RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2024-12-24 20:33:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
83,253 Commits 211 Branches 394 Tags 1.2 GiB
98b718ea29
Commit Graph

83253 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Alfredo Deza
98b718ea29 doc quick-ceph-deploy update for newer ceph-volume API 
Signed-off-by: Alfredo Deza <adeza@redhat.com>
 2018-02-21 13:50:34 -05:00
Sage Weil
db1ca7271e Merge PR #19342 into master 
* refs/pull/19342/head:
	osd: add 'ceph [tell|daemon] osd.id smart'

Reviewed-by: Sage Weil <sage@redhat.com>
 2018-02-21 10:23:48 -06:00
Sage Weil
1d641d137b Merge PR #20465 into master 
* refs/pull/20465/head:
	os/bluestore: avoid frequent allocator dump on bluefs rebalance failure

Reviewed-by: Sage Weil <sage@redhat.com>
 2018-02-21 10:23:43 -06:00
Sage Weil
1292efcd3d Merge PR #20467 into master 
* refs/pull/20467/head:
	mon: mark manager beacons as no_reply

Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: João Eduardo Luís <joao@suse.de>
 2018-02-21 10:23:38 -06:00
Sage Weil
9f5a7ca8bf Merge PR #20484 into master 
* refs/pull/20484/head:
	osd/PrimaryLogPG: cancel all objecter ops atomically
	osdc/Objecter: allow multiple ops to be canceled atomically

Reviewed-by: David Zafman <dzafman@redhat.com>
 2018-02-21 10:23:33 -06:00
Sage Weil
5b41a65d2d Merge PR #20487 into master 
* refs/pull/20487/head:
	os/bluestore: do not account DB volume space in total one reported by statfs method
	os/bluestore: prevent statfs available from going negative

Reviewed-by: Igor Fedotov <ifedotov@suse.com>
 2018-02-21 10:23:29 -06:00
Gregory Farnum
1c3e81828a
Merge pull request #20374 from liewegas/wip-18351 
msg/DispatchQueue: clear queue after wait()

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2018-02-21 07:48:38 -08:00
Kefu Chai
14673a4509
Merge pull request #20475 from tchaikov/wip-std-string-view 
common/str_list: s/boost::string_view/std::string_view

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2018-02-21 20:57:22 +08:00
Kefu Chai
b06dd3bb0a
Merge pull request #20443 from rzarzynski/wip-common-inlineable-ceph_clock_now 
common: make ceph_clock_now() inlineable.

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2018-02-21 10:14:44 +08:00
Kefu Chai
cda5a196fc
Merge pull request #20439 from jcsp/wip-percent_used 
mon: dump percent_used PGMap field as float

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2018-02-21 10:13:48 +08:00
Sage Weil
1e34922fcd
Merge pull request #20177 from liewegas/wip-kill-onreadable 
os,osd: initial work to drop onreadable/onapplied callbacks

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-02-20 14:59:35 -06:00
Jason Dillaman
ab06f835f4
Merge pull request #20499 from idryomov/wip-krbd-discard-tests 
qa: additional krbd discard test cases

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-20 14:02:07 -05:00
Mykola Golub
783bc22438
Merge pull request #20490 from dillaman/wip-rbd-journal-workunit 
qa/workunits/rbd: remove sanity check in journal.sh test

Reviewed-by: Mykola Golub <mgolub@suse.com>
 2018-02-20 18:45:11 +02:00
Matt Benjamin
11526c68c7
Merge pull request #20093 from supriti/wip_rgw_ganesha_df 
RGW-NFS: Use rados cluster_stat to report filesystem usage
 2018-02-20 11:43:57 -05:00
Jason Dillaman
41e9607aae
Merge pull request #20395 from Songweibin/wip-misc-cleanup 
librbd: validate if dst group snap name is the same with src

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-20 10:32:17 -05:00
Jason Dillaman
fae456f60c
Merge pull request #20420 from trociny/wip-unwatch-race 
librbd: potential race in RewatchRequest when resetting watch_handle

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-20 10:31:54 -05:00
Jason Dillaman
0da7e351a5
Merge pull request #20478 from trociny/wip-api-mirror 
librbd: fix structure size check in rbd_mirror_image_get_info/status

