RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2024-12-26 21:43:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
80,138 Commits 211 Branches 0 Tags 1.4 GiB
df2e008d33
Commit Graph

80138 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kefu Chai
12df4aa74e
Merge pull request #18493 from liewegas/wip-unclean-degraded 
mon/PGMap: 'unclean' does not imply damaged

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-10-30 15:02:32 +08:00
Kefu Chai
b3d49f88ea mds: pass a reference of function to sanitize() not a copy 
to save the overhead of creating and destoying a copy of the function
closure.

Signed-off-by: Kefu Chai <kchai@redhat.com>
 2017-10-30 14:51:59 +08:00
Yang Honggang
e08c246ef2 os/bluestore/bluestore_tool: add bluefs-log-dump command to dump bluefs's log 
./bin/ceph-bluestore-tool --command bluefs-log-dump --path dev/osd0/
...
0x1000: txn(seq 2 len 0xd7 crc 0x306e389b)
0x1000:  op_dir_create db
0x1000:  op_dir_create db.wal
0x1000:  op_dir_create db.slow
0x1000:  op_file_update  file

Signed-off-by: Yang Honggang <joseph.yang@xtaotech.com>
 2017-10-29 23:10:00 -04:00
Sage Weil
059d046745
Merge pull request #18553 from liewegas/wip-preempt-feature 
osd/PG: remote recovery preemption, and new feature bit to condition it on

Reviewed-by: David Zafman <dzafman@redhat.com>
 2017-10-29 21:36:38 -05:00
Yuri Weinstein
51d0dbe315
Merge pull request #18594 from zmc/wip-cephmetrics 
suites/cephmetrics: Add Centos 7

Reviewed-by: Yuri Weinstein <yweins@redhat.com>
 2017-10-29 18:25:43 -07:00
Mykola Golub
f2127532df
Merge pull request #18601 from dillaman/wip-21961 
rbd-mirror: clean up spurious error log messages

Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
 2017-10-29 09:03:15 +02:00
Sage Weil
3d1b782cca osd/PG: handle spurious remote revoke or toofull 
If we restart the recovery reservation process for some reason (e.g.,
local preemption), we may still get a racing REVOKE from the replicas in
the previous round.  Ignore.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 22:49:44 -05:00
Jason Dillaman
625222edbc rbd-mirror: journal debug message should not be logged as error 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-28 18:30:17 -04:00
Jason Dillaman
1e1d15eb0c rbd-mirror: avoid attempting to decode an empty client data buffer 
Fixes: http://tracker.ceph.com/issues/21961
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-28 18:29:10 -04:00
Mykola Golub
0d19edf6c5
Merge pull request #18604 from dillaman/wip-21960 
cls/journal: ensure tags are properly expired

Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
 2017-10-29 00:27:39 +03:00
Sage Weil
70ddb0c18b unittest_interval_set: test with flat_map<> too 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
3dafe9d33e include/btree_interval_set: remove it! 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
762dd42971 os/bluestore: use interval_set<...,btree_map<...>> 
This avoid the code duplication, yay!

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
78d5afde43 include/btree_map: clean up wrapper header around btree_map 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
79f9c86dfd os/bluestore/BitMapAllocator: drop useless include 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
7bbb7958df include/interval_set: cbegin/cend -> begin/end 
c{begin,end} don't exist for btree_map<>.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
87aed2026a include/interval_set: tolerate maps that invalidate iterator on change 
These changes picked out of the diff between the original
btree_interval_set.h and interval_set.h (sadly I had it rolled into the
initial commit so it was tedious to identify these).

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:25:05 -05:00
Sage Weil
d254259059 include/interval_set: templating map used 
Default to std::map for backward compat.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:21:38 -05:00
Sage Weil
08fb3351ed osd/PG: handle RELEASE race with Remote*Reserved on replica 
If we get a REQUEST and RELEASE in quick succession, we may process a
local Remote*Reserved back in the RepNotRecovering state.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 16:03:13 -05:00
Adam C. Emerson
00c11ff2f7 Merge pull request #18602 from adamemerson/wip-optional-failure 
rgw: Fix dereference of empty optional

Reviewed-by: Matt Benjamin <mbenjamin@redhat.com>
 2017-10-28 14:14:58 -04:00
Sage Weil
ea0bfe6688 osd/PG: fix Remote*Preempted handling in ReplicaActive 
This was only half-implemented by c1e652a454

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-28 08:12:02 -05:00
Jason Dillaman
19fa1c7f5b cls/journal: ensure tags are properly expired 
Previously, if only the local image was using the journal or if
a disconnected peer was attached, the tag entries could not be
expired even if unreferenced.

