Co-allocating a reservation spanning different compute resources types

• US 8,782,654 B2
• Filed: 12/26/2006
• Issued: 07/15/2014
• Est. Priority Date: 03/13/2004
• Status: Active Grant

• Current Assignee: III Holdings 12, LLC (Intellectual Ventures LLC)
• Original Assignee: Adaptive Computing Enterprises, Inc. (Ala Services LLC)
• Inventors: Jackson, David Brian
• Primary Examiner(s): KAWSAR, ABDULLAH AL
• Application Number:
  US11/616,156
• Publication Number:
  US 20070106994A1
• Time in Patent Office: 2,758 Days
• Field of Search: 718/104
• US Class Current: 718/104
• 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 of reserving resources in a compute environment are disclosed. The method embodiment comprises receiving a request for resources within a computer environment, determining at least one completion time associated with at least one resource type required by the request, and reserving resources within the computer environment based on the determine of at least the completion time. A scaled wall clock time on a per resource basis may also be used to determine what resources to reserve. The system may determine whether to perform a start time analysis or a completion time analysis or a hybrid analysis in the process of generating a co-allocation map between a first type of resource and a second type of resource in preparation for reserving resources according to the generated co-allocation map.

Claims

1. A method comprising:

receiving a request for resources within a compute environment, the request being associated with workload;

identifying feasible resources within the compute environment for the request to yield identified feasible resources;

analyzing each identified feasible resource for its effective speed in fulfilling the request;

based on the request and each identified feasible resource with its effective speed, determining a first completion time associated with a first resource type and a second completion time for a second resource type required by the request to yield a determination comprising a potential completion time range for the request with at least one other requirement, wherein the first resource type is one of a processor, a memory, bandwidth, and a hard drive, and the second resource type is of a different type from the first resource type;

generating a co-allocation map for multiple collections of resources that can meet the request based on the determination; and

reserving resources of the first resource type and the second resource type within the compute environment based on the co-allocation map.

2. The method of claim 1, wherein determining the first completion time and second completion time is at least in part based on wall clock scaling information that is specific to the workload.

3. The method of claim 1, further comprising:

analyzing a workload commitment for each identified feasible resource to yield an analysis.

4. The method of claim 3, wherein the analysis represents a per node availability range.

5. The method of claim 1, further comprising:

merging of at least two mappings of potential completion times for diverse resources in the compute environment.

6. The method of claim 1, further comprising:

determining at least one start time associated with the request using a scaled wall clock limit for the request.

7. The method of claim 1, wherein the first completion time and the second completion time for the request are determined based on a worst case scenario for any particular resource.

8. 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 within a compute environment, the request being associated with workload;

identify feasible resources within the compute environment for the request to yield identified feasible resources;

analyze each identified feasible resource for its effective speed in fulfilling the request;

based on the request and each identified feasible resource with its effective speed, determining a first completion time associated with a first resource type and a second completion time for a second resource type required by the request to yield a determination comprising a potential completion time range for the request with at least one other requirement, wherein the first resource type is one of a processor, a memory, bandwidth, and a hard drive, and the second resource type is of a different type from the first resource type;

generating a co-allocation map for multiple collections of resources that can meet the request based on the determination; and

reserving resources of the first resource type and the second resource type within the compute environment based on the co-allocation map.

9. The system of claim 8, wherein the computer-readable storage medium further comprises instructions, which, when executed by the processor, perform further operations comprising:

determining of the first completion time and the second completion time is at least in part based on wall clock scaling information that is specific to the workload.

10. The system of claim 8, wherein the computer-readable storage medium further comprises instructions, which, when executed by the processor, perform further operations comprising:

analyzing a workload commitment for each identified feasible resource to yield an analysis.

11. The system of claim 10, wherein the analysis represents a per node availability range.

12. The system of claim 8, wherein the computer-readable storage medium further comprises instructions, which, when executed by the processor, perform a method comprising:

merging of at least two mappings of potential completion times for diverse resources in the compute environment.

13. The system of claim 8, wherein the computer-readable storage medium further comprises instructions, which, when executed by the processor, perform a method comprising:

determining at least one start time associated with the request using a scaled wall clock limit for the request.

14. The system of claim 8, wherein the first completion time and the second completion time for the request are determined based on a worst case scenario for any particular resource.

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

receiving a request for resources within a compute environment, the request comprising a wall clock limit for workload that is independent of the compute environment;

identifying feasible resources within the compute environment for the request to yield identified feasible resources;

analyzing each identified feasible resource for its effective speed in fulfilling the request;

based on the request and each identified feasible resource with its effective speed, determining a first completion time associated with a first resource type and a second completion time for a second resource type to yield a determination comprising a potential completion time range for the request with at least one other requirement, wherein the first resource type is one of a processor, a memory, bandwidth, and a hard drive, and the second resource type is of a different type from the first resource type;

generating a co-allocation map for multiple collections of resources that can meet the request based on the determination; and

reserving resources of the first resource type and the second resource type within the compute environment based on the co-allocation map.