RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-24 03:27:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
79,910 Commits 216 Branches 395 Tags 1.4 GiB
f94322066f
Commit Graph

79910 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
David Zafman
f94322066f
Merge pull request #18449 from dzafman/wip-zafman-misc 
mark_unfound_lost fix and some other minor changes

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-10-27 10:21:25 -07:00
Casey Bodley
f9f76e9aef Merge pull request #18402 from cbodley/wip-21831 
rgw: fix for pause in beast frontend

Reviewed-by: Adam Emerson <aemerson@redhat.com>
 2017-10-27 11:22:28 -04:00
Yuri Weinstein
77ea42afd9 Merge pull request #18328 from PCzhangPC/cplostmeta 
librbd: cannot copy all image-metas if we have more than 64 key/value pairs

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 08:17:27 -07:00
Yuri Weinstein
dca707a06f Merge pull request #18419 from majianpeng/librbd-bug-fix 
librbd misc cleanup.

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 08:17:03 -07:00
Yuri Weinstein
20cc43f3fa Merge pull request #18542 from trociny/wip-metadata-open 
librbd: don't read metadata twice on image open

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 08:16:47 -07:00
Yuri Weinstein
89742b3ef0 Merge pull request #18561 from dillaman/wip-librbd-test-notify 
test/librbd: added update_features RPC message to test_notify

Reviewed-by: Mykola Golub <mgolub@mirantis.com>
 2017-10-27 08:16:19 -07:00
Jason Dillaman
c2b45a9db8 Merge pull request #18583 from idryomov/wip-qa-xfstests-except 
qa/tasks/rbd: run all xfstests runs to completion

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 11:12:18 -04:00
Jason Dillaman
900f1c024a Merge pull request #18557 from tchaikov/wip-cmake-cleanup 
cmake: check for aligned_alloc() instead of checking tcmalloc version

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 10:06:08 -04:00
Sage Weil
748068fff3 Merge pull request #18551 from liewegas/wip-object-stat-decode 
osd/osd_types: fix object_stat_sum_t decode

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
 2017-10-27 08:23:02 -05:00
Sage Weil
2cc8cc2db8 Merge pull request #18565 from liewegas/wip-prime-fixes 
ceph-bluestore-tool: prime-osd-dir: update symlinks instead of bailing

Reviewed-by: Alfredo Deza <adeza@redhat.com>
 2017-10-27 08:19:11 -05:00
Andrew Schoen
6e3180874c Merge pull request #18518 from ceph/wip-cv-fix-default-flags 
ceph-volume: ensure correct --filestore/--bluestore behavior

Reviewed-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 08:01:54 -05:00
Pan Liu
2358a8bfca Merge pull request #18502 from optimistyzy/1024_yzy 
bluestore/NVMEDevice: convert the legacy config opt related with SPDK
 2017-10-27 17:41:33 +08:00
Kefu Chai
78116c3b21 Merge pull request #18576 from tchaikov/wip-cmake-no-rados_a 
cmake: do not link against librados.a

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-10-27 16:19:04 +08:00
Kefu Chai
d5c9933350 cmake: remove rados_a target 
rados_a is librados.a, which is not neeeded anymore.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-10-27 13:58:53 +08:00
Kefu Chai
11f8770b34 cmake: link librbd against librados not rados_a 
link librados.so in hope to reduce the size of librdb, also the size of
debug-info.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-10-27 13:58:15 +08:00
Kefu Chai
082876f4c7 cmake: link librados tests against librados.so 
* in hope to shrink the test, and the debug-info rpm package
* also add librados to radostest's target_link_libraries(),  otherwise we might
   run into linker order issue, like

Undefined reference in
/home/jenkins-build/build/workspace/ceph-pull-requests/src/test/librados/test.cc:61
to `rados_application_enable'

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-10-27 13:58:15 +08:00
Kefu Chai
3f171e4010 test/librados/cmd.cc: avoid using non-librados facilities 
a test for librados should be only depending on librados

