Methods and systems for energy management in a virtualized data center

• US 9,213,575 B2
• Filed: 06/21/2013
• Issued: 12/15/2015
• Est. Priority Date: 06/21/2013
• Status: Active Grant

• Current Assignee: Infosys Limited
• Original Assignee: Infosys Limited
• Inventors: Salehi, Mohsen Amini, Buyya, Raj Kumar, Deepak, Krishnamurty Sai, Pisipati, Radha Krishna
• Primary Examiner(s): Lee, Adam
• Assistant Examiner(s): Sun, Charlie
• Application Number:
  US13/924,161
• Publication Number:
  US 20140380304A1
• Time in Patent Office: 907 Days
• Field of Search: 718/1
• US Class Current: 1/1
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2209/5021 Priority
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• 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 method and system provisions a plurality of resources of a data center. A violation risk factor for a set of low priority requests can be computed. A utilization factor of a set of activated resources of the data center shall be evaluated. According to a predefined rule base, one or more of the plurality of resources, shall be provisioned for a received high priority request, whereby the predefined rule base defines performing one or more of; a) preempting a set of virtual machines utilizing a subset of the set of activated resources, whereby the set of virtual machines is associated with the set of low priority requests; b) activating a new set of resources; and c) consolidating a plurality of virtual machines, based on the computed violation risk factor and the evaluated utilization factor.

Claims

1. A method for provisioning a plurality of resources of a data center, the method comprising:

computing a violation risk factor for a set of low priority requests, wherein the violation risk factor is a risk of violating a maximum average waiting time for the set of low priority requests;

evaluating a utilization factor of an activated set of the plurality of resources of the data center; and

provisioning, according to a predefined rule base comprising a plurality of rules that incorporate the violation risk factor for the set of low priority requests and the utilization factor of the activated set of the plurality of resources of the data center, one or more of the plurality of resources for a high priority request, wherein the predefined rule base switches among (a), (b), (c), and one or more combinations thereof based on the violation risk factor for the set of low priority requests and the utilization factor of the activated set of the plurality of resources of the data center;

a) preempting one or more virtual machines of a set of virtual machines, wherein the one or more virtual machines are utilizing a subset of the activated set of the plurality of resources of the data center, wherein the one or more virtual machines are associated with the set of low priority requests;

b) activating a new set of the plurality of resources of the data center;

c) consolidating two or more virtual machines of the set of virtual machines;

wherein the provisioning is based on the computed violation risk factor for the set of low priority requests and the evaluated utilization factor.

2. The method of claim 1, wherein the violation risk factor includes a risk of violating a service level agreement of the set of low priority requests.

3. The method of claim 1, wherein provisioning is performed on receiving the high priority request.

4. The method of claim 1, further comprising:

receiving a new low priority request; and

allocating one or more resources from the activated set of the plurality of resources of the data center to the received new low priority request, when the one or more resources is available.

5. The method of claim 1, wherein:

the violation risk factor is a ratio of an average waiting time of the set of low priority requests and a product of an average duration of the set of low priority requests and a waiting factor.

6. The method of claim 1, wherein the activated set of the plurality of resources of the data center are utilized by a set of allocated requests to the data center.

7. The method of claim 6, wherein the utilization factor is a ratio of a total load on the data center by the set of allocated requests and a product of a latest completion time of the set of allocated requests and a number of the activated set of the plurality of resources.

8. The method of claim 1, wherein:

a value of the violation risk factor ranges from a zero value to a positive value, wherein the zero value indicates a low risk of violating a maximum average waiting time and a value equal to and greater than one indicates a high risk of violating the maximum average waiting time; and

a value of the utilization factor ranges from a zero value to one, wherein the zero value indicates an under-utilization of the activated set of the plurality of resources of the data center, and the one indicates an over utilization of the activated set of the plurality of resources of the data center.

9. The method of claim 8, wherein:

the value of the violation risk factor is classified into one selected from the group consisting of;

a low risk range, a medium risk range, a high risk range and a very high risk range; and

the value of the utilization factor is classified into one selected from the group consisting of;

a very low, a low, a medium, a high and a very high.

10. The method of claim 9,

wherein the low risk range varies from 0 to 0.25, the medium risk range varies from 0.25 to 0.5, the high risk range varies from 0.5 to 0.75 and the very high risk range includes a value greater than 0.75.

