MONITORING RESOURCE USAGE BY A VIRTUAL MACHINE

• US 20130346966A1
• Filed: 06/20/2012
• Published: 12/26/2013
• Est. Priority Date: 06/20/2012
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Natu, Mahesh S., Keshavamurthy, Anil S., Munoz, Alberto J., Thomas, Tessil
• Granted Patent: US 9,122,780 B2
• Time in Patent Office: Days
• US Class Current: 718/1
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 2009/45566 Nested virtual machines
• CPC Class Codes: G06F 2009/45591 Monitoring or debugging support
• CPC Class Codes: G06F 2201/815 Virtual middleware or OS functionality using virtual machines to implement generic software techniques for error detection or fault masking G06F11/1484
• CPC Class Codes: G06F 2201/885 Monitoring specific for caches
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

Embodiments of apparatus, computer-implemented methods, systems, devices, and computer-readable media are described herein for tracking per-virtual machine (“VM”) resource usage independent of a virtual machine monitor (“VMM”). In various embodiments, a first logic unit may associate one or more virtual central processing units (“vCPUs”) operated by one or more physical processing units of a computing device with a first VM of a plurality of VMs operated by the computing device, and collect data about resources used by the one or more physical processing units to operate the one or more vCPUs associated with the first VM. In various embodiments, a second logic unit of the computing device may determine resource-usage by the first VM based on the collected data. In various embodiments, the first and second logic units may perform these functions independent of a VMM of the computing device.

Claims

1. At least one non-transitory computer-readable medium having computer-readable code embodied therein, the computer-readable code comprising instructions configured to provide first and second logic unit to a computing device;

wherein the first logic unit, on execution of the instructions by the computing device, associates one or more virtual central processing units operated by one or more physical processing units of the computing device with a first virtual machine of a plurality of virtual machines operated by the computing device, and collects data about resources used by the one or more physical processing units to operate the one or more virtual central processing units associated with the first virtual machine, wherein the first logic unit performs the association and the collection independent of a virtual machine monitor of the computing device; and

the second logic unit, on execution of the instructions by the computing device, directs the first logic unit to collect the data about the resources used by the one or more physical processing units to operate the one or more virtual central processing units associated with the first virtual machine, and determines resource-usage by the first virtual machine based on the collected data, wherein the second logic unit performs the direction and determination independent of a virtual machine monitor of the computing device.

2. The at least one non-transitory computer-readable medium of claim 1, wherein the second logic unit, on execution of the instructions, aggregates the collected data to determine resources used by the first virtual machine.

3. The at least one non-transitory computer-readable medium of claim 1, wherein the first logic unit, on execution of the instructions, stores, in one or more virtual machine control structures associated with the one or more virtual central processing units, an identifier of the first virtual machine.

4. The at least one non-transitory computer-readable medium of claim 1, wherein the second logic unit, on execution of the instructions, allocates a resource monitor identifier to the first virtual machine, responsive to a request to monitor resource-usage of the first virtual machine, and directs the first logic unit to store, in one or more virtual machine control structures associated with the one or more virtual central processing units, the resource monitor identifier;

and

wherein the first logic unit, on execution of the instructions, further collects the data about resources used by the one or more physical processing units to operate the one or more virtual central processing units associated with the first virtual machine based on operations performed by the one or more physical processing units that involve the one or more virtual machine control structures with the resource monitor identifier.

5. The at least one non-transitory computer-readable medium of claim 1, wherein the first logic unit, on execution of the instructions, provides, to the second logic unit, in response to initialization of a new virtual central processing unit, an association between the new virtual central processing unit and a virtual machine.

6. The at least one non-transitory computer-readable medium of claim 5, wherein the second logic unit, on execution of the instructions, determines, based at least in part on the association provided by the first logic unit, whether the new virtual central processing unit is associated with a new virtual machine or an existing virtual machine.

7. The at least one non-transitory computer-readable medium of claim 6, wherein the second logic unit, on execution of the instructions, instructs the first logic unit to associate a new virtual machine identifier with the new virtual central processing unit where it is determined that the new virtual central processing unit is associated with a new virtual machine, and to associate an existing virtual machine identifier with the new virtual central processing unit where it is determined that the new virtual central processing unit is associated with an existing virtual machine.

8. The at least one non-transitory computer-readable medium of claim 1, wherein the first logic unit, on execution of the instructions, provides, to the second logic unit, in response to initialization of a new virtual central processing unit, an association between the new virtual central processing unit, a virtual machine, and one or more extended page tables.

9. The at least one non-transitory computer-readable medium of claim 8, wherein the second logic unit, on execution of the instructions, determines, based at least in part on the one or more extended page tables, whether the new virtual central processing unit is associated with a new virtual machine or an existing virtual machine.

10. The at least one non-transitory computer-readable medium of claim 1, wherein the first logic unit comprises a microprogram.

11. The at least one non-transitory computer-readable medium of claim 1, wherein the first logic unit has execution privilege higher than execution privilege of the virtual machine monitor and is able to observe creation of new virtual central processing units.

12. The at least one non-transitory computer-readable medium of claim 1, wherein the second logic unit is part of one or more of a microcontroller, a baseboard management controller and a system management mode component.

13. The at least one non-transitory computer-readable medium of claim 1, wherein the second logic unit has execution privileges higher than execution privileges of the virtual machine monitor.

