Dynamic feedback control of resources in computing environments
A method for controlling resource allocation is provided. The method includes determining a service metric associated with a first application, wherein the first application is associated with one or more virtual machines. The method further includes comparing the service metric to an application specific service level goal associated with the first application and modifying a resource allocation associated with the first application at one or more of the virtual machines.
1. A computer implemented method for controlling resource allocation comprising:
determining application specific service level goals for at least one multi-tier application, said at least one multi-tier application hosted across at least one of a first virtual machine operating on a first computer system and a second virtual machine operating on a second computer system, wherein a first layer on said first virtual machine hosts a first tier of said at least one multi-tier application and a second layer on said first virtual machine hosts a second tier of said at least one multi-tier application;
measuring at least one service metric associated with said at least one multi-tier application, wherein said at least one service metric is based on a perspective of a client computer interacting with said at least one multi-tier application;
comparing said at least one service metric to said application specific service level goals;
based on said comparing, determining that said at least one multi-tier application is not meeting a threshold performance service level;
determining that said first virtual machine lacks additional resources for allocation to enable full operation of said first and second tier thereon; and
modifying a resource allocation associated with said at least one multi-tier application at at least one of said first virtual machine and said second virtual machine, wherein said modifying comprises:
prioritizing an operation of either said first tier or said second tier; and
based on said prioritizing, allocating resources of said first virtual machine such that a prioritized tier is fully enabled for operation.
2. The computer implemented method as described in claim 1 , wherein said measuring said at least one service metric comprises:
determining an average end-to-end response time associated with said at least one multi-tier application.
3. The computer implemented method as described in claim 1 , further comprising:
determining resource availability at one or more virtual machines associated with said at least one multi-tier application.
4. The computer implemented method as described in claim 1 , further comprising:
determining a prioritization associated with said at least one multi-tier application.
5. The computer implemented method as described in claim 4 , further comprising:
comparing said prioritization associated with a first multi-tier application of said at least one multi-tier application to a prioritization associated with a second multi-tier application of said at least one multi-tier application; and
modifying resource allocations associated with said first multi-tier application and said second multi-tier application at one or more virtual machines associated with said at least one multi-tier application based on said prioritization.
6. The computer implemented method as described in claim 1 , further comprising:
modifying said application specific service level goals associated with said first multi-tier application.
7. A non-transitory computer readable storage medium comprising executable instructions which, when executed in a processing system, causes the system to perform a method for controlling resource utilization, said method comprising:
determining application specific service level goals for at least one multi-tier application, said at least one multi-tier application hosted across at least one of a first virtual machine operating on a first computer system and a second virtual machine operating on a second computer system, wherein a first layer on said first virtual machine hosts a first tier of said at least one multi-tier application and a second layer on said first virtual machine hosts a second tier of said at least one multi-tier application;
measuring at least one service metric associated with said at least one multi-tier application, wherein said at least one service metric is based on a perspective of a client computer interacting with said at least one multi-tier application;
comparing said at least one service metric to said application specific service level goals;
based on said comparing, determining that said at least one multi-tier application is not meeting a threshold performance service level;
determining that said first virtual machine lacks additional resources for allocation to enable full operation of said first and second tier thereon; and
modifying a resource allocation associated with said at least one multi-tier application at at least one of said first virtual machine and said second virtual machine, wherein said modifying comprises:
prioritizing an operation of either said first tier or said second tier; and
based on said prioritizing, allocating resources of said first virtual machine such that a prioritized tier is fully enabled for operation.
8. The non-transitory computer readable storage medium as described in claim 7 , wherein said measuring said at least one service metric comprises:
determining an average end-to-end response time associated with said at least one multi-tier application.
9. The non-transitory computer readable storage medium as described in claim 7 , wherein said method further comprises:
determining resource availability at one or more virtual machines associated with said at least one multi-tier application.
10. The non-transitory computer readable storage medium as described in claim 7 , wherein said method further comprises:
determining a prioritization associated with said at least one multi-tier application.
11. The non-transitory computer readable storage medium as described in claim 10 , wherein said method further comprises:
comparing said prioritization associated with a first multi-tier application of said at least one multi-tier application to a prioritization associated with a second multi-tier application of said at least one multi-tier application; and
modifying resource allocations associated with said first multi-tier application and said second multi-tier application at one or more virtual machines associated with said at least one multi-tier application based on said prioritization.
12. The non-transitory computer readable storage medium as described in claim 7 , wherein said method further comprises:
modifying said application specific service level goals associated with said first multi-tier application.