System and method for strategic power reduction in a computer system

• US 7,325,050 B2
• Filed: 09/19/2001
• Issued: 01/29/2008
• Est. Priority Date: 09/19/2001
• Status: Expired due to Term

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Products LP (Dell Technologies Inc.)
• Inventors: O'Connor, Clint H., Hartmann, Alfred C.
• Primary Examiner(s): Cardone; Jason
• Assistant Examiner(s): HOSSAIN, TANIM M
• Application Number:
  US09/955,684
• Publication Number:
  US 20030056126A1
• Time in Patent Office: 2,323 Days
• Field of Search: 713/300, 713/320, 709/223
• US Class Current: 709/223
• CPC Class Codes: G06F 1/263 Arrangements for using multiple switchable power supplies, e.g. battery and AC G06F1/30 takes precedence
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/329 by task scheduling
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A system and method are provided for strategic power reduction in a computer system. The system and method includes a plurality of processing resources that process data. Associated with the processing resources are a plurality of power supplies that provide power for the processing resources. A resource management engine determines the demand on the computer system and scales the processing resources to conserve and reduce power consumption. The resource management engine brings online additional processing resources to meet additional demand or brings offline or to a lower power state processing resources to meet a decreased demand. In addition, the resource management engine predicts future demand requirements and adjusts the processing resources in advance to meet the predicted demand levels and allows for dynamic adjustment of the processing resources based on current demand events.

Claims

1. A computer system comprising:

a plurality of processing resources operable to process data;

one or more power supplies associated with the processing resources, the one or more power supplies operable to supply power to the plurality of processing resources;

a resource management engine associated with the processing resources the resource management engine comprising at least one dynamic table listing historical demand data for the system;

the resource management engine operable to;

predict a decreased demand requirement for the processing resources for a first time period based at least on the historical demand data for the system; and

in response to the predicted decreased demand requirement, select between (a) lowering the power state of a particular processing resource and (b) turning off the particular processing resource for the first time period based at least on whether the demand requirement is predicted to increase at a second time period subsequent to the first time period.

2. The system of claim 1 wherein the processing resources comprise mobile processors.

3. The system of claim 1 wherein the processing resources comprise hard disk drives.

4. The system of claim 1 wherein the resource management engine scales the number of processing resources in accordance with an enterprise-wide power management strategy.

5. The system of claim 1 wherein the resource management engine scales the number of processing resources by powering up additional processing resources.

6. The system of claim 1 wherein the resource management engine scales the number of processing resources by powering down the processing resources.

7. The system of claim 6 wherein the resource management engine powering down the processing resources comprises powering off the processing resource.

8. The system of claim 6 wherein the resource management engine powering down the processing resources comprises reducing the processing resource to a lower power state.

9. The system of claim 1 further comprising a plurality of capacity tables associated with the resource management engine, the capacity tables operable to store a plurality of information regarding the processing resources and the one or more power supplies.

10. The system of claim 1 further comprising a plurality of dynamic tables associated with the resource management engine, the dynamic tables operable to store a plurality of predictive analysis information.

11. The system of claim 1 wherein the processing resources comprise a plurality of servers.

12. The system of claim 1 wherein the processing resources comprise a plurality of racks containing a plurality of servers.

13. The system of claim 1 further comprising the resource management engine predicting demand requirements.

14. The system of claim 1 further comprising the resource management engine maintaining a power threshold among the processing resources and the one or more power supplies.

15. A method for the optimizing of power consumption by a computer system having a plurality of processing resources and one or more power supplies associated therewith, the method comprising:

receiving a predicted demand requirement for a first time period based on historical demand data for the computer system;

determining if the demand requirement requires a processing resource change;

adjusting the plurality of processing resources to satisfy the demand requirement including, in response to a predicted decreased demand requirement, selecting between (a) lowering the power state of a particular processing resource and (b) turning off the particular processing resource for the first time period based at least on whether the demand requirement is predicted to increase at a second time period subsequent to the first time period.

16. The method of claim 15 wherein determining if the demand requirement requires a processing resource change comprises consulting a plurality of capacity tables.

17. The method of claim 15 wherein determining if the demand requirement requires a processing resource change comprises deciding whether to power up additional processing resources of the one or more power supplies.

18. The method of claim 15 wherein determining if the demand requirement requires a processing resource change comprises deciding whether to power down at least one of the plurality of processing resources.

19. The method of claim 15 wherein adjusting a plurality of processing resources comprises powering down at least one of the plurality of processing resources when the demand requirement decreases.

20. The method of claim 19 wherein powering down processing resources comprises turning off one or more of the plurality of processing resources.

21. The method of claim 19 wherein powering down at least one of the plurality of processing resources comprises powering at least one processing resource to a lower power state.

22. The method of claim 15 wherein adjusting the plurality of processing resources comprises powering up additional processing resources when the demand requirement increases.

23. The method of claim 22 wherein powering up additional processing resources comprises integrating the additional processing resource with the already operating processing resources.

24. The method of claim 15 further comprising:

predicting future demand requirements; and

adjusting the plurality of processing resources to meet the future demand requirements.

25. The method of claim 24 wherein predicting demand requirements comprise consulting a plurality of dynamic tables, the dynamic tables listing historical demand data associated with the computer system.

26. The method of claim 15 further comprising maintaining a power threshold in the plurality of processing resources.