RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-01-19 01:21:49 +00:00
Code Issues Packages Projects Releases Wiki Activity
77,164 Commits 216 Branches 394 Tags 1.8 GiB
9613210577
Commit Graph

77164 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Gregory Farnum
c46a964e19 Merge pull request #17000 from gregsfortytwo/wip-20985-divergent-handling 
osd: be more precise about our asserts and cases when rebuilding missing sets

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-08-14 06:53:53 -07:00
Boris Ranto
70473011a0 Merge pull request #16753 from ceph/wip-fix-ppc64 
Fix ppc64 support for ceph

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-08-14 15:41:28 +02:00
Jason Dillaman
53e772a45f Merge pull request #16934 from amitkumar50/cov-librbd-2 
librbd: Initializing members image,operation,journal

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-08-14 09:08:29 -04:00
Boris Ranto
a8af61c8da selinux: Allow nvme devices 
This commit allows nvme devices which use a different label than
standard block devices.

Fixes: http://tracker.ceph.com/issues/19200
Signed-off-by: Boris Ranto <branto@redhat.com>
 2017-08-14 13:24:48 +02:00
chuanhong.wang
13ed4504d9 Fix a dead lock when running fio: "RDMADispatcher::polling_stop" hold the lock and wait 
"RDMADispatcher::polling" ending, then RDMADispatcher::polling can't hold the lock and
can't end its work.

Signed-off-by: Wang Chuanhong <chuanhong.wang@163.com>
 2017-08-14 08:49:28 +00:00
Jos Collin
2f8d234dbc rgw: Drop #warning TODO 
Drop "#warning TODO" from rgw_crypt.cc,  as the tracker is created for this requirement and the
corresponding PR is in progress for a long time.

Tracker: http://tracker.ceph.com/issues/19851
PR: https://github.com/ceph/ceph/pull/14498

Signed-off-by: Jos Collin <jcollin@redhat.com>
 2017-08-14 11:33:02 +05:30
Sage Weil
0a8ceaa3a5 Merge pull request #16976 from liewegas/wip-osd-empty 
mgr: implement 'osd safe-to-destroy' and 'osd ok-to-stop' commands

Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
 2017-08-13 14:02:44 -05:00
Sage Weil
e49ca43d4d Merge pull request #16625 from Yan-waller/wip-walle-0727testlibrados 
test/librados: reorder ASSERT_EQ() arguments

Reviewed-by: Jos Collin <jcollin@redhat.com>
 2017-08-13 14:02:22 -05:00
Sage Weil
929c11bf16 Merge pull request #16883 from liewegas/wip-20939 
crush,mon: fix weight-set vs crush device classes

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-08-13 13:59:43 -05:00
Sage Weil
d69f0e120b qa/suites/rados/objectstore/objectstore: less debug 
Saw an ENOSPC.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-13 14:41:43 -04:00
Haomai Wang
00e8ab3ac9 Merge pull request #17007 from alex-mikheev/wip_rdma_notify_fix 
src/msg/rdma: fixes failure on assert in notify()

Reviewed-by: Haomai Wang <haomai@xsky.com>
 2017-08-13 20:13:59 +08:00
Alex Mikheev
44c895ea51
src/msg/rdma: fixes failure on assert in notify() 
The commit fixes incorrect eventfd handling introduced in
2e75b876d1

Signed-off-by: Alex Mikheev <alexm@mellanox.com>
 2017-08-13 10:55:32 +00:00
Yanhu Cao
353a89728c mds/MDSDaemon: add 'is_valid=false' when failed to parse caps 
Fixes: http://tracker.ceph.com/issues/20990

Signed-off-by: Yanhu Cao <gmayyyha@gmail.com>
 2017-08-13 18:19:04 +08:00
Yuri Weinstein
aaf32d8f43 Merge pull request #16978 from gmayyyha/mgr-ms-verify-auth 
mgr/DaemonServer.cc: add 'is_valid=false' when decode caps error

