RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-01-12 14:10:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
74,559 Commits 2 Branches 394 Tags 1.3 GiB
fe4d15191d
Commit Graph

74559 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
xie xingguo
78e0ea3d4d src/vstart.sh: kill dead upmap option 
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 22:14:30 +08:00
Sage Weil
bc867c7299 Merge pull request #15820 from liewegas/wip-20303 
mon/PGMap: slightly better debugging around pgmap updates

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-06-22 08:38:50 -05:00
Sage Weil
4a76eaee7a Merge pull request #15846 from xiexingguo/wip-remap-upmap 
mon/OSDMonitor: _apply_remap -> _apply_upmap; less code redundancy

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-06-22 08:33:35 -05:00
xie xingguo
3e1e10b5d1 mon/OSDMonitor: less code redundancy 
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 20:00:04 +08:00
John Spray
53fc7a5fc1 Merge pull request #15805 from jcsp/wip-mds-flush-upgrade 
client: check for luminous MDS before sending FLUSH_MDLOG

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-06-22 07:08:51 -04:00
John Spray
b7048b2c7b Merge pull request #15800 from ukernel/wip-20340 
mds: save  projected path into inode_t::stray_prior_path

Reviewed-by: John Spray <john.spray@redhat.com>
 2017-06-22 07:07:59 -04:00
John Spray
1e917eb8d6 Merge pull request #15776 from ukernel/wip-20338 
osdc/Journaler: fix memory leak in Journaler::_issue_read()

Reviewed-by: John Spray <john.spray@redhat.com>
 2017-06-22 07:07:21 -04:00
John Spray
7e991fe36e Merge pull request #15430 from jcsp/wip-20165 
mds: fix hangs involving re-entrant calls to journaler

Reviewed-by: Yan, Zheng <zyan@redhat.com>
 2017-06-22 07:06:41 -04:00
John Spray
38dccd2c72 Merge pull request #15548 from ukernel/wip-20196 
mds: improvements for stray reintegration

Reviewed-by: John Spray <john.spray@redhat.com>
 2017-06-22 06:46:27 -04:00
xie xingguo
422e218486 mon/MonCommand: fix description of "osd pg-upmap" 
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 17:26:47 +08:00
xie xingguo
b84ab54280 osd/OSDMap: _apply_remap -> _apply_upmap 
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 16:50:27 +08:00
Igor Fedotov
670d18e61b Merge pull request #15796 from lixiaoy1/fio_ceph_objectstore 
fio_ceph_objectstore: Print db_statistics when rocksdb_perf is enabled
 2017-06-22 12:01:00 +04:00
Orit Wasserman
c320fbd9f8 Merge pull request #15753 from pritha-srivastava/wip-rgw-s3tests-conf 
rgw: Changes for s3test config file, to add user under a tenant.
Reviewed-by: Casey Bodely <cbodley@redhat.com>
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
 2017-06-22 11:00:26 +03:00
Daniel Bar-On
cb920f6485 msg/async/rdma: remove assert from ibv_dealloc_pd in ProtectionDomain 
destructor

issue: 1044307

Change-Id: I2fe2099c5f4403f14877e0fbe5d4868dd34d4f9b
Signed-off-by: DanielBar-On <danielbo@mellanox.com>
 2017-06-22 10:11:13 +03:00
xie xingguo
aa850b9944 os/bluestore: avoid initializing finishers in constructor 
This is a follow up change of https://github.com/ceph/ceph/pull/15666,
which I forget to update.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 14:37:31 +08:00
xie xingguo
041296bdb1 os/bluestore: add "0x" prefix for hex outputs 
Which is the normal case.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 14:37:31 +08:00
xie xingguo
be90d3afba os/bluestore: non-atomic min_alloc_size_order 
This is not necessary because we now write min_alloc_size into disk
during mkfs.

