Commit Graph

33638 Commits

Author SHA1 Message Date
Greg Farnum
04c280e7c1 Merge remote-tracking branch 'origin/master' into wip-4354-mds-optracker
Conflicts:
	src/mds/Locker.cc
	src/osd/OpRequest.cc
	src/osd/OpRequest.h

Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-13 10:54:12 -07:00
Yan, Zheng
26151ec62f mds: lower IO priority of storing backtrace
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-13 13:52:31 +08:00
Gregory Farnum
bfce3d4fac Merge pull request #1771 from ceph/wip-5021
Wip 5021

Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
2014-05-12 21:39:53 -07:00
Yan, Zheng
20814de9e9 Merge pull request #1807 from ceph/wip-mds-flock
mds: reduce verbosity of handle_client_file_{readlock,setlock}
2014-05-13 09:31:00 +08:00
Yan, Zheng
019483fdaa mds: reduce verbosity of handle_client_file_{readlock,setlock}
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-13 09:29:47 +08:00
Greg Farnum
ca313c20be mds: add a Server::submit_mdlog_entry() to provide event marking
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 18:27:42 -07:00
Greg Farnum
9f0825ca13 OSD: verify that client ops are targeted correctly in the current epoch
We were previously only looking at the epoch the op was sent in, which meant
that if we had dropped responsibility somewhere between send_epoch and our
current epoch, we would queue up the op until a new osdmap came along. If it
never did, we could block all client IO against us...

Fixes: #8338

Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 17:22:12 -07:00
Samuel Just
7411477153 ReplicatedPG: block scrub on blocked object contexts
Fixes: #8011
Backport: firefly
Signed-off-by: Samuel Just <sam.just@inktank.com>
2014-05-12 15:31:11 -07:00
Samuel Just
c32c56b739 Merge pull request #1779 from ceph/wip-7553
Wip 7553

Reviewed-by: Samuel Just <sam.just@inktank.com>
2014-05-12 15:29:39 -07:00
Samuel Just
2ec2182745 ReplicatedPG::start_flush: send delete even if there are no snaps
Even if all snaps for the clone have been removed, we still have to
send the delete to ensure that when the object is recreated the
new snaps aren't included in the wrong clone.

Signed-off-by: Samuel Just <sam.just@inktank.com>
2014-05-12 15:08:07 -07:00
Greg Farnum
ca91743003 Locker: mark_event in acquire_locks() when blocking or succeeding
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:44:14 -07:00
Greg Farnum
2df68b6b73 Server: mark events when journaling and replying
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:44:14 -07:00
Greg Farnum
a6aa8121f2 MDCache: mark ops at various finish points
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:44:14 -07:00
Greg Farnum
87f6cd4929 MDS: add an OpTracker and use it
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:44:04 -07:00
Greg Farnum
b27780291c Mutation: add an MDRequestParams struct and use that when building MDRequests
We now have a single constructor and one path to build MDRequests with.

Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:41:20 -07:00
Greg Farnum
ae80a1f308 MDS: add stubs for an AdminSocketHook
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:39:57 -07:00
Greg Farnum
0d89e5ca45 MDCache: pass the causative message to request_start_slave()
We were passing the causative MDS (as an int), but pushing down the
actual Message will help us as we set up an OpTracker.

Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:39:57 -07:00
Greg Farnum
06d6d32ba3 mds: remove a couple leftover declarations of MDRequest
Signed-off-by: Greg Farnum <greg@inktank.com>
2014-05-12 14:39:57 -07:00
Sage Weil
428319e827 doc/release-notes: v0.80.1
Signed-off-by: Sage Weil <sage@inktank.com>
2014-05-12 14:25:53 -07:00
Sage Weil
b99244e575 Merge pull request #1799 from ceph/wip-8305
osd: fix op ordering with pool overlay set/removed

Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
2014-05-12 13:33:27 -07:00
John Wilkins
19f8849a94 doc: Improvements to qemu installation.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
2014-05-12 13:20:14 -07:00
John Wilkins
6e4455d6af doc: Added note on Default requiretty for CentOS and others.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
2014-05-12 11:33:57 -07:00
Sage Weil
59e2381f67 Merge pull request #1801 from ceph/wip-update-gitignore
Update gitignore entries for master

