Managing virtual machines

• US 20070079308A1
• Filed: 09/30/2005
• Published: 04/05/2007
• Est. Priority Date: 09/30/2005
• Status: Active Grant

• Current Assignee: Computer Associates Think Inc. (Broadcom, Inc.)
• Original Assignee: Computer Associates Think Inc. (Broadcom, Inc.)
• Inventors: Narayanan, Karthik, Esfahany, Kouros, Chiaramonte, Michael
• Granted Patent: US 8,104,033 B2
• Time in Patent Office: Days
• US Class Current: 718/1
• CPC Class Codes: G06F 2209/501 Performance criteria
• CPC Class Codes: G06F 2209/5011 Pool
• CPC Class Codes: G06F 2209/5021 Priority
• CPC Class Codes: G06F 2209/503 Resource availability
• CPC Class Codes: G06F 2209/508 Monitor
• 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

Abstract

According to one embodiment, a method for managing one or more virtual machines includes generating a request for at least one performance characteristic for at least one virtual machine, the at least one virtual machine being associated with a processing group, the processing group including one or more processing modules; receiving a response to the generated request for at least one performance characteristic for the at least one virtual machine; automatically determining whether an increase in the number of processing modules included in the processing group is required, by analyzing the received response to the generated request; and, in response to a determination that an increase in the number of processing modules included in the processing group is required, automatically adding at least one processing module to the processing group.

Claims

1. An apparatus for use in managing virtual machines, the apparatus comprising:

a processor; and

software encoded in media operable when executed on the processor to;

access a poll interval and an analysis interval;

access virtual machine criteria for at least one virtual machine having affinity for one or more hardware components, the virtual machine criteria comprising an upper limit and a lower limit for at least one performance characteristic;

receive periodic information comprising the at least one performance characteristic, with the periodic information being received at a rate substantially equal to the poll interval;

determine if the at least one performance characteristic is between the upper limit and the lower limit by periodically analyzing the periodic information at a periodic rate substantially equal to the analysis interval;

in response to a determination that the at least one performance characteristic is not between the upper limit and the lower limit, modifying the virtual machine affinity with respect to the one or more hardware components.

2. The apparatus of claim 1, wherein the poll interval is in the range from 1 second to 120 seconds.

3. The apparatus of claim 1, wherein the analysis interval is in the range from 1 minute to 30 minutes.

4. The apparatus of claim 1, wherein:

the one or more hardware components comprise a plurality of central processing units included within a single server.

5. The apparatus of claim 4, wherein:

modifying the virtual machine affinity with respect to the one or more hardware components comprises modifying the virtual machine affinity to include at least one additional central processing unit.

6. A method for managing one or more virtual machines, the method comprising:

generating a request for at least one performance characteristic for at least one virtual machine, the at least one virtual machine being associated with a processing group, the processing group including one or more processing modules;

receiving a response to the generated request for at least one performance characteristic for the at least one virtual machine;

automatically determining whether an increase in the number of processing modules included in the processing group is required by analyzing the received response to the generated request; and

in response to a determination that an increase in the number of processing modules included in the processing group is required, automatically adding at least one processing module to the processing group.

7. The method of claim 6, wherein:

the at least one performance characteristic comprises processor utilization for the at least one virtual machine.

8. The method of claim 6, wherein:

the at least one performance characteristic comprises priority information for one or more applications associated with the at least one virtual machine.

9. The method of claim 6, wherein:

the one or more processing modules comprise multiple central processing units (CPUs) included within a single server.

10. The method of claim 9, wherein:

adding at least one processing module to the processing group comprises doubling the number of central processing units associated with the processing group.