There are two acaccompanying changes too:
(1) don't call _set_alloc_sizes() during mkfs() any more, which is
not necessary.
(2) don't update min_alloc_size during _set_alloc_sizes(), we instead
update min_alloc_size_order each time we successfully read min_alloc_size
from disk.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 14:37:30 +08:00
Orit Wasserman
ad420d5574 rgw: check all users bucket for resharding, this will reshard bucket created in older versions 
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
 2017-06-22 09:31:02 +03:00
xie xingguo
95b40849e9 os/bluestore: drop _open_alloc() from mkfs 
This is useless as the fsck() process will do necessary validations later.
And dropping this can make mkfs slightly faster.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 13:52:14 +08:00
xie xingguo
3492d3b670 os/bluestore: prefix open_statfs with "_" 
As it is an internal method only.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-22 13:52:14 +08:00
Mykola Golub
0d26ae3be0 Merge pull request #15317 from liupan1111/wip-fix-list 
rbd-nbd: display pool/image/snap information in list output

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Mykola Golub <mgolub@mirantis.com>
 2017-06-22 07:31:32 +03:00
Jos Collin
b4d17bf2ca Merge pull request #15803 from mikulely/cleanup-rgw_rados_doc 
rgw: update function doc in rgw_rados.h  and rgw_rados.cc

Reviewed-by: Jos Collin <jcollin@redhat.com>
 2017-06-22 04:27:29 +00:00
Kefu Chai
fea6e3216a qa/workunits/rbd: do not test --export-format unless supported 
in 55edd81, test for `--export-format` was added to exercise this
option. but this option is only supported on luminous, so we need to
check if it's avaialble before using it.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-06-22 12:19:01 +08:00
Kefu Chai
5d252a27a1 a/workunits/rados/test_envlibrados_for_rocksdb.sh: git clone --depth 1 
no need to clone the whole history of rocksdb, we just need the HEAD of
master. so "--depth 1" is better and faster in this case.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-06-22 12:19:01 +08:00
Kefu Chai
1b3f0bbd66 qa/suites/upgrade/hammer-jewel-x: upgrade all mon to luminous before osd 
luminous osd requires that monmap has REQUIRE_LUMINOUS before it boots.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-06-22 12:19:01 +08:00
Kefu Chai
f11737a643 qa/suites/upgrade/hammer-jewel-x: replace kraken.yaml with luminous.yaml 
* add mgr.x to roles
* to setup mgr and set the require-osd-release bit in osdmap
* do not restart an osd for waiting for healthy: the cluster is not
  healthy until the require-osd-release=luminous is set in osdmap, and a
  mgr is up and running.

Fixes: http://tracker.ceph.com/issues/20342
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-06-22 12:19:01 +08:00
Sage Weil
4c8c3e93b0 Merge pull request #15261 from mychoxin/yuanxin_use_func 
os/filestore: when print log, use __func__ instead of hard code function name

Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
Reviewed-by: Jos Collin <jcollin@redhat.com>
 2017-06-21 21:14:30 -05:00
Sage Weil
288f623878 Merge pull request #15354 from badone/wip-rados-ls-auth-fix 
osd: Reverse order of op_has_sufficient_caps and do_pg_op

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2017-06-21 21:14:01 -05:00
Sage Weil
dd8fed575a Merge pull request #15649 from liewegas/wip-20274 
osd/PrimaryLogPG: record prior_version for DELETE events

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-06-21 21:13:14 -05:00
Sage Weil
8d8f2c3dc3 Merge pull request #15601 from liewegas/wip-no-restful-cert 
mgr: remove default cert; disable both restful and dashboard by default

Reviewed-by: Boris Ranto <branto@redhat.com>
 2017-06-21 21:10:35 -05:00
Jiaying Ren
c61d12e729 rgw: update rgw_rados.h function doc 
+ update system_obj_get_attr func comment
+ drop deprecated func comment for get_obj
+ update func comment for pool_iterate_begin

Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
 2017-06-22 09:33:15 +08:00
Haomai Wang
49fe721073 Merge pull request #15755 from Adirl/wip-HUGEPAGES 
msg/async/rdma: automatically set RDMAV_HUGEPAGES_SAFE according to conf

