System, apparatus and method of enhancing priority boosting of scheduled threads

• US 7,676,809 B2
• Filed: 10/09/2003
• Issued: 03/09/2010
• Est. Priority Date: 10/09/2003
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Vaidyanathan, Basu, Brenner, Larry Bert
• Primary Examiner(s): Jalil; Neveen Abel
• Assistant Examiner(s): Syed; Farhan M
• Application Number:
  US10/682,387
• Publication Number:
  US 20050080824A1
• Time in Patent Office: 2,343 Days
• Field of Search: 711/100, 718/100
• US Class Current: 718/103
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/524 Deadlock detection or avoidance

Abstract

A system, apparatus and method of enhancing priority boosting of scheduled threads are provided. If, while being executed by a second CPU, a second thread determines that it has to wait for a lock on a shared resource held by a first thread that is scheduled to be executed by a first CPU, the second thread may boost the priority of the first thread by passing its priority to the first thread if its priority is higher than the first thread'"'"'s priority. Further, to enhance the priority boost of the first thread, the second thread may reschedule the first thread to be processed by the second CPU. By having been rescheduled on the second CPU, the second thread may be dispatched for execution right thereafter.

Claims

1. A method of enhancing priority boosting of scheduled threads comprising the steps of:

determining by a second thread being executed on a second CPU whether to wait for a lock on a shared resource held by a first thread that is scheduled to be executed by a first CPU, the second thread having a higher priority than the first thread;

boosting the priority of the first thread by passing the higher priority of the second thread to the first thread if the second thread has to wait for the lock on the shared thread; and

enhancing the priority boosting of the first thread by rescheduling the first thread to run on the second CPU.

2. The method of claim 1 wherein when the priority boosting of the first thread is enhanced, the first thread becomes the next thread to be dispatched for execution.

3. The method of claim 2 wherein after the priority boosting of the first thread has been enhanced, the second thread relinquishes the second CPU by going to sleep awaiting the release of the lock by the first thread.

4. The method of claim 3 wherein after the first thread has released the lock, the second thread is awakened and rescheduled for execution by the second CPU.

5. The method of claim 4 wherein after being rescheduled for execution by the second CPU, the second thread is likely the next thread to be dispatched for execution.

6. A computer program product on a computer readable medium for enhancing priority boosting of scheduled threads comprising:

code means for determining by a second thread being executed on a second CPU whether to wait for a lock on a shared resource held by a first thread that is scheduled to be executed by a first CPU, the second thread having a higher priority than the first thread;

code means for boosting the priority of the first thread by passing the higher priority of the second thread to the first thread if the second thread has to wait for the lock on the shared thread; and

code means for enhancing the priority boosting of the first thread by rescheduling the first thread to run on the second CPU.

7. The computer program product of claim 6 wherein when the priority boosting of the first thread is enhanced, the first thread becomes the next thread to be dispatched for execution.

8. The computer program product of claim 7 wherein after the priority boosting of the first thread has been enhanced, the second thread relinquishes the second CPU by going to sleep awaiting the release of the lock by the first thread.

9. The computer program product of claim 8 wherein after the first thread has released the lock, the second thread is awakened and rescheduled for execution by the second CPU.

10. The computer program product of claim 9 wherein after being rescheduled for execution by the second CPU, the second thread is likely the next thread to be dispatched for execution.

11. An apparatus for enhancing priority boosting of scheduled threads comprising:

means for determining by a second thread being executed on a second CPU whether to wait for a lock on a shared resource held by a first thread that is scheduled to be executed by a first CPU, the second thread having a higher priority than the first thread;

means for boosting the priority of the first thread by passing the higher priority of the second thread to the first thread if the second thread has to wait for the lock on the shared thread; and

means for enhancing the priority boosting of the first thread by rescheduling the first thread to run on the second CPU.

12. The apparatus of claim 11 wherein when the priority boosting of the first thread is enhanced, the first thread becomes the next thread to be dispatched for execution.

13. The apparatus of claim 12 wherein after the priority boosting of the first thread has been enhanced, the second thread relinquishes the second CPU by going to sleep awaiting the release of the lock by the first thread.

14. The apparatus of claim 13 wherein after the first thread has released the lock, the second thread is awakened and rescheduled for execution by the second CPU.

15. The apparatus of claim 14 wherein after being rescheduled for execution by the second CPU, the second thread is likely the next thread to be dispatched for execution.

16. A system for enhancing priority boosting of scheduled threads comprising:

at least one storage device for storing code data; and

at least two CPUs, one of the at least two CPUs for processing the code data to determine by a second thread being executed on the at least one CPU whether to wait for a lock on a shared resource held by a first thread that is scheduled to be executed by the other CPU, the second thread having a higher priority than the first thread, to boost the priority of the first thread by passing the higher priority of the second thread to the first thread if the second thread has to wait for the lock on the shared thread, and to enhance the priority boosting of the first thread by rescheduling the first thread to run on the second CPU.

17. The system of claim 16 wherein when the priority boosting of the first thread is enhanced, the first thread becomes the next thread to be dispatched for execution.

18. The system of claim 17 wherein after the priority boosting of the first thread has been enhanced, the second thread relinquishes the second CPU by going to sleep awaiting the release of the lock by the first thread.

19. The system of claim 18 wherein after the first thread has released the lock, the second thread is awakened and rescheduled for execution by the second CPU.

20. The system of claim 19 wherein after being rescheduled for execution by the second CPU, the second thread is likely the next thread to be dispatched for execution.