RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-01-10 21:20:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
86,074 Commits 213 Branches 394 Tags 1.2 GiB
b5263176de
Commit Graph

3578 Commits

Author SHA1 Message Date
Patrick Donnelly
b381cb7ea1
Merge PR #21625 into master 
* refs/pull/21625/head:
	qa: remove racy/buggy test_purge_queue_op_rate

Reviewed-by: Zheng Yan <zyan@redhat.com>
 2018-04-29 11:05:06 -07:00
Yuri Weinstein
32606e4087 qa/tests: fixed typo 
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
 2018-04-29 07:57:27 -07:00
Josh Durgin
aef8d96def
Merge pull request #21710 from neha-ojha/wip-cosbench-workloads 
qa: add cosbench workloads and override teuthology default settings

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-27 18:30:11 -07:00
Neha Ojha
1b6bf0d423 qa/suites/perf-basic: add cosbench write workload 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-27 16:15:30 -07:00
Neha Ojha
f670f2d6d3 qa/suites/perf-basic: override default teuthology settings 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-27 16:07:11 -07:00
Neha Ojha
f01eb7adc6 qa/suites/rados/perf: add cosbench workloads 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-27 16:02:40 -07:00
Jason Dillaman
0cb3e64221
Merge pull request #21704 from liewegas/wip-rados-old-clients 
qa/suites/rados/thrash-old-clients: add rbd tests

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2018-04-27 17:35:58 -04:00
Yuri Weinstein
2c98007a13
Merge pull request #21630 from neha-ojha/wip-rgw-pools 
qa: modify rgw default pool names

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-27 14:21:52 -07:00
Sage Weil
9fbdca34bf qa/suites/rados/thrash-old-clients: add cls_rbd, rbd api tests 
Signed-off-by: Sage Weil <sage@redhat.com>
 2018-04-27 14:04:25 -05:00
Neha Ojha
33db6bdfdd qa/suites/rados/perf: override default teuthology settings 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-27 12:04:00 -07:00
Sage Weil
7cbaa62498 qa/suites/rados/thrash-old-clients: add hammer 
Signed-off-by: Sage Weil <sage@redhat.com>
 2018-04-27 11:40:53 -05:00
Sage Weil
41fae6e9c4
Merge pull request #21679 from liewegas/wip-rados-old-clients 
qa/suites/rados/thrash-old-clients: do some thrashing with jewel and luminous clients

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-27 11:30:39 -05:00
Josh Durgin
f9dbfbe78f
Merge pull request #21656 from neha-ojha/wip-integrate-cosbench 
qa/tasks: run cosbench using the CBT task

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-26 17:38:27 -07:00
Neha Ojha
8198936df1 qa/tasks: run cosbench using the CBT task 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-26 16:36:57 -07:00
Sage Weil
510762f51e
Merge pull request #21061 from jan--f/jan-prometheus-file-sd-command 
pybind/mgr/prometheus: add file_sd_config command

Reviewed-by: Boris Ranto <branto@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
 2018-04-26 12:39:51 -05:00
Sage Weil
2332e63e33
Merge pull request #21646 from liewegas/wip-rados-api-tests 
qa/suites/rados/verify/tasks/rados_api_tests: whitelist OBJECT_MISPLACED
 2018-04-26 12:39:23 -05:00
Kefu Chai
62ccc2a7bb
Merge pull request #21658 from tchaikov/wip-msg-many-failure 
qa: reduce "mon client hunt interval max multiple" to 2 for all clients

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-26 17:48:46 +08:00
Lenz Grimmer
893857fcbd
Merge pull request #21526 from ricardoasmarques/wip-rbd-snapshot-clone 
mgr/dashboard: RBD copy, RBD flatten and snapshot clone (frontend)

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Ricardo Dias <rdias@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
 2018-04-26 10:22:42 +02:00
Kefu Chai
966c76330b qa: reduce "mon client hunt interval max multiple" to 2 for all clients 
because with high failure rate, we need to connect to mon more
frequently if the connection fails.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2018-04-26 12:04:49 +08:00
Sage Weil
e331311b87 qa/suites/rados/verify/tasks/rados_api_tests: whitelist OBJECT_MISPLACED 
The api tests do some splits, which can move data.

