1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
|
commit a913ded2ff138aefb8cb84d347d72164099cfd60
Author: Gary Lowell <gary.lowell@inktank.com>
Date: Fri Dec 20 19:28:37 2013 +0000
v0.72.2
commit b570c8014325fef590d16e6157cb33026155932c
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Dec 18 13:11:01 2013 -0800
rgw: fix use-after-free when releasing completion handle
Backport: emperor, dumpling
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commit c8890ab2d46fe8e12200a0d2f9eab31c461fb871)
commit 451381b4dba9d50fbee2accf5d75562615001ef3
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Dec 18 13:10:21 2013 -0800
rgw: don't return data within the librados cb
Fixes: #7030
The callback is running within a single Finisher thread, thus we
shouldn't block there. Append read data to a list and flush it within
the iterate context.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit d6a4f6adfaa75c3140d07d6df7be03586cc16183)
commit c044b218cb32d7ef2f2aa5db81ebf38ad0dc1049
Author: Sage Weil <sage@inktank.com>
Date: Sun Dec 1 22:21:31 2013 -0800
Partial revert "mon: osd pool set syntax relaxed, modify unit tests"
This reverts commit 08327fed8213a5d24cd642e12b38a171b98924cb, except
for the hashpspool bit. We switched back to an integer argument in
commit 337195f04653eed8e8f153a5b074f3bd48408998.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e80ab94bf44e102fcd87d16dc11e38ca4c0eeadb)
Reviewed-by: Greg Farnum <greg@inktank.com>
commit 1983ed8013637e9b80ca4a0e8d2800d6a36b120e
Author: Joao Eduardo Luis <joao.luis@inktank.com>
Date: Tue Nov 19 23:21:11 2013 +0000
mon: OSDMonitor: drop cmdval_get() for unused variable
We don't ever use any value as a float, so just drop obtaining it. This
makes it easier to partially revert 2fe0d0d9 in an upcoming patch.
Backport: emperor
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 7191bb2b2485c7819ca7b9d9434d803d0c94db7a)
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
commit 1c4759cebb11ae1aa84aa3cbdb2b31e6d111f28e
Author: Joao Eduardo Luis <joao.luis@inktank.com>
Date: Fri Nov 22 02:10:35 2013 +0000
mon: OSDMonitor: receive CephInt on 'osd pool set' instead on CephString
This partially reverts 2fe0d0d9 in order to allow Emperor monitors to
forward mon command messages to Dumpling monitors without breaking a
cluster.
The need for this patch became obvious after issue #6796 was triggered.
Basically, in a mixed cluster of Emperor/Dumpling monitors, if a client
happens to obtain the command descriptions from an Emperor monitor and
then issue an 'osd pool set' this can turn out in one of two ways:
1. client msg gets forwarded to an Emperor leader and everything's a-okay;
2. client msg gets forwarded to a Dumpling leader and the string fails to
be interpreted without the monitor noticing, thus leaving the monitor with
an uninitialized variable leading to trouble.
If 2 is triggered, a multitude of bad things can happen, such as thousands
of pg splits, due to a simple 'osd set pool foo pg_num 128' turning out
to be interpreted as 109120394 or some other random number.
This patch is such that we make sure the client sends an integer instead
of a string. We also make sure to interpret anything the client sends as
possibly being a string, or an integer.
Fixes: 6796
Backport: emperor
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 337195f04653eed8e8f153a5b074f3bd48408998)
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
commit c2e467b42dfaecf082a3838b10e873f9f8bd5633
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Mon Nov 25 13:43:43 2013 -0800
init, upstart: prevent daemons being started by both
There can be only one init system starting a daemon. If there is a
host entry in ceph.conf for a daemon, sysvinit would try to start it
even if the daemon's directory did not include a sysvinit file. This
preserves backwards compatibility with older installs using sysvinit,
but if an upstart file is present in the daemon's directory, upstart
will try to start them, regardless of host entries in ceph.conf.
If there's an upstart file in a daemon's directory and a host entry
for that daemon in ceph.conf, both sysvinit and upstart would attempt
to manage it.
Fix this by only starting daemons if the marker file for the other
init system is not present. This maintains backwards compatibility
with older installs using neither sysvinit or upstart marker files,
and does not break any valid configurations. The only configuration
that would break is one with both sysvinit and upstart files present
for the same daemon.
Backport: emperor, dumpling
Reported-by: Tim Spriggs <tims@uahirise.org>
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 5e34beb61b3f5a1ed4afd8ee2fe976de40f95ace)
commit 8812c4e958b154ca401c7257fd48ccaffe013639
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Nov 27 13:34:00 2013 -0800
rgw: don't error out on empty owner when setting acls
Fixes: #6892
Backport: dumpling, emperor
s3cmd specifies empty owner field when trying to set acls on object
/ bucket. We errored out as it didn't match the current owner name, but
with this change we ignore it.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 14cf4caff58cc2c535101d48c53afd54d8632104)
commit 69e055f367ae37dd771c050f158d684e2a3cb246
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Fri Nov 22 07:04:01 2013 -0800
rgw: lower some debug message
Fixes: #6084
Backport: dumpling, emperor
Reported-by: Ron Allred <rallred@itrefined.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit b35fc1bc2ec8c8376ec173eb1c3e538e02c1694e)
commit 53951fd5459d6396b6ab59b52dc33df0ebcf4414
Author: Samuel Just <sam.just@inktank.com>
Date: Tue Nov 12 15:15:26 2013 -0800
ReplicatedPG: test for missing head before find_object_context
find_object_context doesn't return EAGAIN for a missing head.
I chose not to change that behavior since it might hide bugs
in the future. All other callers check for missing on head
before calling into find_object_context because we potentially
need head or snapdir to map a snapid onto a clone.
Backport: emperor
Fixes: 6758
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
(cherry picked from commit dd9d8b020286d5e3a69455023c3724a7b436d687)
commit 83ee6843de6432278dc2891526691006c51eb1fa
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Mon Nov 18 14:39:12 2013 -0800
osd: fix bench block size
The command was declared to take 'size' in dumpling, but was trying to
read 'bsize' instead, so it always used the default of 4MiB. Change
the bench command to read 'size', so it matches what existing clients
are sending.
Fixes: #6795
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 40a76ef0d09f8ecbea13712410d9d34f25b91935)
|
