Commit Graph

86565 Commits

Author SHA1 Message Date
Kefu Chai
19230378c8 cmake: specify missing settings for dpdk
* after upgrading to gcc-8, seems dpdk requires more settings to compile.
  in which, CONFIG_RTE_MAX_VFIO_GROUPS=64 is copied from config/common_base.
* librte_bus_pci.a depends on librte_pci.a, so reorder the libraries
  in DPDK_LIBRARIES.

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-05-06 15:26:14 +08:00
Jason Dillaman
4f2dbcefc5 rbd-mirror: fix potential race between image sync and shut down
Fixes: http://tracker.ceph.com/issues/24008
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2018-05-05 23:44:34 -04:00
Kefu Chai
c17e3d8346
Merge pull request #21637 from ceph/wip-da-SCA-20180423
misc: mark constructors as explicit

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2018-05-06 11:34:52 +08:00
Kefu Chai
1a87441de1
Merge pull request #19041 from dragonylffly/wip-list-objects-in-a-pg
tools/rados: allow list objects in a specific pg in a pool

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2018-05-06 11:33:47 +08:00
Kefu Chai
4ad013c536
Merge pull request #21765 from yunfeiguan/wip-23962
pybind/ceph_daemon: expand the order of magnitude of daemonperf statistics to ZB

Reviewed-by: Kefu Chai <kchai@redhat.com>
2018-05-06 11:29:26 +08:00
xiexingguo
d48b9b8d6c crush, osd: handle multiple parents properly when applying pg upmaps
Fixes: http://tracker.ceph.com/issues/23921
Signed-off-by: xiexingguo <xie.xingguo@gmail.com>
(cherry picked from commit 482ec97c98)
2018-05-06 11:26:10 +08:00
Kefu Chai
3d6429753e
Merge pull request #21815 from xiexingguo/wip-23921
crush, osd: handle multiple parents properly when applying pg upmaps

Reviewed-by: huangjun <hjwsm1989@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
2018-05-06 11:25:36 +08:00
Kefu Chai
87c000bf49
Merge pull request #21832 from tchaikov/mimic-23627
librados: block MgrClient::start_command until mgrmap

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2018-05-06 11:23:47 +08:00
Kefu Chai
c16371965c osdc: guard op->on_notify_finish with lock
Fixes: http://tracker.ceph.com/issues/23966
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-05-06 11:13:02 +08:00
Kefu Chai
0ab9b101c6 librados: timeout on mgr_command()
because the mgrclient will be waiting for the mgrmap if the mgrmap
is not available, when the client is about to send a mgr command.
and monitor will drop the subscription requests if the client does not
have enough cap for reading mon, so unlike mon commands, the client
won't get an EACCES return code in this case.

in this change, a timeout machinary is introduced. and the client
will wait for "rados-mon-op-timeout" before it gives up. if this
setting is 0, it will wait forever.

Fixes: https://tracker.ceph.com/issues/23627
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit eaa1179965)
2018-05-05 19:04:20 +08:00
John Spray
c8156b9117 librados: fix locking on get_required_monitor_features
This wasn't taking the MonClient lock: should use
with_monmap to protect access to MonClient::monmap.

Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit ef517d0ea0)
2018-05-05 19:04:20 +08:00
John Spray
be23767b34 librados: config mgrclient for pre-luminous cluster
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit 8fd500d736)
2018-05-05 19:04:20 +08:00
John Spray
5a45110785 mgr/MgrClient: add mgr_optional mode
This is for use when talking to pre-luminous
clusters, where we should not block waiting
for MgrMap because it might never come.

Fixes: https://tracker.ceph.com/issues/23627
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit bae47183c2)
2018-05-05 19:04:20 +08:00
Kefu Chai
7bd7559ece
Merge pull request #21811 from tchaikov/wip-23627
librados: block MgrClient::start_command until mgrmap

Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
2018-05-05 19:02:25 +08:00
Kefu Chai
489519edc5
Merge pull request #21790 from dalgaaf/SCA-override-specifier
misc: mark functions with 'override' specifier

Reviewed-by: Kefu Chai <kchai@redhat.com>
2018-05-05 18:59:25 +08:00
Kefu Chai
eb7845a0ba
Merge pull request #21786 from dillaman/wip-23966
osdc: invoke notify finish context on linger commit failure

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
2018-05-05 18:52:44 +08:00
Kefu Chai
99f29da500 qa: fix test on "ceph fs set cephfs allow_new_snaps"
snapshot is now enabled for new fs in 81d0554e, so this test should be
updated accordingly.

Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 5910c2902e)
2018-05-05 18:40:29 +08:00
Kefu Chai
4134a25ebc
Merge pull request #21829 from tchaikov/wip-qa-cephfs-snap
qa: fix test on "ceph fs set cephfs allow_new_snaps"

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2018-05-05 18:39:59 +08:00
Kefu Chai
5910c2902e qa: fix test on "ceph fs set cephfs allow_new_snaps"
snapshot is now enabled for new fs in 81d0554e, so this test should be
updated accordingly.

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-05-05 09:40:41 +08:00
Yuri Weinstein
b6d85cad7c qa/tests: Added mimic runs, removed large suites (rados, rbd, etc) runs on luminous
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
2018-05-04 13:45:29 -07:00
xiexingguo
a8ed81ff05 osd/OSD: drop extra/wrong *unregister_pg*
Signed-off-by: xiexingguo <xie.xingguo@gmail.com>
(cherry picked from commit 6ee6fa79b5)
2018-05-04 15:25:55 -05:00
Sage Weil
6ac59390d2
Merge pull request #21816 from xiexingguo/wip-wrong-unregister-pg
osd/OSD: drop extra/wrong *unregister_pg*

Reviewed-by: Sage Weil <sage@redhat.com>
2018-05-04 15:25:38 -05:00
Sage Weil
bc42e17ce5
Merge pull request #21753 from liewegas/wip-upgrade-enospc
qa/suites/upgrade/luminous-x/stress-split: avoid enospc
2018-05-04 15:25:10 -05:00
Patrick Donnelly
93bc8c53ef
MDSMonitor: promote standby after fs creation
This avoids unnecessary health warnings. However, the original issue in i23885
still exists because the standbys are not available at fs creation time. If you
create a new file system after these standbys are available, then you will
observe that the promotion works to silence the warnings.

