Yan, Zheng [Fri, 15 Mar 2013 02:34:09 +0000 (10:34 +0800)]
mds: don't send MDentry{Link,Unlink} before receiving cache rejoin
The active MDS calls MDCache::rejoin_scour_survivor_replicas() when it
receives the cache rejoin message. The function will remove the objects
replicated by MDentry{Link,Unlink} from replica map.
Yan, Zheng [Thu, 14 Mar 2013 16:08:39 +0000 (00:08 +0800)]
mds: set resolve/rejoin gather MDS set in advance
For active MDS, it may receive resolve/rejoin message before receiving
the mdsmap message that claims the MDS cluster is in resolving/rejoning
state. So instead of set the gather MDS set when receiving the mdsmap.
set them in advance when detecting MDS' failure.
Yan, Zheng [Thu, 14 Mar 2013 04:27:51 +0000 (12:27 +0800)]
mds: don't send resolve message between active MDS
When MDS cluster is resolving, current behavior is sending subtree resolve
message to all other MDS and waiting for all other MDS' resolve message.
The problem is that active MDS can have diffent subtree map due to rename.
Besides gathering active MDS's resolve messages are also racy. The only
function for these messages is disambiguate other MDS' import. We can
replace it by import finish notification.
Yan, Zheng [Wed, 13 Mar 2013 02:28:58 +0000 (10:28 +0800)]
mds: unify slave request waiting
When requesting remote xlock or remote wrlock, the master request is
put into lock object's REMOTEXLOCK waiting queue. The problem is that
remote wrlock's target can be different from lock's auth MDS. When
the lock's auth MDS recovers, MDCache::handle_mds_recovery() may wake
incorrect request. So just unify slave request waiting, dispatch the
master request when receiving slave request reply.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Reviewed-by: Sage Weil <sage@inktank.com>
Yan, Zheng [Tue, 12 Mar 2013 12:24:52 +0000 (20:24 +0800)]
mds: defer eval gather locks when removing replica
Locks' states should not change between composing the cache rejoin ack
messages and sending the message. If Locker::eval_gather() is called
in MDCache::{inode,dentry}_remove_replica(), it may wake requests and
change locks' states.
Yan, Zheng [Sat, 16 Mar 2013 00:02:18 +0000 (08:02 +0800)]
mds: make sure table request id unique
When a MDS becomes active, the table server re-sends 'agree' messages
for old prepared request. If the recoverd MDS starts a new table request
at the same time, The new request's ID can happen to be the same as old
prepared request's ID, because current table client code assigns request
ID from zero after MDS restarts.
This patch make table server send 'ready' messages when table clients
become active or itself becomes active. The 'ready' message updates
table client's last_reqid to avoid request ID collision. The message
also replaces the roles of finish_recovery() and handle_mds_recovery()
callbacks for table client.
Yan, Zheng [Tue, 12 Mar 2013 11:41:13 +0000 (19:41 +0800)]
mds: fix MDCache::adjust_bounded_subtree_auth()
There are cases that need both create new bound and swallow intervening
subtree. For example: A MDS exports subtree A with bound B and imports
subtree B with bound C at the same time. The MDS crashes, exporting
subtree A fails, but importing subtree B succeed. During recovery, the
MDS may create new bound C and swallow subtree B.
Yan, Zheng [Thu, 31 Jan 2013 02:07:35 +0000 (10:07 +0800)]
mds: process finished contexts in batch
If there are several unstable locks in an inode, current Locker::eval(CInode*,)
processes each lock's finished contexts seperately. This may cause very deep
call stack if finished contexts also call Locker::eval() on the same inode.
An extreme example is:
Locker::eval() wakes an open request(). Server::handle_client_open() starts
a log entry, then call Locker::issue_new_caps(). Locker::issue_new_caps()
calls Locker::eval() and wakes another request. The later request also tries
starting a log entry.
Yan, Zheng [Thu, 31 Jan 2013 02:37:11 +0000 (10:37 +0800)]
mds: preserve subtree bounds until slave commit
When replaying an operation that rename a directory inode to non-auth subtree,
if the inode has subtree bounds, we should prevent them from being trimmed
until slave commit.
