RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-22 10:37:15 +00:00
Code Issues Packages Projects Releases Wiki Activity
74,139 Commits 216 Branches 0 Tags 1.4 GiB
146383a21b
Commit Graph

74139 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Yan, Zheng
146383a21b osdc/Journaler: fix memory leak in Journaler::_issue_read() 
Contexts executed by _finish_flush() may call _issue_read(),
_issue_read() may add new context to tail of waitfor_safe list.
So _finish_flush() should first remove contexts from waitfor_safe,
then execute the contexts.

Fixes: http://tracker.ceph.com/issues/20338
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
 2017-06-20 19:00:38 +08:00
Sage Weil
d85f4bb4ca Merge pull request #15365 from ShiqiCooperation/newshiqi 
test/unittest_bluefs: When fsync ret is less than 0, fsync can not be…

Reviewed-by: Varada Kari <varada.kari@gmail.com>
 2017-06-19 18:06:32 -05:00
Sage Weil
36cb4629dc Merge pull request #15533 from liewegas/wip-crush-version 
mon,osd: add crush_version to OSDMap, and allow crush map updates to gate on crush_version

Reviewed-by: Loic Dachary <loic@dachary.org>
 2017-06-19 18:06:07 -05:00
Sage Weil
5c041258f7 Merge pull request #15685 from wjwithagen/wip-wjw-freebsd-ENODATA-2 
core/common: Fix ENODATA for FreeBSD with compat.h

Reviewed-by: Jos Collin <jcollin@redhat.com>
 2017-06-19 18:05:25 -05:00
Sage Weil
132c62685e Merge pull request #15710 from liewegas/wip-20273 
osd: bail from _committed_osd_maps inside osd_lock

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-06-19 18:04:50 -05:00
Casey Bodley
ac3c6c5e43 Merge pull request #15333 from mikulely/validate-bucket-location 
rgw/multisite: validate bucket location during bucket creation

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 16:47:36 -04:00
Casey Bodley
8ab1c4a8d2 Merge pull request #15633 from cloudbau/reduce-rgw-copy-loglevel 
rgw: do not log debug output at level 0

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 16:45:56 -04:00
Casey Bodley
1299808e2a Merge pull request #15598 from aclamk/encryption_refactor 
radosgw, crypto: simplified code in handle_data functions

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 16:45:22 -04:00
Casey Bodley
fbf106bcf2 Merge pull request #15599 from theanalyst/rgw/fix/bl-cstr 
rgw: don't specify a length when converting bl -> string

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 16:42:58 -04:00
Casey Bodley
0b6a13e31a Merge pull request #15756 from rzarzynski/wip-rgw-cleanup-swift-errmapping 
rgw: clean-up error mapping in Swift's authentication strategy.

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 16:42:11 -04:00
Casey Bodley
2c92ccf23d Merge pull request #15677 from zhangsw/fix-rgw-lifecycle-bug 
rgw: lifecycle thread shouldn't process the bucket which has been deleted

Reviewed-by: Daniel Gryniewicz <dang@redhat.com>
 2017-06-19 16:40:13 -04:00
Casey Bodley
0f54fe3468 Merge pull request #15682 from mikulely/rgw-putobj-params 
rgw: abort early when s->length empty during putobj

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 16:39:30 -04:00
Sage Weil
423ce2402d Merge pull request #15747 from liewegas/wip-scrub-retry 
qa/tasks/ceph: osd_scrub_pgs: reissue scrub requests in loop
 2017-06-19 14:29:12 -05:00
Sage Weil
8d10e5fc29 qa/suites/rados/singleton-nomsgr/multi-backfill-reject: clean up 
Set pool size back to 2 so we don't have to have backfill
complete (despite rejection probability) in order to get back to
healthy.  This way we scrub on cleanup.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-19 14:49:56 -04:00
Sage Weil
ef2d22dd46 Merge pull request #15712 from liewegas/wip-19882 
osd/ECTransaction: only read partial stripes when below *original* object size

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
 2017-06-19 13:45:14 -05:00
Sage Weil
15efccab70 qa/suites/rados/singleton-nomsgr/full-tiering: unset quota at end 
If we leave the quota set, the proxied ops will block
indefinitely, which will block scrubbing on the cache tier pgs
indefinitely.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-19 14:37:57 -04:00
Sage Weil
04969eff23 qa/tasks/resolve_stuck_peering: start osd at end 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-19 14:28:28 -04:00
Matt Benjamin
e7a00bcd5c Merge pull request #15679 from guihecheng/rgw_file-fix-setattr 
rgw_file: fix assert upon setattr on bucket
 2017-06-19 14:22:23 -04:00
Casey Bodley
8557916d58 Merge pull request #15660 from fangyuxiangGL/meta_sync_crash 
rgw: meta sync thread crash at RGWMetaSyncShardCR

