RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-23 02:57:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
71,922 Commits 216 Branches 395 Tags 1.4 GiB
c9b93af06a
Commit Graph

71922 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kefu Chai
46da7ee760 Merge pull request #14895 from liewegas/wip-19778 
kv: move 'bluestore-kv' hackery out of KeyValueDB into ceph-kvstore-tool

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-05-02 11:05:54 +08:00
Kefu Chai
4121a3fef7 Merge pull request #14853 from liewegas/wip-aio 
os/fs/aio: use small_vector for aio_t; clean up header location

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-05-02 10:33:38 +08:00
runsisi
7580994cd8 librbd: do not delete ictx twice if open image failed 
Signed-off-by: runsisi <runsisi@zte.com.cn>
 2017-05-02 10:16:47 +08:00
Sage Weil
5898fe4aa0 osd: assert min_epoch <= sent_epoch 
Otherwise the sender is broken and probaby didn't fill in min_epoch
properly!

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:02:34 -05:00
Sage Weil
602c5bfd89 osd: min_epoch for MOSDRepScrub 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:29 -05:00
Sage Weil
200f90b753 osd/ReplicatedBackend: cleanup repop_applied 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:29 -05:00
Sage Weil
c33ee4e357 osd: min_epoch for MOSDRepOp[Reply] 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:29 -05:00
Sage Weil
fad0994cba osd: min_epoch for MOSDPGUpdateLogMissing[Reply] 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:29 -05:00
Sage Weil
024235fcd8 osd: min_epoch for MOSDPGScan 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:29 -05:00
Sage Weil
cb1a5190cd osd: set min_epoch for push/pull/reply 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:28 -05:00
Sage Weil
8c961a311f osd: set min_epoch for MOSDPGBackfill 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:28 -05:00
Sage Weil
152dfdd06c osd: min_epoch for MOSDECSubOp* 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 21:01:28 -05:00
Kefu Chai
611572a610 OSD: stop mgrc earlier in shutdown() 
it's better this way, as MgrClient is more like an internal consumer
of the services offered by OSD, instead of service privider. it could
prevent future problem if we can stop it earlier in the shutdown
process.

see also: http://tracker.ceph.com/issues/19638
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-05-02 09:45:16 +08:00
Sage Weil
f36f0dbcdb Merge pull request #14897 from tchaikov/wip-19814 
mon/OSDMonitor: update creating_pgs using pending_creatings

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-01 20:31:43 -05:00
Sage Weil
7d85bee4b5 Merge pull request #14889 from joscollin/wip-test-write-operations-warning 
test: c_write_operations.cc: silence warning from -Wsign-compare
 2017-05-01 20:30:49 -05:00
Sage Weil
19f2455b76 Merge pull request #14888 from joscollin/wip-test-read-operations-warning 
test: c_read_operations.cc: silence warning from -Wsign-compare
 2017-05-01 20:30:35 -05:00
Sage Weil
475daee9c7 Merge pull request #14799 from xiaoxichen/optimiztic_pg_active 
osd/PG.cc: Optimistic estimation on PG.last_active

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-01 20:30:23 -05:00
Sage Weil
d3b461eac0 Merge pull request #14790 from wjwithagen/wip-wjw-cleanup-unused-variable-v2 
common: Fix unused variable references warnings

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-05-01 20:30:03 -05:00
Sage Weil
5f1c03e536 Merge pull request #14330 from ivancich/wip-bring-in-dmclock 
dmclock: initial commit of dmclock QoS library
 2017-05-01 20:29:43 -05:00
Sage Weil
0bded75235 Merge pull request #14896 from liewegas/wip-19638 
osd: stop MgrClient callbacks on shutdown

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-01 20:25:29 -05:00
Sage Weil
2d6be11c2f Merge pull request #14899 from liewegas/wip-19433 
ceph_test_rados_api_watch_notify: make LibRadosWatchNotify.Watch3Timeout tolerate thrashing

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-01 20:24:48 -05:00
Sage Weil
5376b83b39 Merge pull request #14901 from liewegas/wip-19552 
osdc/Objecter: fix pool dne corner case

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-01 20:23:52 -05:00
Kefu Chai
6ce6acf526 Merge pull request #14881 from tchaikov/wip-crosscompiling-armhf 
cmake: enable cross-compilation of boost 

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-05-02 09:19:51 +08:00
Jason Dillaman
03b0b03071 cls_rbd: default initialize snapshot namespace for legacy clients 
Creating a snapshot on >=Kraken OSDs using <=Jewel clients can result
in an improperly initialized snapshot namespace. As a result, attempting
to remove the snapshot using a >=Kraken client will result in an -EINVAL
error.

Fixes: http://tracker.ceph.com/issues/19413
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-01 21:08:00 -04:00
Neha Ojha
522bd84dc0 objclass-sdk: add override to whitelist the sdk class 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2017-05-01 16:28:54 -07:00
Sage Weil
e4874b4091 Merge pull request #14788 from liewegas/wip-jewel-x-rgw 
qa/suites/jewel-x/point-to-point: don't scane for keys on second s3tests either

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-01 17:12:39 -05:00
Sage Weil
7e6e4bd5de osd/PGBackend: expose interval_start and last_peering_reset to backends 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 15:35:11 -05:00
Sage Weil
0a8c3e409b osd/PG: remove unused op_must_wait_for_map 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 15:35:11 -05:00
Sage Weil
9cde71f243 osd: wait based on min_epoch 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 15:35:11 -05:00
Sage Weil
52cb536077 osd: define min_epoch for fast dispatch messages 
For now, default to the sent_epoch (latest).

