Decoupling a central processing unit from its tasks

• US 20060150187A1
• Filed: 01/06/2005
• Published: 07/06/2006
• Est. Priority Date: 01/06/2005
• Status: Active Grant

• Current Assignee: Twitter Inc (X Holdings Corp.)
• Original Assignee: International Business Machines Corporation
• Inventors: Vaddagiri, Srivatsa
• Granted Patent: US 7,739,685 B2
• Time in Patent Office: Days
• US Class Current: 718/102
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system

Abstract

A method and system for decoupling a central processing unit (CPU) of a plurality of hot CPUs from its assigned tasks. The hot CPUs are managed by an operating system of a computer system. A special flag is set, denoting that the CPU is to be decoupled from its assigned tasks. A special task coupled to the CPU is given a suitable scheduling policy and priority, wherein the special task gets enough continuous execution time to finish its job before another task executes on the CPU. The special task examines the special flag and decouples the first CPU from its assigned tasks after determining that the special flag has been set, wherein the special task does not relinquish control of the CPU. The decoupling of tasks from the CPU leaves at least one remaining CPU and occurs while the at least one remaining CPU is hot.

Claims

1. A method for decoupling a first central processing unit (CPU) from its assigned tasks, said method comprising the steps of:

setting a special flag denoting that a first CPU is to be decoupled from its assigned tasks, said first CPU being comprised by a plurality of hot CPUs within a computer system, said hot CPUs being managed by an operating system of the computer system;

setting a suitable scheduling policy and priority for a first special task coupled to the first CPU, the suitable policy and priority so chosen that the first special task gets enough continuous execution time to finish its job, said continuous execution time being defined as the amount of time allotted to a task for execution on a CPU, before another task is made to execute on the CPU;

adding the first special task in a runqueue of the first CPU; and

executing the first special task on the first CPU, said executing the first special task including examining the special flag and decoupling the first CPU from its assigned tasks after determining that the special flag has been set, said decoupling accomplished by having the first special task not relinquish control of the first CPU such that the first CPU is unable to execute any of its assigned tasks, said decoupling of tasks from the first CPU leaving at least one remaining CPU of the plurality of hot CPUs, said decoupling of tasks from the first CPU occurring while the at least one remaining CPU is hot.

2. The method of claim 1, wherein the first special task is an idle task coupled to the first CPU.

3. The method of claim 1, wherein the first special task is created specially for the purpose of decoupling first CPU from its assigned tasks.

4. The method of claim 1, wherein the step of setting a suitable scheduling policy and priority for the first special task comprises the steps of:

coupling a second special task to some CPU, said some CPU being any CPU of the plurality of hot CPUs, said second special task having the highest scheduling priority and suitable scheduling policy that results in the second special task becoming a highest prioritized task on the runqueue of said some CPU; and

executing the second special task on said some CPU, including setting a suitable scheduling policy and priority for the first special task coupled to first CPU.

5. The method of claim 1, wherein the step of setting the special flag is performed by the operating system.

6. The method of claim 1, wherein the step of setting a suitable scheduling policy and priority for the first special task comprises invoking a system command or system function with respect to the operating system.

7. The method of claim 1, said method further comprising after said decoupling the first CPU from its assigned tasks, migrating to the at least one remaining CPU the tasks decoupled from the first CPU.

8. The method of claim 1, wherein the computer system further comprises a scheduler code for scheduling execution of tasks on the plurality of hot CPUs, and wherein the scheduler code is not adapted to monitor the special flag.

9. The method of claim 1, wherein after decoupling the first CPU from its assigned tasks, said method further comprising not assigning any additional tasks and interrupts to the first CPU.

10. The method of claim 9, wherein after decoupling the first CPU from its assigned tasks, said method further comprising powering down the first CPU.

11. The method of claim 10, said method further comprising after powering down the first CPU:

adding a new CPU to the at least one remaining CPU to replace the first CPU such that the plurality of hot CPUs comprises the new CPU.