Reviewed-by: Haomai Wang <haomai@xsky.com>
 2017-06-22 09:23:29 +08:00
Sage Weil
e5dd3a3ca2 qa/workunits/rest/test_mgr_rest_api: remove ruleset 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 21:17:14 -04:00
Sage Weil
647533f552 qa/suites/rados/rest/mgr-restful: configure cert 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 21:09:58 -04:00
Sage Weil
025debbb9f pybind/mgr/restful: add 'restful restart' command 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 21:00:35 -04:00
Jason Dillaman
fee2ea1c1c Merge pull request #15757 from runsisi/wip-image-ts 
librbd: add create timestamp metadata for image

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-06-21 20:51:52 -04:00
Kefu Chai
720aea32bc Merge pull request #15444 from wjwithagen/wip-wjw-freebsd-termwidth 
test: Make screencandy optional for FreeBSD

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-06-22 07:46:57 +08:00
Sage Weil
7879efdd6b osd/PGLog: ignore ERROR entires in _merge_object_divergent_entries 
Sometimes ERROR log entries do not have prior_version.  Also,
they aren't actually updates and don't affect the object.

Fixes: http://tracker.ceph.com/issues/20274
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 18:25:47 -04:00
Sage Weil
ba46a54f53 qa/objectstore/bluestore: lower full thresholds 
On NVMe we can write really fast... fast enough that we may fill up before
we realize we are nearly full.  It's a problem here only because our
devices are so small that the OSDs fill up proportionally quickly.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 14:52:49 -07:00
Sage Weil
e6d2c0052d mon/PGMap: slightly better debugging around pgmap updates 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 17:50:59 -04:00
Sage Weil
f5def607be qa/suites/powercycle/osd/tasks/radosbench: consume less space 
Fixes: http://tracker.ceph.com/issues/20302
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 14:50:04 -07:00
Sage Weil
b8a9ee8eb3 Merge pull request #15783 from liewegas/wip-20358 
os/bluestore: move sharedblob to new collection in same shard
 2017-06-21 16:01:51 -05:00
Sage Weil
41401c0ad7 Merge pull request #15785 from liewegas/wip-bluestore-fsck 
qa/objectstore/bluestore*: fsck on mount

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-21 16:01:07 -05:00
Sage Weil
3a9fa481c5 qa/objectstore/filestore-btrfs: test btrfs on trusty only 
Centos btrfs hits ENOSPC all the time :(, and now xenial is doing
it too.

See http://tracker.ceph.com/issues/20169
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-21 16:44:25 -04:00
Mykola Golub
039b74ddfb Merge pull request #15734 from dillaman/wip-librbd-image-remove 
librbd: fix issues with image removal state machine

Reviewed-by: Mykola Golub <mgolub@mirantis.com>
 2017-06-21 23:41:33 +03:00
Gregory Farnum
0e51ab1012 Merge pull request #15727 from ovh/bp-runtime-cfg-of-hb-inflator 
osd, messages/MOSDPing: bunch of fixes related to ping inflation

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2017-06-21 16:05:40 -04:00
Yuri Weinstein
88fe387614 Merge pull request #15723 from badone/wip-ceph-mon-startup-error-logging 
mon: Log errors at startup

Reviewed-by: Alfredo Deza <adeza@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-06-21 13:01:35 -07:00
Sage Weil
faa44ed3bc Merge pull request #15784 from liewegas/wip-thrash-cleanup 
qa/tasks/ceph_manager: get osds all in after thrashing
 2017-06-21 14:31:34 -05:00
Sage Weil
a6831381ad Merge pull request #15787 from liewegas/wip-19943-fix 
ceph-objectstore-tool: do not populate snapmapper with missing clones

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2017-06-21 14:31:02 -05:00
Vasu Kulkarni
182acd4411 s3a hadoop '2.8.0' tests 
Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
 2017-06-21 11:52:17 -07:00