Cooperative application workload scheduling for a consolidated virtual environment

Patent metadata

Field	Value
Publication number	US-9304803-B2
Application number	US-201213674180-A
Country	US
Kind code	B2
Filing date	Nov 12, 2012
Priority date	Nov 12, 2012
Publication date	Apr 5, 2016
Grant date	Apr 5, 2016

Abstract

Application resource scheduler module is provided to achieve cooperative application workload scheduling for a consolidated virtual environment. The application resource scheduler aids an application workload scheduler that is part of a distributed computing application, such as Hadoop, to achieve a specified relative priority of the application workload virtual machines to other virtual machines in the virtual environment. The application resource scheduler assists in achieving cooperative workload scheduling by revising the amount of resources that the application workload scheduler sees as available and by setting resource controls for the virtual machines of the distributed computing application to influence the resources the virtual machines receive from the underlying consolidated virtual environment.

First claim

What is claimed is:

1. A method for managing a cluster for a distributed computing application, the method comprising:
receiving, from a user, an indication specifying a workload priority of an application workload for executing a distributed computing application relative to other workloads, wherein the other workloads are not for executing the distributed computing application in a virtualized computing system, wherein the distributed computing application includes a workload scheduler configured to distribute execution of the application workload to a plurality of virtual machines (VMs) allocated from a resource pool within the virtualized computing system;
modifying a resource control for the resource pool based on the workload priority;
responsive to determining that the workload priority indicates a higher priority for executing the distributed computing application relative to the other workloads, determining an amount of available computing resources comprised of resources not reserved by other workloads within the virtualized computing system;
responsive to determining that the workload priority does not indicate a higher priority for executing the distributed computing application relative to the other workloads, determining the amount of available computing resources comprised of inactive resources held by the other workloads within the virtualized computing system; and
modifying a first VM of the plurality of VMs to increase an amount of computing resources seen by the workload scheduler to be available for execution of the application workload based on the determined amount of available computing resources.

2. The method of claim 1 , wherein the step of modifying the resource control for the resource pool comprises:
setting a high shares value for the resource pool based on the workload priority indicating a higher relative priority of the application workload to the other workloads.

3. The method of claim 1 , wherein the step of modifying the first VM of the plurality of VMs further comprises:
launching execution of the first VM, wherein the first VM has a resource allocation based on the determined amount of available computing resources.

4. The method of claim 1 , wherein the step of modifying the first VM of the plurality of VMs further comprises:
modifying a workload capacity of the first VM based on the determined amount of available computing resources, wherein the workload capacity is transmitted to the workload scheduler to advertise an amount of workload that can be handled by the first VM.

5. The method of claim 1 , wherein the step of modifying the resource control for the resource pool comprises:
setting a low shares value for the resource pool based on the workload priority indicating a lower relative priority of the application workload to the other workloads.

6. The method of claim 1 , further comprising:
determining a change in the amount of available computing resources within the virtualized computing system; and
modifying a second VM of the plurality of VMs to decrease the amount of computing resources seen by the workload scheduler to be available for execution of the application workload based on the determined change in the amount of available computing resources.

7. The method of claim 6 , wherein the step of modifying the second VM of the plurality of VMs further comprises:
retrieving, from the workload scheduler, a metric indicating performance of the plurality of VMs within the distributed computing application; and
selecting the second VM for modification based on a determination that the second VM is underutilized according to the retrieved metric.

8. The method of claim 1 , wherein the resource control is used by the virtualized computing system for allocating hardware resources for executing virtual machines.

9. A non-transitory computer-readable storage medium comprising instructions that, when executed in a computing device, manage a cluster for a distributed computing application by performing the steps of:
receiving, from a user, an indication specifying a workload priority of an application workload for executing a distributed computing application relative to other workloads, wherein the other workloads are not for executing the distributed computing application in a virtualized computing system, wherein the distributed computing application includes a workload scheduler configured to distribute execution of the application workload to a plurality of virtual machines (VMs) allocated from a resource pool within the virtualized computing system;
modifying a resource control for the resource pool based on the workload priority;
responsive to determining that the workload priority indicates a higher priority for executing the distributed computing application relative to the other workloads, determining an amount of available computing resources comprised of resources not reserved by other workloads within the virtualized computing system;
responsive to determining that the workload priority does not indicate a higher priority for executing the distributed computing application relative to the other workloads, determining the amount of available computing resources comprised of inactive resources held by the other workloads within the virtualized computing system; and
modifying a first VM of the plurality of VMs to increase an amount of computing resources seen by the workload scheduler to be available for execution of the application workload based on the determined amount of available computing resources.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the step of modifying the resource control for the resource pool comprises:
setting a high shares value for the resource pool based on the workload priority indicating a higher relative priority of the application workload to the other workloads.

11. The non-transitory computer-readable storage medium of claim 9 , wherein the step of modifying the first VM of the plurality of VMs further comprises:
launching execution of the first VM, wherein the first VM has a resource allocation based on the determined amount of available computing resources.

12. The non-transitory computer-readable storage medium of claim 9 , wherein the step of modifying the first VM of the plurality of VMs further comprises:
modifying a workload capacity of the first VM based on the determined amount of available computing resources, wherein the workload capacity is transmitted to the workload scheduler to advertise an amount of workload that can be handled by the first VM.

13. The non-transitory computer-readable storage medium of claim 9 , wherein the step of modifying the resource control for the resource pool comprises:
setting a low shares value for the resource pool based on the workload priority indicating a lower relative priority of the application workload to the other workloads.

14. The non-transitory computer-readable storage medium of claim 9 , further comprising:
determining a change in the amount of available computing resources within the virtualized computing system; and
modifying a second VM of the plurality of VMs to decrease the amount of computing resources seen by the workload scheduler to be available for execution of the application workload based on the determined change in the amount of available computing resources.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the step of modifying the second VM of the plurality of VMs further comprises:
retrieving, from the workload scheduler, a metric indicating performance of the plurality of VMs

Assignees

• Vmware Inc

Inventors

• Nelson Michael
• Gummaraju Jayanth
• Govil Kinshuk
• Holler Anne
• Mcdougall Richard

Classifications

• G06F9/45558 Primary

  Hypervisor-specific management and integration aspects · CPC title

• G06F2009/4557

  Distribution of virtual machine instances; Migration and load balancing · CPC title