Dynamically Move Heterogeneous Cloud Resources Based on Workload Analysis

• US 20150172205A1
• Filed: 12/13/2013
• Published: 06/18/2015
• Est. Priority Date: 12/13/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Anderson, Jason L., Bhatia, Nimesh, Boss, Gregory J., Singh, Animesh
• Granted Patent: US 9,246,840 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation

Abstract

An approach is provided for an information handling system to scale a workload being executed in a cloud computing environment. In the approach, performance of the workload is analyzed by using more than one resource configuration. The resource configurations use different resources that are available in the cloud computing environment. The analysis of the workload results in test results. At least one of the resource configurations is directed to a scaling up of resources that alters resources assigned to a first virtual machine (VM) running the workload. Another resource configuration is directed to a scaling out of resources that adds one or more VMs to a second VM creating a number of VMs running the workload. The test results are compared and an optimal test result is selected. A workload scaling profile is optimized according to the selected optimal test result.

Claims

1. A method, in an information handling system comprising a processor and a memory, of scaling a workload being executed in a cloud computing environment, the method comprising:

analyzing a performance of the workload using a plurality of resource configurations using a plurality of resources available in the cloud computing environment, the analyzing resulting in a plurality of test results, wherein at least one of the resource configurations is directed to a scaling up of resources that alters resources assigned to a first virtual machine (VM) running the workload, and wherein at least one of the resource configurations is directed to a scaling out of resources that adds one or more VMs to a second VM creating a first plurality of VMs running the workload;

comparing the plurality of test results, the comparison resulting in a selected optimal test result; and

optimizing a workload scaling profile that corresponds to the workload using the selected optimal test result.

2. The method of claim 1 wherein at least one of the resource configurations is directed to a diagonal scaling of resources that scales a third VM both up and out by adding one or more VMs to the third VM creating a second plurality of VMs running the workload and by altering resources assigned to the second plurality of VMs.

3. The method of claim 1 further comprising:

creating a mirror image of the first VM to create the second VM, wherein the first and second VMs are both running in the cloud computing environment;

scaling the first VM up by adding the additional resources to the first VM;

scaling the second VM out by adding the one or more VMs to the second VM creating the first plurality of VMs; and

processing incoming traffic by both the first VM and the first plurality of VMs to create a first set of test results corresponding to the first VM and a second set of test results corresponding to the second VM, wherein both the first and second sets of test results are included in the plurality of test results.

4. The method of claim 3 wherein at least one of the additional resources added to the first VM is selected from the group consisting of additional CPU resources, additional memory, additional IP addresses, and additional network bandwidth.

5. The method of claim 1 further comprising:

prior to the analyzing, detecting that the workload is stressed by comparing one or more performance metrics exceed one or more thresholds, wherein the analyzing, comparing, and optimizing are performed in response to the workload not having the workload scaling profile prior to the detecting.

6. The method of claim 1 further comprising:

prior to the analyzing, detecting that the workload is stressed by comparing one or more performance metrics exceed one or more thresholds, wherein the analyzing, comparing, and optimizing are performed in response to the workload already having the workload scaling profile prior to the detecting; and

wherein the workload scaling profile is updated based on the selected optimal test result.

7. The method of claim 6 further comprising:

using a first preferred scaling approach prior to the analyzing, and using a second preferred scaling approach in response to the analyzing, comparing, and optimizing, wherein the first and second scaling approaches are selected from a group consisting of the scaling up and the scaling out.

8. An information handling system comprising:

one or more processors;

a memory coupled to at least one of the processors; and

a set of instructions stored in the memory and executed by at least one of the processors to scale a workload being executed in a cloud computing environment, wherein the set of instructions perform actions of;

analyzing a performance of the workload using a plurality of resource configurations using a plurality of resources available in the cloud computing environment, the analyzing resulting in a plurality of test results, wherein at least one of the resource configurations is directed to a scaling up of resources that alters resources assigned to a first virtual machine (VM) running the workload, and wherein at least one of the resource configurations is directed to a scaling out of resources that adds one or more VMs to a second VM creating a first plurality of VMs running the workload;

comparing the plurality of test results, the comparison resulting in a selected optimal test result; and

optimizing a workload scaling profile that corresponds to the workload using the selected optimal test result.

