]>
 
 
git.apps.os.sepia.ceph.com Git - ceph-ci.git/log 
 
 
 
 
 
 
Neha Ojha  [Tue, 12 Sep 2017 15:26:27 +0000  (08:26 -0700)] 
 
qa: avoid using make install for fio 
 
Signed-off-by: Neha Ojha <nojha@redhat.com>  
Neha Ojha  [Fri, 8 Sep 2017 18:15:11 +0000  (11:15 -0700)] 
 
qa/suites/rados: add perf suite 
 
Signed-off-by: Neha Ojha <nojha@redhat.com>  
Neha Ojha  [Thu, 7 Sep 2017 22:44:48 +0000  (15:44 -0700)] 
 
qa: add cbt task for performance testing 
 
Signed-off-by: Neha Ojha <nojha@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:59:59 +0000  (15:59 -0500)] 
 
Merge pull request #17177 from liupan1111/wip-fix-rm 
 
osd: allow FULL_TRY after failsafe 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:59:32 +0000  (15:59 -0500)] 
 
Merge pull request #17220 from amitkumar50/cov-test-2 
 
test: Check to avoid divide by zero 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:58:54 +0000  (15:58 -0500)] 
 
Merge pull request #17313 from mslovy/wip-fix-storetest 
 
os: kstore fix unittest for FiemapHole 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:58:21 +0000  (15:58 -0500)] 
 
Merge pull request #17329 from xiexingguo/wip-21162 
 
mon/OSDMonitor: make 'osd crush rule rename' idempotent 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:38:10 +0000  (15:38 -0500)] 
 
Merge pull request #17296 from amitkumar50/cov-test-4 
 
test: assert check for negative returns 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:37:31 +0000  (15:37 -0500)] 
 
Merge pull request #17297 from amitkumar50/cov-os-2 
 
os: Removing dead code from LFNIndex.cc 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:29:14 +0000  (15:29 -0500)] 
 
Merge pull request #17334 from chenliuzhong/modify-fault_rang-parameter-in-reshard 
 
os/bluestore: ExtentMap::reshard - fix wrong shard length 
 
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>  
Reviewed-by: Dongsheng Yang <dongsheng.yang@easystack.cn>  
Sage Weil  [Tue, 29 Aug 2017 20:25:04 +0000  (15:25 -0500)] 
 
Merge pull request #17337 from scienceluo/wip-luo-fix-cinder-conf-branch 
 
doc: move glance_api_version option to the right place 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 20:24:29 +0000  (15:24 -0500)] 
 
Merge pull request #17341 from amitkumar50/cov-common-1 
 
common: logically dead code inside shunique_lock.h 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 18:54:01 +0000  (13:54 -0500)] 
 
Merge pull request #16915 from theanalyst/doc-12.2.0-major-changes 
 
doc: 12.2.0 major release announcements 
 
Abhishek Lekshmanan  [Tue, 29 Aug 2017 09:16:46 +0000  (11:16 +0200)] 
 
doc: release notes: changelog for 12.2.0 
 
Amalgamated all the dev & RC changelogs + the changelog we saw post 
12.1.4 into one large 12.2.0 changelog. 
 
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>  
Sage Weil  [Tue, 29 Aug 2017 16:34:37 +0000  (11:34 -0500)] 
 
Merge pull request #17308 from jcsp/wip-21157 
 
mgr: fix crash in MonCommandCompletion 
 
Reviewed-by: Tim Serong <tserong@suse.com>  
Kefu Chai  [Tue, 29 Aug 2017 16:14:21 +0000  (00:14  +0800)] 
 
Merge pull request #17312 from cbodley/wip-21155 
 
qa: create_cache_pool no longer runs 'pool application enable' 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Yuri Weinstein  [Tue, 29 Aug 2017 16:12:43 +0000  (09:12 -0700)] 
 
Merge pull request #17125 from xiexingguo/wip-add-bucket-with-loc 
 
mon/OSDMonitor: add location option for "crush add-bucket" command 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Yuri Weinstein  [Tue, 29 Aug 2017 16:12:25 +0000  (09:12 -0700)] 
 
Merge pull request #17239 from zmedico/PGPool-update-eliminate-expensive-union_of 
 
osd/PG: PGPool::update: avoid expensive union_of 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Yuri Weinstein  [Tue, 29 Aug 2017 16:11:53 +0000  (09:11 -0700)] 
 
