RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2024-12-28 14:34:13 +00:00
Code Issues Packages Projects Releases Wiki Activity
73,293 Commits 211 Branches 0 Tags 1.4 GiB
765b9d25e4
Commit Graph

73293 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kefu Chai
30ce5e5546 install-deps.sh: workaround setuptools' dependency on six 
see also https://github.com/pypa/setuptools/issues/1042

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-06-01 14:52:44 +08:00
Sage Weil
e84a948514 os/bluestore: mempools for writing and writing_deferred 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:50:04 -04:00
Sage Weil
e40f19736b os/bluestore: bluestore_txc mempool 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:45:11 -04:00
Sage Weil
bf790b6a93 os/bluestore: rename cache mempools to bluestore_cache_* 
These map directly onto the bluestore_cache_size setting.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:43:17 -04:00
Sage Weil
0f3f319066 os/bluestore: maybe_rebuild before adding to cache too 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:32:58 -04:00
Sage Weil
2419ec97f8 AUTHORS: update with release manager, backport team 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:32:13 -04:00
Sage Weil
037d6a7d87 Merge pull request #15370 from liewegas/wip-jewel-tunables 
crush, mon: make jewel the lower bound for client/crush compat for new clusters

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-31 21:26:17 -05:00
Sage Weil
8bcb4a663b test/cli/osdmaptool/: fix tests 
CRUSH tunables now default to jewel; outputs vary and
upmap results are a bit different.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:25:26 -04:00
Sage Weil
52a857f578 buffer: fix some append_buffer vs mempool assignment; add tests 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:20:03 -04:00
Sage Weil
affc9ef69c mempool: make dump more concise 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:20:03 -04:00
Sage Weil
495f4c9dd7 test/cli/crushtool: adjust tests 
Specify chooseleaf_stable for --build tests to match prior output.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:01:51 -04:00
Sage Weil
fdeb59d75e mon: set mon_osd_initial_require_min_compat_client = jewel 
IMO a jewel lower bound is reasonable for new clusters.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:01:51 -04:00
Sage Weil
a69a8966d0 crush: set default tunables to jewel 
For new clusters.

This is the last "disruptive" tunable change we've made (where adjusting/
fixing it requires lots of data movement).  For new clusters a lower bound
of jewel seems pretty reasonable, and this has been upstream in Linux
for a while now.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 22:01:51 -04:00
Brad Hubbard
569125c48e Merge pull request #15267 from joscollin/wip-cleanup-redundant-headers-5 
common: Remove redundant includes - 5

Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
 2017-06-01 10:39:15 +10:00
Yehuda Sadeh
1cb7f4aa77 qa/rgw_snaps: move default_idle_timeout config under the client 
Fixes: http://tracker.ceph.com/issues/20128

Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
 2017-05-31 17:14:47 -07:00
Sage Weil
bf82eb5910 Merge pull request #15311 from dachary/wip-crush-add-remove 
crush: update choose_args when items are added/removed

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-31 18:09:36 -05:00
Sage Weil
e5242966f0 Merge pull request #15318 from tchaikov/wip-20067 
mon: trim the creating_pgs after updating it with pgmap

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-31 18:09:06 -05:00
Sage Weil
cbc5a34dad Merge pull request #15352 from liewegas/wip-buffer-mempools 
buffer: allow buffers to be accounted in arbitrary mempools
 2017-05-31 18:08:49 -05:00
Sage Weil
35e7bf190d Merge pull request #15357 from ceph/typo_bluestore 
os/bluestore: fix a typo about bleustore

Reviewed-by: Varada Kari <varada.kari@gmail.com>
 2017-05-31 18:08:34 -05:00
Sage Weil
538dbb09de Merge pull request #15385 from myoungwon/wip-20114 
test/osd/TestRados.cc: run set-redirect test after finishing setup

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-31 18:06:40 -05:00
David Zafman
de97f8b607 Revert "osd: When scrub finds an attr error mark shard inconsistent" 
This reverts commit 44736aac74.

Signed-off-by: David Zafman <dzafman@redhat.com>
 2017-05-31 16:05:10 -07:00
Sage Weil
2984e5a120 Merge pull request #14457 from ceph/wip-rest-flask 
ceph-mgr: Implement new pecan-based rest api
 2017-05-31 17:48:43 -05:00
Yehuda Sadeh
4aea15fed2 rgw: fix import 
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
 2017-05-31 15:01:56 -07:00
John Spray
30da9b7681 mon: revise "ceph status" output 
Signed-off-by: John Spray <john.spray@redhat.com>
 2017-05-31 17:52:40 -04:00
Matt Benjamin
dc12370f8f Merge pull request #15222 from guihecheng/rgw_file-fix-unlink 
rgw_file: fix flags set on unsuccessful unlink
 2017-05-31 16:57:20 -04:00
Matt Benjamin
a94de3ae16 Merge pull request #15329 from guihecheng/rgw_file-readdir 
rgw_file: add lock protection for readdir against gc
 2017-05-31 16:35:37 -04:00
Boris Ranto
f086499251 Merge pull request #14871 from ceph/wip-selinux-optimize 
selinux: Do parallel relabel on package install

Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
 2017-05-31 20:53:14 +02:00
Sage Weil
5f37da539a mempool: dump total, too 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:48:00 -04:00
Sage Weil
1965860810 osd: (loosely) mark cached map bl buffers as osd_mapbl 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:48:00 -04:00
Sage Weil
23a186c7a8 os/bluestore: mark buffer caches buffers as bluestore_data 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:48:00 -04:00
Sage Weil
390b4d15e5 buffer: remove buffer_data mempool 
We are explicitly accounting for buffers via arbitrary pools, defaulting
to buffer_anon, so we don't need buffer_data anymore.  It leads to
double-counting.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:48:00 -04:00
Sage Weil
e2b4a00455 buffer: allow buffers to map into arbitrary mempools 
- default is buffer_anon
- buffer_data includes *all* buffers across all mempools, and is the
*actual* allocation (includes raw_combined).
- buffer_meta is other buffer-related overhead.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:48:00 -04:00
Sage Weil
1dc6393daf mempool: allow pool counts to be adjusted explicitly 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:47:28 -04:00
Sage Weil
6cd6a513ca buffer: fix mempool accounting for claimed chars 
These are allocated by the caller, outside of the mempool; do not
deallocate via the mempool.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:47:28 -04:00
Sage Weil
429b65c639 mempool: kill unittest_? mempools 
These were just annoying.  Use some real ones that will be empty
for the unit tests.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:47:28 -04:00
Sage Weil
b19352eec3 Merge pull request #15291 from liewegas/wip-osdmap-pgtemp 
osd/OSDMap: make pg_temp more efficient

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-05-31 13:47:00 -05:00
Sage Weil
f78051cf27 Merge pull request #15321 from liewegas/wip-failed-msg 
mon/OSDMonitor: change info in 'osd failed' messages

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-05-31 13:46:09 -05:00
Sage Weil
9628b0edc0 pybind/rados: add monitor_log2 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:39:55 -04:00
Sage Weil
241683e01c librados: add rados_monitor_log2 that includes EntityName 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:39:55 -04:00
Sage Weil
2a28267758 librados: use EntityName in monitor_log line 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:39:54 -04:00
Sage Weil
6c520ffb0f common/LogEntry: include EntityName in log entries 
We want the auth name (mon.hostname), not the entity_name_t (mon.0) to
appear in the log messages.  In particular this is helpful for the mgr,
which will now appear as mgr.hostname instead of client.1234.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:39:54 -04:00
Sage Weil
e19448c9f5 common/entity_name: do not populate type_id string for type==0 
The EntityName ctor leaves type == 0.  If we encode and
then decode that value, we end up calling set(), which
tries (and fails) to populate the type_id string, leaving
you with an instance that renders as 'unknown.' instead
of ''.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-05-31 14:39:54 -04:00
Jason Dillaman
aa94770219 Merge pull request #15388 from idryomov/wip-krbd-fallocate-tests 
qa: krbd discard/zeroout tests

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
 2017-05-31 12:38:15 -04:00
Sage Weil
0a8beea82e Merge pull request #15135 from cbodley/wip-denc-sstring 
denc: add encode/decode for basic_sstring

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-05-31 10:38:53 -05:00
Sage Weil
2c231f9b4b Merge pull request #13802 from LiumxNL/wip-170306 
mon/OSDMonitor: use up set instead of acting set in reweight_by_utilization

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-05-31 10:38:24 -05:00
Ganesh Mahalingam
371d45db44 erasure-code: Remove duplicate of isa-l files 
There are two copies of isa-l. While one is a git submodule the other
was a static copy from an older version. This change helps with removing
the duplicate and maintain a single copy.
This is also upgrading isa-l used by (src/erasure-code/isa/isa-l) from
v2.14 to v2.16.0

Signed-off-by: Ganesh Mahalingam <ganesh.mahalingam@intel.com>
 2017-05-31 07:44:49 -07:00
Sage Weil
e4f156f3b8 Merge pull request #15295 from liewegas/wip-bluestore-fsck 
os/bluestore: fix fsck deferred_replay

Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
 2017-05-31 09:39:18 -05:00
myoungwon oh
a058ebbda4 test/osd/TestRados.cc: run test after finishing redirect setup 
set-redirect test creates more objects than default due to redirect mapping
(let's assume that we create 500 objects, oid 1 -> oid 501, oid 2 -> oid 502)
But the test should use objects within pre-defined range. For example,
If the number of object is 500, only 1~500 oid are allowed for test operations.

In the failure cases, test operation tried to use wrong oids (which means
higher than 500). This is because the bug in the setup phase.
If max_inflights > 1, set-redirect can be finished after setup is completed.
(so wrong oid is included in oid_in_use).
We need to completely remove redirect objects in oid_in_use before start the test.

Fixes: http://tracker.ceph.com/issues/20114
Signed-off-by: Myoungwon Oh <omwmw@sk.com>
 2017-05-31 23:25:00 +09:00
Ilya Dryomov
156cf45214 qa: krbd discard/zeroout tests 
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
 2017-05-31 14:39:08 +02:00
Boris Ranto
6991764f3b rpm: Move ceph-disk to ceph-base 
The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk python library is already
packaged in ceph-base so moving ceph-disk to ceph-base seems like a
reasonable next step.

Signed-off-by: Boris Ranto <branto@redhat.com>
 2017-05-31 14:03:53 +02:00