Signed-off-by: Sage Weil <sage@redhat.com>
 2018-04-25 10:33:52 -05:00
Mykola Golub
808503f4d9
Merge pull request #21541 from dillaman/wip-18753 
qa: introduce rbd-mirror thrasher to existing tests

Reviewed-by: Mykola Golub <mgolub@suse.com>
 2018-04-25 16:07:16 +03:00
Jan Fajerski
2eb0b41407 pybind/mgr/prometheus: add file_sd_config command 
This command returns a valid list of static targets pointing to the mgr
prometheus modules for a cluster. The output can be stored in a
file and the file be listed under the file_sd_config stanza in the
prometheus configuration.

Signed-off-by: Jan Fajerski <jfajerski@suse.com>
 2018-04-25 14:24:32 +02:00
Neha Ojha
8158a2c430 qa: add rgw index pool to rgw_snaps.yaml 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-24 15:22:18 -07:00
Sage Weil
27e91a99f5
Merge pull request #21273 from jdurgin/wip-23195 
osd/ECBackend: only check required shards when finishing recovery reads

Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
 2018-04-24 17:20:25 -05:00
Sage Weil
a43c7b3a23 qa/suites/rados/thrash-old-clients: do some thrashing with jewel and luminous clients 
Signed-off-by: Sage Weil <sage@redhat.com>
 2018-04-24 16:14:36 -05:00
Neha Ojha
48f4b8172a qa: correct default rgw pool name 
Signed-off-by: Neha Ojha <nojha@redhat.com>
 2018-04-24 13:45:33 -07:00
Patrick Donnelly
b39972d911
qa: remove racy/buggy test_purge_queue_op_rate 
Fixes: https://tracker.ceph.com/issues/23829

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2018-04-24 12:48:40 -07:00
Ricardo Marques
eeb87d3e42 mgr/dashboard: Add RBD default features REST API endpoint 
Signed-off-by: Ricardo Marques <rimarques@suse.com>
 2018-04-24 16:50:37 +01:00
Ricardo Marques
838c9ce9e3 mgr/dashboard: RBD flatten 
Signed-off-by: Ricardo Marques <rimarques@suse.com>
 2018-04-24 16:50:37 +01:00
Kefu Chai
c01eeadd00
Merge pull request #21555 from tchaikov/wip-23763 
test/librados: increase pgp_num along with pg_num

Reviewed-by: John Spray <john.spray@redhat.com>
 2018-04-24 18:32:21 +08:00
John Spray
f959371a0a
Merge pull request #21607 from jcsp/wip-mgr-selftest-fixup 
mgr: reconcile can_run checks and selftest

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
 2018-04-24 11:17:16 +01:00
Lenz Grimmer
83a740575a
Merge pull request #21602 from votdev/fix_rbd_form 
mgr/dashboard: Adapt RBD form to new application_metadata type

Reviewed-by: Sebastian Wagner <sebastian.wagner@suse.com>
Reviewed-by: Ricardo Marques <rimarques@suse.com>
Reviewed-by: Stephan Müller <smueller@suse.com>
 2018-04-24 11:33:33 +02:00
Patrick Donnelly
613d3b72cf
Merge PR #21536 into master 
* refs/pull/21536/head:
	qa: check old_max_mds is not wiped by marked down twice
	MDSMonitor: do not wipe old_max_mds when marked down twice

Reviewed-by: Douglas Fuller <dfuller@redhat.com>
 2018-04-23 21:27:55 -07:00
Kefu Chai
cdcbd47e1e qa/suite: whitelist PG_AVAILABILITY in rados_api_tests.yaml 
pg will be created when increasing pgp-num and pg-num. so at that
moment, PG_AVAILABILITY is reported. so whitelist it in all tests which
run rados/test.sh. that script exercises ceph_test_rados_api_list.