Merge pull request #17276 from yuyuyu101/wip-mon-loop 
 
msg/async: don't stuck into resetsession/retrysession loop 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Yuri Weinstein  [Tue, 29 Aug 2017 16:11:03 +0000  (09:11 -0700)] 
 
Merge pull request #17288 from yuyuyu101/wip-21143 
 
msg/async: don't kill connection if replacing 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
amitkuma  [Tue, 29 Aug 2017 15:46:50 +0000  (21:16 +0530)] 
 
common: logically dead code inside shunique_lock.h
Fixes the coverity issue:
** 
1352097  Structurally dead code
CID 
1352097  (#1 of 1): Structurally dead code (UNREACHABLE)
unreachable: This code cannot be reached: return ceph::shunique_lock<...
Signed-off-by: Amit Kumar <amitkuma@redhat.com> 
 
Casey Bodley  [Tue, 29 Aug 2017 14:10:49 +0000  (10:10 -0400)] 
 
Merge pull request #17254 from joscollin/wip-cleanup-rgw-override 
 
rgw: add missing override in list_keys_init() 
 
Reviewed-by: Casey Bodley <cbodley@redhat.com>  
Casey Bodley  [Mon, 28 Aug 2017 14:14:03 +0000  (10:14 -0400)] 
 
qa: create_cache_pool no longer runs 'pool application enable' 
 
Fixes: http://tracker.ceph.com/issues/21155  
Signed-off-by: Casey Bodley <cbodley@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 13:40:16 +0000  (08:40 -0500)] 
 
Merge pull request #17311 from hjwsm1989/wip-monop-tracker 
 
mon: use ceph_clock_now if message is self-generated 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 13:38:53 +0000  (08:38 -0500)] 
 
Merge pull request #17330 from xiexingguo/wip-class-rename-idempotent 
 
mon/OSDMonitor: make 'osd crush class rename' idempotent 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Yehuda Sadeh  [Tue, 29 Aug 2017 13:38:45 +0000  (16:38 +0300)] 
 
Merge pull request #16863 from mikulely/fix-curl-referer 
 
rgw: fix opslog can't record referrer when using curl as client 
 
Reviewed-by: Jos Collin <jcollin@redhat.com>  
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>  
Yehuda Sadeh  [Tue, 29 Aug 2017 13:33:42 +0000  (16:33 +0300)] 
 
Merge pull request #16860 from mikulely/fix-opslog 
 
rgw: fix opslog cannot record remote_addr 
 
Reviewed-by: Jos Collin <jcollin@redhat.com>  
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>  
Yehuda Sadeh  [Tue, 29 Aug 2017 13:31:14 +0000  (16:31 +0300)] 
 
Merge pull request #16933 from amitkumar50/cov-rgw-3 
 
rgw: Initialize is_master, max_aio, size 
 
Reviewed-by: Jos Collin <jcollin@redhat.com>  
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>  
Yehuda Sadeh  [Tue, 29 Aug 2017 12:45:23 +0000  (15:45 +0300)] 
 
Merge pull request #17185 from oritwas/wip-rgw-20777 
 
rgw-admin: require --yes-i-really-mean-it when using --inconsistent_index 
 
Reviewed-by: Casey Bodley <cbodley@redhat.com>  
Abhishek Lekshmanan  [Thu, 24 Aug 2017 12:40:33 +0000  (14:40 +0200)] 
 
doc: 12.2.0 major release announcements 
 
Reordered the RC releases sections back to their respective components, 
added a ceph-mon section, added links to documentation wherever 
possible, and a few forgotten RGW announcements. Also cleared up the 
PendingReleaseNotes upto this point 
 
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>  
chenliuzhong  [Tue, 29 Aug 2017 06:28:01 +0000  (02:28  -0400)] 
 
os/bluestore:reshard-fix wrong shard length 
 
change fault_range parameter from 'needs_reshard_end' to 'needs_reshard_end-needs_reshard_begin' 
be given needs_reshard_end may be out of bounds 
 
Signed-off-by: chenliuzhong <liuzhong.chen@easystack.cn>  
Luo Kexue  [Tue, 29 Aug 2017 09:09:41 +0000  (17:09 +0800)] 
 
doc: move glance_api_version option to the right place 
 
Signed-off-by: Luo Kexue <luo.kexue@zte.com.cn>  
Kefu Chai  [Tue, 29 Aug 2017 08:29:16 +0000  (16:29 +0800)] 
 