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-10-27 13:58:15 +08:00
Josh Durgin
a8b000fc41 Merge pull request #18543 from neha-ojha/wip-add-cbt-repo 
qa: add cbt repo parameter

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-10-26 20:24:29 -07:00
Josh Durgin
af97e2f757 Merge pull request #18573 from neha-ojha/wip-add-cbt-workloads 
qa/suites/rados/perf: add workloads

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-10-26 20:13:40 -07:00
Kefu Chai
16f0a67d83 cmake: check for aligned_alloc() 
in case developer is using patched tcmalloc.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-10-27 11:13:15 +08:00
Patrick Donnelly
7ff6ac907a
Merge PR #18174 into master 
* refs/pull/18174/head:
	mds: no assertion on inode being purging in find_ino_peers()

Reviewed-by: Zheng Yan <zyan@redhat.com>
 2017-10-26 19:39:13 -07:00
Patrick Donnelly
58d7d91516
Merge PR #18537 into master 
* refs/pull/18537/head:
	mds: set PRIO_USEFUL on num_sessions counter

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-10-26 19:39:04 -07:00
Neha Ojha
9cf94276cf qa/suites/rados/perf: add workloads 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2017-10-26 18:10:49 -07:00
Sage Weil
3f6e0b6e80 Merge pull request #18524 from liewegas/wip-backfill-rops 
osd/PG: fix recovery op leak

Reviewed-by: David Zafman <dzafman@redhat.com>
 2017-10-26 17:48:25 -05:00
Sage Weil
7740af808c Merge pull request #18552 from liewegas/wip-mds-cluster-down 
qa/workunits/rest/test.py: stop trying to test obsolte cluster_up/down

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-10-26 17:47:51 -05:00
Yehuda Sadeh
a7efb9d84f Merge pull request #18489 from cbodley/wip-21895 
rgw: fix extra_data_len handling in PutObj filters

Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
 2017-10-26 14:16:46 -07:00
Alfredo Deza
634b5caaed ceph-volume lvm.activate remove links on activate before priming 
Signed-off-by: Alfredo Deza <adeza@redhat.com>
 2017-10-26 15:09:18 -04:00
Sage Weil
de8dc42d42 ceph-bluestore-tool: prime-osd-dir: update symlinks instead of bailing 
If the symlink points to the right location, do nothing.  If it doesn't,
replace it.  If it's not a symlink, bail with EEXIST.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-26 13:51:40 -05:00
vasukulkarni
b2a1fd1972 Merge pull request #18451 from zmc/wip-cephmetrics 
Add cephmetrics suite
 2017-10-26 11:31:19 -07:00
Matt Benjamin
664ad1a16c Merge pull request #18198 from cbodley/wip-21735 
rgw: fix error handling in ListBucketIndexesCR
 2017-10-26 13:41:19 -04:00
Ilya Dryomov
48784f3f32 qa/tasks/rbd: run all xfstests runs to completion 
rbd.xfstests task allows spawning xfstests runs on multiple nodes.
Don't unwind task contexts if one of the runs fails -- let the other
runs finish.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
 2017-10-26 19:30:09 +02:00
Zack Cerza
41f55068cd Add cephmetrics suite 
Signed-off-by: Zack Cerza <zack@redhat.com>
 2017-10-26 10:55:30 -06:00
Jason Dillaman
b003ff3200 test/librbd: added update_features RPC message to test_notify 
Fixes: http://tracker.ceph.com/issues/21936
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-26 12:50:43 -04:00
Sage Weil
810a138133 qa/workunits/rest/test.py: stop trying to test obsolete 'mds *' commands 
These were recently removed.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-26 11:22:20 -05:00
John Spray
1fbd3b7b9f Merge pull request #18511 from smithfarm/wip-rpm-recommend-influxdb 
build/ops: rpm: recommend python-influxdb with ceph-mgr

Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Reviewed-by: Tim Serong <tserong@suse.com>
 2017-10-26 17:23:34 +02:00
John Spray
15e8b1904c Merge pull request #18182 from nrdmn/dashboard 
mgr/dashboard: improve error handling

Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-10-26 17:17:37 +02:00
Mykola Golub
0cb485ecb3 librbd: don't read metadata twice on image open 
After adding get_metadata to RefreshRequest it has become redundant
in OpenRequest.