Reviewed-by: Sage Weil <sage@inktank.com>
2014-05-12 06:10:22 -07:00
Sage Weil
b4ffd661af Merge pull request #1800 from ceph/wip-da-SCA-20140510
fixes from SCA

Reviewed-by: Sage Weil <sage@inktank.com>
2014-05-12 05:51:45 -07:00
Dmitry Smirnov
8b682d167e prioritise use of javac executable (gcj provides it through alternatives).
On Debian this fixes FTBFS when gcj-jdk and openjdk-7-jdk are installed at
 the same time because build system will use default `javac` executable
 provided by current JDK through `update-alternatives` instead of blindly
 calling GCJ when it is present.

Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
2014-05-12 14:08:44 +10:00
Dmitry Smirnov
89fe035358 pass '-classpath' option (gcj/javah ignores CLASSPATH environment variable).
This should not affect OpenJDK which understands '-classpath' as well.

 With gcj-jdk we still get FTBFS later:

 ~~~~
    java/native/libcephfs_jni.cc:2878:55: error: invalid conversion from 'const jbyte* {aka const signed char*}' to 'jbyte* {aka signed char*}' [-fpermissive]
                 reinterpret_cast<const jbyte*>(rawAddress));
                                                           ^
    In file included from java/native/libcephfs_jni.cc:27:0:
    /usr/lib/gcc/x86_64-linux-gnu/4.8/include/jni.h:1471:8: error:   initializing argument 4 of 'void _Jv_JNIEnv::SetByteArrayRegion(jbyteArray, jsize, jsize, jbyte*)' [-fpermissive]
       void SetByteArrayRegion (jbyteArray val0, jsize val1, jsize val2, jbyte * val3)
            ^
    make[5] *** [java/native/libcephfs_jni_la-libcephfs_jni.lo] Error 1
 ~~~~

Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
2014-05-12 14:06:54 +10:00
Dmitry Smirnov
0f4120c011 look for "jni.h" in gcj-jdk path, needed to find "jni.h" with gcj-jdk_4.9.0
Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
2014-05-12 13:57:20 +10:00
Yan, Zheng
20015726a6 mds: deny reconnect for closed session
The client that tries reconnect may have dirty caps and unsafe requests.
Allowing the reconnect attempt may compromise consistency.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-12 11:38:40 +08:00
Yan, Zheng
59f539c105 mds: revert EMetaBlob::{fullbit,remotebit,nullbit} encoding optimization
Revert commit 40d56a97 (mds: optimize EMetaBlob::fullbit, remotebit,
nullbit encoding). This optimization creates small segments in the
result bufferlist of encoding EMetaBlob. Perf shows lots of CPU time
are used for allocating list node for bufferlist.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-12 11:26:15 +08:00
Yan, Zheng
f35648bf08 mds: properly clear new flag for stale client cap
CInode::encode_inodestat() should clear the 'new' flag of client
cap even when session is stale, because the 'new' flag prevents
Locker::issue_caps() from sending cap message to client.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-12 11:14:51 +08:00
Yan, Zheng
58ee556079 mds: propagate inode rstat if it has never been propagated
Otherwise the 'last_dirstat_prop' of directory inode keeps in 'never'
state.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-12 11:14:51 +08:00
Yan, Zheng
54a9037665 mds: avoid journaling unnecessary dir context
If base inode is reached, try clearing the 'maybe' list, then stop.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-12 11:14:51 +08:00
Yan, Zheng
1f92f55882 mds: cleanup usage of MDCache::predirty_journal_parent()
The sixth parameter of MDCache::predirty_journal_parent() is 'int'
with default value 0.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-05-12 11:14:51 +08:00
Danny Al-Gaaf
3d7f527cbd BtrfsFileStoreBackend.cc: fix ::unlinkat() result handling
Don't check for 'fd' but for the return value of the ::unlinkat() call.

