Computer workload redistribution schedule

• US 9,391,922 B2
• Filed: 08/05/2015
• Issued: 07/12/2016
• Est. Priority Date: 04/24/2006
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Herington, Daniel Edward, Turicchi, Thomas Edwin Jr.
• Primary Examiner(s): Lee, Tammy
• Application Number:
  US14/819,039
• Publication Number:
  US 20160028649A1
• Time in Patent Office: 342 Days
• Field of Search: None
• US Class Current: 1/1
• 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: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed 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 47/783 Distributed allocation of resources, e.g. bandwidth brokers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A computer system has a capacity planner for creating and updating a workload redistribution schedule. A migration utility provides for redistribution of the workloads. A redistribution orchestrator directs, according to the schedule, the migration utility to implement the workload redistributions.

Claims

1. A method comprising:

executing workloads on at least one server, the workloads including a first workload and a second workload executing on a first server during a first allocation period;

collecting, via a processor, resource-utilization data for the workloads, the resource-utilization data indicating amounts of processing resources consumed by the workloads;

updating, via the processor, an original schedule of workload redistributions based, at least in part, on the resource-utilization data and a management policy to yield an updated schedule, the updated schedule specifying workload redistributions requiring opposing migrations in that the updated schedule specifies the first workload is to be executed on a second server, different from the first server, during a second allocation period after the first allocation period, and on the first server during a third allocation period after the second allocation period; and

implementing, via the processor, the updated schedule at least in part by implementing the opposing migrations by migrating the first workload from the first server to the second server for the second allocation period, and migrating the first workload from the second server to the first server for the third allocation period, and wherein the second workload executes on the first server during the second allocation period and the third allocation period.

2. The method of claim 1, wherein the second server is inactive during the first allocation period and the third allocation period.

3. The method of claim 1, wherein the updated schedule specifies that the second server is to be in a power-on state during the first allocation period and the third allocation period.

4. The method of claim 1, wherein implementing the updated schedule comprises maintaining the second server in a power-on state during the first allocation period and the third allocation period.

5. The method of claim 1, wherein implementing the updated schedule comprises migrating the first workload to the second server twice.

6. The method of claim 1, wherein the updated schedule specifies that the first workload is to be executed on the second server during a fourth allocation period after the third allocation period.

7. The method of claim 6, wherein the updated schedule specifies that a third server, different than the first server and the second server, is to be in a power-off state in the first allocation period and the third allocation period, and in a power-on state in the second allocation period and the fourth allocation period.

8. The method of claim 6, wherein a third server is available to execute the workloads, and wherein the third server is inactive during the first allocation period, the second allocation period, the third allocation period, and the fourth allocation period.

9. The method of claim 1, wherein the management policy comprises to shut down servers not scheduled to run a workload.

10. The method of claim 1, wherein the management policy comprises to reduce a number of active servers as permitted by a configurable percentage of peak combined utilization per resource of active servers.

11. The method of claim 1, wherein the updated schedule specifies that the second server is to be activated at a time before the second allocation period and to be deactivated at a time after the second allocation period, wherein the first server is disposed in a first geographic location, and wherein the second server is disposed in a second geographic location different than the first geographic location.

12. A computer system comprising:

a processor; and

memory storing instructions executable by the processor to;

collect resource-utilization data for workloads executing on at least one server, the workloads including a first workload and a second workload executing on a first server during a first allocation period, wherein the resource-utilization data indicates amounts of processing resources consumed by the workloads;

update an original schedule of workload redistributions based, at least in part, on the resource-utilization data and a management policy to yield an updated schedule, the updated schedule specifying workload redistributions requiring opposing migrations in that the updated schedule specifies the first workload is to be executed on a second server, different from the first server, during a second allocation period after the first allocation period, and on the first server during a third allocation period after the second allocation period; and

implement the updated schedule at least in part by implementing the opposing migrations by migrating the first workload from the first server to the second server for the second allocation period, and migrating the first workload from the second server to the first server for the third allocation period, and wherein the second workload to execute on the first server during the second allocation period and the third allocation period.

13. The computer system of claim 12, wherein the updated schedule specifies that the first workload is to be executed on the second server during a fourth allocation period after the third allocation period, and wherein the second server is inactive during the first allocation period and the third allocation period.

14. The computer system of claim 13, wherein a third server, different than the first server and the second server, is available to execute the workloads, and wherein the updated schedule specifies that the third server is to be in a power-off state in the first allocation period and the third allocation period, and in a power-on state in the second allocation period and the fourth allocation period.

15. The computer system of claim 12, wherein the updated schedule specifies that the second server is to be in a power-on state during the first allocation period and the third allocation period, and wherein to implement the updated schedule comprises to maintain the second server in the power-on state during the first allocation period and the third allocation period.

16. The computer system of claim 12, wherein the management policy comprises to shut down servers not scheduled to run a workload.

17. A non-transitory computer-readable media comprising instructions that direct a processor to:

collect resource-utilization data for workloads executing on at least one server, the workloads including a first workload and a second workload executing on a first server during a first allocation period, wherein the resource-utilization data indicates amounts of processing resources consumed by the workloads;

update an original schedule of workload redistributions based, at least in part, on the resource-utilization data and a management policy to yield an updated schedule, the updated schedule specifying workload redistributions requiring opposing migrations in that the updated schedule specifies the first workload is to be executed on a second server, different from the first server, during a second allocation period after the first allocation period, and on the first server during a third allocation period after the second allocation period; and

implement the updated schedule at least in part by implementing the opposing migrations by migrating the first workload from the first server to the second server for the second allocation period, and migrating the first workload from the second server to the first server for the third allocation period, and wherein the second workload to execute on the first server during the second allocation period and the third allocation period.

18. The non-transitory computer-readable media of claim 17, wherein the updated schedule specifies that the first workload is to be executed on the second server during a fourth allocation period after the third allocation period, and wherein the second server is inactive during the first allocation period and the third allocation period.

19. The non-transitory computer-readable media of claim 18, wherein a third server, different than the first server and the second server, is available to execute the workloads, and wherein the updated schedule specifies that the third server is to be in a power-off state in the first allocation period and the third allocation period, and in a power-on state in the second allocation period and the fourth allocation period.

20. The non-transitory computer-readable media of claim 17, wherein the updated schedule specifies that the second server is to be in a power-on state during the first allocation period and the third allocation period, and wherein to implement the updated schedule comprises to maintain the second server in the power-on state during the first allocation period and the third allocation period.