OPTIMIZING VIRTUAL MACHINES PLACEMENT IN CLOUD COMPUTING ENVIRONMENTS

• US 20130097601A1
• Filed: 10/09/2012
• Published: 04/18/2013
• Est. Priority Date: 10/12/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Podvratnik, Amadeus, Spatzier, Thomas, Teich, Torsten
• Granted Patent: US 9,495,215 B2
• Time in Patent Office: Days
• US Class Current: 718/1
• CPC Class Codes: G06F 2009/45562 Creating, deleting, cloning virtual machine instances
• CPC Class Codes: G06F 2009/45591 Monitoring or debugging support
• CPC Class Codes: G06F 2209/5019 Workload prediction
• CPC Class Codes: G06F 8/61 Installation
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals
• CPC Class Codes: G06F 9/5072 Grid computing
• 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

Placement of instances of virtual machine (VM) images in a cloud computing environment is optimized. A request is received to deploy a new VM image instance. User-specific and generic VM resource usage profiles are read that include resource consumption data. Resource pool profiles for multiple resource pools are read that include resource consumption data for the resource pools. For each of the resource pool profiles, a selected VM resource usage profile is analyzed and aligned with the resource pool profiles. An aggregated resource consumption profile is calculated. A determination is made of one of multiple resource pools with the least aggregated resource consumption.

Claims

1. A method for optimizing the placement of instances of a plurality of virtual machine images in a cloud environment, the cloud environment comprising a plurality of resource pools, each resource pool comprising one or more resources, comprising:

receiving a request from a user to deploy a new instance of one of the virtual machine (VM) images, where the request indicates a VM image to be instantiated;

reading, by a placement engine, a VM resource usage profile stored in association with the indicated VM image, the VM resource usage profile comprising first resource consumption data, the first resource consumption data indicating a predicted resource consumption of the requested instance of the indicated VM image over a first period of time;

reading, by the placement engine, one resource pool profile for each of the plurality of resources pools, each resource pool profile comprising second resource consumption data, the second resource consumption data indicating a predicted resource consumption in a resource pool associated with the resource pool profile over a second period of time, the resource pool profile further comprising a current resource consumption on the resource pool;

reading, if available, a user-specific VM resource usage profile stored in association with the indicated VM image and stored in association with an identifier of the user, the user-specific VM resource usage profile comprising third resource usage data, the third resource usage data indicating a predicted user-specific resource consumption of the requested instance of the indicated VM image over the first period of time;

for each of the resource pool profiles, by the placement engine;

generating a resulting VM resource usage profile by selecting one of the user-specific VM resource usage profile, where the user-specific VM resource usage profile is available, and the VM resource usage profile;

analyzing the resulting VM resource usage profile and the resource pool profile, the analysis comprising aligning the resulting VM resource usage profile and the resource pool profile by aligning the second period of time of the resource pool profile of the resource pool with the first period of time of the resulting VM resource usage profile; and

calculating an aggregated resource consumption profile that predicts a total resource consumption on the resource pool by aggregating the resource consumption of the aligned profiles; and

determining, as a result of the analysis of all resource pool profiles, the one of the plurality of resource pools with a least aggregated resource consumption.

2. The method of claim 1, further comprising:

instantiating the indicated VM image on the determined one of the plurality of resource pools with the least aggregated resource consumption.

3. The method of claim 1, further comprising:

receiving an additional request from the user to use a separate user-selected VM resource usage profile instead of the user-specific VM resource usage profile stored in association with the indicated VM image and in association with the identifier of the user; and

using the user-selected VM resource usage profile instead of the user-specific VM resource usage profile when executing the analysis.

4. The method of claim 1, where the one of the plurality of resource pools with the least aggregated resource consumption is selected from a group consisting of:

a resource pool for which a lowest integral resource consumption value of the aggregated resource consumption profile was calculated; and

a resource pool for which the lowest integral resource consumption value of the aggregated resource consumption profile was calculated and where the aggregated resource consumption profile does not comprise a value exceeding a resource consumption threshold value.

5. The method of claim 1, where the user-specific VM resource usage profile comprises rules, and further comprising:

applying, when executing the analysis, the rules on at least one of the VM resource usage profile, the user-specific VM resource usage profile, and the resource pool profiles.

6. The method of claim 5, where at least some of the rules comprise user-specific conditions on at least one of a number, a type, and an availability of resources for guaranteeing that at least one of the number, the type, and the availability of the resources allocated to the requested VM image instance is in accordance with a service level agreement (SLA).