11. The method of claim 10, wherein the very low includes a value from 0 to 0.4, the low includes a value from 0.2 to 0.5, the medium includes a value from 0.4 to 0.8, the high includes a value from 0.5 to 0.9, and the very high includes a value from 0.8 to 1.0.

12. The method of claim 11, wherein the predefined rule base comprises:

performing a), when the utilization factor is greater than 0.8 and the violation risk factor ranges from zero to 0.5;

performing b), when the violation risk factor is greater than 0.5 and the utilization factor is greater than 0.4;

performing c), when the utilization factor ranges from zero to 0.9, and the violation risk factor ranges from zero to 0.75;

performing a combination of step a) and step b), when the violation risk factor is greater than 0.25 and the utilization factor lies between zero and one; and

performing a combination of step a) and step c), when the violation risk factor is lesser than 0.75 and the utilization factor ranges from 0.2 to 1.

13. A system for provisioning a plurality of resources of a data center, the system comprising:

one or more processors;

a computing engine, configured to compute a violation risk factor of a set of low priority requests, wherein the violation risk factor is a risk of violating a maximum average waiting time for the set of low priority requests;

an energy utilization engine, configured to evaluate a utilization factor of an activated set of the plurality of resources of the data center; and

a fuzzy engine configured to provision, according to a predefined rule base comprising a plurality of rules that incorporate the violation risk factor for the set of low priority requests and the utilization factor of the activated set of the plurality of resources of the data center, one or more of the plurality of resources for a high priority request, the predefined rule base switching among (a), (b), (c), and one or more combinations thereof based on the violation risk factor for the set of low priority requests and the utilization factor of the activated set of the plurality of resources of the data center;

a) preempting one or more virtual machines of a set of virtual machines, wherein the one or more virtual machines are utilizing a subset of the activated set of the plurality of resources of the data center, wherein the one or more virtual machines are associated with the set of low priority requests;

b) activating a new set of the plurality of resources of the data center; and

c) consolidating two or more of the set of virtual machines;

wherein the provisioning is based on the computed violation risk factor and the evaluated utilization factor.

14. The system of claim 13, further comprising an input module, configured to receive the high priority request.

15. The system of claim 14, wherein the fuzzy engine is further configured to:

provision the one or more of the plurality of resources when the high priority request is received; and

receive the computed violation risk factor and the evaluated utilization factor as inputs for applying the rule base.

16. The system of claim 14, wherein the input module is further configured to receive a new low priority request.

17. The system of claim 16, wherein an allocating module is configured to allocate one or more resources from the activated set of the plurality of resources of the data center to the received new low priority request, when the one or more resources is available.

18. The system of claim 13, wherein the violation risk factor includes a risk of violating a service level agreement of the set of low priority requests.

19. The system of claim 18, wherein the computing engine is further configured to compute the violation risk factor by determining a ratio of an average waiting time of the low priority request and a product of an average duration of the set of low priority requests and a waiting factor.

20. The system of claim 13, wherein the activated set of the plurality of resources of the data center is utilized by a set of allocated requests to the data center.

21. The system of claim 20, wherein the utilization factor is a ratio of a total load on the data center by the set of allocated requests and a product of a latest completion time of the set of allocated requests and a number of the activated set of the plurality of resources of the data center.

22. The system of claim 13, wherein:

a value of the violation risk factor ranges from a zero value to a positive value, wherein the zero value indicates a low risk of violating a maximum average waiting time and a value equal to and greater than one indicates a high risk of violating the maximum average waiting time; and

a value of the utilization factor ranges from a zero value to one, wherein the zero value indicates an under-utilization of the activated set of the plurality of resources of the data center, and the one indicates an over utilization of the activated set of the plurality of resources of the data center.

23. The system of claim 22, wherein:

the value of the violation risk factor is classified into one of;

a low risk range, a medium risk range, a high risk range and a very high risk range; and

the value of the utilization factor is classified into one selected from the group consisting of;

a very low, a low, a medium, a high and a very high.

24. The system of claim 23, wherein the low risk range varies from 0 to 0.25, the medium risk range varies from 0.25 to 0.5, the high risk range varies from 0.5 to 0.75 and the very high risk range includes a value greater than 0.75.