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 15:35:11 -05:00
Sage Weil
d60c1c40ce osdc/Objecter: fix pool dne corner case 
We have a request that is queued before a pool exists, there is one
epoch where it exists, and then the pool disappears again.  The two maps
are processed at the same time.  For the first we set needs_resend, map to
an osd, and remove from the homeless sessin.  For the second, the pool
dne, we set osd back to -1, and send a map check request.  Finally,
handle_osd_maps scans need_resend, sees the pool dne, and removes from
need_resend.  The difference from the "usual" case is that we are neither
on the need_resend list nor on the homeless session.

Fix this by concluding immediately that the pool existed (briefly) and
then no longer exists.

Fixes: http://tracker.ceph.com/issues/19552
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 15:10:44 -05:00
James Liu
a76e476bda doc:Adding Alibaba into organization map 
Signed-off-by: James Liu <james.liu@alibaba-inc.com>
 2017-05-01 13:00:11 -07:00
Sage Weil
a28282b157 ceph_test_rados_api_watch_notify: make LibRadosWatchNotify.Watch3Timeout tolerate thrashing 
If the PG moves we will reconnect and fail to time out.
Wait for longer so that we mask the effects of osd thrashing.

Fixes: http://tracker.ceph.com/issues/19433
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 13:21:30 -04:00
Kefu Chai
793c2f2297 mon/OSDMonitor: cleanup pending_created_pgs after done with it 
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-05-02 01:11:06 +08:00
Kefu Chai
b2d29568d7 mon/OSDMonitor: update creating_pgs using pending_creatings 
* without this change, in OSDMonitor::update_pending_pgs(), creating_pgs
  is updated directly without lock, and the change will be overwritten
  with pending changes eventually. so we should update it using
  pending_creatings
* also, should acquire the lock in OSDMonitor::send_pg_creates() when
  reading creating_pgs_by_osd_epoch and createing_pgs.

Fixes: http://tracker.ceph.com/issues/19814
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-05-01 23:48:59 +08:00
Radoslaw Zarzynski
56baf955ad Merge pull request #14775 from Jing-Scott/wip-con-obj-bulkupload 
rgw: add support container and object levels of swift bulkupload

Reviewed-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
 2017-05-01 17:44:36 +02:00
Kefu Chai
ab77b1dd6a Merge pull request #14892 from tchaikov/wip-kill-warnings 
test: kill warnings

Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-01 23:43:51 +08:00
Radoslaw Zarzynski
b4099a9a61 Merge pull request #14750 from theanalyst/rgw/fix/frontend_array 
rgw: civetweb don't go past the array index while calling mg_start

Reviewed-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
 2017-05-01 17:17:45 +02:00
Casey Bodley
cb041c9b16 Merge pull request #14359 from Jing-Scott/remove-zg-dup-post 
rgw multisite: remove the redundant post in OPT_ZONEGROUP_MODIFY

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-05-01 10:54:41 -04:00
Casey Bodley
6ac2dbf89e Merge pull request #14390 from shashalu/drop-unused-param 
rgw: drop unused param "bucket" from select_bucket_placement

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-05-01 10:54:01 -04:00
Casey Bodley
1e0b919e51 Merge pull request #14839 from chardan/jfw-wip-halflife_atomic_t-ebirah 
rgw: migrate atomic_t to std::atomic<> (ebirah)

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-05-01 10:53:00 -04:00
Casey Bodley
0e30e3ef01 Merge pull request #14845 from cbodley/wip-rgw-qa-s3tests 
qa/rgw: add cluster name to path when s3tests scans rgw log

Reviewed-by: Daniel Gryniewicz <dang@redhat.com>
 2017-05-01 10:49:12 -04:00
Sage Weil
83c45ad6a4 osd: stop MgrClient callbacks on shutdown 
Stop the MgrClient callbacks to report PG stats at the
start of shutdown() so that we don't get a callback
during/after we are done shutting down.

Protect the cb update with the MgrClient's lock so that
we don't race with MgrClient::send_report() itself.

Fixes: http://tracker.ceph.com/issues/19638
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 10:33:36 -04:00
Sage Weil
732ad1364e kv: move 'bluestore-kv' hackery out of KeyValueDB into ceph-kvstore-tool 
This avoids contaminating libkv with ObjectStore/BlueStore.  It also makes
the blustore kv startup slightly less weird (no need to skip the open
step).

Fixes: http://tracker.ceph.com/issues/19778
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-01 10:24:03 -04:00
Kefu Chai
8b8646f7ac test/librados: silence -Woverloaded-virtual warning 
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-05-01 22:19:55 +08:00
Kefu Chai
c83c62ea9b test/librbd: silence warning from -Wsign-compare 
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-05-01 22:13:40 +08:00
Jason Dillaman
0f7b5d4ee6 rbd: info command should indicate if parent is in trash 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-01 10:10:16 -04:00
Jason Dillaman
4939ff707b librbd: added trash_get API method to retrieve image status 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-01 10:10:16 -04:00
Jason Dillaman
4b48b9fe68 librbd: extended parent info API to retrieve parent id 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-01 10:10:13 -04:00
Matt Benjamin
1c9a48cec8 Merge pull request #14770 from rzarzynski/wip-rgw-19754 
rgw: fix RadosGW hang during multi-chunk upload of AWSv4.
 2017-05-01 10:09:10 -04:00