ESTIMATING A POWER UTILIZATION OF A COMPUTER SYSTEM

• US 20090271046A1
• Filed: 04/24/2008
• Published: 10/29/2009
• Est. Priority Date: 04/24/2008
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Sun Microsystems Incorporated (Oracle Corporation)
• Inventors: Gross, Kenny C., Vaidyanathan, Kalyanaraman, Lewis, Andrew J.
• Granted Patent: US 7,756,652 B2
• Time in Patent Office: Days
• US Class Current: 700/291
• CPC Class Codes: G06F 11/30 Monitoring
• CPC Class Codes: G06F 11/3096 wherein the means or processing minimize the use of computing system or of computing system component resources, e.g. non-intrusive monitoring which minimizes the probe effect: sniffing, intercepting, indirectly deriving the monitored data from other directly available data

Abstract

One embodiment of the present invention provides a system that estimates a power utilization of a computer system. During operation, a set of performance parameters of the computer system is monitored, wherein the computer system includes a processor. Then the power utilization of the computer system is estimated based on the set of performance parameters and a power-utilization model, wherein the power-utilization model was trained by measuring a power utilization of the computer system while the processor is operating at a first frequency and measuring a power utilization of the computer system while the processor is operating at a second frequency.

Claims

1. A method for estimating a power utilization of a computer system, comprising:

monitoring a set of performance parameters of the computer system, wherein the computer system includes a processor;

using a model training mechanism to generate a power-utilization model;

training the power-utilization model by;

measuring a power utilization of the computer system while the processor is operating at a first frequency by varying a load on the processor from a first minimum load to a first maximum load; and

measuring a power utilization of the computer system while the processor is operating at a second frequency by varying a load on the processor from a second minimum load to a second maximum load; and

estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model.

2. The method of claim 1,

wherein monitoring the set of performance parameters of the computer system includes systematically monitoring and recording a set of performance parameters of the computer system;

and

wherein the recording process keeps track of the temporal relationships between events in different performance parameters.

3. The method of claim 1, wherein the first frequency is a minimum frequency of operation of the processor and the second frequency is a maximum frequency of operation of the processor.

4. The method of claim 1, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes using a pattern-recognition technique.

5. The method of claim 1, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes using a nonlinear, nonparametric regression technique.

6. The method of claim 5, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes using a multivariate state estimation technique.

7. The method of claim 1, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes processing the set of performance parameters using an analytical re-sampling technique.

8. The method of claim 1, wherein the computer system includes a dynamic power-management feature.

9. The method of claim 8, wherein the dynamic power-management feature includes a feature controlling an operating voltage of the processor.

10. The method of claim 8, wherein the dynamic power-management feature includes a feature controlling an operating frequency of the processor.

12. The method of claim 1, wherein training the power-utilization model includes using a pattern-recognition technique.

13. The method of claim 1, wherein training the power-utilization model includes using a nonlinear, nonparametric regression technique.

14. The method of claim 13, wherein training the power-utilization model includes using a multivariate state estimation technique.

11. (canceled)

15. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for estimating a power utilization of a computer system, the method comprising:

monitoring a set of performance parameters of the computer system, wherein the computer system includes a processor;

training the power-utilization model by;

measuring a power utilization of the computer system while the processor is operating at a first frequency by varying a load on the processor from a first minimum load to a first maximum loath and

measuring a power utilization of the computer system while the processor is operating at a second frequency by varying a load on the processor from a second minimum load to a second maximum load; and

estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model.

16. The computer-readable storage medium of claim 15,

wherein monitoring the set of performance parameters of the computer system includes systematically monitoring and recording a set of performance parameters of the computer system;

and

wherein the recording process keeps track of the temporal relationships between events in different performance parameters.

17. The computer-readable storage medium of claim 15, wherein the first frequency is a minimum frequency of operation of the processor and the second frequency is a maximum frequency of operation of the processor.

18. The computer-readable storage medium of claim 15, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes using a pattern-recognition technique.

19. The computer-readable storage medium of claim 15, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes using a nonlinear, nonparametric regression technique.

20. The computer-readable storage medium of claim 19, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes using a multivariate state estimation technique.

21. The computer-readable storage medium of claim 15, wherein estimating the power utilization of the computer system based on the set of performance parameters and the power-utilization model includes processing the set of performance parameters using an analytical re-sampling technique.

22. The computer-readable storage medium of claim 15, wherein the computer system includes a dynamic power-management feature.

23. The computer-readable storage medium of claim 22, wherein the dynamic power-management feature includes a feature controlling an operating voltage of the processor.

24. The computer-readable storage medium of claim 22, wherein the dynamic power-management feature includes a feature controlling an operating frequency of the processor.

26. The computer-readable storage medium of claim 15, wherein training the power-utilization model includes using a pattern-recognition technique.

27. The computer-readable storage medium of claim 15, wherein training the power-utilization model includes using a nonlinear, nonparametric regression technique.

28. The computer-readable storage medium of claim 27, wherein training the power-utilization model includes using a multivariate state estimation technique.

25. (canceled)

29. An apparatus for estimating a power utilization of a computer system, comprising:

a monitoring mechanism configured to monitor a set of performance parameters of the computer system, wherein the computer system includes a processor;

a model-training mechanism configured to train a power-utilization model by;

measuring a power utilization of the computer system while the processor is operating at a first frequency by varying a load on the processor from a first minimum load to a first maximum load; and

measuring a power utilization of the computer system while the processor is operating at a second frequency by varying a load on the processor from a second minimum load to a second maximum load; and

an estimating mechanism configured to estimate the power utilization of the computer system based on the set of performance parameters and the power-utilization model.

30. The apparatus of claim 29, wherein the estimating mechanism includes using a mechanism configured to implement a pattern-recognition technique.

31. The apparatus of claim 29, wherein the computer system includes a dynamic power-management feature.