12. The method of claim 9, wherein the computer system further comprises a plurality of partitions and a hypervisor adapted to manage the plurality of partitions, wherein the plurality of partitions includes a first partition and a second partition, wherein the first partition comprises the plurality of hot CPUs, and wherein after decoupling the first CPU from its assigned tasks said method further comprises moving the first CPU from the first partition to the second partition.

13. The method of claim 12, wherein said moving the first CPU from the first partition to the second partition is performed without powering down the first partition and without powering down the second partition.

14. The method of claim 9, wherein the computer system further comprises a per-CPU resource coupled to each CPU of the plurality of hot CPUs, and wherein said method further comprises

disconnecting the per-CPU resource from the first CPU;

and

after said disconnecting, migrating to the at least one remaining CPU the per-CPU resource disconnected from the first CPU.

15. A computer system for decoupling a central processing unit (CPU) from its assigned tasks, said computer system comprising:

a plurality of hot CPUs including a first CPU, said hot CPUs being managed by an operating system of the computer system;

means for setting a special flag denoting that the first CPU is to be decoupled from its assigned tasks;

means for setting a suitable scheduling policy and priority for a first special task coupled to the first CPU, the suitable policy and priority so chosen that the first special task gets enough continuous execution time to finish its job, said continuous execution time being defined as the amount of time allotted to a task for execution on a CPU, before another task is made to execute on the CPU;

means for adding the first special task in a runqueue of the first CPU; and

means for executing the first special task on the first CPU to examine the special flag; and

means for decoupling the first CPU from its assigned tasks following a determination by the first CPU that the special flag has been set, subject to the first special task not relinquishing control of the first CPU and the first CPU being unable to execute any of its assigned tasks, and further subject to the decoupling of tasks from the first CPU leaving at least one remaining CPU of the plurality of hot CPUs and occurring while the at least one remaining CPU is hot.

16. The computer system of claim 15, wherein the first special task is an idle task coupled to the first CPU.

17. The computer system of claim 15, wherein the first special task is created specially for the purpose of decoupling first CPU from its assigned tasks.

18. The computer system of claim 15, wherein the means for setting a suitable scheduling policy and priority for the first special task comprises:

means for coupling a second special task to some CPU, said some CPU being any CPU of the plurality of hot CPUs, said second special task having the highest scheduling priority and suitable scheduling policy that results in the second special task becoming a highest prioritized task on the runqueue of said some CPU; and

means for executing the second special task on said some CPU, including means for setting a suitable scheduling policy and priority for the first special task coupled to first CPU.

19. The computer system of claim 15, wherein the means for setting a suitable scheduling policy and priority for the first special task comprises means for invoking a system command or system function with respect to the operating system.

20. The computer system of claim 15, further comprising means for migrating to the at least one remaining CPU the tasks decoupled from the first CPU after the first CPU has been decoupled from its assigned tasks.

21. The computer system of claim 15, further comprising a scheduler code for scheduling execution of tasks on the plurality of hot CPUs, and wherein the scheduler code is not adapted to monitor the special flag.

22. The computer system of claim 15, further comprising means for powering down the first CPU after decoupling the first CPU from its assigned tasks.

23. The computer system of claim 22, further comprising means for adding a new CPU to the at least one remaining CPU to replace the first CPU after the first CPU has been powered down following decoupling the first CPU from its assigned tasks.

24. The computer system of claim 15, further comprising a plurality of partitions and a hypervisor adapted to manage the plurality of partitions, wherein the plurality of partitions includes a first partition and a second partition, wherein the first partition comprises the plurality of hot CPUs, and wherein the computer system further comprises means for moving the first CPU from the first partition to the second partition after the first CPU has been decoupled from its assigned tasks.

25. The computer system of claim 24, wherein said means for moving the first CPU from the first partition to the second partition is subject to not powering down the first partition and is subject to not powering down the second partition.

