This project is mirrored from https://github.com/ceph/ceph.
Pull mirroring updated .
- Aug 23, 2013
-
-
Gary Lowell authored
-
- Aug 22, 2013
-
-
Sage Weil authored
Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit edf2c344)
-
Sage Weil authored
client/fuse_ll.cc: In function 'void invalidate_cb(void*, vinodeno_t, int64_t, int64_t)': warning: client/fuse_ll.cc:540: unused variable 'fino' Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit 9833e9da)
-
Sage Weil authored
In file included from json_spirit/json_spirit_writer.cpp:7:0: json_spirit/json_spirit_writer_template.h: In function 'String_type json_spirit::non_printable_to_string(unsigned int)': json_spirit/json_spirit_writer_template.h:37:50: warning: typedef 'Char_type' locally defined but not used [-Wunused-local-typedefs] typedef typename String_type::value_type Char_type; (Also, ha ha, this file uses \r\n.) Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit 6abae35a)
-
Sage Weil authored
Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit c9cdd19d)
-
- Aug 21, 2013
-
-
Josh Durgin authored
Plain Ops that haven't finished yet need to be resent if the osdmap transitions from full or paused to unpaused. If these Ops are triggered by LingerOps, they will be cancelled instead (since should_resend = false), but the LingerOps that triggered them will not be resent. Fix this by checking the registered flag for all linger ops, and resending any of them that aren't paused anymore. Fixes: #6070 Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage.weil@inktank.com> (cherry picked from commit 38a0ca66)
-
- Aug 20, 2013
-
-
Sage Weil authored
This happens after we connect, which means we get ENOSYS always. Instead, parse_env inside the normal setup method, which had the added benefit of being able to debug these tests. Backport: dumpling Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit 6ef19703)
-
Sage Weil authored
Do not leak the message if the watcher is not registered. Also, simplify this block. Fixes (part of): #5949 Backport: dumpling, cuttlefish Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> (cherry picked from commit 6f5d8036)
-
Samuel Just authored
Otherwise the log_oid will be non-empty and the next boot will cause us to try to upgrade again. Fixes: #6057 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> (cherry picked from commit 1f851cb2)
-
Samuel Just authored
This is a debug check which may be causing excessive cpu usage. Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Samuel Just <sam.just@inktank.com> (cherry picked from commit 00080d78)
-
- Aug 19, 2013
-
-
Sage Weil authored
Fixes: #6052 Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com> (cherry picked from commit 67a95b98)
-
Sage Weil authored
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com> (cherry picked from commit eef7cacd)
-
- Aug 18, 2013
-
-
Yehuda Sadeh authored
Fixes: #5953 Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> (cherry picked from commit 3cbf6a7b)
-
Sage Weil authored
If we fail to initialize, delete the handler. Fixes (part of): #5949 Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> (cherry picked from commit 810c52de)
-
Sage Weil authored
Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit 25948319)
-
Sage Weil authored
Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit a3135633)
-
Sage Weil authored
OMG libfcgi is annoying with shutdown and signals. You need to close the fd *and* resend a signal to ensure that you kick the accept loop hard enough to make it shut down. Document this, and switch to the async signal handlers. Put them tightly around the runtime loop as we do with other daemons. Signed-off-by: Sage Weil <sage@inktank.com> (cherry picked from commit 59b13ceb)
-
- Aug 17, 2013
-
-
Gary Lowell authored
-
- Aug 16, 2013
-
-
Dan Mick authored
Fix by restructuring code to hoist common code and have only one place where admin_socket is actually called. Signed-off-by: Dan Mick <dan.mick@inktank.com> (cherry picked from commit 266460e9)
-
- Aug 15, 2013
-
-
Sage Weil authored
The std::copy method leaves a trailing separator. Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com> (cherry picked from commit 35565ee6)
-
Sage Weil authored
The std::copy construct leaves a trailing separator character, which breaks parsing for booleans (among other things) and probably mangles everything else too. Backport: dumpling Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Samuel Just <sam.just@inktank.com> (cherry picked from commit fc23cfe3)
-
Sage Weil authored
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com> (cherry picked from commit ce3a0944)
-
- Aug 14, 2013
-
-
Josh Durgin authored
Check new parameters and check that rados_id is not None again to catch the empty string. Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage.weil@inktank.com> (cherry picked from commit 4422f21a)
-
Josh Durgin authored
