Managing power consumption in a data center

• US 8,595,379 B1
• Filed: 06/13/2012
• Issued: 11/26/2013
• Est. Priority Date: 12/07/2009
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Brandwine, Eric J.
• Primary Examiner(s): Ibrahim, Mohamed
• Application Number:
  US13/495,983
• Time in Patent Office: 531 Days
• Field of Search: None
• US Class Current: 709/244
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/3287 by switching off individual functional units in the computer system
• 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: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Systems and methods are provided for managing resources. In one implementation, a method is provided in which a management server determines whether a condition related to one or more resources has occurred. The management server further determines at least one program instance to terminate. The at least one program instance executes on one of a plurality of servers. The management server further terminates the determined at least one program instance, which was used by an excess program execution capacity user.

Claims

1. A computer-implemented method for managing resources of a computer infrastructure services provider, comprising:

determining, by a management server computer, that a condition has occurred related to operation of a data center;

determining, by the management server computer in response to the determined condition, at least one resource of a plurality of resources of the data center to terminate or shut down, wherein the determining of the at least one resource includes selecting the at least one resource from a first subset of the plurality of resources that are being used for excess program capacity users based at least in part on priority data indicating that the excess program capacity users have a lower priority than other users that are not excess program capacity users, and wherein a second subset of the plurality of resources are being used for the other users; and

terminating or shutting down, by the management server computer, the determined at least one resources.

2. The computer-implemented method of claim 1, wherein the excess program capacity users use excess program execution capacity of the data center that is provided on a non-guaranteed basis.

3. The computer-implemented method of claim 2 wherein the management server computer is affiliated with a program execution service that executes program instances for a plurality of users, and wherein the excess program capacity users are a subset of the plurality of users.

4. The computer-implemented method of claim 2 wherein the other users that are not excess program capacity users include dedicate program execution capacity users who receive dedicated access of a specified amount of program execution capacity and include on-demand variable program execution capacity users who do not receive dedicated access of a specified amount of program execution capacity, and wherein the priority data further indicates that program instances of the excess program capacity users have a lower priority than program instances of the on-demand variable program execution capacity users and that program instances of the on-demand variable program execution capacity users have a lower priority than program instances of the dedicated program execution capacity users.

5. The computer-implemented method of claim 1, wherein the plurality of resources include at least one of one or more of a plurality of servers in the data center, one or more program instances executing on the plurality of servers, one or more power distribution units for the data center, one or more uninterruptible power supplies for the data center, or one or more chillers for the data center.

6. The computer-implemented method of claim 1 further comprising receiving, by the management server computer, resource data from the plurality of resources, wherein the determining that the condition has occurred is based at least in part on the received resource data, and wherein the received resource data includes at least one of temperature or humidity data obtained from at least one of inside or outside the data center.

7. The computer-implemented method of claim 1, wherein the terminating or shutting down of the determined at least one resource includes terminating execution of one or more program instances for one or more of the excess program capacity users.

8. The computer-implemented method of claim 1, wherein the terminating or shutting down of the determined at least one resource includes shutting down one or more servers in the data center that are using the determined at least one resource for one or more of the excess program capacity users.

9. The computer-implemented method of claim 1 further comprising receiving, by the management server computer, resource data from one or more of the plurality of resources, wherein the determining that the condition has occurred is based at least in part on the received resource data, and wherein the received resource data reflects power usage of at least one of the plurality of resources of the data center, processing loads of at least one of a plurality of servers in the data center, and at least one environmental factor related to the data center.

10. The computer-implemented method of claim 1 further comprising receiving, by the management server computer, resource data for one or more of the plurality of resources, wherein the determining that the condition has occurred is based at least in part on the received resource data, and wherein the received resource data reflects power usage of at least one of the plurality of resources of the data center.

11. The computer-implemented method of claim 1 further comprising receiving, by the management server computer, resource data for one or more of the plurality of resources, wherein the determining that the condition has occurred is based at least in part on the received resource data, and wherein the received resource data reflects processing loads of at least one of a plurality of servers in the data center.

