Commit Graph

39813 Commits

Author SHA1 Message Date
Abhishek Lekshmanan
e278484171 mailmap: Robert Jansen affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com>
2015-02-25 12:03:10 +05:30
Abhishek Lekshmanan
a6f2f816ae mailmap: MingXin Liu affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com>
2015-02-25 12:03:10 +05:30
Abhishek Lekshmanan
3d6750e0d7 mailmap: Andrew Bartlett affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com>
Reviewed-by: Andrew Bartlett <abartlet@catalyst.net.nz>
2015-02-25 12:02:10 +05:30
Boris Ranto
a79e9056cb qa: fix python-ceph reference
Signed-off-by: Boris Ranto <branto@redhat.com>
2015-02-24 18:30:18 -08:00
Boris Ranto
46b45e3fc2 doc: fix python-ceph refs in docs
Signed-off-by: Boris Ranto <branto@redhat.com>
2015-02-24 18:30:18 -08:00
Boris Ranto
d1c82ea9f4 ceph.spec: specify version
Signed-off-by: Boris Ranto <branto@redhat.com>
2015-02-24 18:30:18 -08:00
Sage Weil
2a23eac549 debian: split python-ceph
- move argparse to ceph-common
- split out rados, rbd, and cephfs bindings into their own packages
- keep python-ceph as a metapackage

Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-24 18:30:18 -08:00
Noah Watkins
b3329a961b hadoop: workunits don't need java path
Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
2015-02-24 18:26:44 -08:00
Boris Ranto
39982b10ad Split python-ceph to appropriate python-* packages
python-ceph contains various header files/bindings for serveral
libraries, this patch creates *-devel packages for all the
libraries separately and provides the compatibility layer for
the split.

Signed-off-by: Boris Ranto <branto@redhat.com>
2015-02-24 12:50:27 -08:00
Samuel Just
29861b1b64 Merge pull request #3742 from ceph/wip-10788
osd: proxy features with proxied reads; only proxy reads to new peers

Reviewed-by: Samuel Just <sjust@redhat.com>
2015-02-24 11:15:06 -08:00
Sage Weil
1fa56d920c Merge pull request #3787 from ceph/wip-da-SCA-20150219
SCA fixes

Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-02-24 10:53:21 -08:00
Patrick McGarry
07ba2df74f Corrected arch diagram signed off by: pmcgarry@redhat.com 2015-02-24 13:35:38 -05:00
Josh Durgin
3857228ac9 Merge pull request #3786 from ceph/wip-librbd-python-tests
tests: speed up Python RBD random data generation

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2015-02-24 08:45:48 -08:00
Danny Al-Gaaf
c7ed277b3e test/librados/misc.cc: fix -Wsign-compare
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 17:37:07 +01:00
Loic Dachary
edc24c2ed4 Merge pull request #3785 from ceph/wip-da-doc-erasure
doc: add erasure-code-shec to plugin list

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-02-24 15:31:22 +01:00
Jason Dillaman
bd40f23d7d tests: speed up Python RBD random data generation
The RBD large_write test cases was taking multiple minutes to
run under a Fedora 21 VM.  Replaced the million+ random number
generator calls with a single call to os.urandom. The test
now completes within seconds.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2015-02-24 09:25:14 -05:00
Danny Al-Gaaf
d03cc6195b doc: add erasure-code-shec to plugin list
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 15:11:40 +01:00
Danny Al-Gaaf
01a113cc7f fix build with clang/clang++
Fix for:

./include/types.h:121:9: error: call to function 'operator<<'
that is neither visible in the template definition nor found
by argument-dependent lookup

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 14:39:57 +01:00
Loic Dachary
54c41c606d Merge pull request #3784 from Ved-vampir/master
common: add perf counters description

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-02-24 11:52:59 +01:00
Loic Dachary
ef90c6f11e Merge pull request #3783 from tchaikov/update-doc
doc: update doc with latest code

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-02-24 11:49:05 +01:00
Ved-vampir
31b1532b1c common: add perf counters description
Signed-off-by: Kiseleva Alyona <akiselyova@mirantis.com>
2015-02-24 13:47:15 +03:00
Danny Al-Gaaf
0be126d5f2 erasure-code/shec/shec.cc: fix resource leak
Free tmpmat in error case. Fix for:

[src/erasure-code/shec/shec.cc:176]: (error) Memory leak: tmpmat

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 10:50:11 +01:00
Danny Al-Gaaf
50b69e7190 TestErasureCodeShec_all.cc: prefer ++operator for non-primitive iter
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 10:47:07 +01:00
Danny Al-Gaaf
13f6f26bfa osd/osd_types.cc: prefer ++operator for non-primitive iter
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 10:46:17 +01:00
Danny Al-Gaaf
5df917cb9a mon/PGMap.cc: prefer ++operator for non-primitive iter
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 10:45:27 +01:00
Danny Al-Gaaf
609a070560 erasure-code/shec/shec.cc: reduce scope of variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 10:43:57 +01:00
Danny Al-Gaaf
c1abcb71cc ErasureCodeShec.cc: prefer ++operator for non-primitive iter
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 10:41:44 +01:00
Danny Al-Gaaf
b7ea69265d libradosstriper/striping.cc: fix resource leak
Fix for:

