System and method for providing dynamic roll-back reservations in time

• US 7,996,455 B2
• Filed: 08/19/2005
• Issued: 08/09/2011
• Est. Priority Date: 06/17/2005
• Status: Active Grant

• Current Assignee: III Holdings 12, LLC (Intellectual Ventures LLC)
• Original Assignee: Adaptive Computing Enterprises, Inc. (Ala Services LLC)
• Inventors: Jackson, David B.
• Primary Examiner(s): Pwu, Jeffrey
• Assistant Examiner(s): Nooristany, Sulaiman
• Application Number:
  US11/208,138
• Publication Number:
  US 20060288251A1
• Time in Patent Office: 2,181 Days
• Field of Search: 709/200
• US Class Current: 709/200
• CPC Class Codes: G06F 11/1471 involving logging of persistent data for recovery
• CPC Class Codes: G06F 11/1474 in transactions G06F16/20 takes precedence
• CPC Class Codes: G06F 9/5072 Grid computing

Abstract

A systems, method and computer-readable media are disclosed for providing a dynamic roll-back reservation mask in a compute environment. The method of managing compute resources within a compute environment includes, based on an agreement between a compute resource provider and a customer, creating a roll-back reservation mask for compute resources which slides ahead of current time by a period of time. Within the roll-back reservation mask, the method specifies a subset of consumers and compute resource requests which can access compute resources associated with the roll-back reservation mask and, based on received data, the method dynamically modifies at least one of (1) the period of time the roll-back reservation mask slides ahead of current time and (2) the compute resources associated with the roll-back reservation mask.

Claims

1. A method of managing compute resources within a multinode compute environment, the method comprising:

based on an agreement between a compute resource provider and a customer, creating a roll-back reservation mask associated with masked compute resources in the multinode compute environment which has a beginning time that continuously slides ahead of a current time by a period of time, wherein the roll-back reservation mask comprises a policy enforcing mechanism to manage and constrain consumption sub-reservations and wherein the masked compute resources comprise a subset of nodes in the multimode compute environment;

within the roll-back reservation mask, specifying a subset of consumers and compute resource requests which can access the masked compute resources via the consumption sub-reservations; and

based on received data, dynamically modifying the period of time the roll-back reservation mask continuously slides ahead of the current time and the masked compute resources associated with the roll-back reservation mask.

2. The method of claim 1, further comprising:

within the roll-back reservation mask, analyzing the masked compute resources and a compute resource request to allow compute resource reservation of the masked compute resources only by authorized users.

3. The method of claim 1, wherein the at least one of the period of time the roll-back reservation mask continuously slides ahead of the current time and the masked compute resources is modified based on events related to at least one of:

a quality of service success rate, reported statistics, new customers to the compute environment, node failures, new resources available to the compute environment, node failures, system maintenance, backlog thresholds, administrative actions and issues relates to peer-to-peer environments.

4. The method of claim 1, wherein the period of time the roll-back reservation mask continuously slides ahead of the current time is modified based on events related to historical information.

5. The method of claim 4, wherein the historical information relates to at least one of:

quality of service success rates, utilization and responsiveness of the multinode compute environment and recorded statistics.

6. The method of claim 1, wherein the period of time the roll-back reservation mask continuously slides ahead of the current time is modified based on events related to a time associated with a job submission.

7. The method of claim 1, wherein the received data is associated with a negotiation between two entities.

8. The method of claim 7, wherein the two entities are the compute resource provider and at least one of:

a user, a hosting center, a peer-to-peer workload manager, a group and a job.

9. The method of claim 1, wherein the received data is associated with billing the customer for use of the compute resources.

10. The method of claim 9, wherein the received data is further associated with an offer from the consumer to pay an addition amount for at least one of the modified period of time and the modification of the masked compute resources.

11. The method of claim 1, wherein at least one of the period of time the roll-back reservation mask continuously slides ahead of the current time and the modification of the masked compute resources is modified based on a request by at least one of:

a consumer, an administrator and a peer-to-peer workload manager.

12. The method of claim 1, wherein if the masked compute resources are dynamically modified, the dynamic modification further comprises modifying at least one of the following resources allocated to the roll-back reservation:

processor nodes, bandwidth, licenses, memory, generic resources and disk storage.

13. The method of claim 1, wherein the received data is associated with at least one of a policy and a feedback loop.

14. The method of claim 1, wherein the received data is associated with instructions to dynamically modify at least one of (1) the period of time the roll-back reservation mask continuously slides ahead of current time and (2) the masked compute resources in order to remedy an exception to the agreement with the customer.

15. The method of claim 1, wherein the received data is associated with reducing a quality of service due to the customer consuming a prepaid amount of compute resources according to the agreement.

16. A system for managing compute resources within a multinode compute environment, the system comprising:

a processor;

a first module causing the processor, based on an agreement between a compute resource provider and a customer, to create a roll-back reservation mask associated with masked compute resources in the multinode compute environment which has a beginning time that continuously slides ahead of a current time by a period of time, wherein the roll-back reservation mask comprises a policy enforcing mechanism to manage and constrain consumption sub-reservations and wherein the masked compute resources comprise a subset of nodes in the multimode compute environment;

a second module causing the processor, within the roll-back reservation mask, to specify a subset of consumers and compute resource requests which can access the masked compute resources via the consumption sub-reservations associated with the roll back reservation mask; and

a third module causing the processor, based on received data, dynamically modifying the period of time the roll-back reservation mask continuously slides ahead of the current time and the masked compute resources associated with the roll-back reservation mask.

17. The system of claim 16, further comprising:

a fourth module causing the processor, within the roll-back reservation mask, to analyze the masked compute resources and a compute resource request to allow compute resource reservation of the masked compute resources only by authorized users.

