Dynamic Resource Allocation

• US 20100011366A1
• Filed: 07/10/2008
• Published: 01/14/2010
• Est. Priority Date: 07/10/2008
• Status: Active Grant

• Current Assignee: Juniper Networks Incorporated
• Original Assignee: Blackwave Inc. (Juniper Networks Incorporated)
• Inventors: Gerovac, Branko J., Carver, David C.
• Granted Patent: US 8,191,070 B2
• Time in Patent Office: Days
• US Class Current: 718/104
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 2209/5022 Workload threshold
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• 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 computer-implemented method includes detecting an actual workload representative of a pattern of access of a plurality of items of content; comparing the actual workload against a prescriptive workload to determine an occurrence of a substantial deviation from the prescriptive workload; and upon determining the occurrence of the substantial deviation, revising the prescriptive workload based at least in part on the actual workload. The plurality of items is stored on resources of a storage environment according to one of a plurality of resource allocation arrangements. The prescriptive workload including a plurality of categories, each category being associated with a respective one of the plurality of resource allocation arrangements.

Claims

1. A computer-implemented method comprising:

detecting an actual workload representative of a pattern of access of a plurality of items of content, the plurality of items being stored on resources of an storage environment according to one of a plurality of resource allocation arrangements;

comparing the actual workload against a prescriptive workload to determine an occurrence of a substantial deviation from the prescriptive workload, the prescriptive workload including a plurality of categories, each category being associated with a respective one of the plurality of resource allocation arrangements; and

upon determining the occurrence of the substantial deviation, revising the prescriptive workload based at least in part on the actual workload.

2. The computer-implemented method of claim 1, wherein each one of the plurality of categories is defined in relation to a respective range of values of a first attribute, the first attribute characterizing one or more operational objectives of the plurality of items of content.

3. The computer-implemented method of claim 2, wherein the method of revising the prescriptive workload includes:

modifying at least a first category by changing the definition of the first category to a new range of values of the first attribute.

4. The computer-implemented method of claim 3, wherein the method of revising the prescriptive workload further includes:

associating the modified first category with a proper one of the plurality of resource allocation arrangements, such that a result of the association is compatible with an availability of the resources in the storage environment.

5. The computer-implemented method of claim 4, wherein the resources in the storage environment includes storage resources and access resources.

6. The computer-implemented method of claim 1, wherein, for each one of the plurality of categories, the associated respective resource allocation arrangement includes a first specification of the number of instances of an item associated with the category is stored in the storage system, and a second specification of a partially defined destination for elements of the item.

7. The computer-implemented method of claim 6, wherein the resources of the storage environment includes at least a first storage component having a plurality of distinct regions, and the second specification of the partially defined destination for elements of the item associates elements of the item with one of the plurality of distinct regions.

8. The computer-implemented method of claim 7, wherein, for each one of the plurality of categories, a respective level of resource capacity is allocated to the item in the category by applying the respective one of the resource allocation arrangements.

9. The computer-implemented method of claim 8, wherein the respective level of resource capacity includes at least:

a storage capacity that relates to the number of instances of the item in the category stored on resources of the storage environment; and

an access capacity that relates to an allowable access bandwidth provided to the item in the category.

10. The computer-implemented method of claim 8, wherein the method of revising the prescriptive workload includes, for at least some of the plurality of categories:

changing the respective level of resource capacity by changing the respective one of the resource allocation arrangements associated with the category.

11. The computer-implemented method of claim 10, wherein changing the respective one of resource allocation arrangements includes:

changing the first specification of the number of instances of the item associated with the category is stored in the storage system.

12. The computer-implemented method of claim 10, wherein changing the respective one of resource allocation arrangements includes:

changing the second specification of the partially defined destination for elements of the item.

13. The computer-implemented method of claim 1, wherein the prescriptive workload is maintained in a first database.

14. The computer-implemented method of claim 1, further comprising:

generating a new prescriptive workload based on a result of revising the prescriptive workload;

wherein the new prescriptive workload enables re-allocation of resources of the storage environment to the plurality of items, the re-allocation being reflective of the actual workload.

15. The computer-implemented method of claim 1, wherein the substantial deviation occurs when a deviation of the actual workload from the prescriptive workload exceeds a deviation threshold.

16. The computer-implemented method of claim 1, wherein the method of detecting the actual workload includes obtaining information on one or more of the following:

a number of concurrent access requests to each one of the plurality of items at a given time, an aggregate of access requests to each one of plurality of items during a detection period, and a number and frequency of access requests being denied with respective to each one of plurality of items due to resource unavailability.

17. A computer-implemented method comprising:

detecting an actual workload representative of a pattern of access of a plurality of items of content, the plurality of items being stored on resources of an storage environment according to one of a plurality of resource allocation arrangements;

comparing the actual workload against a first workload model to determine an occurrence of a substantial deviation from the first workload model, the first workload model including a first set of schemas, each schema being associated with a respective one of a first set of resource allocation arrangements; and

upon determining the occurrence of the substantial deviation, determining a second workload model based at least in part on the actual workload, the second workload model including a second set of schemas, each schema being associated with a respective one of a second set of resource allocation arrangements.