Kefu Chai
6425111861
Merge pull request #5587 from caibo2014/master
...
rbd: remove the output file if rbd export-diff fails
Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-08-21 19:33:59 +08:00
Gregory Farnum
2daccff5de
Merge pull request #5632 from ceph/wip-fix-ftbfs-4998
...
osd: fix the FTBFS introduced by be28319
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2015-08-21 12:22:34 +01:00
Kefu Chai
d1c4086808
osd: fix the FTBFS introduced by be28319
...
the signature of Scrubber::write_blocked_by_scrub() was changed in #5470 .
Signed-off-by: Kefu Chai <kchai@redhat.com>
2015-08-21 02:24:52 -07:00
Kefu Chai
e06207a38b
Merge pull request #4998 from wonzhq/hitset-remove-all
...
osd: implement hit_set_remove_all
Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-08-21 16:51:46 +08:00
Zhiqiang Wang
5fedc8414b
osd: consolidate encoding snaps into pg log code in finish_ctx
...
'MODIFY', 'PROMOTE' and 'CLEAN' are sharing the same encoding snaps
code.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
2015-08-21 16:08:46 +08:00
Zhiqiang Wang
fd38902dd4
osd: only remove all the hit set objects on primary osd
...
Only the primary PG is allowed to remove all the hit set objects. And
the PG should be in the active or peered states.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
2015-08-21 15:48:20 +08:00
Zhiqiang Wang
5812adb6c8
osd: no need to check current hitset object is degraded when persisting
...
hit set
The current hit set object doesn't exist yet. We are about to create it.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
2015-08-21 15:48:20 +08:00
Zhiqiang Wang
be28319bf3
osd: implement hit_set_remove_all
...
When hit set is not configured on startup or on a change, remove all
previous hitsets.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
2015-08-21 15:45:04 +08:00
Yunchuan Wen
9c325d2b11
skip promote if flag set when doing proxy read
...
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
2015-08-21 14:38:21 +08:00
Haomai Wang
faa964d3e5
Fix compile warning unused-result
...
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
2015-08-21 14:16:17 +08:00
Kefu Chai
b33209b469
Merge pull request #5315 from tchaikov/wip-10930
...
mon: remove osd_epoch to avoid out-dated osdmap_cache
Reviewed-by: Sage Weil <sage@redhat.com>
2015-08-21 11:18:32 +08:00
Yehuda Sadeh
8314384a3c
Merge pull request #5579 from jbweber/s3_encoding_type
...
rgw: implement s3 encoding-type for get bucket
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
2015-08-20 15:45:53 -07:00
Jeff Weber
180ca7b56b
rgw: implement s3 encoding-type for get bucket
...
This change introduces handling for the encoding-type request
parameter on the get bucket operation. An object key may contain
characters which are not supported in XML. Passing the value "url" for
the encoding-type parameter will cause the key to be urlencoded in the
response.
Fixes : #12735
Signed-off-by: Jeff Weber <jweber@cofront.net>
2015-08-20 22:33:35 +00:00
Sage Weil
566907779d
buffer: move inline memory ops to inline_memory.h; gcc + x86_64 only
...
Keep the architecture-sensitive code in a separate header.
Avoid duplicating the unrolled memcpy in each buffer.cc
method.
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-20 16:40:53 -04:00
Sage Weil
cdaf9974de
unittest_bufferlist: benchmark buffer::ptr::append, copy_in, copy_out
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-20 16:30:44 -04:00
Sage Weil
5686d9badb
Merge branch 'dont-cache-recovery' of git://github.com/yuyuyu101/ceph
...
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
# Conflicts:
# src/osd/ReplicatedBackend.cc
# src/osd/ReplicatedBackend.h
# src/osd/ReplicatedPG.cc
2015-08-20 15:20:44 -04:00
Sage Weil
779466e34d
Merge pull request #5259 from branch-predictor/bp-tuned-bufferlists
...
Bufferlist tuning
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Reviewed-by: Samuel Just <sjust@redhat.com>
2015-08-20 15:09:17 -04:00
Orit Wasserman
8bb76f2927
Merge pull request #5575 from ceph/wip-12370
...
rgw: don't preserve acls when copying object
2015-08-20 20:59:49 +02:00
Sage Weil
181dc28845
Merge pull request #5518 from ceph/wip-12652
...
osd/PGLog: dirty_to is inclusive
Reviewed-by: Samuel Just <sjust@redhat.com>
2015-08-20 14:53:30 -04:00
Sage Weil
6468ffb67b
Merge pull request #5539 from wonzhq/flush-mode-stat
...
mon: show # of PGs at high flush mode in the command output
Reviewed-by: Sage Weil <sage@redhat.com>
2015-08-20 14:47:24 -04:00
Yehuda Sadeh
aeb80d03e1
Merge pull request #5556 from zaitcev/cleanup-dead-code
...
rgw: cleanup dead init_bucket
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
2015-08-20 09:15:01 -07:00
Yehuda Sadeh
f04322a848
Merge pull request #5598 from jasuarez/remove-useless-code
...
rgw: Remove useless code in calc_hmac_sha1()
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
2015-08-20 09:13:55 -07:00
Loic Dachary
bf108a3471
Merge pull request #5620 from dachary/wip-12734-uuid
...
build/ops: add uuid-runtime to debian/control
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
2015-08-20 17:49:08 +02:00
Loic Dachary
d2d540c165
build/ops: add uuid-runtime to debian/control
...
uuid-runtime was incorrectly removed by
62bfc7a1ab
, restore it.
http://tracker.ceph.com/issues/12734 Fixes : #12734
Signed-off-by: Loic Dachary <ldachary@redhat.com>
2015-08-20 16:19:00 +02:00
Loic Dachary
4e88268d93
Merge pull request #5621 from ceph/revert-5613-wip-12729
...