Reviewed-by: Casey Bodley <cbodley@redhat.com>
 2017-06-19 14:14:44 -04:00
Sage Weil
74087cf5ab qa/workunits/cephtool/test.sh: silence dev warnings 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-19 14:11:57 -04:00
Sage Weil
cc902a1f6b qa/tasks/ceph: osd_scrub_pgs: reissue scrub requests in loop 
The scrub commands are not reliable: if the OSD doesn't happen to
be connected at the time the command is issued it may not get
delivered.  Re-request scrubs for each PG that has not yet been
scrubbed so that we don't wait forever when the original request
is dropped.

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-19 12:00:12 -04:00
Sage Weil
32361a798f qa/tasks/ceph: osd_scrub_pgs: tolerate down osd at initial scrub time 
Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-19 12:00:12 -04:00
Casey Bodley
fdf98241cd Merge pull request #15738 from cbodley/wip-rgw-string-constexpr 
rgw: fix constexpr for string_size in clang

Reviewed By: Adam C. Emerson <aemerson@redhat.com>
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
 2017-06-19 11:25:04 -04:00
John Spray
18de794a90 Merge pull request #15544 from taodd/master 
mds:  Client syncfs is slow (waits for next MDS tick)

Reviewed-by: Yan, Zheng <zyan@redhat.com>
 2017-06-19 10:53:51 -04:00
Sage Weil
c5a178fe03 Merge pull request #15746 from liewegas/wip-20227 
os/bluestore: better debug output on unsharing blobs

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-19 09:32:43 -05:00
dongdong
616e763178 client: signal MDS to flush log when doing a syncfs 
Fixes: http://tracker.ceph.com/issues/20129
Signed-off-by: dongdong tao <tdd21151186@gmail.com>
 2017-06-19 21:49:15 +08:00
dongdong
2222bf5eb2 Client: signal MDS to flush log when doing a syncfs 
Fixes: http://tracker.ceph.com/issues/20129
Signed-off-by: dongdong tao <tdd21151186@gmail.com>
 2017-06-19 21:47:40 +08:00
Jos Collin
da7c8255f7 Merge pull request #15745 from zealoussnow/wip-0617 
.gitignore: exclude rpm files

Reviewed-by: Jos Collin <jcollin@redhat.com>
 2017-06-19 13:08:31 +00:00
John Spray
35fcb156c9 Merge pull request #15481 from jcsp/wip-20178 
client: avoid returning negative space available

Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
 2017-06-19 08:41:25 -04:00
John Spray
abb65803f7 Merge pull request #15614 from jcsp/wip-jt-help 
tools/cephfs: fix cephfs-journal-tool --help

Reviewed-by: Douglas Fuller <dfuller@redhat.com>
 2017-06-19 05:35:21 -04:00
Radoslaw Zarzynski
cba0a07f3b rgw: clean-up error mapping in Swift's authentication strategy. 
Signed-off-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
 2017-06-19 10:54:45 +02:00
Haomai Wang
8e4665dbae Merge pull request #15749 from Adirl/wip 
msg/async/rdma: handle buffers after close msg

Reviewed-by: Haomai Wang <haomai@xsky.com>
 2017-06-19 13:54:31 +08:00
fang.yuxiang
45877d38fd rgw: meta sync thread crash at RGWMetaSyncShardCR 
Fixes: http://tracker.ceph.com/issues/20251

Signed-off-by: fang yuxiang fang.yuxiang@eisoo.com
 2017-06-19 10:14:01 +08:00
Sage Weil
93317c9ec1 Merge pull request #15725 from xiexingguo/wip-noupin 
mon/OSDMonitor: batch noup/noin osds support

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-06-18 10:37:18 -05:00
Daniel Bar-On
29d41af571 msg/async/rdma: remove assert from srq destroy in ~Infiniband 
issue:1040242

Even though ibv_destroy_srq does not return 0, all resources
are destroyed. No need to assert.

