Moveable distributed synchronization objects

• US 10,623,487 B2
• Filed: 01/11/2017
• Issued: 04/14/2020
• Est. Priority Date: 01/11/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Krauss, Kirk J.
• Primary Examiner(s): Parry, Chris
• Assistant Examiner(s): Nguyen, Steven C
• Application Number:
  US15/403,312
• Publication Number:
  US 20180198731A1
• Time in Patent Office: 1,189 Days
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes

Abstract

A resource sharing method, system, and computer program product in a distributed computing environment, includes in response to a first condition, determining a first node on which an access rate of a synchronization object is greatest, storing the synchronization object on the first node for use in synchronizing access to a resource, and in response to a second condition, determining a second node on which an access rate of the synchronization object is greatest, and relocating the synchronization object from a storage on the first node to a storage on the second node.

Claims

1. A computer-implemented resource sharing method in a distributed computing environment, the method comprising:

in response to a first condition, determining a first node in the distributed computing environment on which an access rate of a synchronization object is greatest;

storing the synchronization object on the first node, for use in synchronizing access to a resource;

in response to a second condition, determining a second node in the distributed computing environment on which an access rate of the synchronization object is greatest; and

relocating, as a lock move, the synchronization object from a storage on the first node to a storage on the second node,

wherein a profile based lock placement and the lock move is used on the first node and the second node,

wherein the profile includes the lock placement and the lock move and usage of the lock in a pool that extends across all nodes in the distributed computing environment,

wherein the lock move is not moved when the synchronization object is being used to protect the resource,

wherein the node on which the access rate of the synchronization object is greatest is determined by an analysis of profiling results, and

wherein the node on which the access rate of the synchronization object is greatest is determined by a speculative code analysis or execution.

2. The computer-implemented method of claim 1, wherein the first condition comprises a beginning of a run and a second condition comprises an entry of a routine, and

wherein the second condition comprises a relocation of a resource as the lock move from the first node to the second node.

3. The computer-implemented method of claim 2, wherein the routine is resident on the second node and the relocating of the synchronization object from the first node to the second node is performed in response to entering the routine.

4. The computer-implemented method of claim 1, wherein the relocating the synchronization object from the storage on the first node to the storage on the second node comprises invalidating an instance of the synchronization object on the first node and validating a pre-existing instance of the synchronization object on the second node.

5. The computer-implemented method of claim 1, wherein a status of the lock placement is cached by each node in the distributed computing environment on which the lock is not resident.

6. The computer-implemented method of claim 1, wherein the lock protects the resource by serializing access to the resource.

7. A computer program product for resource sharing, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform:

in response to a first condition, determining a first node in the distributed computing environment on which an access rate of a synchronization object is greatest;

storing the synchronization object on the first node, for use in synchronizing access to a resource;

in response to a second condition, determining a second node in the distributed computing environment on which an access rate of the synchronization object is greatest; and

relocating, as a lock move, the synchronization object from a storage on the first node to a storage on the second node,

wherein a profile based lock placement and the lock move is used on the first node and the second node,

wherein the profile includes the lock placement and the lock move and usage of the lock in a pool that extends across all nodes in the distributed computing environment,

wherein the lock move is not moved when the synchronization object is being used to protect the resource,

wherein the node on which the access rate of synchronization object is greatest is determined by an analysis of profiling results, and

wherein the node on which the access rate of the synchronization object is greatest is determined by a speculative code analysis or execution.

8. The computer program product of claim 7, wherein the first condition comprises a beginning of a run and a second condition comprises an entry of a routine.

9. The computer program product of claim 8, wherein the routine is resident on the second node and the relocating of the synchronization object from the first node to the second node is performed in response to entering the routine.

10. The computer program product of claim 7, wherein the relocating the synchronization object from the storage on the first node to the storage on the second node comprises invalidating an instance of the synchronization object on the first node and validating a pre-existing instance of the synchronization object on the second node.

11. A resource sharing system, said system comprising:

a processor; and

a memory, the memory storing instructions to cause the processor to perform;

in response to a first condition, determining a first node in the distributed computing environment on which an access rate of a synchronization object is greatest;

storing the synchronization object on the first node, for use in synchronizing access to a resource;

in response to a second condition, determining a second node in the distributed computing environment on which an access rate of the synchronization object is greatest; and

relocating, as a lock move, the synchronization object from a storage on the first node to a storage on the second node,

wherein a profile based lock placement and the lock move is used on the first node and the second node,

wherein the profile includes the lock placement and the lock move and usage of the lock in a pool that extends across all nodes in the distributed computing environment,

wherein the lock move is not moved when the synchronization object is being used to protect the resource,

wherein the node on which the access rate of the synchronization object is greatest is determined by an analysis of profiling results, and

wherein the node on which the access rate of the synchronization object is greatest is determined by a speculative code analysis or execution.

12. The system of claim 11, wherein the first condition comprises a beginning of a run and a second condition comprises an entry of a routine.

13. The system of claim 12, wherein the routine is resident on the second node and the relocating of the synchronization object from the first node to the second node is performed in response to entering the routine.

14. The system of claim 11, wherein the relocating the synchronization object from the storage on the first node to the storage on the second node comprises invalidating an instance of the synchronization object on the first node and validating a pre-existing instance of the synchronization object on the second node.

15. The system of claim 11, embodied in a cloud-computing environment.