Lock Spin Wait Operation for Multi-Threaded Applications in a Multi-Core Computing Environment

• US 20150254113A1
• Filed: 03/05/2014
• Published: 09/10/2015
• Est. Priority Date: 03/05/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chiang, Men-Chow, Vu, Ken V.
• Granted Patent: US 9,378,069 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/526 Mutual exclusion algorithms

Abstract

A method, system and computer-usable medium are disclosed for a lock-spin-wait operation for managing multi-threaded applications in a multi-core computing environment. A target processor core, referred to as a “spin-wait core” (SAC), is assigned (or reserved) for primarily running spin-waiting threads. Threads operating in the multi-core computing environment that are identified as spin-waiting are then moved to a run queue associated with the SAC to acquire a lock. The spin-waiting threads are then allocated a lock response time that is less than the default lock response time of the operating system (OS) associated with the SAC. If a spin-waiting fails to acquire a lock within the allocated lock response time, the SAC is relinquished, ceding its availability for other spin-waiting threads in the run queue to acquire a lock. Once a spin-waiting thread acquires a lock, it is migrated to its original, or an available, processor core.

Claims

1. A computer-implemented method for managing multi-threaded applications in a multi-core computing system, comprising:

assigning a first processor core to manage spin waits in a multi-core system;

detecting a failure of a thread to acquire a lock on a second processor core, the failure to acquire a lock indicating that the thread is a first spin-waiting thread;

transferring the first spin-waiting thread to the first processor core to acquire a lock; and

allocating a lock response time for the first spin-waiting thread to acquire a lock from the first processor.

2. The method of claim 1, wherein the transferring comprises placing the first spin-waiting thread in a run queue associated with the first processor core, the run queue containing a second spin-waiting thread.

3. The method of claim 2, wherein the allocated lock-response time is less than the default lock response time of an operating system (OS) associated with the first processor core.

4. The method of claim 3, further comprising:

issuing an OS call to set a lock state, the OS call issued by the first spin-waiting thread and the lock state providing an indication of a lock acquisition failure by the first spin-waiting thread.

5. The method of claim 4, further comprising

relinquishing the first processor core to allow the second spin-waiting thread in the run queue to acquire a lock, the relinquishing of the first processor core performed after the OS call has been issued.

6. The method of claim 1, further comprising:

migrating the first spin-waiting thread to the second processor core subsequent to the first spin-waiting thread acquiring a lock from the first processor core.

7. A system comprising:

a processor;

a data bus coupled to the processor; and

a computer-usable medium embodying computer program code, the computer-usable medium being coupled to the data bus, the computer program code used for managing multi-threaded applications in a multi-core computing system and comprising instructions executable by the processor and configured for;

assigning a first processor core to manage spin waits in a multi-core system;

detecting a failure of a thread to acquire a lock on a second processor core, the failure to acquire a lock indicating that the thread is a first spin-waiting thread;

transferring the first spin-waiting thread to the first processor core to acquire a lock; and

allocating a lock response time for the first spin-waiting thread to acquire a lock from the first processor.

8. The system of claim 7, wherein the transferring comprises placing the first spin-waiting thread in a run queue associated with the first processor core, the run queue containing a second spin-waiting thread.

9. The system of claim 8, wherein the allocated lock-response time is less than the default lock response time of an operating system (OS) associated with the first processor core.

10. The system of claim 9, further comprising:

issuing an OS call to set a lock state, the OS call issued by the first spin-waiting thread and the lock state providing an indication of a lock acquisition failure by the first spin-waiting thread.

11. The system of claim 10, further comprising:

relinquishing the first processor core to allow the second spin-waiting thread in the run queue to acquire a lock, the relinquishing of the first processor core performed after the OS call has been issued.

12. The system of claim 7, further comprising:

migrating the first spin-waiting thread to the second processor core subsequent to the first spin-waiting thread acquiring a lock from the first processor core.

13. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:

assigning a first processor core to manage spin waits in a multi-core system;

detecting a failure of a thread to acquire a lock on a second processor core, the failure to acquire a lock indicating that the thread is a first spin-waiting thread;

transferring the first spin-waiting thread to the first processor core to acquire a lock; and

allocating a lock response time for the first spin-waiting thread to acquire a lock from the first processor.

14. The non-transitory, computer-readable storage medium of claim 13, wherein the transferring comprises placing the first spin-waiting thread in a run queue associated with the first processor core, the run queue containing a second spin-waiting thread.

15. The non-transitory, computer-readable storage medium of claim 14, wherein the allocated lock-response time is less than the default lock response time of an operating system (OS) associated with the first processor core.

16. The non-transitory, computer-readable storage medium of claim 15, further comprising:

issuing an OS call to set a lock state, the OS call issued by the first spin-waiting thread and the lock state providing an indication of a lock acquisition failure by the first spin-waiting thread.

17. The non-transitory, computer-readable storage medium of claim 16, further comprising:

relinquishing the first processor core to allow the second spin-waiting thread in the run queue to acquire a lock, the relinquishing of the first processor core performed after the OS call has been issued.

18. The non-transitory, computer-readable storage medium of claim 13, further comprising:

migrating the first spin-waiting thread to the second processor core subsequent to the first spin-waiting thread acquiring a lock from the first processor core.

19. The non-transitory, computer-readable storage medium of claim 13, wherein the computer executable instructions are deployable to a client system from a server system at a remote location.

20. The non-transitory, computer-readable storage medium of claim 13, wherein the computer executable instructions are provided by a service provider to a user on an on-demand basis.