Previously it had no name parameter, so the default will be used by old clients. However, if an old client set rados_id, a new check that both rados_id and name are set would result in an error. Fix this by only applying the default names after the check, and add tests of this behavior. This was introduced in 783b7ec8, so it does not affect cuttlefish. Fixes: #5970 Reported-by: Michael Morgan <mmorgan@dca.net> Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage.weil@inktank.com> (cherry picked from commit 34da9cbc)
-
Sage Weil authored
For aio flush, we register a wait on the most recent write. The write completion code, however, was *only* waking the waiter if they were waiting on that write, without regard to previous writes (completed or not). For example, we might have 6 and 7 outstanding and wait on 7. If they finish in order all is well, but if 7 finishes first we do the flush completion early. Similarly, if we - start 6 - start 7 - finish 7 - flush; wait on 7 - finish 6 we can hang forever. Fix by doing any completions that are prior to the oldest pending write in the aio write completion handler. Refs: #5919 Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Tested-by: Oliver Francke <Oliver.Francke@filoo.de> (cherry picked from commit 16ed0b9a)
-
Josh Durgin authored
Add an already-locked helper so that C_Aio{Safe,Complete} can increment the reference count when their caller holds the lock. C_AioCompleteAndSafe's caller is not holding the lock, so call regular get() to ensure no racing updates can occur. This eliminates all direct manipulations of AioCompletionImpl->ref, and makes the necessary locking clear. The only place C_AioCompleteAndSafe is used is in handling aio_flush_async(). This could cause a missing completion. Refs: #5919 Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Tested-by: Oliver Francke <Oliver.Francke@filoo.de> (cherry picked from commit 7a52e2ff)
-
- Aug 13, 2013
-
-
Gary Lowell authored
-
- Aug 12, 2013
-
-
Yehuda Sadeh authored
Fixes: #5931 Backport: bobtail, cuttlefish Fix a bad check, where we compare the wrong field. Instead of comparing the ret code to 0, we compare the string value to 0 which generates implicit casting, hence the crash. Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
-
- Aug 10, 2013
-
-
Sage Weil authored
Commit 6cbe0f02 added a mount_options but in certain cases it may be blank. Fill in with the defaults, just as we do in mount(). Backport: cuttlefish Reviewed-by: Dan Mick <dan.mick@inktank.com> Signed-off-by: Sage Weil <sage@inktank.com>
-
Samuel Just authored
Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: David Zafman <david.zafman@inktank.com>
-
- Aug 09, 2013
-
-
Sage Weil authored
We can race with a mon upgrade: - get command descriptions, get EINVAL - mons upgrade, new quorum - send old-style command - get EINVAL In this case, we should try one last time to get the command descriptions. Fixes: #5788 Reviewed-by: Dan Mick <dan.mick@inktank.com> Signed-off-by: Sage Weil <sage@inktank.com>
-
João Eduardo Luís authored
The Observer class we defined to observe conf changes and thus avoid triggering #5205 (as fixed by eb86eebe), was returning always the same const static array, which would lead us to always populate the observer's list with an observer for 'public_addr'. This would of course become a problem when trying to obtain the observer for 'cluster_add' during md_config_t::set_val() -- thus triggering the same assert as initially reported on #5205. Backport: cuttlefish Fixes: #5205 Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com> Reviewed-by: Sage Weil <sage@inktank.com>
-
Yehuda Sadeh authored
Fixes: #5882 Translate the EBUSY we get when trying to lock a shard / object to 423 Locked response. Beforehand it was just translated to the default 500. Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
-
Yehuda Sadeh authored
This will make it easier to catch interface changes, like the ones that triggered #5921. Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
-
Yehuda Sadeh authored
The same as with #5921, fixing a missed interface change. Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
-
Yehuda Sadeh authored
Fixes: #5921 As part of the work that was made for dumpling, the http client in-data callback was renamed in order to avoid confusion. However, we missed the rename in a couple of places, which this patch amend. Reported-by: Roald van Loon <roaldvanloon@gmail.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
-
Samuel Just authored
Otherwise, the monclient shutdown may deadlock waiting on a context trying to take the RadosClient lock. Fixes: #5897 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com>
-
Sage Weil authored
huangjun <hjwsm1989@gmail.com> reports that this fixes the compilation on CentOS5. Signed-off-by: Sage Weil <sage@inktank.com>
-
Alfredo Deza authored
Signed-off-by: Alfredo Deza <alfredo@deza.pe> (cherry picked from commit 34831d09)
-
Sage Weil authored
ceph.in: Re-enable ceph interactive mode (missing its output). Reviewed-by: Sage Weil <sage@inktank.com>
-