Commit Graph

88282 Commits

Author SHA1 Message Date
Jason Dillaman
7c94366b8a
Merge pull request #22945 from cxytt/master
librbd:optionally support FUA (force unit access) on write requests

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
2018-07-14 14:18:02 -04:00
Jason Dillaman
09bb605002
Merge pull request #22637 from zy751713126/resize_equal_size
rbd: error if new size is equal to original size

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
2018-07-14 14:17:17 -04:00
Jason Dillaman
0216fa878e
Merge pull request #20112 from liyichao/aio_fail
librbd: handle aio failure in ManagedLock and PreReleaseRequest

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
2018-07-14 14:16:57 -04:00
Kefu Chai
3d1eae0d5b
Merge pull request #23046 from tchaikov/wip-ftbfs-rgw-kefu
rgw: fix FTBFS introduced by abca9805
2018-07-14 21:33:08 +08:00
Kefu Chai
2d7237557e rgw: fix FTBFS introduced by abca9805
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-14 18:26:19 +08:00
Kefu Chai
4e87c5a492
Merge pull request #22809 from tchaikov/wip-with-seastar
run-make-check: enable --with-seastar option

Reviewed-by: Casey Bodley <cbodley@redhat.com>
2018-07-14 17:36:20 +08:00
Kefu Chai
c675f2b1a1
Merge pull request #22964 from tchaikov/wip-import-pub-key-without-hkp-server
install-deps.sh: import ubuntu-toolchain-r's key without keyserver

Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
2018-07-14 15:47:00 +08:00
Patrick Donnelly
8eea2dbf5a
Merge PR #22971 into master
* refs/pull/22971/head:
	qa: optionally use old fs name during cephfs remount
	qa: remove dead code
	qa: run asok command on correct machine
2018-07-13 18:16:51 -07:00
Patrick Donnelly
1ad8d86bd0
qa: optionally use old fs name during cephfs remount
This fixes errors caused by remount done by some tests (test_recovery_pool.py)
where the fs name is not given.

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-13 18:16:06 -07:00
Patrick Donnelly
a2ff87d4e2
qa: remove dead code
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-13 18:15:03 -07:00
Patrick Donnelly
fa25d6c8d1
qa: run asok command on correct machine
The MDS may not be on the same machine where the cluster command is run.

Fixes: http://tracker.ceph.com/issues/24858

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-13 16:07:30 -07:00
Patrick Donnelly
333444e8aa
Merge PR #21885 into master
* refs/pull/21885/head:
	qa: update cluster log health warning message
	qa: add tests for client features
	mds: evict clients that lack required features
	mds: cleanup MDSRank::evict_client
	mds: infer client version by client metadata and connection's features
	mds: introduce "ceph fs set <fs_name> min_compat_client <release_name>"
	mds: tell client why it's rejected
	mds: introduce cephfs' own feature bits
	mds: make Server::prepare_force_open_sessions() update client metadata

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-13 13:57:17 -07:00
Patrick Donnelly
9298e3ae9c
Merge PR #23018 into master
* refs/pull/23018/head:
	qa: use 4 mds cluster for multifs tests

Reviewed-by: Zheng Yan <zyan@redhat.com>
2018-07-13 13:57:10 -07:00
Patrick Donnelly
3b7233a402
qa: use 4 mds cluster for multifs tests
Fixes: http://tracker.ceph.com/issues/24899

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-13 12:11:44 -07:00
Patrick Donnelly
87dcaab130
qa: update cluster log health warning message
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-13 12:06:11 -07:00
Matt Benjamin
d36d6815e5
Merge pull request #23033 from linuxbox2/wip-rgw-409
rgw: do not ignore EEXIST in RGWPutObj::execute
2018-07-13 12:36:24 -04:00
Kefu Chai
e2c348ebce
Merge pull request #23020 from tchaikov/wip-config-value-friend
common/config_values: friend md_config_impl<>

Reviewed-by: Mykola Golub <mgolub@suse.com>
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
2018-07-13 23:32:47 +08:00
Matt Benjamin
7c18258e54 rgw: do not ignore EEXIST in RGWPutObj::execute
The existing logic appears able to cause propagation of a failed
exclusive create to the client, when it should instead have been
retried, due to disagreement about the logical write offset. (The
value of ofs here could be > 0 due to the operation of a stacked
write filter [e.g., compressor], when the RADOS write offset was
0 and hence an exclusive write that should be retried).

