On LevelDBStore, instead of using leveldb's GetApproximateSizes() function,
we will instead assess what's the store's raw size from the contents of
the store dir (this means .sst's, .log's, etc). The reason behind this
approach is that GetApproximateSizes() would expect us to provide a range
of keys for which to obtain an approximate size; on the other hand, what we
really want is to obtain the size of the store -- not the size of the
data (besides, with the compaction issues we've been seeing, we wonder
how reliable such approximation would be).
Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
It is possible that we begin the paxos recovery with an uncommitted
value for, say, commit 100. During last/collect we discover 100 has been
committed already. But also, another node provides an uncommitted value
for 101 with the same pn. Currently, we refuse to learn it, because the
pn is not strictly > than our current uncommitted pn... even though it is
the next last_committed+1 value that we need.
There are two possible fixes here:
- make this a >= as we can accept newer values from the same pn.
- discard our uncommitted value metadata when we commit the value.
Let's do both!
Fixes: #6090
Signed-off-by: Sage Weil <sage@inktank.com>
Fixes: #6056
When removing a bucket metadata entry we first unlink the bucket
and then we remove the bucket entrypoint object. Originally
when unlinking the bucket we first overwrote the bucket entrypoint
entry marking it as 'unlinked'. However, this is not really needed
as we're just about to remove it. The original version triggered
a bug, as we needed to propagate the new header version first (which
we didn't do, so the subsequent bucket removal failed).
Reviewed-by: Greg Farnum <greg@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Some distro's have a lack of ltp-kernel packages and all we need is
fstress. This just modified the shell script to download/compile
fstress from source and copy it to the right location if it doesn't
currently exist where it is expected. It is a very small/quick
compile and currently only SLES and debian do not have it already.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Some distro's have a lack of ltp-kernel packages and all we need is
fstress. This just modified the shell script to download/compile
fstress from source and copy it to the right location if it doesn't
currently exist where it is expected. It is a very small/quick
compile and currently only SLES and debian do not have it already.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
This fixes a small memory leak when we have messages queued for the mon
when we shut down. It is harmless except for the valgrind leak check
noise that obscures real leaks.
Backport: dumpling
Signed-off-by: Sage Weil <sage@inktank.com>
Moving the watch/notify init before the zone init,
as we might need to send a notification.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
If the redhat-rpm-config package is installed, the debuginfo rpms will
be built by default. The build will fail when the package installed
and the specfile also invokes the macro.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
This is from Intel's ISA-L library and licensed under BSD 3-clause.
It needs to build with yasm, which means we go through all sorts of pain
to make this work with libtool:
- strip out args it doesn't understand with yasm-wrapper
- detect whether it is recent enough during configure
The code is conditional on:
- build-time support (yasm)
- run-time support (sse4.2)
Signed-off-by: Sage Weil <sage@inktank.com>
libtool passes all kinds of crap to yasm that yasm does not understand.
Hide it with this ugly wrapper. Sigh.
Signed-off-by: Sage Weil <sage@inktank.com>
When the parent xattrs of active inodes that the mds attempts to open
during rejoin lack pool info (struct_v < 5), this field will be filled
in with -1, causing the mds to retry fetching a backtrace with a pool
number that matches the expected value, which fails and causes the
err==-ENOENT branch to be taken and retry pool 1, which succeeds, but
with pool -1, and so keeps on bouncing between the two retry cases
forever.
This patch arranges for the mds to go along with pool -1 instead of
insisting that it be refetched, enabling it to complete recovery
instead of eating cpu, network bandwidth and metadata osd's resources
like there's no tomorrow, in what AFAICT is an infinite and very busy
loop.