Change-Id: I96562130d22352390f9f7f9a3e0ddbe77a82d8f4
Signed-off-by: DanielBar-On <danielbo@mellanox.com>
 2017-06-18 13:26:24 +00:00
Adirl
fef4e859a1 msg/async/rdma: handle buffers after close msg 
fixing an issue of OSD’s going down during recovery process while traffic
is running in the background.
fix is making sure that messages previously pulled from the cqe and are
now stored in the socket queue “buffers” will always be handled and fd
will be notified even if cqe is empty.

issue: 1025030

Change-Id: I6ced6b8ee0152e233632700ccc9ec19970e66b6a
Signed-off-by: Alexander Mikheev <alexm@mellanox.com>
Signed-off-by: Adir Lev <adirl@mellanox.com>
 2017-06-18 13:16:49 +00:00
Abhishek L
1ce55c4649 Merge pull request #15748 from Liuchang0812/wip-fix-release-note 
doc/release-note: update release-note

Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
 2017-06-18 11:24:10 +02:00
Orit Wasserman
54b916bfd8 Merge pull request #15736 from cbodley/wip-20297 
rgw: forward RGWPutBucketPolicy to meta master
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
 2017-06-18 09:09:01 +03:00
Orit Wasserman
33a7fc0c3f Merge pull request #15132 from cbodley/wip-doc-rgw-remove-agent 
doc/rgw: remove Federated Configuration, clean up multisite
 2017-06-18 09:06:46 +03:00
liuchang0812
5e3b7e41c6 doc/release-note: update release-note 
Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
 2017-06-18 11:56:07 +08:00
Jiaying Ren
25e4d1e454 rgw/multisite: check location constraint existness 
to match the behavior of AWS S3

Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
 2017-06-18 11:24:43 +08:00
Jiaying Ren
96db3d7fd0 rgw/multisite: unify zg is_master judge 
Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
 2017-06-18 11:24:43 +08:00
Jiaying Ren
db13592398 rgw: fix bucket location s3 compatible issue 
create bucket with location constraint doesn't exist in AWS S3
will response like the following:

{'data': '<?xml version="1.0" encoding="UTF-8"?>\n
<Error><Code>InvalidLocationConstraint</Code>
<Message>The specified location-constraint is not valid</Message>
<LocationConstraint>ap-southeast-4</LocationConstraint>
<RequestId>15D886DFEF49765A</RequestId>
<HostId>IroSlmBZq7iSluYIgea7y+72OXbOSmjX2eVYING0tUuGR8BAHLcYPOgUWUIJUuG1z/1FhfaxJUo=</HostId></Error>',
 'headers': {'connection': 'close',
             'content-type': 'application/xml',
             'date': 'Thu, 25 May 2017 03:45:49 GMT',
             'server': 'AmazonS3',
             'transfer-encoding': 'chunked',
             'x-amz-id-2': 'IroSlmBZq7iSluYIgea7y+72OXbOSmjX2eVYING0tUuGR8BAHLcYPOgUWUIJUuG1z/1FhfaxJUo=',
             'x-amz-request-id': '15D886DFEF49765A'},
 'reason': 'Bad Request',
 'status': 400}

Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
 2017-06-18 11:24:43 +08:00
xie xingguo
f53559f95b mon/OSDMonitor: batch noup/noin osds support 
This is a follow-up change of https://github.com/ceph/ceph/pull/15381.
This patch also simplifies the original code logic a bit.

Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
 2017-06-18 08:39:50 +08:00
Sage Weil
c994071bac Merge pull request #15658 from xiexingguo/wip-fix-reshard 
os/bluestore: fix possible out of order shard(offset == 0); add sanity check

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-06-17 16:21:28 -05:00
Sage Weil
6856fe7d6c Merge pull request #15716 from jcsp/wip-mgr-fsmap 
mgr: fix MgrStandby eating messages

Reviewed-by: Kefu Chai <kchai@redhat.com>
 2017-06-17 16:21:03 -05:00
Sage Weil
0598bf53d2 Merge pull request #15732 from liewegas/wip-osd-boot-message 
osd: do not try to boot until we've seen the first osdmap
 2017-06-17 16:20:12 -05:00
Sage Weil
68ae47f24d Merge pull request #15740 from liewegas/wip-pgmap-debug 
mon,mgr: print pgmap reports to debug (not cluster) log

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
 2017-06-17 16:19:41 -05:00
Sage Weil
a1e55e7d31 Merge pull request #15389 from gregsfortytwo/wip-18126 
qa: do not restrict valgrind runs to centos

Reviewed-by: Sage Weil <sage@redhat.com>
 2017-06-17 16:16:00 -05:00
Sage Weil
98b18836f9 os/bluestore: better debug output on unsharing blobs 
Looking for http://tracker.ceph.com/issues/20227

Signed-off-by: Sage Weil <sage@redhat.com>
 2017-06-17 09:33:40 -04:00