Each monitor is independently encoding the full OSDMap and storing it in
its local store. Sometime this happens when we do not have a valid value
for quorum_features (for example, it can happen during sync).
Instead, use the feature bits the Incremental was encoded with for the full
OSDMap so that they always match.
Note that this conveniently the *only* place in the mon where we encode
the full OSDMap, so we're capturing all paths. Yay!
Signed-off-by: Sage Weil <sage@inktank.com>
The monitor will need to know what features the incremental was encoded
with so that it can encode the OSDMap using the same bits. Introduce a
member that is set during decode. During encode, encoding the value passed
in by the caller.
Signed-off-by: Sage Weil <sage@inktank.com>
and canonical name. Also fix the name "Deutsche Telekom"
Reviewed-by: Thomas Bechtold <t.bechtold@telekom.de>
Signed-off-by: Loic Dachary <loic@dachary.org>
Although this is not exactly the context in which ceph-disk is run when
invoked by udev, it makes sure there is at least one sensible way of
using it when PATH is undefined.
Also make src/ceph.in not fail if PATH is not defined.
Signed-off-by: Loic Dachary <loic@dachary.org>
Otherwise slow machines may timeout just because they are slow and not
because the process is blocked by an actual problem.
Signed-off-by: Loic Dachary <loic@dachary.org>
Maintain an internal xattr called "spill_out" that indicates whether we
(may) have xattrs stored in omap. If attribute is set, it will indicate
that we should or should not look in omap. If the attribute is not
present, then we do not know and will also need to check.
For new stores, this will avoid the overhead of consulting omap in the
general case until a particular objects gets enough (or big) xattrs and
spills over.
For old stores, we will effectively fall back to the previous behavior
of always checking.
Implements #7059
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
close_image() among other things unregisters a watcher that's been
registered by open_image(). Even though it'll timeout in 30 or so
seconds, it's not nice now that we check for watchers before starting
the removal process.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Check for watchers before trimming image data to try to avoid getting
into the following situation:
- user does 'rbd rm' on a mapped image with an fs mounted from it
- 'rbd rm' trims (removes) all image data, only header is left
- 'rbd rm' tries to remove a header and fails because krbd has a
watcher registered on the header
- at this point image cannot be unmapped because of the mounted fs
- fs cannot be unmounted because all its data and metadata is gone
Unfortunately, this fix doesn't make it impossible to happen (the
required atomicity isn't there), but it's a big improvement over the
status quo.
Fixes: http://tracker.ceph.com/issues/7076
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Commit b28b64a0b6 ("pybind: use find_library for libcephfs and
librbd") switched us to find_library(), but this function doesn't seem
to respect LD_LIBRARY_PATH. There are numerous python tickets, dating
back several years, but alas. Work around it by using the soname as
a fallback. (rados.py has been fixed by commit e46d2ca067 ("fix the
bug ctypes.util.find_library to search for librados failed on
Centos6.4.")
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Via gtest's value-parameterized feature, let the successors of
ObjectStore share the same unit tests.
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
KeyValueStore is another ObjectStore implementation with FileStore. It
uses KV store wrapper(StripObjectMap) which inherited GenericObjectMap
to implement ObjectStore APIs.
Each object has a header key in KV backend, which encapsulated the metadata
of object such as size, the status of keys. A complete object data maybe spread
around multi keys. The CRUD operation of object need to access the header key
of object to know the details, then the actual data keys will be get.
Now the actual KV backend of KeyValueStore is only LevelDB, more KV backend
(RocksDB, NVM API) will be introduced in the near future.
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Now we already have DBObjectMap which implement ObjectMap and other
interfaces, and ObjectMap.h implied that ObjectMap is used to encapsulates
the FileStore key value store. There exists limitation in current DBObjectMap
implementation, such as lacking of "coll_t" in "key", complicated prefix
hard-coded and inflexible extending.
So in order to provide a more flexible API and clear implementation to wrap KV
store, I copy the origin DBObjectMap and redesign the partial implementation.
Adding "coll_t" argument to all API and export "prefix" to callers. Prefixes
are divided into two parts "INTERN" and "USER". "INTERN" keys used by self to
manage and "USER" keys are managed by callers. Besides above, misc fixes are
imported such as more clear member function name and extendible header
structure.
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