11. A method for managing a plurality of virtual machines, the method comprising:

receiving priority information for the plurality of virtual machines; and

based on the received priority information, assigning each of the plurality of virtual machines to one of a plurality of groups of central processing units, such that each of the plurality of virtual machines has affinity with all of the central processing units in the group to which it is assigned;

receiving at least one performance characteristic for at least one of the plurality of virtual machines; and

automatically determining if the central processing units, to which the at least one of the plurality of virtual machines has affinity, are over-utilized by analyzing the at least one performance characteristic; and

in response to a determination the central processing units are over-utilized, automatically allocating at least one additional central processing unit to each of the plurality of groups of central processing units.

12. The method of claim 11, wherein:

the plurality of groups of central processing units comprise multiple central processing units included within a single server.

13. The method of claim 11, wherein the received priority information identifies a priority level for each virtual machine and the priority level is based on a business priority for:

the virtual machine;

a user associated with the virtual machine;

or one or more applications running on the virtual machine.

14. A method for managing a plurality of virtual machines, the method comprising:

receiving priority information for the plurality of virtual machines; and

based on the received priority information, assigning each of the plurality of virtual machines to one of a plurality of buckets such that each bucket is associated with a group of hardware components, the plurality of buckets comprising a first bucket and a second bucket, with the group of hardware components associated with the first bucket being a subset of the group of hardware components associated with the second bucket.

15. The method of claim 14, wherein the group of hardware components associated with the first bucket comprise one or more central processing units (CPUs).

16. The method of claim 14, wherein the group of hardware components associated with the first bucket comprise one or more memory modules.

17. The method of claim 14, wherein the plurality of buckets further comprises a third bucket, with the group of hardware associated with the second bucket being a subset of the group of hardware components associated with the third bucket.

18. The method of claim 14, wherein the received priority information identifies a priority level for each virtual machine and the priority level is based on a business priority for:

the virtual machine;

a user associated with the virtual machine;

or one or more applications running on the virtual machine.

19. The method of claim 14, further comprising:

receiving at least one performance characteristic for at least one of the plurality of virtual machines; and

automatically determining if one or more hardware components for the at least one of the plurality of virtual machines is over-utilized by analyzing the at least one performance characteristic; and

in response to a determination that one or more hardware components for the at least one of the plurality of virtual machines is over-utilized, automatically associating at least one additional hardware component to each of the plurality of buckets.

20. Software for use in managing a plurality of virtual machines each having processing capability through association with one or more of a plurality of central processing units, the software embodied in a computer-readable medium and when executed using one or more processors, operable to:

access performance criteria comprising;

a first range, a second range, and a third range for at least one performance characteristic associated with the plurality of central processing units; and

a fourth range and a fifth range for at least one performance characteristic associated with each of the plurality of virtual machines;

determine a value of the at least one performance characteristic associated with the plurality of central processing units and the value of the at least one performance characteristic associated with each of the plurality of virtual machines;

in response to a determination that the at least one performance characteristic associated with the plurality of central processing units is in the first range and that the at least one performance characteristic associated with each of the plurality of virtual machines is in the fourth range for each of the plurality of virtual machines, automatically reduce the number of central processing units included in the plurality of central processing units;

in response to a determination that the at least one performance characteristic associated with the plurality of central processing units is in the second range and that the at least one performance characteristic associated with each of the plurality of virtual machines is in the fifth range for one or more of the plurality of virtual machines, automatically increase the number of central processing units included in the plurality of central processing units; and

in response to a determination that the at least one performance characteristic associated with the plurality of central processing units is in the third range, automatically increase the number of central processing units included in the plurality of central processing units.

21. The software of claim 20, wherein:

the at least one performance characteristic associated with the plurality of central processing units comprises a processing capability utilization for the plurality of central processing units;

the first range corresponds to under-utilization;

the second range corresponds to normal utilization; and

the third range corresponds to over-utilization.

22. The software of claim 20, wherein:

the at least one performance characteristic associated with each of the plurality of virtual machines comprises a processing capability utilization for each of the plurality of virtual machines;

the fourth range corresponds to normal utilization; and

the fifth range corresponds to over-utilization.