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-20 10:31:14 -05:00
Ilya Dryomov
153af6b90a qa: krbd_blkroset.t: attempt discards in addition to writes 
The block layer used to not enforce ioctl(BLKROSET) and set_disk_ro().
This has been fixed in 4.16-rc1.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
 2018-02-20 15:54:41 +01:00
Mykola Golub
c6d9ae9416
Merge pull request #20491 from dillaman/wip-23043 
qa/workunits/rbd: fix issues within permissions test

Reviewed-by: Mykola Golub <mgolub@suse.com>
 2018-02-20 14:39:17 +02:00
Mykola Golub
6f6d21092a
Merge pull request #20481 from dillaman/wip-rbd-remove-error 
rbd: don't overwrite the error code from the remove action

Reviewed-by: Mykola Golub <mgolub@suse.com>
 2018-02-20 14:35:23 +02:00
Mykola Golub
f4cd2772e1
Merge pull request #20486 from dillaman/wip-11502 
test/librbd: utilize unique pool for cache tier testing

Reviewed-by: Mykola Golub <mgolub@suse.com>
 2018-02-20 14:34:45 +02:00
David Zafman
648a4c3d47
Merge pull request #20450 from dzafman/wip-22996 
Snapset inconsistency is detected with its own error

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2018-02-19 22:43:02 -08:00
Alfredo Deza
379897e894
Merge pull request #20492 from tchaikov/wip-boost-cmake-3.0 
cmake: disable DOWNLOAD_NO_PROGRESS if cmake ver is lower than 3.1

Reviewed-by: Alfredo Deza <adeza@redhat.com>
Reviewed-by: Dan Mick <dmick@redhat.com>
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
 2018-02-19 18:09:12 -05:00
Kefu Chai
d051bf0441 cmake: disable DOWNLOAD_NO_PROGRESS if cmake ver is lower than 3.1 
see https://cmake.org/cmake/help/v3.1/module/ExternalProject.html and
https://cmake.org/cmake/help/v3.0/module/ExternalProject.html. the
former has DOWNLOAD_NO_PROGRESS, while the latter does not.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2018-02-20 06:40:15 +08:00
Jason Dillaman
bc80c8c7f9 qa/workunits/rbd: remove sanity check in journal.sh test 
When the OSDs are being concurrently thrashed, this can result in
sporadic failures due to the admin socket disappearing.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-19 15:21:46 -05:00
Jason Dillaman
1374acdf1a qa/workunits/rbd: correct permission test handling for clone v2 images 
Fixes: http://tracker.ceph.com/issues/23043
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-19 15:16:40 -05:00
Jason Dillaman
7b9161eb05 qa/workunits/rbd: utilize RBD profiles in permissions.sh test case 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-19 14:53:27 -05:00
Igor Fedotov
f798b13a04 os/bluestore: do not account DB volume space in total one reported by statfs method 
Signed-off-by: Igor Fedotov <ifedotov@suse.com>
 2018-02-19 13:11:44 -06:00
Sage Weil
8709cbc2ec os/bluestore: prevent statfs available from going negative 
Fixes: https://tracker.ceph.com/issues/23040
Signed-off-by: Sage Weil <sage@redhat.com>
 2018-02-19 13:10:36 -06:00
Ilya Dryomov
8fa9dec271 qa: krbd_fallocate.sh: add -ENOENT handling test case 
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
 2018-02-19 20:02:57 +01:00
Greg Farnum
57ecc1ef1c mon: mark manager beacons as no_reply 
We never reply to manager beacons, and we have to mark them
that way or else forwarded messages pile up pending replies
and things eventually block.

Fixes: http://tracker.ceph.com/issues/22114
Reported-by: Hongpeng Lu <ludehp@163.com>

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
 2018-02-19 09:32:13 -08:00
Jason Dillaman
c42c54d0ec test/librbd: utilize unique pool for cache tier testing 
Fixes: http://tracker.ceph.com/issues/11502
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-19 10:25:15 -05:00
Sage Weil
93fd56ed03 osd/PrimaryLogPG: cancel all objecter ops atomically 
We want to avoid a situation like this:

- start proxy op A (epoch E)
- start proxy op B (epoch E)
- start proxy op C (epoch E)
- objecter sends none of these because target is down in epoch E
- osdmap update to E+1
- pg cancels requeues A, B
- objecter updates to E+1
- objecter sends C
- pg cancels/requeues C

Note that the key thing is that operations on each object are canceled
atomically.  On the interval change we do it all at once.  In the other
cases, we cancel everything on the given object together.

