Resource evaluation for a batch job and an interactive session concurrently executed in a grid computing environment

• US 7,774,457 B1
• Filed: 03/25/2005
• Issued: 08/10/2010
• Est. Priority Date: 03/25/2005
• Status: Active Grant

• Current Assignee: Valtrus Innovations Limited (f/k/a Dolya Holdco 9 Limited) (Key Patent Innovations Limited)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Kumar, Raj, Talwar, Vanish, Basu, Sujoy
• Primary Examiner(s): Patel; Haresh N
• Application Number:
  US11/090,714
• Time in Patent Office: 1,964 Days
• Field of Search: 709200-203, 709217-228, 718/102, 718/103
• US Class Current: 709/224
• CPC Class Codes: G06F 2209/5016 Session
• CPC Class Codes: G06F 2209/5019 Workload prediction
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: H04L 67/08 specially adapted for terminal emulation, e.g. Telnet
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

A method of allocating resources in a grid computing environment is provided. The method includes allocating resources for concurrently executing a batch job and an interactive session.

Claims

1. A method of allocating resources in a grid computing environment, comprising:

receiving at least one request for a batch job;

receiving at least one request for an interactive session;

determining, by at least one hardware processing unit, computer resources needed for concurrently executing the batch job and the interactive session;

allocating the computer resources for concurrently executing both the batch job and the interactive session, wherein the allocating includes using a multivariable best fit algorithm to allocate the computer resources to reduce fragmentation among the computer resources;

evaluating resource requirements for admitting an application session established through the interactive session, wherein the evaluating includes predicting resource requirements for the application session; and

admitting the application session in response to the resource requirements for the application session being available.

2. The method of claim 1, wherein determining computer resources needed for concurrently executing the batch job and the interactive session further comprises:

determining computing requirements for the batch job and the interactive session; and

selecting available computer resources from a pool of resources operable to satisfy the computing requirements for the batch job and the interactive session.

3. The method of claim 2, wherein the pool of computer resources are provided in a single data center.

4. The method of claim 2, wherein the pool of computer resources are provided in a plurality of data centers.

5. The method of claim 4, wherein the plurality of data centers comprises data centers provided within a grid computing environment.

6. The method of claim 4, wherein the pool of computer resources provided in the plurality of data centers comprises heterogeneous resources.

7. The method of claim 4, wherein the pool of computer resources provided in the plurality of data centers comprises geographically distributed resources.

8. The method of claim 4, wherein the pool of computer resources provided in the plurality of data centers comprises shared resources.

9. The method of claim 1, wherein determining computer resources needed for executing the interactive session comprises evaluating at least one of a static resource requirement of a compute node, network bandwidth requirements, required CPU cycles, unutilized CPU cycles, a resource requirement by a user, at least one authorization policy to identify resources which the user is authorized to use, and other performance criteria.

10. The method of claim 9, wherein the at least one static resource requirement comprises processor speed, processor type, and memory size.

11. The method of claim 9, wherein the resource requirement by a user comprises at least one of a type of operating system, protocol requirements, session duration requirements, and security requirements.

12. The method of claim 1, wherein allocating the computer resources comprises allocating the computer resources utilizing a least loaded algorithm.

13. The method of claim 1, wherein allocating the computer resources utilizing a multiple variable best fit algorithm further comprises:

performing weighted best fitting to allocate the computer resources.

14. The method of claim 1, wherein allocating the computer resources further comprises allocating a compute node for the interactive session.

15. The method of claim 1, further comprising executing the batch job on one compute node and concurrently executing the interactive session on the same compute node.

16. The method of claim 1, further comprising executing the batch job on one compute node and concurrently executing the interactive session on another compute node.

17. The method of claim 1, further comprising executing the interactive session as a remote desktop session.

18. The method of claim 1, further comprising executing the remote desktop session in a virtual network computing environment.

19. A system for allocation of resources, comprising:

means for receiving an interactive session request;

means for receiving a batch job request;

means for determining computing requirements for the interactive session request;

means for determining computing requirements for the batch job request;

means for allocating computer resources for concurrently executing the batch job and the interactive session based on determined computing requirements for the batch job and the interactive session, wherein the allocating includes using a multivariable best fit algorithm to allocate the computer resources to reduce fragmentation among the computer resources;

means for evaluating resource requirements for admitting an application session established through the interactive session, wherein the evaluating includes predicting resource requirements for the application session; and

means for admitting the application session in response to the resource requirements for the application session being available.

20. The system of claim 19, wherein the means for selecting utilizes at least one of an application performance model, a remote desktop session performance model, a resource model, and real-time utilization data from each compute node of a plurality of compute nodes.

21. A non-transitory computer storage medium on which is embedded one or more computer programs, said one or more computer programs, when executed by a computer system, implementing a method of allocating resources in a grid computing environment, the method comprising:

receiving a request for a batch job;

receiving a request for an interactive session;

determining computer resources needed to satisfy computing requirements for concurrently executing the batch job and the interactive session;

allocating the computer resources for concurrently executing both the batch job and the interactive session, wherein the allocating includes using a multivariable best fit algorithm to allocate the computer resources to reduce fragmentation among the computer resources;

evaluating resource requirements for admitting an application session established through the interactive session, wherein the evaluating includes predicting resource requirements for the application session; and

admitting the application session in response to the resource requirements for the application session being available.