Commit Graph

79028 Commits

Author SHA1 Message Date
Sage Weil
0c212d2bbf Merge pull request #18091 from vasilyMellanox/gid_idx_fix
msg/async/rdma: uninitialized variable fix

Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Jos Collin <jcollin@redhat.com>
2017-10-05 11:19:15 -05:00
Sage Weil
96c831167b Merge pull request #18092 from tchaikov/wip-cmake-cleanup
cmake: do not link against unused or duplicated libraries

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-05 11:18:27 -05:00
Sage Weil
eaa350be95 Merge pull request #18094 from xiexingguo/wip-tracker-21618
qa/standalone/scrub/osd-scrub-repair.sh: add extents flag into object_info_t

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-05 11:14:01 -05:00
Yuri Weinstein
0408ee0706 Merge pull request #17907 from amitkumar50/cov-rgw-10
rgw: Ignoring the returned error

Reviewed-by: Orit Wasserman <owasserm@redhat.com>
2017-10-05 08:46:39 -07:00
Yuri Weinstein
9a3d2432c6 Merge pull request #18106 from kmroz/wip-keystone-revocator-thread-assert
rgw: stop/join TokenCache revoke thread only if started.

Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
2017-10-05 08:45:54 -07:00
Sage Weil
15a20eb2f5 Merge pull request #18120 from liewegas/wip-bluefs-allocation
os/bluestore: make bluefs behave better near enospc

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2017-10-05 09:13:46 -05:00
Mykola Golub
667e14e2ca Merge pull request #18114 from dillaman/wip-21670
librbd: list_children should not attempt to refresh image

Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
2017-10-05 15:34:09 +03:00
Sage Weil
7d1c99f77a Merge pull request #18118 from liewegas/wip-21470
os/bluestore: fix another aio stall/deadlock

Reviewed-by: Varada Kari <varada.kari@gmail.com>
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2017-10-05 06:57:14 -05:00
Sage Weil
f9cfe843a1 Merge pull request #18105 from gregsfortytwo/wip-sigpipe-porting
msg: reimplement sigpipe blocking

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-04 22:07:26 -05:00
Sage Weil
4341f27446 Merge pull request #17710 from Songweibin/wip-add-pybind
pybind/rados: add support open_ioctx2 API

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2017-10-04 22:06:10 -05:00
Sage Weil
f26c3c79a6 Merge pull request #18079 from liewegas/wip-21618
qa/standalone/scrub/osd-scrub-repair: no -y to diff

Reviewed-by: David Zafman <dzafman@redhat.com>
2017-10-04 22:05:20 -05:00
Sage Weil
75dc9b69f0 Merge pull request #18088 from dillaman/wip-21629
osd: additional protection for out-of-bounds EC reads

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-04 22:04:33 -05:00
Sage Weil
65be614f2b os/bluestore: add bluestore_bluefs_min_free
We need at least ~1GB free so we can write out new SSTs (which are 256MB
each).

Signed-off-by: Sage Weil <sage@redhat.com>
2017-10-04 17:34:23 -05:00
Sage Weil
569e924812 os/bluestore/BlueFS: crash on enospc
We were passing this error back to rocksdb, which would then crash (much)
later with a corrupted SST file!  No good.

Signed-off-by: Sage Weil <sage@redhat.com>
2017-10-04 17:34:19 -05:00
Sage Weil
67ec758057 os/bluestore: use normal Context for async deferred_try_submit
I'm not quite sure why the FunctionContext did not ever execute on the
finisher thread (perhaps the [&] captured some state on the stack that it
shouldn't have?).  In any case, using a traditional Context here appears
to resolve the problem (of the async deferred_try_submit() never executing,
leading to a bluestore stall/deadlock).

Fixes: http://tracker.ceph.com/issues/21470
Signed-off-by: Sage Weil <sage@redhat.com>
2017-10-04 16:54:02 -05:00
Sage Weil
633b170077 os/bluestore: wake kv thread when blocking on deferred_bytes
We need to wake the kv thread whenever setting deferred_aggressive to
ensure that txns with deferred io that have committed but haven't submitted
their deferred writes get submitted.  This aligns us with the other
users of deferred_aggressive (e.g., _osr_drain_all).

