker.ceph.com/issues/19885

Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-05-26 10:27:26 +08:00
Brad Hubbard
096249707d Merge pull request #15192 from badone/wip-tracker-19900-wait_auth_rotating-crash 
mgr: Mark session connections down on shutdown

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-05-26 08:35:29 +10:00
Sage Weil
890f482568 mgr/MgrStandby: prevent use-after-free on just-shut-down Mgr 
Fixes: http://tracker.ceph.com/issues/19595
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 18:25:27 -04:00
Sage Weil
d292b5419f qa/tasks/repair_test: unset flags we set 
In particular, noscrub and nodeepscrub leave a health
warning, which prevents shutdown with at-end.yaml.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 18:05:42 -04:00
myoungwon oh
6dbcbb5515 osd: prevent upgrading unsupported cluster 
Signed-off-by: Myoungwon Oh omwmw@sk.com
Signed-off-by: Sage Weil sage@redhat.com
 2017-05-26 05:52:56 +09:00
Yuri Weinstein
25b8e0f63f Merge pull request #15146 from tchaikov/wip-split-test-tiering 
qa: split test_tiering into smaller pieces

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-25 13:43:53 -07:00
Yuri Weinstein
0f7e269880 Merge pull request #15156 from tchaikov/wip-ceph.in-assert-connected 
ceph.in: assert(state==connected) before help_for_target()

Reviewed-by: Jos Collin <jcollin@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
 2017-05-25 13:43:17 -07:00
Yuri Weinstein
516c3ec452 Merge pull request #15224 from tchaikov/wip-denc-no-deep-copy-for-segmented-buffer 
denc: add need_contiguous to denc_traits

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-05-25 13:40:23 -07:00
Sage Weil
9b81fa43db crush/CrushTreeDumper: allow children to filter results 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-25 16:31:52 -04:00
Matt Benjamin
448edbfa55 rgw_file: store bucket uxattrs on the bucket 
This turns out to be the corollary of the earlier bug in removing
buckets w/uxattrs. Rather than conditionally put the attrs on a '/'
object, put them on the bucket--because that works, and will be
slightly more efficient when the check for the '/' object goes
away.

Fixes: http://tracker.ceph.com/issues/20082

Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
 2017-05-25 16:28:02 -04:00
Mohamad Gebai
69d5ad5295 tracing: remove -pie if using function instrumentation 
Signed-off-by: Mohamad Gebai <mgebai@suse.com>
 2017-05-25 15:16:21 -04:00
Mohamad Gebai
021dcf7bfb tracing: add documentation for function instrumentation 
Signed-off-by: Mohamad Gebai <mgebai@suse.com>
 2017-05-25 15:16:21 -04:00
Mohamad Gebai
73ab6c2d13 tracing: add -finstrument-functions for OSD 
Signed-off-by: Mohamad Gebai <mgebai@suse.com>
 2017-05-25 15:16:21 -04:00
Mohamad Gebai
27fe5320bb tracing: add cyg_profile tracepoint provider 
Signed-off-by: Mohamad Gebai <mgebai@suse.com>
 2017-05-25 15:16:21 -04:00
Mohamad Gebai
0baebc308c cmake: configuration for OSD function instrumentation 
Signed-off-by: Mohamad Gebai <mgebai@suse.com>
 2017-05-25 15:16:14 -04:00