Commit Graph

102686 Commits

Author SHA1 Message Date
Kefu Chai
a6da8559ff
Merge pull request #30518 from liewegas/wip-mon-less-snap-metadata
mon/OSDMonitor: clean up removed_snap keys

Reviewed-by: Kefu Chai <kchai@redhat.com>
2019-09-27 15:04:38 +08:00
Kefu Chai
c1ab6d436e
Merge pull request #30530 from dzafman/wip-42015
osd: Remove unused osdmap flags full, nearfull from output

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2019-09-27 15:01:39 +08:00
Patrick Donnelly
7baf44b89c
Merge PR #30406 into master
* refs/pull/30406/head:
	doc: move MDS deployment from main quick start to CephFS quick start
	doc: update CephFS Quick Start doc

Reviewed-by: Sidharth Anupkrishnan <sanupkri@redhat.com>
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
2019-09-26 23:51:15 -07:00
Patrick Donnelly
fa1ee5b4f6
Merge PR #30561 into master
* refs/pull/30561/head:
	doc/ceph-fuse: mention -k option in ceph-fuse man page

Reviewed-by: Douglas Fuller <dfuller@redhat.com>
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
Reviewed-by: Varsha Rao <varao@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: Sidharth Anupkrishnan <sanupkri@redhat.com>
2019-09-26 23:11:05 -07:00
Kefu Chai
a6c08712e7
Merge pull request #30404 from shun-s/cleanup-failure-pending
osd: make osd recover more smoothly by avoiding failure peer info to resent

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Sage Weil <sage@redhat.com>
2019-09-27 13:50:17 +08:00
Kefu Chai
7ae9ffff65
Merge pull request #30517 from tchaikov/wip-test/dashboard/scheme-allow-unknown
qa/tasks/mgr/dashboard/test_health: add "allow_unknown" in mgr_map

Reviewed-by: Ernesto Puerta <epuertat@redhat.com>
2019-09-27 13:36:23 +08:00
Patrick Donnelly
719cb3f5b4
Merge PR #30297 into master
* refs/pull/30297/head:
	test_cephfs_shell: add note on how to run this testsuite
	cephfs-shell: rewrite help text for put and get commands

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
2019-09-26 22:34:28 -07:00
Kefu Chai
f1ffba31a5
Merge pull request #30533 from cxytt/fix-complete-to-not-reset
osd/PGLog: reset log.complete_to when recover obect failed

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2019-09-27 13:32:19 +08:00
Kefu Chai
de44ad700c
Merge pull request #30538 from tchaikov/wip/test/ceph_argparse/yet-another-test
mon.test: improve validation and add a test for "osd pool create"

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2019-09-27 13:31:38 +08:00
Kefu Chai
866eac0834
Merge pull request #30504 from Songweibin/wip-app-meta-get
pybind/rados: add application_metadata_get

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2019-09-27 13:24:56 +08:00
Kefu Chai
120dd3367d
Merge pull request #30421 from sebastian-philipp/prometheus-always-on-modules
mgr/prometheus: Fix KeyError in get_mgr_status

Reviewed-by: Jan Fajerski <jfajerski@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
2019-09-27 13:21:10 +08:00
Kefu Chai
3fcaa765cd
Merge pull request #30200 from NancySu05/dev
mon/OSDMonitor: trim not-longer-exist failure reporters

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2019-09-27 13:18:19 +08:00
Patrick Donnelly
07db3c12a1
Merge PR #29906 into master
* refs/pull/29906/head:
	vstart_runner: name booleans for options differently
	qa/vstart_runner.py: add an option to remove old log
	qa/vstart_runner.py: make log initialization code reusable
	qa/vstart_runner.py: make printing of stdout of ps optional
	qa/vstart_runner.py: add timeout for vstart.sh and stop.sh
	qa/vstart_runner.py: add an option to teardown cluster

Reviewed-by: Jeff Layton <jlayton@redhat.com>
2019-09-26 22:12:03 -07:00
Kefu Chai
0308ffd7ab
Merge pull request #30612 from tchaikov/wip-install-deps.sh/do-not-fail-if-already-installed
install-deps: do not install if rpm already installed

Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
2019-09-27 11:24:09 +08:00
Kefu Chai
45a4173bcf install-deps: do not install if rpm already installed
there is chance that the system already have epel-release-latest-7.noarch.rpm
installed, in that case, install-deps.sh should not fail.

Signed-off-by: Kefu Chai <kchai@redhat.com>
2019-09-27 11:07:30 +08:00
Xie Xingguo
2914402345
Merge pull request #30466 from xiexingguo/wip-41924
osd/PGLog: persist num_objects_missing for replicas when peering is done

Reviewed-by: Neha Ojha <nojha@redhat.com>
2019-09-27 10:18:33 +08:00
Xie Xingguo
d502a41b7a
Merge pull request #30576 from xiexingguo/wip-42052
osd/OSDMap: do not trust partially simplified pg_upmap_item

Reviewed-by: Sage Weil <sage@redhat.com>
2019-09-27 10:17:54 +08:00
Xie Xingguo
5044a14c9a
Merge pull request #30560 from xiexingguo/wip-balancer-upmap-cli
mgr/balancer: enable pg_upmap cli for future use

Reviewed-by: Sage Weil <sage@redhat.com>
2019-09-27 10:17:09 +08:00
Sage Weil
239c8e8564 Merge PR #30223 into master
* refs/pull/30223/head:
	msg/async: do not register lossy client connections
	msg/async: allow anonymous client-side connections