Merge pull request #16774 from yanyixing/fix-sidenav 
 
mgr/dashboard: fix rbd's pool sub menu 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Mykola Golub  [Tue, 29 Aug 2017 06:34:32 +0000  (09:34 +0300)] 
 
Merge pull request #17283 from liupan1111/wip-final-nbd 
 
rbd-nbd: cleanup for NBDServer shut down 
 
Reviewed-by: Mykola Golub <mgolub@mirantis.com>  
Kefu Chai  [Tue, 29 Aug 2017 03:32:04 +0000  (11:32 +0800)] 
 
Merge pull request #17269 from liewegas/wip-health 
 
mon: fix two stray legacy get_health() callers 
 
Reviewed-by: Kefu Chai <kchai@redhat.com  
Josh Durgin  [Tue, 29 Aug 2017 03:26:31 +0000  (20:26 -0700)] 
 
Merge pull request #17328 from tchaikov/wip-kill-gcc-warning 
 
test/unittest_pg_log: silence gcc warning 
 
Reviewed-by: Josh Durgin <jdurgin@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 02:58:28 +0000  (21:58 -0500)] 
 
Merge pull request #17146 from shangzhong/wip-add-line-break 
 
common: add line break for "ceph daemon TYPE.ID version" 
 
Reviewed-by: huanwen ren <ren.huanwen@zte.com.cn>  
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Sage Weil  [Tue, 29 Aug 2017 02:56:32 +0000  (21:56 -0500)] 
 
Merge pull request #17091 from liupan1111/wip-txc-add 
 
os/bluestore: support calculate cost when using spdk. 
 
Reviewed-by: Haomai Wang <haomai@xsky.com>  
Sage Weil  [Tue, 29 Aug 2017 02:55:52 +0000  (21:55 -0500)] 
 
Merge pull request #17251 from Songweibin/wip-unused-variable 
 
os/bluestore: drop unused param "what" in apply() 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
xie xingguo  [Tue, 29 Aug 2017 01:33:51 +0000  (09:33 +0800)] 
 
mon/OSDMonitor: make 'osd crush class rename' idempotent 
 
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>  
Kefu Chai  [Tue, 29 Aug 2017 02:16:12 +0000  (10:16 +0800)] 
 
test/unittest_pg_log: silence gcc warning 
 
this silences following warning: 
 
In file included from ceph/src/test/osd/TestPGLog.cc:24:0: 
ceph/src/googletest/googletest/include/gtest/gtest.h:430:16: 
warning: ‘virtual void testing::Test::SetUp()’ was hidden 
[-Woverloaded-virtual] 
   virtual void SetUp(); 
                ^~~~~ 
ceph/src/test/osd/TestPGLog.cc:2703:8: warning:   by ‘void 
PGLogTrimTest::SetUp(unsigned int, unsigned int, unsigned int)’ 
[-Woverloaded-virtual] 
   void SetUp(unsigned min_entries, unsigned max_entries, unsigned 
dup_track) { 
        ^~~~~ 
 
Signed-off-by: Kefu Chai <kchai@redhat.com>  
Kefu Chai  [Tue, 29 Aug 2017 02:02:55 +0000  (10:02 +0800)] 
 
Merge pull request #17326 from neha-ojha/wip-21023-contd 
 
doc: fix order of options in osd new 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Kefu Chai  [Tue, 29 Aug 2017 01:25:33 +0000  (09:25 +0800)] 
 
Merge pull request #17180 from tchaikov/wip-literals-for-options 
 
common/options: use user-defined literals for default values 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Reviewed-by: John Spray <john.spray@redhat.com>  
Kefu Chai  [Tue, 29 Aug 2017 01:12:47 +0000  (09:12 +0800)] 
 
Merge pull request #16066 from tanghaodong25/bluefs-sync-write 
 
os/bluestore/BlueFS: don't need wait for aio when using _sync_write 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Kefu Chai  [Tue, 29 Aug 2017 01:11:58 +0000  (09:11 +0800)] 
 
