System and method of performing a pre-reservation analysis to yield an improved fit of workload with the compute environment

• US 9,778,959 B2
• Filed: 12/13/2013
• Issued: 10/03/2017
• Est. Priority Date: 03/13/2004
• Status: Active Grant

• Current Assignee: III Holdings 12, LLC (Intellectual Ventures LLC)
• Original Assignee: III Holdings 12, LLC (Intellectual Ventures LLC)
• Inventors: Jackson, David B.
• Primary Examiner(s): Zhao, Bing
• Application Number:
  US14/106,254
• Publication Number:
  US 20140101666A1
• Time in Patent Office: 1,390 Days
• Field of Search: None
• CPC Class Codes: G06F 2209/5014 Reservation
• CPC Class Codes: G06F 2209/506 Constraint
• CPC Class Codes: G06F 9/5038 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration scheduling strategies G06F9/4881 and subgroups
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system

Abstract

A system and method are disclosed for receiving a request for resources in a compute environment to process workload, the request including a specification of a quality of fit. The system generates a substantial maximum potential quality of fit based on compute environment with an assumption of no competing workload to yield an analysis. The system evaluates a first resource allocation and a second resource allocation against the analysis to yield the first fit in a respective second fit. The system selects one of the first resource allocation and the second resource allocation based on a comparison of the first fit to the second fit as well as a cost associated with any delays.

Claims

1. A method comprising:

receiving a request for resources in a compute environment to process workload, the request comprising a specification of a quality fit, wherein the specification of the quality fit includes an operating system type and a computer hardware type;

generating a substantially optimal potential quality of fit based on the compute environment and the specification of the quality fit, with an assumption of no competing workload and all the computing resources were healthy and operating at full performance, to yield an analysis;

evaluating a first resource allocation for the workload with different resource allocation and time of allocation than those of the optimal potential quality fit against the analysis to yield a first fit relative to the optimal potential quality fit;

evaluating a second resource allocation for the workload with different resource allocation and time of allocation then those of the optimal potential quality fit and the first fit against the analysis to yield a second fit relative to the optimal potential quality fit; and

selecting one of the first resource allocation or the second resource allocation based on one of a comparison of the first fit to the second fit and a cost associated with a delay in allocation of the first fit or the second fit.

2. The method of claim 1, further comprising:

reserving resources in the compute environment based on the selecting.

3. The method of claim 1, wherein the delay relates to a start time when workload can start in one of the first resource allocation and the second resource allocation.

4. The method of claim 1, wherein one of the first fit and the second fit are based on an application model associated with the workload.

5. The method of claim 1, wherein a first time associated with the first fit provides a variance of fit from a substantial maximum potential quality of fit.

6. The method of claim 1, wherein the potential quality of fit is a substantial maximum potential quality of fit.

7. A system comprising:

a processor; and

a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising;

receiving a request for resources in a compute environment to process workload, the request comprising a specification of a quality fit, wherein the specification of the quality fit includes one of an operating system type and a computer hardware type;

generating a substantially optimal potential quality of fit based on the compute environment and the specification of the quality fit, with an assumption of no competing workload and all the computing resources were healthy and operating at full performance to yield an analysis;

evaluating a first resource allocation for the workload with different resource allocation and time of allocation than those of the optimal potential quality fit against the analysis to yield a first fit relative to the optimal potential quality fit;

evaluating a second resource allocation for the workload with different resource allocation and time of allocation then those of the optimal potential quality fit and the first fit against the analysis to yield a second fit relative to the optimal potential quality fit; and

selecting one of the first resource allocation or the second resource allocation based on one of a comparison of the first fit to the second fit and a cost associated with a delay in allocation of the first fit or the second fit.

8. The system of claim 7, wherein the computer-readable storage medium stores further instructions which, when executed by the processor, cause the processor to perform a further operation comprising:

reserving resources in the compute environment based on the selecting.

9. The system of claim 7, wherein the delay relates to a start time when workload can start in one of the first resource allocation and the second resource allocation.

10. The system of claim 7, wherein one of the first fit and the second fit are based on an application model associated with the workload.

11. The system of claim 7, wherein a first time associated with the first fit provides a variance of fit from a substantial maximum potential quality of fit.

12. The system of claim 7, wherein the potential quality of fit is a substantial maximum potential quality of fit.

13. A non-transitory computer-readable storage device storing instructions which, when executed by the processor, cause the processor to perform operations comprising:

receiving a request for resources in a compute environment to process workload, the request comprising a specification of a quality fit, wherein the specification of the quality fit includes one of an operating system type and a computer hardware type;

generating a substantially optimal potential quality of fit based on the compute environment and the specification of the quality fit, with an assumption of no competing workload and all the computing resources were healthy and operating at full performance to yield an analysis;

evaluating a first resource allocation for the workload with different resource allocation and time of allocation than those of the optimal potential quality fit against the analysis to yield a first fit relative to the optimal potential quality fit;

evaluating a second resource allocation for the workload with different resource allocation and time of allocation then those of the optimal potential quality fit and the first fit against the analysis to yield a second fit relative to the optimal potential quality fit; and

selecting one of the first resource allocation or the second resource allocation based on one of a comparison of the first fit to the second fit and a cost associated with a delay in allocation of the first fit or the second fit.

14. The non-transitory computer-readable storage device of claim 13, wherein the computer-readable storage device stores instructions which, when executed by the processor, cause the processor to perform a further operation comprising:

reserving resources in the compute environment based on the selecting.

15. The non-transitory computer-readable storage device of claim 13, wherein the delay relates to a start time when workload can start in one of the first resource allocation and the second resource allocation.

16. The non-transitory computer-readable storage device of claim 13, wherein one of the first fit and the second fit are based on an application model associated with the workload.

17. The non-transitory computer-readable storage device of claim 13, wherein a first time associated with the first fit provides a variance of fit from a substantial maximum potential quality of fit.

18. The non-transitory computer-readable storage device of claim 13, wherein the potential quality of fit is a substantial maximum potential quality of fit.