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2019-09-26 19:28:51 -05:00
Sage Weil
ca80c3fc21 osd: send ops back to primary if replica is not readable
This is the simplest strategy--much simpler than queueing them and
waking them up again later.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:22:22 -05:00
Sage Weil
1d0c6f5319 osd/PeeringState: set WAIT state and block ops to wait for prior readable_until
If we start a new interval and the prior interval may have OSDs that
are still readable, set the WAIT state bit and block operations until
sufficient time has elapsed.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:22:22 -05:00
Sage Weil
7aec060e0a osd: add CheckReadable pg event, queue_check_readable()
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:22:22 -05:00
Sage Weil
6119f693d6 osd/PeeringState: update prior_readable_until_ub on new interval
If a new interval starts, apply the old interval's readable_until_ub to
our prior.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
6945cc52fd osd/PeeringState: refresh prior_readable_until_ub in pg_history_t on share
Before we share pg_history_t, refresh the prior_readable_until_ub to be
a simple duration from *now*, so that it is completely clock-independent.
The receiver can interpret it based on the receive time for the message,
which loses a bit of precision but is safe since this is an upper bound.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
3bb8a7210a osd: requeue ops when PG is no longer laggy
When we get a lease_ack, leave the laggy state.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
9c4d780c5d osd/PrimaryLogPG: put ops on waitlist when PG is laggy
Move PG to laggy state if we aren't readable

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
c6358390e3 crimson/osd/pg: add schedule_renew_lease stub
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
1e87f1494e osd/PeeringState: do full on_new_interval on new peering interval
This looks like a bug from the PeeringState transition.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
d883db7028 osd: schedule regular lease renewals
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
19d770832b osd: send and process lease[_ack] messages
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
0863bdeb40 osd: add lease/readable tracking members, helpers
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
a48da26ea9 osd/osd_types: add pg_lease[_ack]_t
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
5b5aa8b0c8 osd: add mono_timer
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
6b6392bef6 osd/osd_types: add READ_LEASE_INTERVAL pool property, osd_pool_readable_min_ratio
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
893fb92e58 osd/PeeringStage: PGPool::get_readable_interval() accessor
For now, just do the heartbeat interval * 2.  Eventually we'll want a
pool property.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
a0b453ad33 osd/osd_types: add PG_STATE_WAIT
PG is waiting for previous intervals' readable intervals to expire.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
7df85a66cd osd/osd_types: add PG_STATE_LAGGY
PG is laggy (unreadable) because ping(s) are delayed.

Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Sage Weil
caaf0f8eb6 osd/osd_types: pg_history_t: add prior_readable_until_ub
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 12:21:53 -05:00
Lenz Grimmer
f742283f1a
mgr/dashboard: REST API: OpenAPI docs require internet connect… (#30477)
mgr/dashboard: REST API: OpenAPI docs require internet connection

Reviewed-by: Ernesto Puerta <epuertat@redhat.com>
Reviewed-by: Tiago Melo <tmelo@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
2019-09-26 16:14:45 +00:00
Nathan Cutler
048f5ae726
Merge pull request #30557 from smithfarm/wip-42023
install-deps.sh: add EPEL repo for non-x86_64 archs as well

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
2019-09-26 18:03:50 +02:00
Sage Weil
3c9a28568f osd/PeeringState: PG state 64 bits wide
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 10:55:09 -05:00
Volker Theile
5730883b7e mgr/dashboard: Configuring an URL prefix does not work as expected
Fixes: https://tracker.ceph.com/issues/41797

Signed-off-by: Volker Theile <vtheile@suse.com>
2019-09-26 17:37:16 +02:00
jtlayton
f0dfc7f3b3
Merge pull request #30590 from jtlayton/wip-42032
ceph.spec.in: fix Cython package dependency for Fedora
2019-09-26 11:35:36 -04:00
Lenz Grimmer
b8951d43e6
Merge pull request #29460 from rhcs-dashboard/bucket-versioning
mgr/dashboard: enable/disable versioning on RGW bucket

Reviewed-by: Volker Theile <vtheile@suse.com>
2019-09-26 15:27:58 +00:00
Nathan Cutler
fe4d094985 qa/distros/all: add openSUSE 15.1, drop openSUSE 12.2
Signed-off-by: Nathan Cutler <ncutler@suse.com>
2019-09-26 17:09:32 +02:00
Sage Weil
71cbda4cd5 qa/tasks/ceph.conf.template: disable power-of-2 warning
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 09:29:32 -05:00
Sage Weil
d8d2b71db5 qa/standalone/mon/health-mute: use power of 2 for pg_num
Signed-off-by: Sage Weil <sage@redhat.com>
2019-09-26 09:29:32 -05:00
Ricardo Marques
14763dfb51
Merge pull request #30208 from ricardoasmarques/support-iscsi-controls-types
mgr/dashboard: Controls UI inputs based on "type"

Reviewed-by: Tiago Melo <tmelo@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
2019-09-26 14:45:58 +01:00
Patrick Donnelly
9fb9d9b326
Merge PR #28834 into master
* refs/pull/28834/head:
	libcephfs: Add test for lazyio via libcephfs
	libcephfs: Add lazyio_propogate and lazyio_synchronize methods to libcephfs

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
2019-09-26 06:26:46 -07:00
Patrick Donnelly
ed7e20b5e8
Merge PR #29818 into master
* refs/pull/29818/head:
	client/MetaRequest: Add age to MetaRequest dump
	osdc/Objecter: Add age to the ops
	common/ceph_time: Use fixed floating-point notation for mono_clock

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Adam C. Emerson <aemerson@redhat.com>
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
2019-09-26 06:25:17 -07:00