12. The computer-implemented method of claim 1 further comprising receiving, by the management server computer, resource data for one or more of the plurality of resources, wherein the determining that the condition has occurred is based at least in part on the received resource data, and wherein the received resource data reflects at least one environmental factor related to the data center.

13. A computer-implemented method for managing resources, comprising:

determining, by a management server computer, that a condition related to one or more resources has occurred;

determining, by the management server computer, at least one program instance to terminate based at least in part on priority data associated with a first group of program execution capacity users, the at least one program instance executing on one or more servers for one of the program execution capacity users of the first group; and

terminating, by the management server computer, the determined at least one program instance.

14. The computer-implemented method of claim 13, further comprising receiving, by the management server computer, data from the one or more resources, and wherein the determining that the condition has occurred is based at least in part on the received data.

15. The computer-implemented method of claim 14 wherein the one or more servers are located in a data center, and wherein the received data from the one or more resources reflects at least one of a power usage level for the data center, a processing load for the data center, or an environmental condition related to the data center.

16. The computer-implemented method of claim 13, wherein the first group of program execution capacity users are excess program execution capacity users who use excess program execution capacity, and wherein the method further comprises receiving, by the management server computer, the priority data, the priority data reflecting priorities related to terminating one or more program instances.

17. The computer-implemented method of claim 16 wherein a second group of program execution capacity users use other program execution capacity that is not excess program execution capacity, and wherein the priority data indicates that program instances using excess program execution capacity have a lower priority than other program instances that are not using excess program execution capacity.

18. The computer-implemented method of claim 16, wherein the priority data is based at least in part on an indicated priority between multiple distinct classes of service associated with multiple executing program instances.

19. The computer-implemented method of claim 13, wherein the determining that the condition has occurred is based at least in part on received data related to the one or more resources, and wherein the condition related to the one or more resources is based at least in part on a power consumption level or a temperature.

20. The computer-implemented method of claim 13, wherein the one or more servers are located inside a data center.

21. The computer-implemented method of claim 13, wherein the termination of the determined at least one program instance includes powering down of at least one of the one or more resources that had been being used by the determined at least one program instance.

22. The computer-implemented method of claim 16 wherein the one or more servers further execute one or more other program instances for one or more dedicated program execution capacity users who receive dedicated access of a specified amount of program execution capacity, and wherein the priority data further indicates that excess program capacity users have a lower priority than dedicated program execution capacity users.

23. The computer-implemented method of claim 16 wherein the one or more servers further execute one or more other program instances for one or more on-demand variable program execution capacity users who do not use excess program execution capacity, and wherein the priority data further indicates that excess program capacity users have a lower priority than on-demand variable program execution capacity users.

24. The computer-implemented method of claim 13 wherein the management server computer is affiliated with a program execution service that executes program instances for a plurality of users, and wherein the one program capacity user of the first group is one of the plurality of users.

25. A system for managing resources, comprising:

a processor for executing program instructions; and

a memory storing the program instructions, wherein the program instructions, upon execution by the processor, cause the system to;

determine whether a condition related to one or more resources has occurred;

determine at least one program instance to terminate based at least in part on priority data associated with one of more program execution capacity users, the determined at least one program instance executing on one of a plurality of servers for one of the one or more program execution capacity users; and

terminate the determined at least one program instance.

26. The system of claim 25, wherein the priority data is associated with excess program execution capacity users who use excess program execution capacity, wherein the determined at least one program instance is being executed for one of the excess program execution capacity users, and wherein the program instructions further cause the system to receive the priority data.

27. The system of claim 26 wherein the priority data indicates that program instances using excess program execution capacity have a lower priority than other program instances that are not using excess program execution capacity.

28. The system of claim 25 wherein the plurality of servers are located in one or more data centers, and wherein the determining of whether the condition has occurred is based at least in part on received data for the one or more resources that reflects at least one of a power usage level, a processing load, or an environmental condition related to the one or more data centers.