Merge pull request #15479 from yonghengdexin735/wip-zzz-const 
 
messages/MDentryLink: add const to member function 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Kefu Chai  [Tue, 29 Aug 2017 01:11:22 +0000  (09:11 +0800)] 
 
Merge pull request #17256 from scienceluo/wip-luo-add-log-branch 
 
auth: add err reason for log info in load function 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
xie xingguo  [Tue, 29 Aug 2017 00:21:07 +0000  (08:21 +0800)] 
 
mon/OSDMonitor: make 'osd crush rule rename' idempotent 
 
Fixes: http://tracker.ceph.com/issues/21162  
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>  
Neha Ojha  [Mon, 28 Aug 2017 22:59:19 +0000  (15:59 -0700)] 
 
doc: fix order of options in osd new 
 
Signed-off-by: Neha Ojha <nojha@redhat.com>  
Sage Weil  [Mon, 28 Aug 2017 18:14:16 +0000  (13:14 -0500)] 
 
Merge pull request #17307 from liewegas/wip-powercycle-slow-trim 
 
qa/suites/powercycle/osd/whitelist_health: whitelist slow trimming 
 
Sage Weil  [Mon, 28 Aug 2017 13:38:58 +0000  (09:38 -0400)] 
 
qa/suites/powercycle/osd/whitelist_health: whitelist more 
 
"2017-08-26 16:09:27.704418 mon.a mon.0 172.21.15.169:6789/0 876 : cluster [WRN] MDS health message (mds.0): Behind on trimming (66/30)" in cluster log 
 
Signed-off-by: Sage Weil <sage@redhat.com>  
John Spray  [Mon, 28 Aug 2017 17:28:34 +0000  (18:28 +0100)] 
 
Merge pull request #16857 from yanyixing/chartfix 
 
pybind: fix chart size become bigger when refresh 
 
Reviewed-by: John Spray <john.spray@redhat.com>  
amitkuma  [Mon, 28 Aug 2017 16:46:18 +0000  (22:16 +0530)] 
 
os: Removing dead code from LFNIndex.cc
Fixes the coverity issue:
** 
1394832  Logically dead code
cannot_single: At condition r, the value of r
cannot be equal to 0.
dead_error_condition: The condition r must be true.
CID 
1394832  (#1 of 1): Logically dead code (DEADCODE)
dead_error_line: Execution cannot reach the expression
-22 inside this statement: return r ? 0 : -22;.
Signed-off-by: Amit Kumar <amitkuma@redhat.com> 
 
Ning Yao  [Mon, 28 Aug 2017 15:48:50 +0000  (15:48 +0000)] 
 
os:kstore fix unittest for FiemapHole 
 
kstore always return [0, object_size] regardless of offset and length 
 
Signed-off-by: Ning Yao <yaoning@unitedstack.com>  
amitkuma  [Thu, 24 Aug 2017 18:02:46 +0000  (23:32 +0530)] 
 
test: Check to avoid divide by zero
Fixes the coverity issue:
** 
1219467  Division or modulo by zero
CID 
1219467  (#1 of 1): Division or modulo by zero (DIVIDE_BY_ZERO)
74. divide_by_zero: In expression 100 / atoi(args[i + 1U]), division
 by expression atoi(args[i + 1U]) which may be zero has undefined behavior.
Signed-off-by: Amit Kumar amitkuma@redhat.com 
 
amitkuma  [Mon, 28 Aug 2017 15:43:37 +0000  (21:13 +0530)] 
 
test: assert check for negetive returns
Fixes the coverity issue:
** 
1395371  Argument cannot be negative
1. negative_return_fn: Function open(file, 578, 448) returs a negative number.
2. var_assign: Assigning: signed variable fd = open
** 
1395427  Argument cannot be negative
1. negative_return_fn: Function open(file, 578, 448) returns a negative number.
2. var_assign: Assigning: signed variable fd = open
Signed-off-by: Amit Kumar <amitkuma@redhat.com> 
 
Matt Benjamin  [Mon, 28 Aug 2017 15:01:03 +0000  (11:01 -0400)] 
 