Fixes: http://tracker.ceph.com/issues/23763
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2018-04-24 10:16:12 +08:00
Kefu Chai
60e3a2404f qa/tasks/mgr: pass "--force" to "mgr module enable" 
Signed-off-by: Kefu Chai <kchai@redhat.com>
 2018-04-23 17:30:40 -04:00
Jason Dillaman
2311eff622 qa/suites/rbd: thrash rbd-mirror daemon during tests 
Fixes: http://tracker.ceph.com/issues/18753
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-04-23 16:02:59 -04:00
Volker Theile
9a4d379705 mgr/dashboard: Fix bug in RBD form. 
Signed-off-by: Volker Theile <vtheile@suse.com>
 2018-04-23 17:13:31 +02:00
Jason Dillaman
b28b2ee875 qa/tasks: thrasher for rbd-mirror daemon 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-04-23 10:22:50 -04:00
John Spray
4b3f026d07 qa: update mgr test for MgrModule.OPTIONS 
Signed-off-by: John Spray <john.spray@redhat.com>
 2018-04-23 10:14:31 -04:00
John Spray
d4ed33c2e0 qa: test mgr live configuration updates 
Signed-off-by: John Spray <john.spray@redhat.com>
 2018-04-23 07:29:47 -04:00
Mykola Golub
7ca8e70471
Merge pull request #21564 from dillaman/wip-23809 
rbd: cleanup handling of IEC byte units

Reviewed-by: Mykola Golub <mgolub@suse.com>
 2018-04-23 09:07:19 +03:00
Kefu Chai
4f73c6035a
Merge pull request #21549 from rjfd/wip-dashboard-fix-qa-whitelist 
qa/suites/rados/mgr/tasks/dashboard: add MDS_ALL_DOWN to whitelist

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2018-04-21 23:15:53 +08:00
Ricardo Dias
7309be145b
qa/suites/rados/mgr/tasks/dashboard: add MDS_(ALL_DOWN|UP_LESS_THAN_MAX) to whitelist 
Signed-off-by: Ricardo Dias <rdias@suse.com>
 2018-04-21 15:58:23 +01:00
Kefu Chai
586ea5cb29
Merge pull request #21579 from tchaikov/wip-test.sh-with-multi-mds 
qa/workunits/cephtool/test.sh: fix test_mon_mds()

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-21 22:31:43 +08:00
Kefu Chai
6f834d5da6
Merge pull request #21552 from smithfarm/wip-23805 
qa/standalone/ceph-helpers.sh: provide argument to dirname

Reviewed-by: David Zafman <dzafman@redhat.com>
 2018-04-21 22:30:33 +08:00
Kefu Chai
735d5fd414
Merge pull request #21507 from liewegas/wip-rados-test 
qa/workunits/rados/test.sh: ensure tee output is valid filename

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-21 09:30:02 +08:00
Kefu Chai
106737323d qa/workunits/cephtool/test.sh: fix test_mon_mds() 
"ceph fs set cephfs allow_multimds false" is deprecated, and multimds is
enabled by default, so "ceph fs set cephfs max_mds 4" won't fail with
the default settings.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2018-04-21 09:20:35 +08:00
Josh Durgin
234d652317 qa/suites/rados: add coverage for osd_recovery_max_single_start > 1 
Signed-off-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-20 19:42:15 -04:00
Josh Durgin
d4808256d2 osd/ECBackend: preserve requests for other objects when sending extra reads 
When multiple objects are in flight for the same ReadOp, swap() on the
map<hobject_t, read_request_t> would remove requests for all objects.

We just want to replace the requests for the single object we're
dealing with in send_all_remaining_reads().

This prevents crashing trying to look up rop.to_read[hoid] when another
object in the same ReadOp gets an EIO and tries to send more requests.

Test this by using osd-recovery-max-single-start to bundle multiple
reads into one ReadOp. Save and restore CEPH_ARGS so custom settings
are reset for each test.

Fixes: http://tracker.ceph.com/issues/23195 (the 2nd crash there)
Signed-off-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-20 19:42:15 -04:00
Josh Durgin
b162a5478d osd/ECBackend: recover from EIO based on the minimum data necessary 
Discount shards that already returned EIO, and use minimum_to_decode()
to request just what is necessary to recover or read the originally
requested extents of the object.

Signed-off-by: Josh Durgin <jdurgin@redhat.com>
 2018-04-20 19:42:14 -04:00