CID 1221525 (#1 of 1): Resource leak (RESOURCE_LEAK)
 leaked_storage: Failing to save or free storage allocated
 by this->getObjName(soid, 0UL) leaks it.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2015-02-24 09:27:36 +01:00
Kefu Chai
c1e792d8aa doc: update doc with latest code
* also silence some warnings of doxygen

Signed-off-by: Kefu Chai <kchai@redhat.com>
2015-02-24 16:05:12 +08:00
Gregory Farnum
eb0c34b61a Merge pull request #3782 from ceph/hadoop-workunits
Hadoop workunits
2015-02-23 22:35:08 -08:00
Gregory Farnum
e4959ed24e Merge pull request #3753 from ceph/wip-10743
mds: wait for mydir replicas to go away in stopping

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-02-23 22:26:36 -08:00
Gregory Farnum
001de29fb9 Merge pull request #3775 from ceph/wip-10862
mon: do not try and "deactivate" the last MDS

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-02-23 22:22:27 -08:00
Noah Watkins
15da810086 qa: update old replication tests
Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
2015-02-23 20:00:24 -08:00
Noah Watkins
6bc2b024fd hadoop: add terasort workunit
Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
2015-02-23 20:00:24 -08:00
Josh Durgin
c1c38afcf9 Merge pull request #3780 from ceph/wip-osdc-watch-error
osdc: watch error callback invoked on cancelled context

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2015-02-23 17:21:04 -08:00
Josh Durgin
e332d84efc Merge pull request #3781 from ceph/wip-librbd-image-watcher-tests
tests: fix potential race conditions in test_ImageWatcher

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2015-02-23 17:20:52 -08:00
Jason Dillaman
655e616249 tests: fix potential race conditions in test_ImageWatcher
The tests were sending invalid responses back to ImageWatchers
(missing the result code), which had the potential to allow the
lock to be acquired sooner than the test was expecting since
ImageWatcher would assume the last of response code meant no
clients owned the exclusive lock and would retry as fast as
possible.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2015-02-23 20:09:56 -05:00
Jason Dillaman
9c03750acd osdc: watch error callback invoked on cancelled context
The C_DoWatchError context did not verify whether or not the
watch was cancelled prior to invoking the callback.  This
resulted in sporadic crashes when reconnect errors bubbled
up to destroyed objects.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2015-02-23 20:00:43 -05:00
Josh Durgin
11f8cd81da Merge pull request #3779 from liewegas/wip-watch-timeout-test
make watch timeout test less likely to fail under thrashing

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2015-02-23 14:51:49 -08:00
Sage Weil
a9bfd5ddda ceph_test_rados_api_watch_notify: wait longer for watch timeout
OSD thrashing can delay this indefinitely; longer delay means lower
probability of that happening.

Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 14:46:16 -08:00
Loic Dachary
92d26bb82b Merge pull request #3686 from ceph/wip-crushtool
crushtool: process commands in a sensible order

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-02-23 23:20:32 +01:00
Sage Weil
f85f2f206d Merge pull request #3778 from dachary/wip-crushtool
crush: re-organize the help to clarify ordering
2015-02-23 13:32:23 -08:00
Loic Dachary
62e7b4a377 crush: re-organize the help to clarify ordering
The options are grouped according to the stage they relate to

   - input/build
   - tunables adjustments
   - modifications
   - display/test
   - output

Signed-off-by: Loic Dachary <ldachary@redhat.com>
2015-02-23 21:12:21 +01:00
Sage Weil
b8d497e493 crushtool: add test for crushtool ordering
Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 11:21:25 -08:00
Sage Weil
dca345280e crushtool: send --tree to stdout
Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 11:21:25 -08:00
Sage Weil
2b92320b9a crushtool: name osds with --build function
Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 11:21:25 -08:00
Sage Weil
f52840c8a9 crushtool: do not dump tree on build
This pollutes the output.

Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 11:21:25 -08:00
Sage Weil
b5d6e76790 doc/release-notes: v0.87.1
Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 10:46:56 -08:00
Sage Weil
91cda52c10 osd: better debug for maybe_handle_cache
Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 10:10:54 -08:00
Sage Weil
bee91548b0 osd,mon: explicitly specify OSD features in MOSDBoot
We are using the connection features to populate the features field in the
OSDMap, but this is the *intersection* of mon and osd features, not the
osd features.  Fix this by explicitly specifying the features in
MOSDBoot.

Fixes: #10911
Backport: giant, firefly
Signed-off-by: Sage Weil <sage@redhat.com>
2015-02-23 10:10:54 -08:00