ALLOCATING RESOURCES TO VIRTUAL MACHINES VIA A WEIGHTED COST RATIO

• US 20130263117A1
• Filed: 03/28/2012
• Published: 10/03/2013
• Est. Priority Date: 03/28/2012
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Konik, Rafal P., Mittelstadt, Roger A., Muras, Brian R., Theuer, Mark W.
• Application Number:
  US13/432,815
• Publication Number:
  US 20130263117A1
• Time in Patent Office: Days
• US Class Current: 718/1
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• 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

In an embodiment, a plurality of estimates of costs of executing a plurality of respective queries is received from a plurality of respective virtual machines using a plurality of respective estimated resources allocated to the plurality of respective virtual machines. A selected virtual machine of the plurality of respective virtual machines is selected with a lowest weighted cost ratio, as compared to all other of the plurality of respective virtual machines. A source virtual machine is found with a lowest current resource usage. An amount of a resource to deallocate from the source virtual machine is calculated, which further comprises estimating the amount of the resource to deallocate that does not raise the lowest current resource usage over a maximum resource threshold. The amount of the resource from the source virtual machine is deallocated. The amount of the resource is allocated to the selected virtual machine.

Claims

1. A method comprising:

receiving a plurality of estimates of costs of executing a plurality of respective queries from a plurality of respective virtual machines using a plurality of respective estimated resources allocated to the plurality of respective virtual machines;

selecting a selected virtual machine of the plurality of respective virtual machines with a lowest weighted cost ratio as compared to all other of the plurality of respective virtual machines;

finding a source virtual machine from among the plurality of respective virtual machines with a lowest current resource usage percentage;

calculating an amount of a resource to deallocate from the source virtual machine, wherein the calculating further comprises estimating the amount of the resource to deallocate that does not raise the lowest current resource usage percentage of the source virtual machine over a maximum resource threshold;

deallocating the amount of the resource from the source virtual machine; and

allocating the amount of the resource to the selected virtual machine.

2. The method of claim 1, further comprising:

executing one of the plurality of respective queries at the selected virtual machine using the amount of the resource allocated by the allocating.

3. The method of claim 1, wherein the selecting the selected virtual machine of the plurality of respective virtual machines with the lowest weighted cost ratio as compared to all other of the plurality of respective virtual machines further comprises:

calculating a plurality of weighted cost ratios for the plurality of respective virtual machines, wherein the calculating the plurality of weighted cost ratios for the plurality of respective virtual machines further comprises multiplying a priority of the respective virtual machine by an estimated cost squared of an estimated amount of a resource divided by a current cost of a current amount of the resource allocated to the virtual machine.

4. The method of claim 1, wherein the estimating the amount of the resource to deallocate from the source virtual machine that does not raise the lowest current resource usage percentage of the source virtual machine over a maximum resource threshold further comprises:

multiplying the lowest current resource usage percentage of the source virtual machine by an amount of current resources allocated to the source virtual machine; and

dividing a result of the multiplying by an amount of estimated resources present after prospective deallocation from the source virtual machine to create a resultant estimated usage.

5. The method of claim 4, further comprising:

comparing the resultant estimated usage to the maximum resource threshold; and

if the resultant estimated usage is greater than the maximum resource threshold, refraining from deallocating the amount of the resource from the source virtual machine.

6. The method of claim 5, further comprising:

if the resultant estimated usage is greater than the maximum resource threshold, recomputing the resultant estimated usage from a different amount of estimated resources present.

7. The method of claim 6 further comprising:

if the resultant estimated usage is less than or equal to the maximum resource threshold, deallocating the amount of the resource from the source virtual machine.

8. The method of claim 1, wherein the plurality of respective queries comprise a workload.

9. A computer-readable medium encoded with instructions, wherein the instructions when executed comprise:

receiving a plurality of estimates of costs of executing a plurality of respective queries from a plurality of respective virtual machines using a plurality of respective estimated resources allocated to the plurality of respective virtual machines;

selecting a selected virtual machine of the plurality of respective virtual machines with a lowest weighted cost ratio as compared to all other of the plurality of respective virtual machines;

finding a source virtual machine from among the plurality of respective virtual machines with a lowest current resource usage percentage;

calculating an amount of a resource to deallocate from the source virtual machine, wherein the calculating further comprises estimating the amount of the resource to deallocate that does not raise the lowest current resource usage percentage of the source virtual machine over a maximum resource threshold;

deallocating the amount of the resource from the source virtual machine;

allocating the amount of the resource to the selected virtual machine; and

executing one of the plurality of respective queries at the selected virtual machine using the amount of the resource allocated by the allocating.