Fix for:
[src/os/BtrfsFileStoreBackend.cc:72] -> [src/os/BtrfsFileStoreBackend.cc:74]:
 (warning) Opposite conditions in nested 'if' blocks lead to a dead code block.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 02:33:44 +02:00
Danny Al-Gaaf
5f89128f60 TestLFNIndex.cc: remove unused variable 'mangled_name'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 02:17:49 +02:00
Danny Al-Gaaf
a4455299d9 rgw_user.cc: remove dead assignment in generate_key()
Fix for:
[src/rgw/rgw_user.cc:778]: (style) Variable 'subuser' is
 assigned a value that is never used.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 02:07:10 +02:00
Danny Al-Gaaf
b1196795c2 rgw_user.cc: cleanup RGWAccessKeyPool::check_op()
Remove dead assignment and unsued variable 'secret_key'. Check
op_state.get_access_key() directly for emptiness without extra
variable. Fix comment above check for access key.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 02:01:10 +02:00
Danny Al-Gaaf
b731c472de rgw_rados.cc: remove dead assignment / unused variable 'obj_name'
Fix for:
[src/rgw/rgw_main.cc:1086]: (style) Variable 'frontend_frameworks'
 is assigned a value that is never used.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 01:47:32 +02:00
Danny Al-Gaaf
10e6d6e621 rgw_main.cc: remove dead assignment and unused variable
Fix for:

[src/rgw/rgw_main.cc:1086]: (style) Variable 'frontend_frameworks' is
 assigned a value that is never used.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 01:43:09 +02:00
Danny Al-Gaaf
d2d6b0f6d5 PGMap.cc: remove dead assignment
[src/mon/PGMap.cc:865]: (style) Variable 'first' is assigned a value
 that is never used.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 01:36:58 +02:00
Danny Al-Gaaf
cd611b4b7a MDBalancer.cc: remove some since 2009 unused code
Remove some since long time unused code and variables (commented out
since 2009).

Fix for:

[src/mds/MDBalancer.cc:757]: (style) Variable 'total_sent' is
 assigned a value that is never used.
[src/mds/MDBalancer.cc:665]: (style) Variable 'total_goal' is
 assigned a value that is never used.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 01:26:56 +02:00
Danny Al-Gaaf
6cda1e17dc chain_xattr.cc: fix memory leak, free 'expected'
Fix for:
[src/test/objectstore/chain_xattr.cc:186]: (error) Memory leak:
 expected

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 01:14:55 +02:00
Danny Al-Gaaf
1d39b11de8 confutils.cc: remove unused variable 'val'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 01:09:53 +02:00
Danny Al-Gaaf
1cac4915cb SyntheticClient.cc: remove double check for "getdir"
Fix for:
[src/client/SyntheticClient.cc:1143]: (style) Expression is always
 false because 'else if' condition matches previous condition at line 1139.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 00:49:29 +02:00
Danny Al-Gaaf
5e05acaff4 rgw_op.cc: reduce scope of 'int r' in execute()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 00:38:48 +02:00
Danny Al-Gaaf
f45a50f1d6 rgw_op.cc: use static_cast instead of c-style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 00:33:00 +02:00
Danny Al-Gaaf
8f90cd23c1 rgw_quota.cc: remove unused variable 'key'
[src/rgw/rgw_quota.cc:455]: (style) Variable 'key' is assigned a
 value that is never used.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 00:27:37 +02:00
Danny Al-Gaaf
4753ae8728 test_rgw_admin_log.cc: prefer ++operators for iterators
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 00:06:55 +02:00
Danny Al-Gaaf
218b6d8060 test_cls_rbd.cc: use 'delete []' if 'new char[len]' was used
Fix for:
[src/test/cls_rbd/test_cls_rbd.cc:82]: (error) Mismatching allocation
 and deallocation: b
[src/test/cls_rbd/test_cls_rbd.cc:95]: (error) Mismatching allocation
 and deallocation: b
[src/test/cls_rbd/test_cls_rbd.cc:97]: (error) Mismatching allocation
 and deallocation: b

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-12 00:06:43 +02:00
Danny Al-Gaaf
20455a6bb8 test_rgw_admin_log.cc: prefer empty() over size() for emptiness check
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-05-11 23:25:36 +02:00