9. The information handling system of claim 8 wherein at least one of the resource configurations is directed to a diagonal scaling of resources that scales a third VM both up and out by adding one or more VMs to the third VM creating a second plurality of VMs running the workload and by altering resources assigned to the second plurality of VMs.

10. The information handling system of claim 8 where the actions further comprise:

creating a mirror image of the first VM to create the second VM, wherein the first and second VMs are both running in the cloud computing environment;

scaling the first VM up by adding the additional resources to the first VM;

scaling the second VM out by adding the one or more VMs to the second VM creating the first plurality of VMs; and

processing incoming traffic by both the first VM and the first plurality of VMs to create a first set of test results corresponding to the first VM and a second set of test results corresponding to the second VM, wherein both the first and second sets of test results are included in the plurality of test results.

11. The information handling system of claim 10 wherein at least one of the additional resources added to the first VM is selected from the group consisting of additional CPU resources, additional memory, additional IP addresses, and additional network bandwidth.

12. The information handling system of claim 8 where the actions further comprise:

prior to the analyzing, detecting that the workload is stressed by comparing one or more performance metrics exceed one or more thresholds, wherein the analyzing, comparing, and optimizing are performed in response to the workload not having the workload scaling profile prior to the detecting.

13. The information handling system of claim 8 where the actions further comprise:

prior to the analyzing, detecting that the workload is stressed by comparing one or more performance metrics exceed one or more thresholds, wherein the analyzing, comparing, and optimizing are performed in response to the workload already having the workload scaling profile prior to the detecting; and

wherein the workload scaling profile is updated based on the selected optimal test result.

14. The information handling system of claim 13 where the actions further comprise:

using a first preferred scaling approach prior to the analyzing, and using a second preferred scaling approach in response to the analyzing, comparing, and optimizing, wherein the first and second scaling approaches are selected from a group consisting of the scaling up and the scaling out.

15. A computer program product stored in a computer readable medium, comprising computer instructions that, when executed by an information handling system, causes the information handling system to scale a workload being executed in a cloud computing environment by performing actions comprising:

analyzing a performance of the workload using a plurality of resource configurations using a plurality of resources available in the cloud computing environment, the analyzing resulting in a plurality of test results, wherein at least one of the resource configurations is directed to a scaling up of resources that alters resources assigned to a first virtual machine (VM) running the workload, and wherein at least one of the resource configurations is directed to a scaling out of resources that adds one or more VMs to a second VM creating a first plurality of VMs running the workload;

comparing the plurality of test results, the comparison resulting in a selected optimal test result; and

optimizing a workload scaling profile that corresponds to the workload using the selected optimal test result.

16. The computer program product of claim 15 wherein at least one of the resource configurations is directed to a diagonal scaling of resources that scales a third VM both up and out by adding one or more VMs to the third VM creating a second plurality of VMs running the workload and by altering resources assigned to the second plurality of VMs.

17. The computer program product of claim 15 where the actions further comprise:

creating a mirror image of the first VM to create the second VM, wherein the first and second VMs are both running in the cloud computing environment;

scaling the first VM up by adding the additional resources to the first VM;

scaling the second VM out by adding the one or more VMs to the second VM creating the first plurality of VMs; and

processing incoming traffic by both the first VM and the first plurality of VMs to create a first set of test results corresponding to the first VM and a second set of test results corresponding to the second VM, wherein both the first and second sets of test results are included in the plurality of test results.

18. The computer program product of claim 17 wherein at least one of the additional resources added to the first VM is selected from the group consisting of additional CPU resources, additional memory, additional IP addresses, and additional network bandwidth.

19. The computer program product of claim 15 where the actions further comprise:

prior to the analyzing, detecting that the workload is stressed by comparing one or more performance metrics exceed one or more thresholds, wherein the analyzing, comparing, and optimizing are performed in response to the workload not having the workload scaling profile prior to the detecting.

20. The computer program product of claim 15 where the actions further comprise:

prior to the analyzing, detecting that the workload is stressed by comparing one or more performance metrics exceed one or more thresholds, wherein the analyzing, comparing, and optimizing are performed in response to the workload already having the workload scaling profile prior to the detecting; and

wherein the workload scaling profile is updated based on the selected optimal test result.