7. The method of claim 1, further comprising generating the VM resource usage profile of at least one of the plurality of VM images by:

evaluating, by a VM usage supervisor module, a current resource consumption of all instances of the at least one of the plurality of VM images to provide first evaluated data;

predicting resource consumption of any instance of the at least one of the plurality of VM images over the first period of time by evaluating the first evaluated data; and

updating the VM resource usage profile stored in association with the at least one of the plurality of VM images with the predicted resource consumption.

8. The method of claim 1, further comprising generating the user-specific VM resource usage profile of at least one of the plurality of VM images by:

monitoring, by a VM usage supervisor module, a current resource consumption of all instances of the at least one of the plurality of VM images whose instantiation has been requested by the user to provide second monitoring data;

predicting resource consumption of any instance of the at least one of the plurality of VM images to be requested by the user over the second period of time by evaluating the second monitoring data; and

updating the user-specific VM resource usage profile stored in association with the at least one of the plurality of VM images with the predicted resource consumption.

9. The method of claim 1, further comprising generating the resource pool profiles by, for each of the plurality of resource pools:

monitoring a number and a type of the resources of the resource pool allocated to one instance of the plurality of VM images running on the resource pool to provide second monitoring data, the second monitoring data comprising a measured physical assignment of resources to the VM image instances over the second period of time;

superposing the second monitoring data obtained for all instances of the plurality of VM images running on the resource pool to generate a superposed resource consumption profile for the resource pool; and

using the superposed resource consumption profile to one of generate and update the resource pool profile of the resource pool.

10. The method of claim 1, where each VM image instance running on one of the plurality of resource pools has assigned one or more resources of the resource pool, and further comprising:

determining, by a VM usage supervisor, all resources in the one of the plurality of resource pools that are unoccupied over the second period of time by subtracting the aggregated resource consumption profile from a known number of all resources of the one of the plurality of resource pools;

determining, for the requested VM image instance to be instantiated on the one of the plurality of resource pools, one or more currently required resources by evaluating one of the VM resource usage profile and the user-specific VM resource usage profile of the indicated VM image; and

triggering, by the placement engine, the instantiation of the requested VM image instance on another resource pool if a number of resources of a first resource type determined to be required by the requested VM image instance exceeds the determined number of currently unoccupied resources of the first resource type in the one of the plurality of resource pools.

11. The method of claim 1, further comprising performing, by a resource manager, a reallocation of at least one resource allocated to the deployed VM image upon its instantiation, where the aggregated resource consumption profile is used as input for determining one of the VM image instances to which the at least one resource is to be reallocated.

12. The method of claim 11, further comprising updating the resource pool profiles of the plurality of resource pools with new resource consumption data resulting from the reallocation of the at least one resource or from a movement of the VM image instance.

13. The method of claim 1, where one of the first resource consumption data specified in the VM resource usage profile and the third resource usage data specified in the user-specific VM resource usage profile is used to determine if the resources required by the requested VM image instance in one or more future moments of time will be available in one of the plurality of resource pools in the one or more future moments in time.

14. A system, comprising:

a storage device comprising a plurality of virtual machine (VM) images;

a plurality of resource pools, each resource pool comprising one or more resources;

an interface configured to receive a request from a user to deploy a new instance of one of the VM images, where the request indicates a VM image to be instantiated;

a placement engine configured to;

read a VM resource usage profile stored in association with the indicated VM image, the VM resource usage profile comprising first resource consumption data, the first resource consumption data indicating a predicted resource consumption of the requested instance of the indicated VM image over a first period of time;

read one resource pool profile for each of the plurality of resources pools, each resource pool profile comprising second resource consumption data, the second resource consumption data indicating a predicted resource consumption in a resource pool associated with the resource pool profile over a second period of time, the resource pool profile further comprising a current resource consumption on the resource pool;

read, if available, a user-specific VM resource usage profile stored in association with the indicated VM image and stored in association with an identifier of the user, the user-specific VM resource usage profile comprising third resource usage data, the third resource usage data indicating a predicted user-specific resource consumption of the requested instance of the indicated VM image over the first period of time;

for each of the resource pool profiles;

generate a resulting VM resource usage profile by selecting one of the user-specific VM resource usage profile, where the user-specific VM resource usage profile is available, and the VM resource usage profile;

analyze the resulting VM resource usage profile and the resource pool profile, the analysis comprising aligning the resulting VM resource usage profile and the resource pool profile by aligning the second period of time of the resource pool profile of the resource pool with the first period of time of the resulting VM resource usage profile; and

calculate an aggregated resource consumption profile that predicts a total resource consumption on the resource pool by aggregating the resource consumption of the aligned profiles; and

determine, as a result of the analysis of all resource profiles, the one of the plurality of resource pools with a least aggregated resource consumption.

15. The system of claim 14, where the placement engine is further configured to:

instantiate the indicated VM image on the determined one of the plurality of resource pools with the least aggregated resource consumption.