14. The at least one non-transitory computer-readable medium of claim 1, wherein the first logic unit, on execution of the instructions, initiates a cache quality-of-service monitor or a memory bandwidth monitor to collect the data about the resources used by the one or more physical processing units to operate the one or more virtual central processing units.

15. A system comprising:

one or more physical processing units configured to operate a plurality of virtual central processing units to operate a plurality of virtual machines, and a virtual machine monitor to manage the virtual machines;

a per-virtual machine resource monitor configured to associate one or more of the virtual central processing units with a first virtual machine of the virtual machines, and to collect data about resources used by the one or more physical processing units to operate the one or more virtual central processing units associated with the first virtual machine, wherein the per-virtual machine resource monitor performs the association and the collection independent of the virtual machine monitor; and

a platform-level aggregator configured to aggregate the collected data to determine resources used by the first virtual machine, wherein the platform-level aggregator performs the aggregating independent of the virtual machine monitor.

16. The system of claim 15, wherein the per-virtual machine resource monitor is further configured to store, in one or more virtual machine control structures associated with the one or more virtual central processing units, an identifier of the first virtual machine.

17. The system of claim 15, wherein the platform-level aggregator is configured to allocate a resource monitor identifier to the first virtual machine, in response to a request to monitor resource-usage of the first virtual machine, and direct the per-virtual machine resource monitor to store, in one or more virtual machine control structures associated with the one or more virtual central processing units, the resource monitor identifier;

and

wherein the per-virtual machine resource monitor is further configured to collect the data about resources used by the one or more physical processing units based on operations performed by the one or more physical processing units that involve the one or more virtual machine control structures with the resource monitor identifier.

18. The system of claim 15, wherein the per-virtual machine resource monitor is further configured to provide, to the platform-level aggregator, in response to initialization of a new virtual central processing unit, an association between the new virtual central processing unit and a virtual machine.

19. The system of claim 18, wherein the platform-level aggregator is further configured to determine, based at least in part on the association provided by the per-virtual machine resource monitor, whether the new virtual central processing unit is associated with a new virtual machine or an existing virtual machine.

20. The system of claim 19, wherein the platform-level aggregator is further configured to instruct the per-virtual machine resource monitor to associate a new virtual machine identifier with the new virtual central processing unit where it is determined that the new virtual central processing unit is associated with a new virtual machine, and to associate an existing virtual machine identifier with the new virtual central processing unit where it is determined that the new virtual central processing unit is associated with an existing virtual machine.

21. The system of claim 15, wherein the per-virtual machine resource monitor is further configured to provide, to the platform-level aggregator, in response to initialization of a new virtual central processing unit, an association between the new virtual central processing unit, a virtual machine, and one or more extended page tables;

and

the platform-level aggregator is further configured to determine, based at least in part on the one or more extended page tables, whether the new virtual central processing unit is associated with a new virtual machine or an existing virtual machine.

22. The system of claim 15, wherein the per-virtual machine resource monitor comprises a microprogram.

23. The system of claim 15, wherein the virtual machine monitor is a first virtual machine monitor, and the per-virtual machine resource monitor or platform-level aggregator comprises a second virtual machine monitor with an execution privilege higher than an execution privilege of the first virtual machine monitor.

24. The system of claim 15, wherein the platform-level aggregator comprises one or more of a microcontroller, a baseboard management controller and a system management mode component.

25. The system of claim 15, wherein the per-virtual machine resource monitor is configured to initiate a cache quality of service monitor to collect the data about the resources used by the one or more physical processing units to operate the one or more virtual central processing units.

26. The system of claim 15, wherein the per-virtual machine resource monitor is configured to initiate a memory bandwidth monitor to collect the data about the resources used by the one or more physical processing units to operate the one or more virtual central processing units.

27. A computer-implemented method, comprising:

directing, by a first logic unit of a computing device, a second logic unit of the computing device to collect data about resources used by one or more physical processing units of the computing device to operate a first virtual machine of a plurality of virtual machines;

associating, by the second logic unit, one or more virtual central processing units operated by the one or more physical processing units of the computing device with the first virtual machine;

collecting, by the second logic unit, data about resources used by the one or more physical processing units to operate the one or more virtual central processing units associated with the first virtual machine; and

aggregating, by the first logic unit, the collected data to determine resource-usage by the first virtual machine;

wherein the first logic unit performs the directing and the determining independent of a virtual machine monitor of the computing device, and wherein the second logic unit performs the associating and the collecting independent of the virtual machine monitor of the computing device.

28. The computer-implemented method of claim 27, further comprising storing, by the second logic unit, in one or more virtual machine control structures associated with the one or more virtual central processing units, an identifier of the first virtual machine.

29. The computer-implemented method of claim 27, further comprising allocating, by the first logic unit, a resource monitor identifier to the first virtual machine, in response to a request to monitor resource-usage of the first virtual machine;

directing, by the first logic unit, the second logic unit to store, in one or more virtual machine control structures associated with the one or more virtual central processing units, the resource monitor identifier, and

collecting, by the second logic unit, the data about resources used by the one or more physical processing units based on operations performed by the one or more physical processing units that involve the one or more virtual machine control structures with the resource monitor identifier.

30. The computer-implemented method of claim 27, further comprising:

providing, by the second logic unit, to the first logic unit, in response to initialization of a new virtual central processing unit, an association between the new virtual central processing unit and a virtual machine; and

determining, by the first logic unit, based at least in part on the association provided by the second logic unit, whether the new virtual central processing unit is associated with a new virtual machine or an existing virtual machine.