System and method providing a virtual private cluster

• US 9,979,672 B2
• Filed: 01/06/2015
• Issued: 05/22/2018
• Est. Priority Date: 03/16/2005
• Status: Active Grant

• Current Assignee: III Holdings 12, LLC (Intellectual Ventures LLC)
• Original Assignee: III Holdings 12, LLC (Intellectual Ventures LLC)
• Inventors: Jackson, David Brian
• Primary Examiner(s): Swearingen, Jeffrey R
• Application Number:
  US14/590,102
• Publication Number:
  US 20150113150A1
• Time in Patent Office: 1,232 Days
• Field of Search: 709226
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 15/173 using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
• CPC Class Codes: G06F 2209/5014 Reservation
• CPC Class Codes: G06F 2209/509 Offload
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources
• 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
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G08C 17/00 Arrangements for transmitting signals characterised by the use of a wireless electrical link
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 47/80 Actions related to the user profile or the type of traffic
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network

Abstract

The present invention provides a system, method and computer-readable media for generating virtual private clusters out of a group of compute resources. Typically, the group of compute resources involves a group of clusters independently administered. The method provides for aggregating the group of compute resources, partitioning the aggregated group of compute resources and presenting to each user in an organization a partition representation the organization'"'"'s virtual private cluster. The users transparently view their cluster and have control over its operation. The partitions may be static or dynamic.

Claims

1. A method of establishing a virtual private cluster, the method comprising:

aggregating compute resources comprising at least a plurality of computer processors to yield aggregated compute resources, wherein the compute resources comprise a group of independently administered clusters;

establishing partitions within the aggregated compute resources based at least in part on policies associated with different organizations to yield partitioned resources; and

presenting a virtual private cluster using the partitioned resources which delivers a quality of service to a respective organization, wherein the aggregation, establishing and presenting steps occur at least in part via communications through an application programming interface between a workload manager and a resource manager in which the workload manager schedules and inserts workload from the respective organization into the virtual private cluster.

2. The method of claim 1, further comprising masking information not directly associated with the virtual private cluster.

3. The method of claim 2, wherein masking information comprises using workload, credentials, statistics, and resources associated with the virtual private cluster to determine what information is masked.

4. The method of claim 3, wherein the information that is masked comprises at least are of people, credentials and jobs associated with other partitions.

5. The method of claim 1, wherein aggregating compute resources further comprises aggregating same-type resources and aggregating distinct types of resources.

6. The method of claim 1, wherein establishing partitions within the aggregated compute resources enables compute resources to be uniformly distributed amongst the different organizations.

7. The method of claim 1, wherein aggregating compute resources further comprises aggregating data, network and software resources.

8. The method of claim 7, wherein aggregating compute resources further comprises aggregating compute resources together with network resources, license management resources and/or storage management resources.

9. The method of claim 1, wherein aggregating compute resources further comprises aggregating a portion of available compute resources.

10. The method of claim 1, wherein aggregating compute resources further comprises aggregating all compute resources.

11. The method of claim 1, wherein the virtual private cluster is presented transparently to users such that users in the respective organization view the virtual private cluster with a desired level of control.

12. The method of claim 11, wherein a desired level of control has at least three tiers comprising a system administrator, a virtual cluster administrator and end user.

13. The method of claim 12, wherein the system administrator makes the virtual private cluster, the virtual cluster administrator makes policies in the virtual private cluster, and the end user is subject to the policies.

14. The method of claim 1, wherein partitioning occurs based on organizational required criteria and preferred criteria by which the partitions are bounded.

15. The method of claim 14, wherein partitioning further is guaranteed to satisfy the required criteria and seeks to maximize satisfaction of the preferred criteria.

16. The method of claim 14, wherein as organization needs are dynamic, the step of establishing partitions is dynamically executed to modify the partitioned compute resources within the virtual private cluster to match changing organization criteria.

17. The method of claim 16, wherein the organization needs are dynamic in terms of time.

18. The method of claim 16, wherein the organization needs are dynamic in terms of required criteria and preferred criteria.

19. The method of claim 16, wherein the organization needs are dynamic in terms environmental factors.

20. The method of claim 19, wherein the environmental factors may comprise one or more from the following list:

current load, quality of service, various guarantees relates to factors of time.

21. The method of claim 9, wherein the users of the virtual private cluster only see their own jobs, their own historical information, their own resources, their own credentials, users, groups and classes.

22. The method of claim 1, wherein establishing partitions further comprises establishing partitions of resources, workloads, policies/services and statistics.

23. The method of claim 1, wherein establishing the partitions of the compute resources further comprises partitioning the compute resources based at least in part on accessibility credentials.

24. The method of claim 1, wherein partitioning the compute resources is based on either static or dynamic policies.

25. A virtual private cluster generated by a method comprising:

aggregating compute resources comprising at least a plurality of processors to yield aggregated resources wherein the compute resources comprise a group of independently administered clusters;

establishing partitions within the aggregated compute resources based at least in part on policies associated with different organizations to yield partitioned resources; and

presenting the virtual private cluster, using the partitioned compute resources, which delivers a quality of service to a respective organization, wherein the aggregating, establishing and presenting steps occur at least in part via communications through an application programming interface between a workload manager and a resource manager in which the workload manager schedules and inserts workload from the respective organization into the virtual private cluster.

26. A system for generating a virtual private cluster from compute resources, the system comprising;

means for aggregating the compute resources comprising at least a plurality of processors to yield aggregated compute resources wherein the compute resources comprise a group of independently administered clusters;

means for establishing partitions within the aggregated compute resources based at least in part on policies associated with different organizations to yield partitioned compute resources; and

means for presenting a virtual private cluster, using the partitioned compute resources, which delivers a particular quality of service guaranteed to users of a respective organization, wherein the aggregating, establishing and presenting steps occur at least in part via communication through an application programming interface between a workload manager and a resource manager in which the workload manager scheduled and inserts workload from the respective organization into the virtual private cluster.

27. A system for establishing a virtual private cluster, the system comprising:

a first module configured to control a processor to aggregate compute resources comprising at least a plurality of processors to yield aggregated compute resources wherein the compute resources comprise a group of independently administered clusters;

a second module configured to control the processor to establish partitions within the aggregated compute resources based at least in part on policies associated with different organizations to yield partitioned resources; and

a third module configured to control the processor to present a virtual private cluster, using the partitioned resources, which delivers a quality of service to a respective organization, wherein the first module, second module, and third module operate at least in part via an application programming interface between a workload manager and a resource manager in which the workload manager schedules and inserts workload from the respective organization into the virtual private cluster.