This is not a new problem: I've had it even before upgrading from
Cuttlefish to Dumpling, I'd just never managed to track it down, and
force-unmounting the filesystem and then restarting the mds was an
easier (if inconvenient) work-around, particularly because it always
hit when the filesystem was under active, heavy-ish use (or there
wouldn't be much reason for caps recovery ;-)
There are two issues not addressed in this patch, however. One is
that nothing seems to proactively update the parent xattr when it is
found to be outdated, so it remains out of date forever. Not even
renaming top-level directories causes the xattrs to be recursively
rewritten. AFAICT that's a bug.
The other is that inodes that don't have a parent xattr (created by
even older versions of ceph) are reported as non-existing in the mds
rejoin message, because the absence of the parent xattr is signaled as
a missing inode (?failed to reconnect caps for missing inodes?). I
suppose this may cause more serious recovery problems.
I suppose a global pass over the filesystem tree updating parent
xattrs that are out-of-date would be desirable, if we find any parent
xattrs still lacking current information; it might make sense to
activate it as a background thread from the backtrace decoding
function, when it finds a parent xattr that's too out-of-date, or as a
separate client (ceph-fsck?).
Backport: dumpling, cuttlefish
Signed-off-by: Alexandre Oliva <oliva@gnu.org>
Reviewed-by: Zheng, Yan <zheng.z.yan@intel.com>
All new ObjectContext are replaced with calls to
SharedPtrRegistry::lookup_or_create to ensure that they are all
registered. Because the constructor is invoked with no argument, care
is taken to always initialize the destructor_callback data member
immediately afterwards.
ReplicatedPG::get_object_context contains a redundant call to
get_snapset_context that is removed.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
ReplicatedPG::C_PG_ObjectContext is added to encapsulate a
call to ReplicatedPG::object_context_destructor_callback method
which is reponsible for
* manually de-allocating the SnapSetContext of the ObjectContext if
any. It will eventually be managed by a SharedPtrRegistry.
ReplicatedPG::C_PG_ObjectContext must be added to the destructor_callback
member of ObjectContext immediately after it is created.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
SharedPtrRegistry does not provide an iterator equivalent to
map<hobject_t, ObjectContext*>::iterator i
It is replaced with a thread safe get_next method roughly used
as follows:
pair<hobject_t, ObjectContextRef> i;
while (object_contexts.get_next(i.first, &i))
All occurences of the iterator are replaced with get_next style
traversal.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
Both ReplicatedPG::lookup_object_context and
ReplicatedPG::_lookup_object_context methods are provided by
SharedPtrRegistry.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
ObjectContext manual reference counting and managing the
object_contexts object involves calls to
* obc->ref++ and obc->get()
* put_object_context and put_object_contexts
* register_object_context
* assertions on obc->registered
They are all removed because SharedPtrRegistry provides the
same service.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
The map of hobject_t to ObjectContext is made a
SharedPtrRegistry owned by ReplicatedPG
- map<hobject_t, ObjectContext*> object_contexts;
+ SharedPtrRegistry<hobject_t, ObjectContext> object_contexts;
All ObjectContext pointers are changed into ObjectContextRef, i.e.
shared_ptr.
In Watch.h std::tr1::shared_ptr<ObjectContext> is used instead
of ObjectContextRef because Watch.h is included before it is
defined.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
When creating a new object SharedPtrRegistry::lookup_or_create uses
the default ObjectContext constructor with no argument. The existing
ObjectContext constructor is modified to have no argument and the
initialization that was previously done within the constructor is done
by the caller (that only happens three times).
The ObjectContext::get method is removed: its only purpose is to
increment the ref.
The ObjectContext::registered data member is removed as well as all
the associated assert()
The ObjectContext::destructor_callback data member Context is added
and called by the destructor. It will allow the caller to perform
additional cleanup, if necessary.
All ObjectContext * data members are replaced with shared_ptr.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
snapset_contexts_locks is added and locked in each function where
snapset_contexts or the SnapSetContext::ref data member needs to be
accessed or modified.
http://tracker.ceph.com/issues/5510 refs #5510
Signed-off-by: Loic Dachary <loic@dachary.org>