Signed-off-by: Sage Weil <sage@redhat.com>
2017-10-04 16:52:18 -05:00
Mykola Golub
cd9bc853ff Merge pull request #18099 from dillaman/wip-21628
librbd: journal should ignore -EILSEQ errors from compare-and-write

Reviewed-by: Venky Shankar <vshankar@redhat.com>
Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
2017-10-04 23:31:55 +03:00
Marcus Watts
b4c0ef0dfb Merge pull request #17959 from gaosibei/branch2
RGW: Multipart upload may double the quota
2017-10-04 16:12:21 -04:00
Sage Weil
d36e6cdcc1 Merge pull request #18087 from liu-chunmei/fix_dpdk_build
build: fix dpdk build error

Reviewed-by: Haomai Wang <haomai@xsky.com>
2017-10-04 14:01:21 -05:00
Sage Weil
23b22ddba0 Merge pull request #18115 from mogeb/rados-doc
doc: add osd_max_object_size in osd configuration

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-04 13:59:58 -05:00
Sage Weil
cb48d6c37c Merge pull request #18072 from dragonylffly/wip-optimize-assert
assert(false)->ceph_abort()

Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: J. Eric Ivancich <ivancich@redhat.com>
2017-10-04 13:59:19 -05:00
Sage Weil
2ad8c3706b Merge pull request #18073 from dragonylffly/wip-check-monitor-address-configuration
mon: check monitor address configuration

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-04 13:58:48 -05:00
Sage Weil
776b581272 Merge pull request #18082 from Liuchang0812/wip-21624
os/bluestore: make BlueStore opened by start_kv_only umountable

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-04 13:58:09 -05:00
Sage Weil
1de1109f4c Merge pull request #18083 from Liuchang0812/wip-21625
tool: ceph-kvstore-tool doesn't umount BlueStore properly

Reviewed-by: Sage Weil <sage@redhat.com>
2017-10-04 13:56:26 -05:00
chunmei
bad1193375 fix dpdk build error.
when ./do_cmake.sh add  -DWITH_DPDK=ON -DUSE_CRYPTOPP=ON -DWITH_NSS=OFF -DWITH_TESTS=OFF
    if build debian package, need remove some file froms install since we disabled TESTS.

    Signed-off-by: chunmei <chunmei.liu@intel.com>
2017-10-04 11:26:43 -07:00
Mohamad Gebai
7440a32801 doc: add osd_max_object_size in osd configuration
Having osd_max_write_size in the doc without osd_max_object_size
is confusing.

Signed-off-by: Mohamad Gebai <mgebai@suse.com>
2017-10-04 12:51:02 -04:00
Andrew Schoen
7d85e1892f Merge pull request #18110 from ceph/wip-volume-api-change
ceph-volume lvm api refactor/move

Reviewed By: Andrew Schoen <aschoen@redhat.com>
2017-10-04 11:13:25 -05:00
Kefu Chai
6081aeb95e Merge pull request #17380 from ceph/wip-21189
mgr/status: format byte quantities in base 2 multiples

Reviewed-by: Kefu Chai <kchai@redhat.com>
2017-10-04 23:10:30 +08:00
Jason Dillaman
4c585d826f librbd: list_children should not attempt to refresh image
The snap_lock is being held when this method is invoked, which can
result in a deadlock.

Fixes: http://tracker.ceph.com/issues/21670
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2017-10-04 10:46:46 -04:00
John Spray
e25d30c612 Merge pull request #17746 from elliswuuuuuuuu/wip-prometheus
ceph-mgr: can not change prometheus port for mgr

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
2017-10-04 15:13:45 +01:00
Greg Farnum
0e15cab5c4 Revert "REVERT msgr: force use of the SIGPIPE stopper for testing"
This reverts commit a76181df4a71ad15aee8dd2e4adcebce8330fae4.

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2017-10-04 07:10:23 -07:00
Greg Farnum
4c343669a9 REVERT msgr: force use of the SIGPIPE stopper for testing
Note that since this sets MSG_NOSIGNAL to 0 it won't take effect
on the ::send[msg] invocations

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2017-10-04 07:10:23 -07:00
Greg Farnum
cba20a95e8 msgr: add a mechanism for Solaris to avoid dying on SIGPIPE
This is fairly clean: we define an RAII object in the Messenger.h on
Solaris, and "declare" it with a macro in the implementations. There's
no code duplication and on Linux it's just entirely compiled out.