Revert "Fix compile warning unused-result"
Reviewed-by: Loic Dachary <ldachary@redhat.com>
2015-08-20 16:18:01 +02:00
Loic Dachary
951a3d6dcd
Revert "Fix compile warning unused-result"
2015-08-20 16:17:13 +02:00
Sage Weil
910cc17b63
Merge pull request #5613 from ceph/wip-12729
...
Fix compile warning unused-result
Reviewed-by: Sage Weil <sage@redhat.com>
2015-08-20 09:08:14 -04:00
Yan, Zheng
bb70ac8e23
Merge pull request #5523 from ceph/wip-scan-use-layout
...
Striped layouts in cephfs-data-scan
2015-08-20 18:13:02 +08:00
Kefu Chai
aef8491319
Merge pull request #5272 from chenji-kael/work-branch
...
rados.py: wrap omap operation for librados
Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-08-20 18:10:03 +08:00
Yan, Zheng
ea103798f3
Merge pull request #5614 from liewegas/wip-logtomonitors
...
mds/MDSRank: less noisy about log_to_monitors
2015-08-20 17:47:38 +08:00
caibo
2050d08cfd
rbd:remove the local file when rbd export-diff fail
...
Signed-off-by: Bo Cai <cai.bo@h3c.com>
2015-08-20 17:40:41 +08:00
Radoslaw Zarzynski
69cf089596
rgw: url_decode values from X-Object-Manifest during GET on Swift DLO.
...
Fixes : #12728
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
2015-08-20 11:25:16 +02:00
chenji
d353dbc53a
rados.py: This module now supports omap operations
...
you can operate omap in python
test_rados.py: add unit-test cases
Signed-off-by: Ji Chen <insomnia@139.com>
2015-08-20 17:19:45 +08:00
Kefu Chai
050e1c5c74
Merge pull request #5601 from wonzhq/doc-peering
...
doc: fix the format of peering.rst
Reviewed-by: Kefu Chai <kchai@redhat.com>
2015-08-20 11:01:29 +08:00
Sage Weil
4b75baa4dd
mds/MDSRank: less noisy about log_to_monitors
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 22:16:28 -04:00
Haomai Wang
5ae3e36b29
Fix compile warning unused-result
...
Fix #12729
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
2015-08-20 10:10:21 +08:00
Zhiqiang Wang
73d4b7dbf2
doc: fix the format of peering.rst
...
Fix an incorrent number in the ordered list and some indention issue.
Make the ordered list to use '1' or 'a' for the first item, and '#' for
the remaining items.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
2015-08-20 09:48:07 +08:00
Samuel Just
afb4db73cc
Merge remote-tracking branch 'origin/wip-sam-proxy-write'
...
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Conflicts:
src/include/ceph_features.h
src/osd/ReplicatedPG.cc
src/osd/ReplicatedPG.h
2015-08-19 16:07:30 -07:00
Sage Weil
f0ca14df06
osd/PGLog: dirty_to is inclusive
...
There are only two callers of mark_dirty_to who do not pass max,
and they are both in the merge_log extending tail path. In that
case, we want to include the last version specified in the log
writeout. Fix the tail extending code to always specify the
last entry added, inclusive.
Fixes : #12652
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:13:28 -04:00
Sage Weil
f021e91e61
os/RocksDBStore: log any options we pass to rocksdb
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:04:35 -04:00
Sage Weil
c7d281b831
os/FileStore: ensure sync() doesn't wait forever
...
Avoid
2015-08-19 01:46:37.586450 7f89a53ca980 10 filestore(b.10) start_sync
2015-08-19 01:46:37.586451 7f89a53ca980 10 filestore(b.10) sync waiting
2015-08-19 01:46:37.586528 7f899e2b1700 20 filestore(b.10) sync_entry woke after 5.398564
2015-08-19 01:46:37.586539 7f899e2b1700 20 filestore(b.10) sync_entry waiting for another 35994.601435 to reach min interval 36000.000000
by setting force_sync flag.
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:58 -04:00
Sage Weil
4afb08413e
common/hobject: rename get_bitreverse_key* -> get_bitwise_key*
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:58 -04:00
Sage Weil
11946129ef
os/GenericObjectMap: use bitwise hash, not nibblewise
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:58 -04:00
Sage Weil
d94a52c932
common/hobject: rename get_filestore_key* -> get_nibblewise_key*
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:58 -04:00
Sage Weil
333f3a01a9
rbd: fix bench-write
...
Make each IO get a unique offset!
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:57 -04:00
Sage Weil
c6b4f08fbb
ceph-kvstore-tool: take a db type too
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:57 -04:00
Sage Weil
11a069db35
common/hobject: make hobject_t::set_key avoid dups
...
If the key matches the oid name, clear it.
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:57 -04:00
Sage Weil
7ffb7b077a
test_objectstore_memstore.sh on make check
...
This'll give us some coverage from ceph_test_objectstore, albeit
on the memstore backend. Upside is that this takes < 10s.
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:57 -04:00
Sage Weil
79da9d664f
ceph_test_objectstore: test many small writes
...
This exercises the overlay code better.
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:57 -04:00
Sage Weil
1c48837082
ceph_test_objectstore: strengthen clone test w/ new assert
...
Signed-off-by: Sage Weil <sage@redhat.com>
2015-08-19 17:03:57 -04:00