Reviewed-by: Jos Collin <jcollin@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
 2017-08-12 14:45:28 -07:00
Sage Weil
196e7f317c Merge pull request #16906 from liewegas/wip-bluestore-stupid 
os/bluestore: switch default allocator to stupid; test both bitmap and stupid in qa

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-08-12 16:10:31 -05:00
Sage Weil
46ded6eb5b crush/CrushWrapper: fixing timing of removal in remove_item_under 
Do it after we reweight, not before

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-12 15:25:28 -04:00
Sage Weil
061c21786a crush/CrushWrapper: fix iterator invalidation in cleanup_dead_classes 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-12 15:25:28 -04:00
Sage Weil
b3838c83d5 crush/CrushWrapper: keep weights and/or ids null if empty 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-12 15:25:28 -04:00
Sage Weil
5a982050c1 crush/builder: fix ENOENT when removing last bucket item 
We were decrementing size and then breaking out ENOENT condition check.
Fix by decrementing size only after we break out of the loop and verify
we found the item.

Fix a follow-on bug by avoiding realloc when we have 0 items left.  This case
was never exercised before due to the ENOENT issue; now we return explicitly.
It's really not necessary to realloc at all, probably, since these are very
small arrays, but in any case leaving a single item allocation there in place of
a 0-length allocation is fine.  (And the 0-length allocation behvaior on realloc
is undefined.. may either return a pointer or NULL.)

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-12 15:24:04 -04:00
Sage Weil
ba3602b216 Merge pull request #17005 from liewegas/wip-verify-slowness 
qa/suites/rados/verify/validater/valgrind: whitelist PG_
 2017-08-12 13:19:23 -05:00
Sage Weil
41e5a85308 qa/suites/rados/verify/validater/valgrind: whitelist PG_ 
Peering might be slow due to valgrind.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-12 14:18:59 -04:00
Sage Weil
f04360c917 Merge pull request #17004 from liewegas/wip-clock-skew-whitelist 
qa/suites/rados/multimon/tasks/mon_lock_with_skew: whitelist PG_
 2017-08-12 13:15:50 -05:00
Sage Weil
12007044b1 qa/suites/rados/multimon/tasks/mon_lock_with_skew: whitelist PG_ 
Default pool pgs not up because mons too broken for OSDs to peer.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-12 14:15:15 -04:00
Sage Weil
5dd89cc17a Merge pull request #15921 from joscollin/wip-CID1411830-Uninitialized-pointer-field 
test/osd: Non-static class members not initialized in UnsetRedirectOp

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-08-12 13:03:58 -05:00
mychoxin
e6855210e0 os/bluestore: function collect_metadata, use 'const string&' to reduce copy 
Signed-off-by: mychoxin <mychoxin@gmail.com>
 2017-08-12 16:49:10 +08:00
mychoxin
a3b27da52e os/bluestore: move aio_callback and aio_callback_priv to class BlockDevice 
Signed-off-by: mychoxin <mychoxin@gmail.com>
 2017-08-12 16:48:44 +08:00
Jos Collin
b1b6688b50 test/osd: Non-static class member not initialized in UnsetRedirectOp 
Fixes the coverity scan report:
CID 1411830: Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member completion is not initialized in this constructor nor in any functions that it calls.
4. uninit_member: Non-static class member comp is not initialized in this constructor nor in any functions that it calls.

Signed-off-by: Jos Collin <jcollin@redhat.com>
 2017-08-12 13:36:08 +05:30
Jos Collin
0ec42b03c9 Merge pull request #15922 from joscollin/wip-CID1411829-Uninitialized-scalar-field 
test/osd: initialize Non-static class members in WeightedTestGenerator

Reviewed-by: Xie Xingguo <xie.xingguo@zte.com.cn>
 2017-08-12 07:50:05 +00:00
Sage Weil
4f6ae418c0 Merge pull request #16924 from liewegas/wip-20923 
os/bluestore: fail early on very large objects

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-08-11 21:55:34 -05:00
Sage Weil
ba66977a34 test/osd/safe-to-destroy.sh: test 'osd safe-to-destroy' 
This is hard with workunits/cephtool/test.sh because we don't
control the whole cluster.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-11 22:54:33 -04:00
Sage Weil
bf9380457b mgr: implement 'osd safe-to-destroy' and 'ok-to-stop' commands 
An osd is safe to destroy if