Signed-off-by: Mykola Golub <to.my.trociny@gmail.com>
 2017-10-26 17:55:11 +03:00
Sage Weil
c337b8739d Merge pull request #18533 from tchaikov/wip-qa-cephtool 
qa: do not "ceph fs get cephfs" w/o a cephfs fs

Reviewed-by: Douglas Fuller <dfuller@redhat.com>
 2017-10-26 09:19:11 -05:00
Sage Weil
8afd4ec647 osd/PG: handle remote backfill recovation while waiting for other targets 
If we have multiple targets, we may still be waiting on them when we get
a revocation.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-26 08:42:34 -05:00
Alfredo Deza
fb36087bc3 ceph-volume lvm.activate ceph-bluestore-tool needs --cluster too 
Signed-off-by: Alfredo Deza <adeza@redhat.com>
 2017-10-26 07:48:24 -04:00
Mykola Golub
fb48989eeb Merge pull request #18545 from batrick/pr18393-revert 
Revert "ceph_context: re-expand admin_socket metavariables in child process"

Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
 2017-10-26 10:28:58 +03:00
Sage Weil
028e15d62f Merge pull request #18496 from liewegas/wip-pgmap 
build: remove PGMap.cc from libcommon

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-10-25 21:53:07 -05:00
Sage Weil
efd1a77147 osd/PG: make scan recovery op cancellation match up reliably 
Previously, there was only one time we would end up in this region of code:
when the backfill was rejected by the peer.  Previously that was apparently
reliably when we had an outstanding SCAN request, because we would
unconditionally cancle the MAX recovery op and clear waiting_on_backfill.

See 624aaf2a4e for when this code appeared.

Now we have several similar paths, and we don't always have an outstanding
scan call (I don't think!).  Regardless, move most these three cases into
a common helper and make the finish_recovery_op completion conditional
on whether there is an outstanding SCAN.  This fixes a leak of a recovery
op when we defer while a scan is outstanding (this bug was recently
introduced by e708410542 and then
duplicated by 2463c6463d).

Note that there is still one other time we register MAX ops: when we are
finishing backfill.  There, we start one per target.  But we will always
get back our reply and process it in the normal way (that old commit
did not change the timing for these).

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-25 21:52:12 -05:00
Sage Weil
ebb4093c2c osd/PG: make recovering_oids a multiset 
For multiple backfill targets, we start MAX multiple times.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-25 21:50:12 -05:00
Sage Weil
f1afb1684c Merge pull request #18527 from xiexingguo/wip-hunt-scrub-mismatch 
osd/PrimaryLogPG: several oi.extents fixes

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-10-25 21:49:45 -05:00
Sage Weil
b3bb61ede6 Merge pull request #18531 from majianpeng/msg-async 
msg/async misc cleanup 

Reviewed-by: Haomai Wang <haomai@xsky.com>
 2017-10-25 21:49:27 -05:00
Jianpeng Ma
e564518350 msg/async: record correctly l_msgr_send_bytes if "rc == 0". 
If rc == 0, it mean all data of outcoming_bl whether old or new data.

Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
 2017-10-26 18:08:54 +08:00
Sage Weil
68f38a0544 osd/osd_types: fix object_stat_sum_t decode 
Broken by 71bf04775b

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-25 21:39:23 -05:00
Patrick Donnelly
2bba5d8e0f
Merge PR #18192 into master 
* refs/pull/18192/head:
	qa/cephfs: test ec data pool
	qa/suites/fs/basic_functional/clusters: more osds

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-10-25 17:05:38 -07:00
Alfredo Deza
2b7ff497fe ceph-volume lvm.activate consume cluster_name from lvm metadata 
Signed-off-by: Alfredo Deza <adeza@redhat.com>
 2017-10-25 18:57:28 -04:00