Conditional message delivery to holder of locks relating to a distributed locking manager
A method of and system for managing storage resources in a distributed file system is described. A lock for a storage resource is maintained on a lock-holding node. A master node that controls the lock-holding node receives a lock request from a requesting node. The lock request includes a request to obtain a lock for the storage resource, and a request to perform an action by the lock-holding node on the storage resource if the request to obtain the lock is not granted immediately.
1. A method of managing storage resources in a distributed file system, the method comprising:
a) maintaining a first lock for a storage resource using a lock holder; and
b) receiving, at a master node that manages said lock-holder, a lock request from a requesting node, wherein said lock request includes:
b-i) a request to obtain a second lock for said storage resource, and
b-ii) a request for a node to perform an action on said storage resource, wherein said lock holder resides on said node.
2. The method of claim 1 , wherein the master node performs:
granting said second lock to said requesting node in response to said lock request in accordance with a mutual exclusion requirement of said first and second locks.
3. The method of claim 1 , further comprising:
calculating a cost of releasing said first lock; and
calculating a cost of performing said requested action.
4. The method of claim 3 , further comprising:
releasing said first lock if said cost of releasing said first lock is less than said cost of performing said requested action.
5. The method of claim 4 , further comprising:
maintaining said first lock if said cost of performing said requested action is less than said cost of releasing said first lock.
6. The method of claim 5 , further comprising:
performing said requested action without releasing said first lock.
7. The method of claim 1 , further comprising:
identifying a node that accesses said resource most frequently; and
designating said identified node as said master node.
8. A system of clustered nodes that includes a file system for managing storage resources of the cluster, the system comprising:
a lock-holding node on which a first lock for a storage resource resides;
a lock-requesting node from which a lock request to release said lock is initiated; and
a master-lock node configured to receive said lock request from said lock-requesting node, wherein said lock request includes:
a) a request to obtain a second lock for said storage resource, and
b) a request for said lock-holding node to perform an action on said storage resource.
9. The system of claim 8 , wherein said lock-holding node is configured to initiate calculations for determining a cost of releasing said first lock and a cost of performing said requested action.
10. The system of claim 9 , wherein said lock-holding node is further configured to cause said first lock to be released from said lock-holding node if said cost of releasing said first lock is less than said cost of performing said requested action.
11. The system of claim 9 , wherein said lock-holding node is further configured to cause said first lock to be maintained on said lock-holding node if said cost of performing said requested action is less than said cost of releasing said first lock.
12. The system of claim 8 , wherein said master-lock node is configured to initiate calculations for determining a cost of releasing said first lock and a cost of performing said requested action.
13. The system of claim 12 , wherein said master-lock node is further configured to cause said first lock to be released from said lock-holding node if said cost of releasing said first lock is less than said cost of performing said requested action.
14. The system of claim 12 , wherein said master-lock node is further configured to cause said first lock to be maintained on said lock-holding node if said cost of performing said requested action is less than said cost of releasing said first lock.
15. The system of claim 9 , further comprising a distributed lock manager configured to identify a node that accesses said resource most frequently and to designate said identified node as said master node.
16. The system of claim 9 , wherein said lock-holding node is configured to perform said action without releasing said first lock.
17. A computer program product, residing on a computer-readable storage medium, the computer program product comprising computer instructions for configuring a computer to perform the acts of:
a) maintaining a first lock for a storage resource using a lock-holder; and
b) receiving, at a master node that controls said lock-holder, a lock request from a requesting node, wherein said lock request includes:
b-i) a request to obtain a second lock for said storage resource, and
b-ii) a request for a node to perform an action on said storage resource, wherein said lock holder resides on said node.
18. The storage medium of claim 17 , further comprising instructions to configure said master node to:
grant said second lock to said requesting node in response to said lock request in accordance with a mutual exclusion requirement of said first and second locks.
19. The storage medium of claim 17 , further comprising instructions for performing the acts of:
calculating an amount of input/output operations required to release said first lock;
calculating a frequency of said lock-holding node using said storage resource; and
calculating a cost of performing said requested action.
20. The storage medium of claim 19 , further comprising instructions for performing the act of:
releasing said first lock if said cost of releasing said first lock is lower than said cost of performing said requested action.
21. The storage medium of claim 19 , further comprising instructions for performing the act of:
maintaining said first lock if said cost of performing said requested action is lower than said cost of releasing said first lock.