Rationale for fix by Casey.

http://tracker.ceph.com/issues/22790

Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
2018-07-13 11:08:32 -04:00
Kefu Chai
0bf02e8fe5 rbd-ggate: filter out ceph options from args
we can just filter out ceph options from command line args instead of
parsing config in env variables, conf files and argvs.

the config-parsing steps were modeled after the ones in rbd-nbd.cc, but
the whole purpose of reading configurations from env/conf-file is to get
the "rbd_default_pool" for setting cfg->poolname. apparently, this does
not apply to rbd-ggate, where global_init() will take care of all the
trivial work to populate the settings. moreover, `config` is not
read after being initialized in main.cc. so drop it.

Signed-off-by: Mykola Golub <mgolub@suse.com>
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-13 21:06:32 +08:00
Kefu Chai
6147ed1bbd common/config_values: friend md_config_impl<>
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-13 15:05:15 +08:00
Patrick Donnelly
9f6e99db6f
Merge PR #22995 into master
* refs/pull/22995/head:
	qa: use root to find client admin socket

Reviewed-by: Nathan Cutler <ncutler@suse.com>
2018-07-12 21:38:36 -07:00
Patrick Donnelly
441a2730e5
qa: add tests for client features
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-07-12 10:12:12 -07:00
Yan, Zheng
4414f4e20d
mds: evict clients that lack required features
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
2018-07-12 08:21:16 -07:00
Kefu Chai
3e8ddaf301
Merge pull request #22938 from tchaikov/wip-bundled-dpdk
cmake: do not depend on ${DPDK_LIBRARIES} if not using bundled dpdk

Reviewed-by: Casey Bodley <cbodley@redhat.com>
2018-07-12 23:10:54 +08:00
Yan, Zheng
e147020a99 mds: cleanup MDSRank::evict_client
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
2018-07-12 22:08:45 +08:00
Yan, Zheng
44148347ec mds: infer client version by client metadata and connection's features
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
2018-07-12 22:08:45 +08:00
Yan, Zheng
eeac2c76ba mds: introduce "ceph fs set <fs_name> min_compat_client <release_name>"
The command set the oldest version of client that is allowed to connect
to mds.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
2018-07-12 22:08:45 +08:00
Yan, Zheng
43c1193915 mds: tell client why it's rejected
Signed-off-by: Yan, Zheng <zyan@redhat.com>
2018-07-12 22:08:44 +08:00
Yan, Zheng
353fcee10a mds: introduce cephfs' own feature bits
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Fixes: http://tracker.ceph.com/issues/14456
2018-07-12 22:08:44 +08:00
Yan, Zheng
c740000044 mds: make Server::prepare_force_open_sessions() update client metadata
The function is used for opening sessions for importing caps. It didn't
set client metadata for new sessions.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
2018-07-12 22:08:44 +08:00
Kefu Chai
1e9a79d92f
Merge pull request #22594 from wido/mgr-pg-states
mgr: Centralize PG_STATES to MgrModule

Reviewed-by: Lenz Grimmer <lgrimmer@suse.com>
Reviewed-by: Jan Fajerski <jfajerski@suse.com>
Reveiwed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Boris Ranto <branto@redhat.com>
2018-07-12 20:44:59 +08:00
Kefu Chai
467411ba6b
Merge pull request #22952 from tchaikov/wip-cmake-atomic
cmake: should link against libatomic if libcxx/libstdc++ does not off…

Reviewed-by: Casey Bodley <cbodley@redhat.com>
2018-07-12 20:40:41 +08:00
Kefu Chai
d33d295055 cmake: link libcrimson against libceph-common
as libcrimson uses symbols exposed by the later, among other things, the
Authorization related stuff.

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:54:45 +08:00
Kefu Chai
2a6bec88c3 cmake: remove unittest_seastar_{messenger,echo} from tests
unittest_seastar_echo cannot be run as unittest w/o starting two
instances.
unittest_seastar_messenger times out. need to RCA it.

