Sage Weil [Sun, 25 May 2014 15:38:38 +0000 (08:38 -0700)]
osd: fix map advance limit to handle map gaps
The recent change in cf25bdf6b0090379903981fe8cee5ea75efd7ba0 would stop
advancing after some number of epochs, but did not take into consideration
the possibilty that there are missing maps. In that case, it is impossible
to advance past the gap.
Fix this by increasing the max epoch as we go so that we can always get
beyond the gap.
Sage Weil [Mon, 19 May 2014 17:32:12 +0000 (10:32 -0700)]
osd: skip out of order op checks on tiered pools
When we send redirected ops, we do not assign a new tid, which means that
a given client's ops for a pool may not have strictly ordered tids. Skip
this check if the pool is tiered to avoid false positives.
Fixes: #8380 Signed-off-by: Sage Weil <sage@inktank.com>
Greg Farnum [Thu, 15 May 2014 23:50:43 +0000 (16:50 -0700)]
OSD: fix an osdmap_subscribe interface misuse
When calling osdmap_subscribe, you have to pass an epoch newer than the
current map's. _maybe_boot() was not doing this correctly -- we would
fail a check for being *in* the monitor's existing map range, and then
pass along the map prior to the monitor's range. But if we were exactly
one behind, that value would be our current epoch, and the request would
get dropped. So instead, make sure we are not *in contact* with the monitor's
existing map range.
Signed-off-by: Greg Farnum <greg@inktank.com> Reviewed-by: Samuel Just <sam.just@inktank.com>
John Spray [Tue, 13 May 2014 16:32:03 +0000 (17:32 +0100)]
doc: update instructions for RPM distros
Fix RPM building instructions: this has been broken since
libs3 was included inline in the ceph repo as a submodule.
"rpmbuild -tb" was concatenating the ceph.spec and
libs3.spec files, resulting in something that didn't work.
Also, the instructions suggested downloading a .tar.gz file
whereas the specfile requires a .tar.bz2 file.
Also, add a convenient yum command line for getting the compile
dependencies on Fedora 20.
Signed-off-by: John Spray <john.spray@inktank.com>
Dmitry Smirnov [Mon, 12 May 2014 04:08:44 +0000 (14:08 +1000)]
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.
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.
Yan, Zheng [Mon, 12 May 2014 02:24:51 +0000 (10:24 +0800)]
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.
Danny Al-Gaaf [Mon, 12 May 2014 00:33:44 +0000 (02:33 +0200)]
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>
Danny Al-Gaaf [Mon, 12 May 2014 00:01:10 +0000 (02:01 +0200)]
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>
Danny Al-Gaaf [Sun, 11 May 2014 23:26:56 +0000 (01:26 +0200)]
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>
Danny Al-Gaaf [Sun, 11 May 2014 22:05:15 +0000 (00:05 +0200)]
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>
Danny Al-Gaaf [Sun, 11 May 2014 21:13:00 +0000 (23:13 +0200)]
test/ObjectMap/KeyValueDBMemory.cc: use empty() instead of size()
Use empty() instead of 'size() == 0' to fix:
[src/test/ObjectMap/KeyValueDBMemory.cc:83]: (performance)
Possible inefficient checking for 'db' emptiness.
[src/test/ObjectMap/KeyValueDBMemory.cc:97]: (performance)
Possible inefficient checking for 'db' emptiness.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Sun, 11 May 2014 09:52:04 +0000 (11:52 +0200)]
cls_kvs.cc: remove dead assignment
Fix for:
[src/key_value_store/cls_kvs.cc:383] -> [src/key_value_store/cls_kvs.cc:386]:
(performance) Variable 'r' is reassigned a value before the old one has been used.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Sun, 11 May 2014 09:28:26 +0000 (11:28 +0200)]
rgw_user.cc:
Remove bool variable 'same_email' compare emails directly in
if check.
Fix for:
[src/rgw/rgw_user.cc:1926] -> [src/rgw/rgw_user.cc:1927]: (performance)
Variable 'same_email' is reassigned a value before the old one has been used.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Sat, 10 May 2014 22:36:20 +0000 (00:36 +0200)]
libcephfs.cc: fix possible NULL pointer deref
Fix possible NULL pointer dereference of 'inode' in ceph_ll_lookup_inode().
It's not enough to check for 'inode' without assert or error handling before
assert for '*inode != NULL' since this doesn't handle the 'inode == NULL'
case for the later calls.
Fix for:
1192 r = (cmount->get_client())->lookup_parent(*inode, &parent);
5 Dereference of null pointer (loaded from variable 'inode')
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Sat, 10 May 2014 17:06:32 +0000 (19:06 +0200)]
mds/Server.cc: remove unused initialization of 'destdnl'
Remove initialization of 'destdnl' since the assigned value was
never used and the same call is used some lines later again before
first usage. Fix for:
6579 CDentry::linkage_t *destdnl = destdn->get_linkage();
Value stored to 'destdnl' during its initialization is never read
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Sage Weil [Thu, 8 May 2014 17:42:42 +0000 (10:42 -0700)]
mon/OSDMonitor: force op resend when pool overlay changes
If a client is sending a sequence of ops (say, a, b, c, d) and partway
through that sequence it receives an OSDMap update that changes the
overlay, the ops will get send to different pools, and the replies will
come back completely out of order.
To fix this, force a resend of all outstanding ops any time the overlay
changes.
Fixes: #8305 Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 8 May 2014 17:52:11 +0000 (10:52 -0700)]
osdc/Objecter: resend ops in the last_force_op_resend epoch
If we are a client, and process a map that sets last_force_op_resend to
the current epoch, force a resend of this op.
If the OSD expects us to do this, it will discard our previous op. If the
OSD is old, it will process the old one, this will appear as a dup, and we
are no worse off than before.
Danny Al-Gaaf [Sat, 10 May 2014 08:58:56 +0000 (10:58 +0200)]
test_librbd.cc: fix sizeof() in malloc call
Use 'char' instead of 'char *'.
228 names = (char *) malloc(sizeof(char *) * 1024);
Result of 'malloc' is converted to a pointer of type 'char',
which is incompatible with sizeof operand type 'char *'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Sat, 10 May 2014 08:50:32 +0000 (10:50 +0200)]
CrushWrapper.cc: fix sizeof() call in calloc
Use __u32 instead of __s32 due to type of bucket->parm to fix:
1028 bucket->perm = (__u32*)calloc(1, bucket->size * sizeof(__s32));
Result of 'calloc' is converted to a pointer of type '__u32',
which is incompatible with sizeof operand type '__s32'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Sage Weil [Fri, 24 May 2013 00:12:27 +0000 (17:12 -0700)]
client: invalidate dentry leases when unlinking
In many case when we are unlinking inodes we also need to invalidate the
dentry lease, as we are not promised that the dentry is NULL. Be a bit
over-conservative here for good measure.
Signed-off-by: Sage Weil <sage@inktank.com> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Sage Weil [Fri, 9 May 2014 16:20:34 +0000 (09:20 -0700)]
osd: handle race between osdmap and prepare_to_stop
If we get a MOSDMarkMeDown message and set service.state == STOPPING, we
kick the prepare_to_stop() thread. Normally, it will wake up and then
set osd.state == STOPPING, and when we process the map message next we
will not warn. However, if dispatch() takes the lock instead and processes
the map, it will fail the preparing_to_stop check and issue a spurious
warning.
Fix by checking for either preparing_to_stop or stopping.
Fixes: #8319
Backport: firefly, emperor, dumpling Signed-off-by: Sage Weil <sage@inktank.com>
projects / ceph.git / log