26. The computer system of claim 15, further comprising:

a per-CPU resource coupled to each CPU of the plurality of hot CPUs;

means for disconnecting the per-CPU resource from the first CPU; and

means for migrating to the at least one remaining CPU the per-CPU resource disconnected from the first CPU.

27. A computer program product, comprising a computer usable medium having a computer readable program code embodied therein, said computer readable program code comprising an algorithm adapted to implement a method for decoupling a first central processing unit (CPU) from its assigned tasks, said method comprising the steps of:

setting a special flag denoting that a first CPU is to be decoupled from its assigned tasks, said first CPU being comprised by a plurality of hot CPUs within a computer system, said hot CPUs being managed by an operating system of the computer system;

setting a suitable scheduling policy and priority for a first special task coupled to the first CPU, the suitable policy and priority so chosen that the first special task gets enough continuous execution time to finish its job, said continuous execution time being defined as the amount of time allotted to a task for execution on a CPU, before another task is made to execute on the CPU;

adding the first special task in a runqueue of the first CPU; and

executing the first special task on the first CPU, said executing the first special task including examining the special flag and decoupling the first CPU from its assigned tasks after determining that the special flag has been set, said decoupling accomplished by having the first special task not relinquish control of the first CPU such that the first CPU is unable to execute any of its assigned tasks, said decoupling of tasks from the first CPU leaving at least one remaining CPU of the plurality of hot CPUs, said decoupling of tasks from the first CPU occurring while the at least one remaining CPU is hot.

28. The computer program product of claim 27, wherein the first special task is an idle task coupled to the first CPU.

29. The computer program product of claim 27, wherein the first special task is created specially for the purpose of decoupling first CPU from its assigned tasks.

30. The computer program product of claim 27, wherein the step of setting a suitable scheduling policy and priority for the first special task comprises the steps of:

coupling a second special task to some CPU, said some CPU being any CPU of the plurality of hot CPUs, said second special task having the highest scheduling priority and suitable scheduling policy that results in the second special task becoming a highest prioritized task on the runqueue of said some CPU; and

executing the second special task on said some CPU, including setting a suitable scheduling policy and priority for the first special task coupled to first CPU.

31. The computer program product of claim 27, wherein the step of setting the special flag is performed by the operating system.

32. The computer program product of claim 27, wherein the step of setting a suitable scheduling policy and priority for the first special task comprises invoking a system command or system function with respect to the operating system.

33. The computer program product of claim 27, said method further comprising after said decoupling the first CPU from its assigned tasks, migrating to the at least one remaining CPU the tasks decoupled from the first CPU.

34. The computer program product of claim 27, wherein the computer system further comprises a scheduler code for scheduling execution of tasks on the plurality of hot CPUs, and wherein the scheduler code is not adapted to monitor the special flag.

35. The computer program product of claim 27, wherein after decoupling the first CPU from its assigned tasks, said method further comprising not assigning any additional tasks and interrupts to the first CPU.

36. The computer program product of claim 35, wherein after decoupling the first CPU from its assigned tasks, said method further comprising powering down the first CPU.

37. The computer program product of claim 36, said method further comprising after powering down the first CPU:

adding a new CPU to the at least one remaining CPU to replace the first CPU such that the plurality of hot CPUs comprises the new CPU.

38. The computer program product of claim 35, wherein the computer system further comprises a plurality of partitions and a hypervisor adapted to manage the plurality of partitions, wherein the plurality of partitions includes a first partition and a second partition, wherein the first partition comprises the plurality of hot CPUs, and wherein after decoupling the first CPU from its assigned tasks said method further comprises moving the first CPU from the first partition to the second partition.

39. The computer program product of claim 38, wherein said moving the first CPU from the first partition to the second partition is performed without powering down the first partition and without powering down the second partition.