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:54:45 +08:00
Kefu Chai
abca980589 common: extract SubProcess impl into .cc
cleanup the header dependencies and speed-up the compiling

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:54:45 +08:00
Kefu Chai
61e748ba69 seastar: pick up fixes to address build failures
see also https://groups.google.com/forum/#!topic/seastar-dev/uEMYGgYJKOY

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:54:45 +08:00
Kefu Chai
f1f1526166 run-make-check.sh: enable WITH_SEASTAR
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:51:22 +08:00
Kefu Chai
25d5122b55 rpm,install-deps.sh: add --with-seastar option
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:49:34 +08:00
Kefu Chai
6240e5ee57 crimson: include seastar headers with 'seastar/' prefix
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-07-12 17:47:57 +08:00
ningtao
4c20310db8 librbd:optionally support FUA (force unit access) on write requests
Fixes: http://tracker.ceph.com/issues/19366

Signed-off-by: ningtao <63358@sangfor.com>
2018-07-12 17:44:33 +08:00
Sage Weil
360211ed7b Merge PR #22877 into master
* refs/pull/22877/head:
	common: fix races when visiting a TrackedOp.

Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2018-07-11 22:02:02 -05:00
Sage Weil
910f3aec1a Merge PR #22946 into master
* refs/pull/22946/head:
	os/bluestore: batch handle get_fragmentation.

Reviewed-by: Igor Fedotov <ifedotov@suse.com>
2018-07-11 22:01:57 -05:00
Sage Weil
a28907fb14 Merge PR #22950 into master
* refs/pull/22950/head:
	rpm: move make check-specific build deps to appropriate conditional block
	rpm: remove universal requires from distro-specific conditional blocks

Reviewed-by: Kefu Chai <kchai@redhat.com>
2018-07-11 22:01:52 -05:00
Sage Weil
d1653a4cbc Merge PR #22972 into master
* refs/pull/22972/head:
	os/bluestore: fix races on SharedBlob::coll in ~SharedBlob.

Reviewed-by: Sage Weil <sage@redhat.com>
2018-07-11 22:01:47 -05:00
Sage Weil
b7b5105d0c Merge PR #22974 into master
* refs/pull/22974/head:
	qa/standalone/osd/ec-error-rollforward: reproduce bug 24597
	qa/suites/rados/thrash-erasure-code: add many deletes workload
	qa/standalone/osd/repro_long_log.sh: fix test
	osd/PG: do not blindly roll forward to log.head

Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2018-07-11 22:01:42 -05:00
Sage Weil
4108ebc0ab qa/standalone/osd/ec-error-rollforward: reproduce bug 24597
This reproduces http://tracker.ceph.com/issues/24597

Signed-off-by: Sage Weil <sage@redhat.com>
2018-07-11 16:15:49 -05:00
Sage Weil
1fdd424815 qa/suites/rados/thrash-erasure-code: add many deletes workload
Having lots of deletes will mean deletes on objects that don't exist,
which will in turn mean error log entries and more coverage of the
append_log_entries_update_missing code.  Hopefully this will trigger
http://tracker.ceph.com/issues/24597

Signed-off-by: Sage Weil <sage@redhat.com>
2018-07-11 16:15:49 -05:00
Sage Weil
4f9fdd98e2 qa/standalone/osd/repro_long_log.sh: fix test
The log trimming case wasn't quite right.  Before HEAD^ we were
rolling forward too aggressively and miscalculating the can_rollforward_to,
which affected the trim_to calculation.

Signed-off-by: Sage Weil <sage@redhat.com>
2018-07-11 16:15:49 -05:00
Sage Weil
858ff647ff osd/PG: do not blindly roll forward to log.head
If we are told we can roll forward by the primary, we should only roll
forward as far as the primary says we can.

This probably came out of the similar case in append_log(), but notably
that roll_forward() only happens if !transaction_applied (i.e., backfill
target), and that condition is not checked here.

Fixes: http://tracker.ceph.com/issues/24597
Signed-off-by: Sage Weil <sage@redhat.com>
2018-07-11 16:15:49 -05:00
Abhishek L
65c41200bc
Merge pull request #22989 from theanalyst/doc/releases/v10.2.11
doc: releases: release notes for v10.2.11 Jewel

Reviewed-By: Nathan Cutler <ncutler@suse.com>
2018-07-11 23:01:10 +02:00