Merge pull request #17267 from linuxbox2/wip-lock-qlane 
 
rgw_file:  fix LRU lane lock in evict_block() 
 
huangjun  [Mon, 28 Aug 2017 14:52:37 +0000  (22:52 +0800)] 
 
mon: use ceph_clock_now if message is self-generated 
 
Signed-off-by: huangjun <huangjun@xsky.com>  
John Spray  [Mon, 28 Aug 2017 14:08:12 +0000  (10:08 -0400)] 
 
mgr: fix crash in MonCommandCompletion 
 
Fixes: http://tracker.ceph.com/issues/21157  
Signed-off-by: John Spray <john.spray@redhat.com>  
Sage Weil  [Mon, 28 Aug 2017 13:55:18 +0000  (08:55 -0500)] 
 
Merge pull request #17293 from tchaikov/wip-jewel-x-singleton 
 
qa/suites/rados/upgrade/jewel-x-singleton: tolerate sloppy past_intervals 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Kefu Chai  [Mon, 28 Aug 2017 11:17:33 +0000  (19:17 +0800)] 
 
Merge pull request #17019 from dachary/wip-doc-ceph-disk 
 
doc: document ceph-disk prepare class hierarchy 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Kefu Chai  [Mon, 28 Aug 2017 07:19:10 +0000  (15:19 +0800)] 
 
qa/suites/rados/upgrade/jewel-x-singleton: tolerate sloppy past_intervals
See-also: 
d5d5d7d1 
Signed-off-by: Kefu Chai <kchai@redhat.com> 
 
Pan Liu  [Mon, 28 Aug 2017 02:01:58 +0000  (10:01 +0800)] 
 
Merge pull request #17284 from liupan1111/wip-nvme-cleanup 
 
bluestore/NVMEDevice: code cleanup 
 
Xie Xingguo  [Mon, 28 Aug 2017 00:35:01 +0000  (08:35 +0800)] 
 
Merge pull request #17253 from hjwsm1989/fix-qa-bug 
 
qa: fix the potential delay of pg state change 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Haomai Wang  [Sun, 27 Aug 2017 20:37:18 +0000  (13:37 -0700)] 
 
msg/async: don't kill connection if replacing 
 
when existing connection is replacing, then meet send error, we can't kill 
this existing connection. otherwise, when peer side reconnect, we will detect 
reset condition and send resetsession to make peer discard messages. 
 
Fixes: http://tracker.ceph.com/issues/21143  
Signed-off-by: Haomai Wang <haomai@xsky.com>  
Pan Liu  [Sun, 27 Aug 2017 15:14:12 +0000  (23:14 +0800)] 
 
bluestore/NVMEDevice: remove useless IOSegment, and set 
dpdk_thread_adaptor as static. 
 
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com>  
Signed-off-by: Ziye Yang <optimistyzy@intel.com>  
Pan Liu  [Sun, 27 Aug 2017 15:06:55 +0000  (23:06 +0800)] 
 
bluestore/NVMEDevice: remove useless aio_stop in class NVMEDevice 
 
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com>  
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>  
Pan Liu  [Sun, 27 Aug 2017 15:03:15 +0000  (23:03 +0800)] 
 
os/bluestore/NVMEDevice: remove not used BufferedExtents. 
 
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com>  
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>  
Pan Liu  [Sun, 27 Aug 2017 12:45:10 +0000  (20:45 +0800)] 
 
rbd-nbd: don't need call "stop()" seperately, and ~NBDServer will do it. 
 
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com>  
Jason Dillaman  [Sun, 27 Aug 2017 12:39:18 +0000  (08:39 -0400)] 
 
Merge pull request #17055 from dillaman/wip-21017 
 
mgr/dashboard: fix duplicate images listed on iSCSI status page 
 
Reviewed-by: John Spray <john.spray@redhat.com>  
Jason Dillaman  [Sun, 27 Aug 2017 12:33:35 +0000  (08:33 -0400)] 
 
Merge pull request #17216 from Yan-waller/wip-walle-0824imagectx 
 
test/librbd: fix mock method macro of set_journal_policy 
 
Reviewed-by: Jason Dillaman <dillaman@redhat.com>  
Haomai Wang  [Sun, 27 Aug 2017 05:09:54 +0000  (22:09 -0700)] 
 
msg/async: don't stuck into resetsession/retrysession loop 
 
if exist connection's connect_seq is zero and state is STANDBY and peer 
connection is new, we will reply with RETRYSESSION and make peer connection 
incr connect_seq. Then we receive connect.connect_seq==1, but 
existing->connect_seq is still zero, so RESETSESSION tag replied. 
 