18. The system of claim 16, wherein the at least one of the period of time the roll-back reservation mask continuously slides ahead of the current time and the masked compute resources is modified based on events related to at least one of:

a quality of service success rate, reported statistics, new customers to the compute environment, node failures, new resources available to the compute environment, node failures, system maintenance, backlog thresholds, administrative actions and issues relates to peer-to-peer environments.

19. The system of claim 16, wherein the period of time the roll-back reservation mask continuously slides ahead of the current time is modified based on events related to historical information.

20. The system of claim 19, wherein the historical information relates to at least one of:

quality of service success rates, utilization and responsiveness of the compute environment and recorded statistics.

21. The system of claim 16, wherein the period of time the roll-back reservation mask continuously slides ahead of the current time is modified based on events related to a time associated with a job submission.

22. The system of claim 16, wherein the received data is associated with a negotiation between two entities.

23. The system of claim 22, wherein the two entities are the compute resource provider and at least one of:

a user, a hosting center, a peer-to-peer workload manager, a group and a job.

24. The system of claim 16, wherein the received data is associated with billing the customer for use of the compute resources.

25. The system of claim 24, wherein the received data is further associated with an offer from the consumer to pay an addition amount for at least one of the modified period of time and the modification of the masked compute resources.

26. The system of claim 16, wherein at least one of the period of time the roll-back reservation mask continuously slides ahead of the current time and the modification of the masked compute resources is modified based on a request by at least one of:

a consumer, an administrator and a peer-to-peer workload manager.

27. The system of claim 16, wherein if the masked compute resources are dynamically modified, the dynamic modification further comprises modifying at least one of the following resources:

processor nodes, bandwidth, licenses, memory, generic resources and disk storage.

28. The system of claim 16, wherein the received data is associated with at least one of a policy and a feedback loop.

29. The system of claim 16, wherein the received data is associated with instructions to dynamically modify at least one of (1) the period of time the roll-back reservation mask continuously slides ahead of current time and (2) the masked compute resources in order to remedy an exception to the agreement with the customer.

30. The system of claim 16, wherein the received data is associated with reducing a quality of service due to the customer consuming a prepaid amount of compute resources according to the agreement.

31. A non-transitory computer-readable storage medium storing instructions for controlling a computing device to manage compute resources within a multinode compute environment, the instructions comprising:

based on an agreement between a compute resource provider and a customer, creating a roll-back reservation mask associated with masked compute resources in the multinode compute environment which has a beginning time that continuously slides ahead of a current time by a period of time, wherein the roll-back reservation mask comprises a policy enforcing mechanism to manage and constrain consumption sub-reservations and wherein the masked compute resources comprise a subset of nodes in the multimode compute environment;

within the roll-back reservation mask, specifying a subset of consumers and compute resource requests which can access the masked compute resources via the consumption sub-reservations; and

based on received data, dynamically modifying the period of time the roll-back reservation mask continuously slides ahead of the current time and the masked compute resources associated with the roll-back reservation mask.

32. The non-transitory computer-readable storage medium of claim 31, the instructions further comprising:

within the roll-back reservation mask, analyzing the masked compute resources and a compute resource request to allow compute resource reservation of the masked compute resources only by authorized users.

33. The non-transitory computer-readable storage medium of claim 31, wherein the at least one of the period of time the roll-back reservation mask continuously slides ahead of the current time and the masked compute resources is modified based on events related to at least one of:

a quality of service success rate, reported statistics, new customers to the compute environment, node failures, new resources available to the compute environment, node failures, system maintenance, backlog thresholds, administrative actions and issues relates to peer-to-peer environments.

34. The non-transitory computer-readable storage medium of claim 31, wherein the period of time the roll-back reservation mask continuously slides ahead of the current time is modified based on events related to historical information.

35. The non-transitory computer-readable storage medium of claim 34, wherein the historical information relates to at least one of:

quality of service success rates, utilization and responsiveness of the compute environment and recorded statistics.

36. The non-transitory computer-readable storage medium of claim 31, wherein the period of time the roll-back reservation mask slides ahead of the current time is modified based on events related to a time associated with a job submission.

37. The non-transitory computer-readable storage medium of claim 31, wherein the received data is associated with a negotiation between two entities.

38. The non-transitory computer-readable storage medium of claim 37, wherein the two entities are the compute resource provider and at least one of:

a user, a hosting center, a peer-to-peer workload manager, a group and a job.

39. The non-transitory computer-readable storage medium of claim 31, wherein the received data is associated with billing the customer for use of the compute resources.

40. The non-transitory computer-readable storage medium of claim 39, wherein the received data is further associated with an offer from the consumer to pay an addition amount for at least one of the modified period of time and the modification of the masked compute resources.

41. The non-transitory computer-readable storage medium of claim 31, wherein at least one of the period of time the roll-back reservation mask continuously slides ahead of the current time and the modification of the masked compute resources is modified based on a request by at least one of:

a consumer, an administrator and a peer-to-peer workload manager.

42. The non-transitory computer-readable storage medium of claim 31, wherein if the masked compute resources are dynamically modified, the dynamic modification further comprises modifying at least one of the following resources:

processor nodes, bandwidth, licenses, memory, generic resources and disk storage.

43. The non-transitory computer-readable storage medium of claim 31, wherein the received data is associated with at least one of a policy and a feedback loop.

44. The non-transitory computer-readable storage medium of claim 31, wherein the received data is associated with instructions to dynamically modify at least one of (1) the period of time the roll-back reservation mask continuously slides ahead of current time and (2) the masked compute resources in order to remedy an exception to the agreement with the customer.

45. The non-transitory computer-readable storage medium of claim 31, wherein the received data is associated with reducing a quality of service due to the customer consuming a prepaid amount of compute resources according to the agreement.