The lifetime of a mle is limited to the duration of the lockres mastery
process. While typically this lifetime is fairly short, we have noticed
the number of mles explode under certain circumstances. This patch tracks
the number of each different types of mles and should help us determine
how best to speed up the mastery process.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
With this patch, the mles are stored in a hash and not a simple list.
This should improve the mle lookup time when the number of outstanding
masteries is large.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch adds code to create and destroy the dlm->master_hash.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
For master mle, the name it stored in the attached lockres in struct qstr.
For block and migration mle, the name is stored inline in struct dlm_lock_name.
This patch attempts to make struct dlm_lock_name look like a struct qstr. While
we could use struct qstr, we don't because we want to avoid having to malloc
and free the lockname string as the mle's lifetime is fairly short.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch encapsulates adding and removing of the mle from the
dlm->master_list. This patch is part of the series of patches that
converts the mle list to a mle hash.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch adds a new lock, dlm->tracking_lock, to protect adding/removing
lockres' to/from the dlm->tracking_list. We were previously using dlm->spinlock
for the same, but that proved inadequate as we could be freeing a lockres from
a context that did not hold that lock. As the new lock only protects this list,
we can explicitly take it when removing the lockres from the tracking list.
This bug was exposed when testing multiple processes concurrently flock() the
same file.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch moves some mle related definitions from dlmmaster.c
to dlmcommon.h. Future patches need these definitions to dump mle
debugging information.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.beckeroracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch dumps the dlm state (dlm_ctxt) into a debugfs file.
Useful for debugging.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch creates the debugfs directories that will hold the
files to be used to dump the dlm state.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch links all the lockres' to a tracking list in dlm_ctxt.
We will use this in an upcoming patch that will walk the entire
list and to dump the lockres states to a debugfs file.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This patch makes the o2dlm allocate memory for lockres, lockname and lock
structures from slabcaches rather than kmalloc. This allows us to not only
make these allocs more efficient but also allows us to track the memory being
consumed by these structures.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
During migration, the recovery master node may be asked to master a lockres
it may not know about. In that case, it would not only have to create a
lockres and add it to the hash, but also remember to to do the _put_
corresponding to the kref_init in dlm_init_lockres(), as soon as the migration
is completed. Yes, we don't wait for the dlm_purge_lockres() to do that
matching put. Note the ref added for it being in the hash protects the lockres
from being freed prematurely.
This patch adds that missing put, as described above, to plug a memleak.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
struct dlm_query_join_packet is made up of four one-byte fields. They
are effectively in big-endian order already. However, little-endian
machines swap them before putting the packet on the wire (because
query_join's response is a status, and that status is treated as a u32
on the wire). Thus, a big-endian and little-endian machines will
treat this structure differently.
The solution is to have little-endian machines swap the structure when
converting from the structure to the u32 representation.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Currently, when ocfs2 nodes connect via TCP, they advertise their
compatibility level. If the versions do not match, two nodes cannot speak
to each other and they disconnect. As a result, this provides no forward or
backwards compatibility.
This patch implements a simple protocol negotiation at the dlm level by
introducing a major/minor version number scheme for entities that
communicate. Specifically, o2dlm has a major/minor version for interaction
with o2dlm on other nodes, and ocfs2 itself has a major/minor version for
interacting with the filesystem on other nodes.
This will allow rolling upgrades of ocfs2 clusters when changes to the
locking or network protocols can be done in a backwards compatible manner.
In those cases, only the minor number is changed and the negotatied protocol
minor is returned from dlm join. In the far less likely event that a
required protocol change makes backwards compatibility impossible, we simply
bump the major number.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
There is a small window where a joining node may not see the node(s) that
just died but are still part of the domain. To fix this, we must disallow
join requests if the joining node has a different node map.
A new field node_map is added to dlm_query_join_request to send the current
nodes nodemap along with join request. On the receiving end the nodes that
are part of the cluster verifies if this new node sees all the nodes that
are still part of the cluster. They disallow the join if the maps mismatch.
Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Eventhough the set refmap bit message is sent before the clear refmap
message, currently there is no guarentee that the set message will be
handled before the clear. This patch prevents the clear refmap to be
processed while the node is sending assert master messages to other
nodes. (The set refmap message is sent as a response to the assert
master request).
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This patch prevents the dlm from sending the clear refmap message
before the set refmap. We use the newly created post function handler
routine to accomplish the task.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Currently o2net allows one handler function per message type. This
patch adds the ability to call another function to be called after
the handler has returned the message to the other node.
Handlers are now given the option of returning a context (in the form of a
void **) which will be passed back into the post message handler function.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
dlmthread was removing lockres' from the dirty list
and resetting the dirty flag before shuffling the list.
This patch retains the dirty state flag until the lists
are shuffled.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Sunil Mushran <Sunil.Mushran@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This patch makes some needlessly global functions static.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This was previously broken and migration of some locks had to be temporarily
disabled. We use a new (and backward-incompatible) set of network messages
to account for all references to a lock resources held across the cluster.
once these are all freed, the master node may then free the lock resource
memory once its local references are dropped.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
The OCFS2 DLM uses strlen() to determine lock name length, which excludes
the possibility of putting binary values in the name string. Fix this by
requiring that string length be passed in as a parameter.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
dlm_lockres_master_requery() became global without any external usage.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
The work that is done can block for long periods of time and so is not
appropriate for keventd.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Makes it easier for the recovery process to deal with node death.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Take a reference on lockres structures while they are on the recovery list.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
The check for an empty lvb should check the entire buffer not just the first
byte.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
The OCFS2 DLM allocates a number of pages for a hash to lookup locks.
There was a bug where a PAGE_SIZE bigger than the hash size (eg, 64K
pages) would result in zero pages allocated.
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
This allows us to have a hash table greater than a single page which greatly
improves dlm performance on some tests.
Signed-off-by: Daniel Phillips <phillips@google.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Gains us a bit of performance on loads which heavily hit the lockres hash.
Patch suggested by Daniel Phillips <phillips@google.com>.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
when starting lock mastery (excepting the recovery lock) wait on any nodes
needing recovery. fix one instance where lock resources were left attached
to the recovery list after recovery completed. ensure that the node_down
code is run uniformly regardless of which node found the dead node first.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Switch from list_head to hlist_head. Make the size of the hash dependent
upon the allocated area, rather than a constant.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
* add dlm_wait_for_node_death function to be used after receiving a network
error. this will wait for the given timeout to allow the heartbeat
callbacks to update the domain map. without this, some paths may spin
and consume enough cpu that the heartbeat gets starved and never updates.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
* fix a hang which can occur during shutdown migration
* do not allow nodes to join during recovery
* when restarting lock mastery, do not ignore nodes which come up
* more than one node could become recovery master, fix this
* sleep to allow some time for heartbeat state to catch up to network
* extra debug info for bad recovery state problems
* make DLM_RECO_NODE_DATA_DONE a valid state for non-master recovery nodes
* prune all locks from dead nodes on $RECOVERY lock resources
* do NOT automatically add new nodes to mle nodemaps until they have properly
joined the domain
* make sure dlm_pick_recovery_master only exits when all nodes have synced
* properly handle dlmunlock errors in dlm_pick_recovery_master
* do not propagate network errors in dlm_send_begin_reco_message
* dead nodes were not being put in the recovery map sometimes, fix this
* dlmunlock was failing to clear the unlock actions on DLM_DENIED
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
A distributed lock manager built with the cluster file system use case
in mind. The OCFS2 dlm exposes a VMS style API, though things have
been simplified internally. The only lock levels implemented currently
are NLMODE, PRMODE and EXMODE.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Sunil Mushran