RESET->RETRY->RESET loop is forever 
 
Signed-off-by: Haomai Wang <haomai@xsky.com>  
Sage Weil  [Sun, 27 Aug 2017 02:22:04 +0000  (21:22 -0500)] 
 
Merge pull request #17275 from ceph/revert-17268-wip-21089 
 
Revert "os/bluestore: compensate for bad freelistmanager size/blocks metadata" 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Kefu Chai  [Sun, 27 Aug 2017 02:14:14 +0000  (10:14 +0800)] 
 
Merge pull request #16494 from asomers/bin_bash 
 
misc: Fix bash path in shebangs 
 
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>  
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Xie Xingguo  [Sun, 27 Aug 2017 02:12:46 +0000  (10:12 +0800)] 
 
Revert "os/bluestore: compensate for bad freelistmanager size/blocks metadata" 
 
Xie Xingguo  [Sun, 27 Aug 2017 01:38:14 +0000  (09:38 +0800)] 
 
Merge pull request #17268 from liewegas/wip-21089 
 
os/bluestore: compensate for bad freelistmanager size/blocks metadata 
 
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>  
Xie Xingguo  [Sun, 27 Aug 2017 01:36:09 +0000  (09:36 +0800)] 
 
Merge pull request #17271 from xiexingguo/wip-ls-by-class 
 
mon/MonCommands: fix copy-and-paste error 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Xie Xingguo  [Sun, 27 Aug 2017 01:34:58 +0000  (09:34 +0800)] 
 
Merge pull request #17272 from scienceluo/wip-luo-silence-buiding-warning-branch 
 
common: silence jenkins's buiding warning in obj_bencher.cc 
 
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Pan Liu  [Sat, 26 Aug 2017 14:29:54 +0000  (22:29 +0800)] 
 
Merge pull request #17200 from optimistyzy/823_queue_depth 
 
os/bluestore/NVMEDevice: fix the nvme queue depth issue 
 
Luo Kexue  [Sat, 26 Aug 2017 02:58:39 +0000  (10:58 +0800)] 
 
common: silence jenkins's buiding warning in obj_bencher.cc 
 
Signed-off-by: Luo Kexue <luo.kexue@zte.com.cn>  
xie xingguo  [Sat, 26 Aug 2017 02:09:11 +0000  (10:09 +0800)] 
 
mon/MonCommands: fix copy-and-paste error 
 
Class is definitely required by default for the "crush rule ls-by-class" 
command. 
 
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>  
Pan Liu  [Wed, 23 Aug 2017 04:00:53 +0000  (12:00 +0800)] 
 
osd: allow FULL_TRY after failsafe 
 
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com>  
Xie Xingguo  [Sat, 26 Aug 2017 01:11:13 +0000  (09:11 +0800)] 
 
Merge pull request #17270 from liewegas/wip-luminous-note 
 
doc/release-notes: clarify purpose of require-osd-release 
 
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>  
Ziye Yang  [Wed, 23 Aug 2017 14:04:01 +0000  (22:04 +0800)] 
 
NVMEDevice: fix the nvme queue depth issue 
 
We need to track the queue depth usage for each qpair to 
prevent submit too many I/Os. If there are too many requests, 
we need to poll the qpair, to make sure there is enough slots 
for next I/O submit. 
 
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>  
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com>  
Sage Weil  [Fri, 25 Aug 2017 22:48:09 +0000  (18:48 -0400)] 
 
doc/release-notes: clarify purpose of require-osd-release 
 
Signed-off-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 22:30:12 +0000  (18:30 -0400)] 
 
mon: fix two stray legacy get_health() callers 
 
These need to call the new method when appropriate. 
 
Signed-off-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 22:08:25 +0000  (18:08 -0400)] 
 
os/bluestore: compensate for bad freelistmanager size/blocks metadata
This repairs bluestores created before http://tracker.ceph.com/issues/21089
was fixed in 
f6f1ae3724d593d3709d982c973ec18a25a47b6e .
In both cases, the freelistmanager's size is off by one block (4k).  In
one case, it is just a matter of fixing the size and twiddling the trailing
bit.  In the second case, the size delta causes freelistmanager to need
a new row, which means the blocks count also changes, and we have lots
of bits to zero (all but one in the new row).
Both are silently corrected by fsck in this patch.
Fixes: http://tracker.ceph.com/issues/21089 
Signed-off-by: Sage Weil <sage@redhat.com> 
 
Matt Benjamin  [Fri, 25 Aug 2017 21:55:11 +0000  (17:55 -0400)] 
 
rgw_file:  fix LRU lane lock in evict_block() 
 
Found by "Supriti Singh" <Supriti.Singh@suse.com>. 
 