40. The computer program product of claim 35, wherein the computer system further comprises a per-CPU resource coupled to each CPU of the plurality of hot CPUs, and wherein said method further comprises

disconnecting the per-CPU resource from the first CPU;

and

after said disconnecting, migrating to the at least one remaining CPU the per-CPU resource disconnected from the first CPU.

41. A process for deploying computing infrastructure, comprising integrating computer-readable code into a computer system, wherein the code in combination with the computer system is capable of performing a method for decoupling a first central processing unit (CPU) from its assigned tasks, said method comprising the steps of:

setting a special flag denoting that a first CPU is to be decoupled from its assigned tasks, said first CPU being comprised by a plurality of hot CPUs within a computer system, said hot CPUs being managed by an operating system of the computer system;

setting a suitable scheduling policy and priority for a first special task coupled to the first CPU, the suitable policy and priority so chosen that the first special task gets enough continuous execution time to finish its job, said continuous execution time being defined as the amount of time allotted to a task for execution on a CPU, before another task is made to execute on the CPU;

adding the first special task in a runqueue of the first CPU; and

executing the first special task on the first CPU, said executing the first special task including examining the special flag and decoupling the first CPU from its assigned tasks after determining that the special flag has been set, said decoupling accomplished by having the first special task not relinquish control of the first CPU such that the first CPU is unable to execute any of its assigned tasks, said decoupling of tasks from the first CPU leaving at least one remaining CPU of the plurality of hot CPUs, said decoupling of tasks from the first CPU occurring while the at least one remaining CPU is hot.

42. The method of claim 41, wherein the first special task is an idle task coupled to the first CPU.

43. The process of claim 41, wherein the first special task is created specially for the purpose of decoupling first CPU from its assigned tasks.

44. The process of claim 41, wherein the step of setting a suitable scheduling policy and priority for the first special task comprises the steps of:

coupling a second special task to some CPU, said some CPU being any CPU of the plurality of hot CPUs, said second special task having the highest scheduling priority and suitable scheduling policy that results in the second special task becoming a highest prioritized task on the runqueue of said some CPU; and

executing the second special task on said some CPU, including setting a suitable scheduling policy and priority for the first special task coupled to first CPU.

45. The process of claim 41, wherein the step of setting the special flag is performed by the operating system.

46. The process of claim 41, wherein the step of setting a suitable scheduling policy and priority for the first special task comprises invoking a system command or system function with respect to the operating system.

47. The process of claim 41, said method further comprising after said decoupling the first CPU from its assigned tasks, migrating to the at least one remaining CPU the tasks decoupled from the first CPU.

48. The process of claim 41, wherein the computer system further comprises a scheduler code for scheduling execution of tasks on the plurality of hot CPUs, and wherein the scheduler code is not adapted to monitor the special flag.

49. The process of claim 41, wherein after decoupling the first CPU from its assigned tasks, said method further comprising not assigning any additional tasks and interrupts to the first CPU.

50. The process of claim 49, wherein after decoupling the first CPU from its assigned tasks, said method further comprising powering down the first CPU.

51. The process of claim 50, said method further comprising after powering down the first CPU:

adding a new CPU to the at least one remaining CPU to replace the first CPU such that the plurality of hot CPUs comprises the new CPU.

52. The process of claim 49, wherein the computer system further comprises a plurality of partitions and a hypervisor adapted to manage the plurality of partitions, wherein the plurality of partitions includes a first partition and a second partition, wherein the first partition comprises the plurality of hot CPUs, and wherein after decoupling the first CPU from its assigned tasks said method further comprises moving the first CPU from the first partition to the second partition.

53. The process of claim 52, wherein said moving the first CPU from the first partition to the second partition is performed without powering down the first partition and without powering down the second partition.

54. The process of claim 49, wherein the computer system further comprises a per-CPU resource coupled to each CPU of the plurality of hot CPUs, and wherein said method further comprises:

disconnecting the per-CPU resource from the first CPU; and

after said disconnecting, migrating to the at least one remaining CPU the per-CPU resource disconnected from the first CPU.