Fixes: http://tracker.ceph.com/issues/23885

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-05-04 11:01:09 -07:00
Patrick Donnelly
ad75128c8e
MDSMonitor: always prints standbys even if no fs
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
2018-05-04 11:01:05 -07:00
Alfredo Deza
9432c620bb
Merge pull request #21824 from tchaikov/mimic-cmake-jni
mimic: cmake: use javac -h for creating JNI native headers

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:50:45 -04:00
Alfredo Deza
190b7d6a1d Merge branch 'mimic' of github.com:ceph/ceph into mimic 2018-05-04 13:46:20 -04:00
Alfredo Deza
8deb088f10 ceph-volume tests verify get_devices captures device metadata
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:23:03 -04:00
Alfredo Deza
9d820e82ac ceph-volume tests.conftest allow custom dirs in tmpfile fixture
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:52 -04:00
Alfredo Deza
4ad42f4244 ceph-volume tests ensure human_readable_size works up to terabytes
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:52 -04:00
Alfredo Deza
9cfd37344c ceph-volume tests verify mapper and /dev devices
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:52 -04:00
Alfredo Deza
672c4c4d1c ceph-volume tests add tests for get_block_devs
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:52 -04:00
Alfredo Deza
2c4d46955e ceph-volume tests verify _map_dev_paths mappings
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:51 -04:00
Alfredo Deza
e3b04c9677 ceph-volume devices.auto initial take on auto sub-command
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:51 -04:00
Alfredo Deza
c6559538db ceph-volume util.disk create a device metadata utility
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:22:51 -04:00
Alfredo Deza
c06e63fed8 ceph-volume util.disk add dev mapping helpers for path resolution
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:19:27 -04:00
Alfredo Deza
0177f71cab ceph-volume tests verify get_file_contents utility
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:19:27 -04:00
Alfredo Deza
39792573da ceph-volume util.system capture file contents
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:19:27 -04:00
Alfredo Deza
5649bd724b ceph-volume devices.auto initial take on auto sub-command
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2018-05-04 13:19:22 -04:00
Kefu Chai
0449dca6f5 cmake: bump up JDK version to 1.8
as JDK 7 is EOL. see
http://www.oracle.com/technetwork/java/eol-135779.html and
https://www.java.com/en/download/faq/java_7.xml

Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit df27ed3a38)
2018-05-05 00:15:29 +08:00
Kefu Chai
3731560bda cmake: use javac -h for creating JNI native headers
JDK 1.10 does not offer javah anymore, so we need to use "javac -h" or
add_jar(... GENERATE_NATIVE_HEADERS) instead.

Fixes: http://tracker.ceph.com/issues/24012
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit edc504b9d4)
2018-05-05 00:15:29 +08:00
Kefu Chai
4afd5ece9c
Merge pull request #21822 from tchaikov/wip-24012
cmake: use javac -h for creating JNI native headers

Reviewed-by: Casey Bodley <cbodley@redhat.com>
2018-05-05 00:08:23 +08:00
Kefu Chai
df27ed3a38 cmake: bump up JDK version to 1.8
as JDK 7 is EOL. see
http://www.oracle.com/technetwork/java/eol-135779.html and
https://www.java.com/en/download/faq/java_7.xml

Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-05-04 22:55:44 +08:00
Kefu Chai
edc504b9d4 cmake: use javac -h for creating JNI native headers
JDK 1.10 does not offer javah anymore, so we need to use "javac -h" or
add_jar(... GENERATE_NATIVE_HEADERS) instead.

Fixes: http://tracker.ceph.com/issues/24012
Signed-off-by: Kefu Chai <kchai@redhat.com>
2018-05-04 22:34:57 +08:00
Sage Weil
02f882dd03 Merge remote-tracking branch 'gh/mimic' 2018-05-04 08:44:36 -05:00
xiexingguo
6ee6fa79b5 osd/OSD: drop extra/wrong *unregister_pg*
Signed-off-by: xiexingguo <xie.xingguo@gmail.com>
2018-05-04 21:43:51 +08:00
Brad Hubbard
303e71fe07 mgr: Include daemon details in SLOW_OPS output
Currently there is no way to see which daemons were involved in a slow
op after the op has cleared. This change allows us to record which
daemons were implicated in the logs.

Partially fixes: http://tracker.ceph.com/issues/23205

Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
(cherry picked from commit b5263176de)
2018-05-04 08:43:08 -05:00
Sage Weil
dd702b9fad qa/suites/upgarde/luminous-x/stress-split: 8 osds (not 6)
Signed-off-by: Sage Weil <sage@redhat.com>
2018-05-04 08:42:29 -05:00
xiexingguo
482ec97c98 crush, osd: handle multiple parents properly when applying pg upmaps
Fixes: http://tracker.ceph.com/issues/23921
Signed-off-by: xiexingguo <xie.xingguo@gmail.com>
2018-05-04 21:40:07 +08:00
Sage Weil
6e64a4e4d9
Merge pull request #21750 from badone/wip-summarise-osds-when-issuing-slow-request-warning-post-luminous
mgr: Include daemon details in SLOW_OPS output

Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
2018-05-04 08:36:02 -05:00