16. The system of claim 14, where:

the interface is further configured to receive an additional request from the user to use a separate user-selected VM resource usage profile instead of the user-specific VM resource usage profile stored in association with the indicated VM image and in association with the identifier of the user; and

the placement engine is further configured to use the user-selected VM resource usage profile instead of the user-specific VM resource usage profile when executing the analysis.

17. The system of claim 14, where the one of the plurality of resource pools with the least aggregated resource consumption is selected from a group consisting of:

a resource pool for which a lowest integral resource consumption value of the aggregated resource consumption profile was calculated; and

a resource pool for which the lowest integral resource consumption value of the aggregated resource consumption profile was calculated and where the aggregated resource consumption profile does not comprise a value exceeding a resource consumption threshold value.

18. The system of claim 14, where the user-specific VM resource usage profile comprises rules, and where the placement engine is further configured to:

apply, when executing the analysis, the rules on at least one of the VM resource usage profile, the user-specific VM resource usage profile, and the resource pool profiles.

19. The system of claim 18, where at least some of the rules comprise user-specific conditions on at least one of a number, a type, and an availability of resources for guaranteeing that at least one of the number, the type, and the availability of the resources allocated to the requested VM image instance is in accordance with a service level agreement (SLA).

20. A computer program product for optimizing the placement of instances of a plurality of virtual machine images in a cloud environment, the cloud environment comprising a plurality of resource pools, each resource pool comprising one or more resources, comprising:

a computer readable storage medium having computer readable program code embodied therewith, where the computer readable program code when executed on a computer causes the computer to;

receive a request from a user to deploy a new instance of one of the virtual machine (VM) images, where the request indicates a VM image to be instantiated;

read a virtual machine (VM) resource usage profile stored in association with the indicated VM image, the VM resource usage profile comprising first resource consumption data, the first resource consumption data indicating a predicted resource consumption of the requested instance of the indicated VM image over a first period of time;

read one resource pool profile for each of the plurality of resources pools, each resource pool specific profile comprising second resource consumption data, the second resource consumption data indicating a predicted resource consumption in a resource pool associated with the resource pool profile over a second period of time, the resource pool profile further comprising a current resource consumption on the resource pool;

read, if available, a user-specific VM resource usage profile stored in association with the indicated VM image and stored in association with an identifier of the user, the user-specific VM resource usage profile comprising third resource usage data, the third resource usage data indicating a predicted user-specific resource consumption of the requested instance of the indicated VM image over the first period of time;

for each of the resource pool profiles;

generate a resulting VM resource usage profile by selecting one of the user-specific VM resource usage profile, where the user-specific VM resource usage profile is available, and the VM resource usage profile;

analyze the resulting VM resource usage profile and the resource pool profile, the analysis comprising aligning the resulting VM resource usage profile and the resource pool profile by aligning the second period of time of the resource pool profile of the resource pool with the first period of time of the resulting VM resource usage profile; and

calculate an aggregated resource consumption profile that predicts a total resource consumption on the resource pool by aggregating the resource consumption of the aligned profiles; and

determine, as a result of the analysis of all resource profiles, the one of the plurality of resource pools with a least aggregated resource consumption.

21. The computer program product of claim 20, where the computer readable program code when executed on the computer further causes the computer to:

instantiate the indicated VM image on the determined one of the plurality of resource pools with the least aggregated resource consumption.

22. The computer program product of claim 20, where the computer readable program code when executed on the computer further causes the computer to:

receive an additional request from the user to use a separate user-selected VM resource usage profile instead of the user-specific VM resource usage profile stored in association with the indicated VM image and in association with the identifier of the user; and

use the user-selected VM resource usage profile instead of the user-specific VM resource usage profile when executing the analysis.

23. The computer program product of claim 20, where the one of the plurality of resource pools with the least aggregated resource consumption is selected from a group consisting of:

a resource pool for which a lowest integral resource consumption value of the aggregated resource consumption profile was calculated; and

a resource pool for which the lowest integral resource consumption value of the aggregated resource consumption profile was calculated and where the aggregated resource consumption profile does not comprise a value exceeding a resource consumption threshold value.

24. The computer program product of claim 20, where the user-specific VM resource usage profile comprises rules, and where the computer readable program code when executed on the computer further causes the computer to:

apply, when executing the analysis, the rules on at least one of the VM resource usage profile, the user-specific VM resource usage profile, and the resource pool profiles.

25. The computer program product of claim 24, where at least some of the rules comprise user-specific conditions on at least one of a number, a type, and an availability of resources for guaranteeing that at least one of the number, the type, and the availability of the resources allocated to the requested VM image instance is in accordance with a service level agreement (SLA).