Fixes: http://tracker.ceph.com/issues/22123
Signed-off-by: Sage Weil <sage@redhat.com>
 2018-02-19 08:54:58 -06:00
Sage Weil
7459d4a479 osdc/Objecter: allow multiple ops to be canceled atomically 
This allows multiple cancellations without worrying about a race with an
(objecter) osdmap update.

Signed-off-by: Sage Weil <sage@redhat.com>
 2018-02-19 08:52:51 -06:00
Jason Dillaman
11c1a0784c rbd: don't overwrite the error code from the remove action 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2018-02-19 09:35:31 -05:00
Mykola Golub
01a2719549 librbd: fix structure size check in rbd_mirror_image_get_info/status 
Signed-off-by: Mykola Golub <mgolub@suse.com>
 2018-02-19 12:31:10 +02:00
Igor Fedotov
d87cb07c8e os/bluestore: avoid frequent allocator dump on bluefs rebalance failure 
Signed-off-by: Igor Fedotov <ifedotov@suse.com>
 2018-02-19 13:27:07 +03:00
Kefu Chai
1b3d19a46b
Merge pull request #20031 from tchaikov/wip-doc-macos 
doc/dev/macos: add doc for building on MacOS
 2018-02-19 15:21:50 +08:00
Kefu Chai
939db758e4 common/str_list: s/boost::string_view/std::string_view 
since string_view is include by standard library, we can now switch from
boost::string_view to std::string_view.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2018-02-19 10:55:08 +08:00
Kefu Chai
3b10d16235
Merge pull request #20474 from wjwithagen/wjw-wip-pthread_set_name_2 
include: compat.h, fix the return result of pthread_set_name()

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2018-02-19 10:45:31 +08:00
Patrick Donnelly
039165276e
Merge PR #20168 into master 
* refs/pull/20168/head:
	Handle dir->dentries.empty()
	client: lookup_ino when i1 becomes NULL

Reviewed-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: Zheng Yan <zyan@redhat.com>
 2018-02-18 10:36:34 -08:00
Patrick Donnelly
14da9d77b1
Merge PR #20424 into master 
* refs/pull/20424/head:
	qa: ignore io pause warnings in mds-full test

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2018-02-18 10:36:30 -08:00
Patrick Donnelly
81d0a52a2a
Merge PR #20428 into master 
* refs/pull/20428/head:
	qa: ignore MON_DOWN while thrashing mons

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2018-02-18 10:36:25 -08:00
Patrick Donnelly
852b8491e8
Merge PR #20470 into master 
* refs/pull/20470/head:
	qa: ignore full cluster warnings for mds-full

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2018-02-18 10:36:21 -08:00
Willem Jan Withagen
23074ce4a7 include: compat.h, fix the return result of pthread_set_name() 
On FreeBSD the function type is void(). Make it compatible with return
value on other platforms.

Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
 2018-02-18 14:45:56 +01:00
Patrick Donnelly
27b6bfbd81
qa: ignore full cluster warnings for mds-full 
Fixes: http://tracker.ceph.com/issues/23033

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2018-02-17 16:09:57 -08:00
Sage Weil
448b6967db qa/suites/rados/objectstore: increase open file limit 
Signed-off-by: Sage Weil <sage@redhat.com>
 2018-02-17 10:17:57 -06:00
Sage Weil
d034945ba2 os: do not inject read EIO on meta pool objects 
Avoid EIO on, say, osdmaps until we fix
http://tracker.ceph.com/issues/23029

Signed-off-by: Sage Weil <sage@redhat.com>
 2018-02-17 10:17:39 -06:00
Kefu Chai
483f14cd80
Merge pull request #20274 from adamemerson/wip-socket-to-me! 
common/admin_socket: various cleanups

Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
 2018-02-17 10:05:08 +08:00
Sage Weil
08324f7118 test_filestore_idempotent_sequence: put txn object in each collection 
The transactions are idependent in each collection/sequencer, so we
can't record to a single txn object with racing transactions.  Fix
it by doing one in each collection, and when reading the latest op,
use the highest txn value we see.

Signed-off-by: Sage Weil <sage@redhat.com>
 2018-02-16 16:50:04 -06:00