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2017-10-04 07:10:23 -07:00
Greg Farnum
21bdb73093 Revert "SIGPIPE suppression for platforms without SO_NOSIGPIPE or MSG_NOSIGNAL"
This reverts commit 131deb3976. It added
code that shouldn't have entered the project repo.

Conflicts:
	src/msg/async/AsyncConnection.cc
	src/msg/async/AsyncConnection.h
	src/msg/simple/Pipe.cc
	src/msg/simple/Pipe.h

Signed-off-by: Greg Farnum <gfarnum@redhat.com>
2017-10-04 07:10:23 -07:00
Sage Weil
e462f6cc8a Merge pull request #18089 from liewegas/wip-localpool-min-size
mgr/localpool: default to 3x; allow min_size adjustment

Reviewed-by: John Spray <john.spray@redhat.com>
2017-10-04 08:26:07 -05:00
Sage Weil
7623513935 mgr/localpool: fix rule selection
The 'osd pool create' arg parsing is broken; the rule name for
'ceph osd pool create $name $numpgs replicated $rulename' is passed
via the erasure_code_profile param.  Too many req=false options
without a way to disambiguate them.

Work around it by passing both 'rule' and 'erasure_code_profile'
keys, so that if/when the hack in OSDMonitor.cc is removed it will
still work.  Blech.

Signed-off-by: Sage Weil <sage@redhat.com>
2017-10-04 08:25:38 -05:00
Alfredo Deza
eec0c8a5c2 ceph-volume tests move lvm api tests into its new test module
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:44:54 -04:00
Alfredo Deza
66fd41fd4b ceph-volume tests refactor lvm api import for test_listing
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:43:36 -04:00
Alfredo Deza
2a9a36bd24 ceph-volume tests refactor lvm api import for api tests
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:43:18 -04:00
Alfredo Deza
d81aa8c112 ceph-volume tests refactor lvm api import for activate tests
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:42:47 -04:00
Alfredo Deza
a00aff7066 ceph-volume tests refactor lvm api import in conftest
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:42:01 -04:00
Alfredo Deza
f4bee6cb42 ceph-volume devices.lvm refactor importing api to come from api/lvm.py
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:38:18 -04:00
Alfredo Deza
bb72480d2b ceph-volume move lvm/api.py to api/lvm.py so disk can consume it
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:38:11 -04:00
Alfredo Deza
f72368641d ceph-volume create an api module to hold common api modules
Signed-off-by: Alfredo Deza <adeza@redhat.com>
2017-10-04 06:38:05 -04:00
Kefu Chai
1b9a833356 Merge pull request #18048 from badone/wip-boost-mirrors
make-dist,cmake: Try multiple URLs to download boost before failing

Reviewed-by: Kefu Chai <kchai@redhat.com>
2017-10-04 10:28:35 +08:00
Brad Hubbard
598556f98b make-dist,cmake: Try multiple URLs to download boost before failing
Remove SPOF during boost download for make-dist and later cmake > 3.7

Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
2017-10-04 11:13:34 +10:00
Karol Mroz
26f2da083c
rgw: stop/join TokenCache revoke thread only if started.
Thread::join triggers an assert otherwise.

Fixes http://tracker.ceph.com/issues/21666

Signed-off-by: Karol Mroz <kmroz@suse.de>
2017-10-03 18:12:41 -07:00
Mykola Golub
8152fecd37 Merge pull request #18097 from dillaman/wip-21663
qa/workunits/rbd: fixed variable name for resync image id

Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
2017-10-03 23:39:54 +03:00
Jason Dillaman
c7a9b04580 librbd: journal should ignore -EILSEQ errors from compare-and-write
Fixes: http://tracker.ceph.com/issues/21628
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2017-10-03 15:42:50 -04:00
Sage Weil
15b63d6795 qa/standalone/scrub/osd-scrub-repair: no -y to diff
With -y you can't see the entire line when it is long, which is
needed to identify the diff failure in
http://tracker.ceph.com/issues/21618

Instead, let the interactive user specify the option if they want it.

Signed-off-by: Sage Weil <sage@redhat.com>
2017-10-03 14:35:35 -05:00