- we have osd_stat for it
- osd_stat indicates no pgs stored
- all pgs are known
- no pgs map to it

An osd is ok ot stop if

- we have pg stats
- no pgs will drop below min_size

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-11 22:54:33 -04:00
Sage Weil
a7612d33d1 mgr/ClusterState: record osd_stat for out osds too 
I'm not quite sure why we were doing this. :/

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-11 22:47:50 -04:00
Sage Weil
c2945479f4 osd/osd_types: include number of locally stored PGs in osd_stat_t 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-11 22:47:50 -04:00
Sage Weil
6fc33a046b osd/OSDMap: add parse_osd_id_list helper 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-11 22:47:50 -04:00
Sage Weil
8619fb6a2a Merge pull request #16992 from liewegas/wip-20977 
os/bluestore: do not segv on kraken upgrade debug print

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-08-11 21:36:53 -05:00
Sage Weil
f1d8a40122 Merge pull request #16993 from liewegas/wip-mimic 
common: kick off mimic

Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
 2017-08-11 21:36:32 -05:00
Sage Weil
ae739b31f1 Merge pull request #16994 from liewegas/wip-20983 
os/bluestore: fix clone dirty_range again

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-08-11 21:35:35 -05:00
Sage Weil
93b1b5ca49 Merge pull request #16995 from liewegas/wip-20738 
os/memstore: memstore_page_set=false

Reviewed-by: Adam Emerson <aemerson@redhat.com>
 2017-08-11 21:34:48 -05:00
Sage Weil
300e395c75 Merge pull request #16996 from liewegas/wip-mgr-vs-clock-skew 
qa/suites/rados/multimon: whitelist mgr down vs clock skew test
 2017-08-11 21:34:07 -05:00
Greg Farnum
6f7545e0b5 mon: correctly print out mds versions (instead of mon ones) 
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
 2017-08-11 15:31:43 -07:00
Greg Farnum
a9921a2fda osd: be more precise about our asserts and cases when rebuilding missing sets and handling divergent priors 
Fixes: http://tracker.ceph.com/issues/20985

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
 2017-08-11 15:10:01 -07:00
Gregory Farnum
4e69d80e6b Merge pull request #16898 from amitkumar50/cov-messages-6 
messages: Initialization of member variables

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2017-08-11 14:25:16 -07:00
Sage Weil
50523a225b os/bluestore: do not segv on kraken upgrade debug print 
When loading an onode from kraken we have a compat path that calls
get_ref before the SharedBlob pointer is initialized.  This is fine except
that if debugging is enabled the operator<< on the Blob will segv on
printing *b.shared_blob (which is NULL).

Fix operator<< to print something else if it is NULL.  shared_blob does
get set up right after the call to decode() so having it be NULL at this
point is otherwise harmless.

Fixes: http://tracker.ceph.com/issues/20977
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-08-11 16:44:48 -04:00
David Zafman
75b425671a osd: In scrub's be_select_auth_object() detect multiple errors better 
Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:32 -07:00
David Zafman
4c949b6258 osd, rados: Adding ss_attr_missing and ss_attr_corrupt errors to list-inconsistent-obj 
Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:32 -07:00
David Zafman
5f58301a13 osd, rados: Improve size scrub error handling 
Fixes: http://tracker.ceph.com/issues/20243

Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:32 -07:00
David Zafman
437e5cf106 osd: Compare all object info even when can't consider for auth copy 
Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:32 -07:00
David Zafman
8e2b9a07e0 osd: Change a check to an assert() since it can't happen anymore 
Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:03 -07:00
David Zafman
8ad4b29113 osd: Add whether shard is primary in list-inconsistent-obj 
Add new field in the client interface
Update test case

Fixes: http://tracker.ceph.com/issues/18836

Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:03 -07:00
David Zafman
c0606b9eea test: Add undocumented corrupt-size for testing 
Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-08-11 11:37:03 -07:00