10. The computer-readable medium of claim 9, wherein the selecting the selected virtual machine of the plurality of respective virtual machines with the lowest weighted cost ratio as compared to all other of the plurality of respective virtual machines further comprises:

calculating a plurality of weighted cost ratios for the plurality of respective virtual machines, wherein the calculating the plurality of weighted cost ratios for the plurality of respective virtual machines further comprises multiplying a priority of the respective virtual machine by an estimated cost squared of an estimated amount of a resource divided by a current cost of a current amount of the resource allocated to the virtual machine.

11. The computer-readable medium of claim 9, wherein the estimating the amount of the resource to deallocate from the source virtual machine that does not raise the lowest current resource usage percentage of the source virtual machine over a maximum resource threshold further comprises:

multiplying the lowest current resource usage percentage of the source virtual machine by an amount of current resources allocated to the source virtual machine; and

dividing a result of the multiplying by an amount of estimated resources present after prospective deallocation from the source virtual machine to create a resultant estimated usage.

12. The computer-readable medium of claim 11, further comprising:

comparing the resultant estimated usage to the maximum resource threshold; and

if the resultant estimated usage is greater than the maximum resource threshold, refraining from deallocating the amount of the resource from the source virtual machine.

13. The computer-readable medium of claim 12, further comprising:

if the resultant estimated usage is greater than the maximum resource threshold, recomputing the resultant estimated usage from a different amount of estimated resources present.

14. The computer-readable medium of claim 13 further comprising:

if the resultant estimated usage is less than or equal to the maximum resource threshold, deallocating the amount of the resource from the source virtual machine.

15. A computer system comprising:

a processor; and

memory communicatively connected to the processor, wherein the memory is encoded with instructions, and wherein the instructions when executed by the processor comprise

receiving a plurality of estimates of costs of executing a plurality of respective queries from a plurality of respective virtual machines using a plurality of respective estimated resources allocated to the plurality of respective virtual machines,

selecting a selected virtual machine of the plurality of respective virtual machines with a lowest weighted cost ratio as compared to all other of the plurality of respective virtual machines,

finding a source virtual machine from among the plurality of respective virtual machines with a lowest current resource usage percentage,

calculating an amount of a resource to deallocate from the source virtual machine, wherein the calculating further comprises estimating the amount of the resource to deallocate that does not raise the lowest current resource usage percentage of the source virtual machine over a maximum resource threshold,

deallocating the amount of the resource from the source virtual machine,

allocating the amount of the resource to the selected virtual machine, and

executing one of the plurality of respective queries at the selected virtual machine using the amount of the resource allocated by the allocating.

16. The computer system of claim 15, wherein the selecting the selected virtual machine of the plurality of respective virtual machines with the lowest weighted cost ratio as compared to all other of the plurality of respective virtual machines further comprises:

calculating a plurality of weighted cost ratios for the plurality of respective virtual machines, wherein the calculating the plurality of weighted cost ratios for the plurality of respective virtual machines further comprises multiplying a priority of the respective virtual machine by an estimated cost squared of an estimated amount of a resource divided by a current cost of a current amount of the resource allocated to the virtual machine.

17. The computer system of claim 15, wherein the estimating the amount of the resource to deallocate from the source virtual machine that does not raise the lowest current resource usage percentage of the source virtual machine over a maximum resource threshold further comprises:

multiplying the lowest current resource usage percentage of the source virtual machine by an amount of current resources allocated to the source virtual machine; and

dividing a result of the multiplying by an amount of estimated resources present after prospective deallocation from the source virtual machine to create a resultant estimated usage.

18. The computer system of claim 17, wherein the instructions further comprise:

comparing the resultant estimated usage to the maximum resource threshold; and

if the resultant estimated usage is greater than the maximum resource threshold, refraining from deallocating the amount of the resource from the source virtual machine.

19. The computer system of claim 18, wherein the instructions further comprise:

if the resultant estimated usage is greater than the maximum resource threshold, recomputing the resultant estimated usage from a different amount of estimated resources present.

20. The computer system of claim 19, wherein the instructions further comprise:

if the resultant estimated usage is less than or equal to the maximum resource threshold, deallocating the amount of the resource from the source virtual machine.