Fixes: http://tracker.ceph.com/issues/21960
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-28 08:48:00 -04:00
Yao Zongyou
39c68d128c ceph-bluestore-tool: the link target should not ending with new line 
Signed-off-by: Yao Zongyou <yaozongyou@vip.qq.com>
 2017-10-28 18:23:30 +08:00
Yao Zongyou
d418a04e9f ceph-bluestore-tool: the right action is prime-osd-dir not prime-osd-dev 
Signed-off-by: Yao Zongyou <yaozongyou@vip.qq.com>
 2017-10-28 18:22:27 +08:00
Mykola Golub
9625274d3f
Merge pull request #18592 from dillaman/wip-21956 
cls/journal: fixed possible infinite loop in expire_tags

Reviewed-by: Mykola Golub <to.my.trociny@gmail.com>
 2017-10-28 09:36:30 +03:00
PCzhangPC
85713bdcc3 test_librbd:add a test case of 70 key/val pairs in TestClone2 
Signed-off-by: PCzhangPC <pengcheng.zhang@easystack.cn>
 2017-10-28 14:33:27 +08:00
PCzhangPC
3e08577a29 test_librbd:add a test case of 70 key/val pairs in TestClone 
Signed-off-by: PCzhangPC <pengcheng.zhang@easystack.cn>
 2017-10-28 14:33:22 +08:00
Xie Xingguo
32f2edd5fd
Merge pull request #18607 from yaozongyou/fix-typo 
doc: fix typo e.g,. => e.g.,

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-10-28 09:44:53 +08:00
Yao Zongyou
9eb9b8f3da doc: fix typo e.g,. => e.g., 
Signed-off-by: Yao Zongyou <yaozongyou@vip.qq.com>
 2017-10-28 09:06:24 +08:00
Sage Weil
cd94b1bedf
Merge pull request #18519 from liewegas/wip-21712-c 
ceph_test_objectstore: do not change model for 0-length zero

Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-10-27 17:41:35 -05:00
Sage Weil
81c3e4f868 osd/PG: send release to remote reservations in progress 
If we have a REQUEST outstanding and then cancel, send a RELEASE to the
REQUEST target too, so that they too can clean up.  This avoids leaving
the replica in the RepRecovering state when the primary is restarting
the whole reservation process.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-10-27 17:37:47 -05:00
Adam C. Emerson
5249139be7 rgw: Fix dereference of empty optional 
Due to the lack of a return, there was a case where an invalid ARN
could cause a dereference of an uninitialized boost::optional.

As a bit of defensive programming, restructure a couple functions to
make that kind of error impossible by ensuring the optional is only in
scope when it is initialized and relying less in early return on
error.

Fixes: http://tracker.ceph.com/issues/21962

Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
 2017-10-27 18:26:11 -04:00
Patrick Donnelly
ca52f3bd93
MDSMonitor: wait for readable OSDMap before sanitizing 
Fixes: http://tracker.ceph.com/issues/21945

Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-10-27 13:49:21 -07:00
Jason Dillaman
27613a63d1 qa/suites/rbd: run cls tests for all dependencies 
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 15:23:45 -04:00
Jason Dillaman
9e66dca495 cls/journal: fixed possible infinite loop in expire_tags 
Fixes: http://tracker.ceph.com/issues/21956
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
 2017-10-27 15:23:44 -04:00
Matt Benjamin
e000669840
Merge pull request #18571 from linuxbox2/wip-rgwfile-21940 
rgw_file:  set s->obj_size from bytes_written
 2017-10-27 14:52:12 -04:00
Patrick Donnelly
f66f1fbd19
mon: use mono clock for duration 
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-10-27 11:38:00 -07:00
Patrick Donnelly
41af6a4a30
mon: remove unused class member 
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-10-27 10:26:46 -07:00
David Zafman
f94322066f
Merge pull request #18449 from dzafman/wip-zafman-misc 
mark_unfound_lost fix and some other minor changes

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-10-27 10:21:25 -07:00
Zack Cerza
58b7e4bbb1 Use a symlink for Ubuntu fragment 
Signed-off-by: Zack Cerza <zack@redhat.com>
 2017-10-27 10:34:06 -06:00
Zack Cerza
53abe7119c suites/cephmetrics: Add Centos 7 
Signed-off-by: Zack Cerza <zack@redhat.com>
 2017-10-27 10:34:06 -06:00
Andrew Schoen
1a8561d38d ceph-volume: set journal_uuid and journal_device when using a partition 
This correctly sets the tags when a partition is used for a filestore
journal.

Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:29:50 -05:00
Andrew Schoen
3e93a31ded docs for ceph-volume lvm zap 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:45 -05:00
Andrew Schoen
3d5e391693 ceph-volume: add tests for ceph-volume lvm zap 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:44 -05:00
Andrew Schoen
6d70762dee ceph-volume: print success message if zap succeeds 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:44 -05:00
Andrew Schoen
a5454eba24 ceph-volume: terminal.write only takes one argument 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:44 -05:00
Andrew Schoen
e3a9113e70 ceph-volume: the metadata field for the lv path is lv_path not path 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:44 -05:00
Andrew Schoen
cbc38c4e4a ceph-volume: update help text for ceph-volume lvm zap 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:44 -05:00
Andrew Schoen
5f57fc8720 ceph-volume: remove lvm metadata when zapping an lv 
Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:43 -05:00
Andrew Schoen
3c9401f161 ceph-volume: adds Volume.clear_tags 
Will remove all tags for the current lv

Signed-off-by: Andrew Schoen <aschoen@redhat.com>
 2017-10-27 11:15:43 -05:00