This patch also fixes a bug in ESlaveUpdate::replay(). EMetaBlob::replay()
should be called before MDCache::finish_uncommitted_slave_update().
Loic Dachary [Sat, 30 Mar 2013 10:26:12 +0000 (11:26 +0100)]
fix null character in object name triggering segfault
Parsing \n in lfn_parse_object_name is implemented with
out->append('\0');
which segfaults when using libstdc++ and g++ version 4.6.3 on Debian
GNU/Linux. It is replaced with
(*out) += '\0';
to avoid the bugous implicit conversion. There is no append(charT)
method in C++98 or C++11, which means it relies on an implicit
conversion that is bugous. It would be better to rely on the
basic_string& operator+=(charT c); method as defined in ISO 14882-1998
(page 385) thru ISO 14882-2012 (page 640)
A set of tests is added to generate and parse object names. They need
access to the private function lfn_parse_object_name because there is
no convenient protected method to exercise it. The tests contain a
LFNIndex derived class, TestWrapLFNIndex which is made a friend of
LFNIndex to gain access to the private methods.
Loic Dachary [Thu, 28 Mar 2013 12:38:09 +0000 (13:38 +0100)]
unit test LFNIndex::remove_object and LFNIndex::lfn_unlink
When the object name is short, check that the corresponding file is
::unlink()ed. When the object name is long, there may be multiple files
with the same name, modulo the anti-collision number showing just before
the FILENAME_COOKIE. The following scenarii are tested:
* there only is one file
* there are multiple files and the last one is removed
* there are multiple files and the last one is moved in place of the
file that is to be removed
lfn_unlink and remove_object are tested together because
lfn_unlink is a private function and remove_object is a protected function
that does very little beside calling lfn_unlink
mon: ConfigKeyService: stash config keys on the monitor
Building up on the Single-Paxos and our existing k/v store that backs
the monitor, we now introduce a simple service so that the monitors
act as a generic k/v store available to the cluster, in which a user
can stash (and later obtain) configuration keys at his own discretion.
Users can put, get, delete, list and check for values using the
following commands:
- ceph config-key put <key> [<value>]
or
- ceph config-key put <key> [-i <in-file>]
with 'value' and 'in-file' being optional; if these are not specified,
'put' will act as 'touch' if 'key' does not exist, or will overwrite
the value of 'key' with a zero byte value (i.e., truncates the
contents of the value to zero)
- ceph config-key get <key>
or
- ceph config-key get <key> -o <out-file>
- ceph config-key delete <key>
- ceph config-key list [-o <out-file]
- ceph config-key exists <key>
Fixes: #4313 Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Gary Lowell [Thu, 28 Mar 2013 23:12:33 +0000 (16:12 -0700)]
ceph.spec.in: Move four scripts from sbin to usr/bin
The ceph-create-keys, ceph-disk, ceph-disk-activate, and
ceph-disk-prepare scripts are built in sbin, but debian installs
them into usr/bin, and several utilities look for them there.
This commit changes the RPM to install them in /usr/bin. (Bug #3921)
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
ceph: propagate do_command()'s return value to user space
We were returning '1' regardless of what do_command() returned in case
of error. This would make building tools relying on command error codes
short of useless, and forced them to rely instead on error messages.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit e91405d540ce11b9996e4977212553bd33afb3ed)
ceph: propagate do_command()'s return value to user space
We were returning '1' regardless of what do_command() returned in case
of error. This would make building tools relying on command error codes
short of useless, and forced them to rely instead on error messages.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com>
Josh Durgin [Thu, 21 Mar 2013 23:04:10 +0000 (16:04 -0700)]
librbd: add an async flush
At this point it's a simple wrapper around the ObjectCacher or
librados.
This is needed for QEMU so that its main thread can continue while a
flush is occurring. Since this will be backported, don't update the
librbd version yet, just add a #define that QEMU and others can use to
detect the presence of aio_flush().
Josh Durgin [Wed, 27 Mar 2013 22:42:10 +0000 (15:42 -0700)]
librbd: use the same IoCtx for each request
Before we were duplicating the IoCtx for each new request since they
could have a different snapshot context or read from a different
snapshot id. Since librados now supports setting these explicitly
for a given request, do that instead.