25. The system of claim 24, wherein the very low includes a value from 0 to 0.4, the low includes a value from 0.2 to 0.5, the medium includes a value from 0.4 to 0.8, the high includes a value from 0.5 to 0.9, and the very high includes a value from 0.8 to 1.0.

26. The system of claim 25, wherein the predefined rule base comprises:

performing a), when the utilization factor is greater than 0.8 and the violation risk factor ranges from zero to 0.5,

performing b), when the violation risk factor is greater than 0.5 and the utilization factor is greater than 0.4,

performing c), when the utilization factor ranges from zero to 0.9, and the violation risk factor ranges from zero to 0.75, and

performing a combination comprising one of step a) and step b);

or step a) and step c), when the violation risk factor is greater than 0.25 and the utilization factor lies between zero and one.

27. A computer program product comprising a plurality of program instructions stored on a non-transitory computer-readable medium that, when executed by a computing device, performs a method for provisioning a plurality of resources of a data center, the method comprising:

computing a violation risk factor for a set of low priority requests, wherein the violation risk factor comprises a risk of violating a maximum average waiting time for the set of low priority requests;

evaluating a utilization factor of an activated set of the plurality of resources of the data center; and

provisioning, according to a predefined rule base comprising a plurality of rules that incorporate the violation risk factor for the set of low priority requests and the utilization factor of the activated set of the plurality of resources of the data center, wherein the predefined rule base switches among (a), (b), (c), and one or more combinations thereof based on the violation risk factor for the set of low priority requests and the utilization factor of the activated set of the plurality of resources of the data center;

performing a first provisioning of one or more of the plurality of resources of the data center for a first high priority request according to a predefined rule base, wherein the first provisioning comprises preempting one or more virtual machines of a set of virtual machines, wherein the one or more virtual machines are utilizing a subset of the activated set of the plurality of resources of the data center, wherein the one or more virtual machines are associated with the set of low priority requests, further wherein the first provisioning is based on the computed violation risk factor and the evaluated utilization factor;

(b) performing a second provisioning of one or more of the plurality of resources of the data center for a second high priority request according to the predefined rule base, wherein the second provisioning comprises activating a new set of the plurality of resources of the data center, further wherein the second provisioning is based on the computed violation risk factor and the evaluated utilization factor; and

(c) performing a third provisioning of one or more of the plurality of resources of the data center for a third high priority request according to the predefined rule base, wherein the third provisioning comprises consolidating two or more of the set of virtual machines, further wherein the third provisioning is based on the computed violation risk factor and the evaluated utilization factor.

28. A method for provisioning a plurality of resources of a data center, the method comprising:

computing a violation risk factor for a set of low priority requests, wherein a value of the violation risk factor ranges from a zero value to a positive value, wherein the zero value indicates a low risk of violating the maximum average waiting time and a value equal to and greater than one indicates a high risk of violating the maximum average waiting time, wherein the value of the violation risk factor is classified into one selected from the group consisting of;

a low risk range, a medium risk range, a high risk range and a very high risk range, further wherein the low risk range varies from 0 to 0.25, the medium risk range varies from 0.25 to 0.5, the high risk range varies from 0.5 to 0.75 and the very high risk range includes a value greater than 0.75;

evaluating a utilization factor of an activated set of the plurality of resources of the data center, wherein a value of the utilization factor ranges from a zero value to one, wherein the zero value indicates an under-utilization of the activated set of the plurality of resources of the data center, and the one indicates an over utilization of the activated set of the plurality of resources of the data center, wherein the value of the utilization factor is classified into one selected from the group consisting of;

a very low, a low, a medium, a high and a very high; and

provisioning, according to a predefined rule base, one or more of the plurality of resources for a high priority request, whereby the predefined rule base defines performing one or more of;

a) preempting one or more virtual machines of a set of virtual machines, wherein the one or more virtual machines are utilizing a subset of the activated set of the plurality of resources of the data center, whereby the one or more virtual machines are associated with the set of low priority requests;

b) activating a new set of the plurality of resources of the data center;

or

c) consolidating two or more of the set of virtual machines, based on the computed violation risk factor and the evaluated utilization factor.

29. The method of claim 28, wherein:

the very low includes a value from 0 to 0.4, the low includes a value from 0.2 to 0.5, the medium includes a value from 0.4 to 0.8, the high includes a value from 0.5 to 0.9, and the very high includes a value from 0.8 to 1.0.