Fixes http://tracker.ceph.com/issues/21141 
 
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>  
Josh Durgin  [Fri, 25 Aug 2017 21:52:43 +0000  (14:52 -0700)] 
 
Merge pull request #17245 from jdurgin/wip-dup-perf 
 
osd/PGLog: write only changed dup entries 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Kefu Chai  [Fri, 25 Aug 2017 16:53:39 +0000  (00:53  +0800)] 
 
Merge pull request #17225 from liewegas/wip-bluestore-fsck-leaks 
 
os/bluestore: print leaked extents to debug output 
 
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>  
Kefu Chai  [Fri, 25 Aug 2017 16:52:39 +0000  (00:52  +0800)] 
 
Merge pull request #17242 from neha-ojha/wip-21023 
 
mon: warn about using osd new instead of osd create 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Kefu Chai  [Fri, 25 Aug 2017 16:44:05 +0000  (00:44  +0800)] 
 
Merge pull request #17248 from tchaikov/wip-20987 
 
mon/OSDMonitor: check last_scan_epoch instead when sending creates 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Kefu Chai  [Fri, 25 Aug 2017 16:37:16 +0000  (00:37  +0800)] 
 
Merge pull request #17246 from tchaikov/wip-20913 
 
osd/PGBackend: release a msg using msg->put() not delete 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Reviewed-by: Josh Durgin <jdurgin@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 15:21:38 +0000  (10:21 -0500)] 
 
Merge pull request #17029 from xiexingguo/wip-crush-rule-rename 
 
mon: "ceph osd crush rule rename" support 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 15:12:29 +0000  (10:12 -0500)] 
 
Merge pull request #17103 from C2python/clear_attr 
 
common: Destroy attr of RWLock after initialized 
 
Reviewed-by: Casey Bodley <cbodley@redhat.com>  
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 15:11:06 +0000  (10:11 -0500)] 
 
Merge pull request #17126 from xiexingguo/wip-nicenum 
 
common/types: make numbers a bit nicer when displaying space usage 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Reviewed-by: Kefu Chai <kchai@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 15:10:31 +0000  (10:10 -0500)] 
 
Merge pull request #17182 from tchaikov/wip-obj-bencher 
 
common/obj_bencher: set {min,max}_iops if runtime < 1 sec 
 
Reviewed-by: PCzhangPC <pengcheng.zhang@easystack.cn>  
Sage Weil  [Fri, 25 Aug 2017 15:09:42 +0000  (10:09 -0500)] 
 
Merge pull request #17221 from xiexingguo/wip-pg-sparse-read 
 
osd/PrimaryLogPG: fix sparse read won't trigger repair correctly 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 15:09:11 +0000  (10:09 -0500)] 
 
Merge pull request #17222 from xiexingguo/wip-propagate-eagain 
 
osd/PrimaryLogPG: do_osd_ops - propagate EAGAIN/EINPROGRESS on failok 
 
Reviewed-by: Sage Weil <sage@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 15:04:18 +0000  (10:04 -0500)] 
 
Merge pull request #17258 from liewegas/wip-21127 
 
qa/standalone/scrub/osd-scrub-repair: fix grep pattern 
 
Reviewed-by: David Zafman <dzafman@redhat.com>  
Sage Weil  [Fri, 25 Aug 2017 13:45:51 +0000  (09:45 -0400)] 
 
qa/standalone/scrub/osd-scrub-repair: fix grep pattern
PGMap shows
    ss << pg_sum.stats.sum.num_objects_unfound
       << "/" << pg_sum.stats.sum.num_objects << " objects unfound (" << b << "%)";
but we were grepping for "1/1 unfound" instead of "1/1 objects
unfound".
Introduced by 
fe81b7e3a5034ce855303f93f3e413f3f2dc74a8 .
Fixes: http://tracker.ceph.com/issues/21127 
Signed-off-by: Sage Weil <sage@redhat.com>