Since librados tracks outstanding requests on a per-IoCtx basis, this
also fixes a bug that causes flush() without caching to ignore
all the outstanding requests, since they were to separate,
duplicate IoCtxs.
Josh Durgin [Wed, 27 Mar 2013 22:32:29 +0000 (15:32 -0700)]
librados: add versions of a couple functions taking explicit snap args
Usually the snapid to read from or the snapcontext to send with a write
are determined implicitly by the IoCtx the operations are done on.
This makes it difficult to have multiple ops in flight to the same
IoCtx using different snapcontexts or reading from different snapshots,
particularly when more than one operation may be needed past the initial
scheduling.
Add versions of aio_read, aio_sparse_read, and aio_operate
that don't depend on the snap id or snapcontext stored in the IoCtx,
but get them from the caller. Specifying this information for each
operation can be a more useful interface in general, but for now just
add it for the methods used by librbd.
Josh Durgin [Thu, 28 Mar 2013 17:34:37 +0000 (10:34 -0700)]
ObjectCacher: remove unneeded var from flush_set()
The gather will only have subs if there is something to flush. Remove
the safe variable, which indicates the same thing, and convert the
conditionals that used it to an else branch. Movinig gather.activate()
inside the has_subs() check has no effect since activate() does
nothing when there are no subs.
This removes the last remnants of b5e9995f59d363ba00d9cac413d9b754ee44e370. If there's nothing to flush,
immediately call the callback instead of deleting it. Callers were
assuming they were responsible for completing the callback whenever
flush_set() returned true, and always called complete(0) in this
case. Simplify the interface and just do this in flush_set(), so that
it always calls the callback.
Since C_GatherBuilder deletes its finisher if there are no subs,
only set its finisher when subs are present. This way we can still
call ->complete() for the callback.
Josh Durgin [Wed, 13 Mar 2013 16:37:21 +0000 (09:37 -0700)]
ObjectCacher: optionally make writex always non-blocking
Add a callback argument to writex, and a finisher to run the
callbacks. Move the check for dirty+tx > max_dirty into a helper that
can be called from a wrapper around the callbacks from writex, or from
the current place in _wait_for_write().
Loic Dachary [Wed, 27 Mar 2013 20:02:57 +0000 (16:02 -0400)]
unit test LFNIndex::lfn_get_name
The escape logic is tested for
* leading . => \.
* / => \s
* \ => \\
* leading DIR_ => \d
The file names for small object names ( size < FILENAME_PREFIX_LEN )
are created with CEPH_NOSNAP and checked to contain the _head string
and not the _long string.
The file names for long object names ( size >= FILENAME_PREFIX_LEN )
are tested to contain the _long string. A matching file is created to
check that it is removed unless it contains the expected extended
attribute.
If the SHA1 of two long object names collide and they have the same
prefix, lfn_get_name increments an anticollision counter to
differentiate them. This condition is engineered because it would be
really difficult to find two long names that actually create such a
collision.
The lfn_get_name method is private and the get_mangled_name method is
used to access it. The out_path argument is not available and cannot
be tested. However it is a trivial concatenation of the stringsin the
path vector.
A TestIndex class is derived from the LFNIndex class to set the pure
virtual functions. The TestLFNIndex fixture is derived from it so that
the tests get access to the protected methods of LFNIndex
The SetUp method of the fixture creates a PATH directory to be used by
all tests as the base path for all object files.
Josh Durgin [Thu, 28 Mar 2013 00:30:42 +0000 (17:30 -0700)]
librbd: flush cache when set_snap() is called
If there are writes pending, they should be sent while the image
is still writeable. If the image becomes read-only, flushing the
cache will just mark everything dirty again due to -EROFS.
Sage Weil [Thu, 28 Mar 2013 01:43:59 +0000 (18:43 -0700)]
ceph-disk: reimplement is_partition
Previously we were assuming any device that ended in a digit was a
partition, but this is not at all correct (e.g., /dev/sr0, /dev/rbd1).
Instead, look in /dev/disk/by-id and see if there is a symlink that ends in
-partNN that links to our device.
projects / ceph.git / log