Power conservation in partitioned data processing systems

• US 20040111596A1
• Filed: 12/09/2002
• Published: 06/10/2004
• Est. Priority Date: 12/09/2002
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Rawson, Freeman Leigh III
• Granted Patent: US 7,007,183 B2
• Time in Patent Office: Days
• US Class Current: 713/1
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/3268 Power saving in hard disk drive
• CPC Class Codes: G06F 1/3275 Power saving in memory, e.g. RAM, cache
• CPC Class Codes: G06F 2209/5014 Reservation
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: G06F 9/5094 where the allocation takes into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A power-aware, logically partitioned data processing system and corresponding method of use include a set of physical resources and a hypervisor. The hypervisor creates partitions and allocates at least some of the physical resources to the partitions. The system further includes means for reducing the power consumption of any physical resources not allocated to a partition. The hypervisor may allocate physical resources to the partitions to maximize the number of unallocated physical resources. The physical resources may include processors and the hypervisor may allocate a fractional portion of at least one processor to a partition. In this embodiment, the system may reduce power consumption by scaling the supply voltage or clocking frequency to the fractionally allocated processor. The resources may include memory modules and the hypervisor may dynamically reduce the allocated memory and power consumption by minimizing the number of memory modules needed to support the memory allocated to the partitions. The resources may also include disks provided through a storage-area network (SAN). This SAN may be partitioned in the same manner as the main data processing system, and the SAN partitioning may turn off power to unallocated or unused disk drives to reduce power consumption.

Claims

1. A data processing system comprising:

a set of physical resources;

a hypervisor to create partitions within the system and allocate at least some of the physical resources to the partitions; and

means for reducing power consumption of physical resources not allocated by the hypervisor.

2. The system of claim 1, wherein the hypervisor allocates physical resources to the partitions wherein the amount of unallocated physical resources is maximized.

3. The system of claim 1, wherein the set of physical resources comprises a set of processors and further wherein the hypervisor allocates a fractional portion of at least one of the processors to at least one of the partitions.

4. The system of claim 3, wherein the means for reducing power consumption includes means for scaling a power supply voltage and a clocking frequency to the at least one fractionally allocated processor and means for turning off power to unallocated processors.

5. The system of claim 1, wherein the set of physical resources comprises a set of memory modules and further wherein the means for reducing power consumption includes means for terminating power to the unallocated memory modules.

6. The system of claim 5, wherein the hypervisor includes means for dynamically reducing the amount of allocated memory modules by paging selected physical page frames out to disk storage based on predetermined selection criteria.

7. The system of claim 5, wherein the predetermined selection criteria includes the frequency with which a physical page is accessed or information provided by the operating systems running within the partitions.

8. The system of claim 5, wherein the predetermined selection criteria is based on information provided by memory page information operating systems running within the partitions.

9. The system of claim 1, wherein the set of physical resources includes a set of storage disks configured as a storage area network (SAN) connected to the data processing system and further wherein the means for reducing energy consumption includes means for logically partitioning the SAN to reflect the partitions of the data processing system and means for powering down disks not allocated to any of the SAN partitions.

10. A data processing system, comprising:

a set of physical resources;

means for creating partitions within the system, wherein each partition is configured to execute a corresponding operating system independently of the other partitions;

means for allocating at least some of the physical resources to the partitions by packing the partitions into a minimum subset of the physical resources; and

means for turning off physical resources not allocated to any of the partitions.

11. The system of claim 10, wherein packing the partitions includes allocating fractional partition portions of at least two of the partitions to a common physical resource.

12. The system of claim 11, wherein packing the partitions includes splitting a fractional partition portion between two different physical resources when the fractional partition portion exceeds the capacity of a first of the two physical resources.

13. The system of claim 10, wherein the set of physical resources comprises a set of processors and further wherein a fractional portion of at least one of the processors is allocated to at least one of the partitions.

14. The system of claim 13, further comprising reducing power consumption of at least one of the fractionally allocated processors by scaling its power supply voltage and clocking frequency and reducing power consumption of unallocated processors by turning off power to them.

15. The system of claim 10, wherein the set of physical resources comprises a set of memory modules and further wherein the system includes means for dynamically reducing the amount of allocated memory modules by paging selected physical page frames out to disk storage based on predetermined selection criteria.

16. A computer program product for use in allocating resources in a data processing system, the computer program product comprising computer readable program code stored on a computer readable storage medium and including:

code means for creating logical partitions within the system;

code means for allocating at least some of the physical resources to the partitions by packing the partitions into a minimum subset of the physical resources; and

code means for reducing power to physical resources not allocated to any of the partitions.

17. The computer program product of claim 16, wherein packing the partitions includes code means for allocating fractional partition portions of at least two of the partitions to a common physical resource.

18. The computer program product of claim 17, wherein packing the partitions includes code means for splitting a fractional partition portion between two different physical resources when the fractional partition portion exceeds the capacity of a first of the two physical resources.

19. The computer program product of claim 16, wherein the set of physical resources comprises a set of processors and further wherein a fractional portion of at least one of the processors is allocated to at least one of the partitions.

20. The computer program product of claim 19, further comprising code means for reducing power consumption of at least one of the fractionally allocated processors by scaling its power supply voltage and clocking frequency and code means for turning off power to unallocated processors.

21. The computer program product of claim 16, wherein the set of physical resources comprises a set of memory modules and further wherein the system includes code means for dynamically reducing the amount of allocated memory modules by paging selected physical page frames out to disk storage based on predetermined selection criteria.