Edge-based resource spin-up for cloud computing

• US 8,539,079 B2
• Filed: 08/10/2012
• Issued: 09/17/2013
• Est. Priority Date: 09/26/2011
• Status: Active Grant

• Current Assignee: Limelight Networks, Inc.
• Original Assignee: Limelight Networks, Inc.
• Inventors: Thireault, Jason
• Primary Examiner(s): BAROT, BHARAT
• Application Number:
  US13/572,505
• Publication Number:
  US 20130080626A1
• Time in Patent Office: 403 Days
• Field of Search: 709/203, 709217-219, 709223-226
• US Class Current: 709/226
• CPC Class Codes: G06F 9/5055 considering software capabilities, i.e. software resources associated or available to the machine
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: H04L 41/0806 for initial configuration or provisioning, e.g. plug-and-play
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Aspects of the present invention include distributing new resources closer to end-users which are making increased demands by spinning-up additional virtualized instances (as part of a cloud provisioning) within servers that are physically near to the network equipment (i.e., web servers, switches, routers, load balancers) that are receiving the requests.

Claims

1. A method of implementing edge-based cloud computing including an edge server that communicates with end users and arranges application resources, the method comprising:

determining an edge server from a plurality of geographically distributed edge servers within a cloud to use to communicate with a user device based on an efficiency threshold, wherein a content delivery network comprises the plurality of geographically distributed edge servers;

receiving, at the determined edge server, an application service request from a user device;

analyzing the application service request to gather metrics about historical responses provided by applications in each of a plurality of clouds;

based on the gathered metrics, determining a cloud of the plurality of clouds to which to direct the application service request;

forwarding the application service request to a compute platform in the determined cloud;

capturing a response to the application service request from the determined cloud; and

responding to the application service request.

2. The method of implementing edge-based cloud including the edge server that communicates with end users and arranges application resources computing of claim 1, wherein the cloud is also determined based on a business rule.

3. The method of implementing edge-based cloud including the edge server that communicates with end users and arranges application resources computing of claim 1, wherein the historical responses include responses to past application service requests from user devices.

4. The method of implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources of claim 1, wherein the historical responses include historical responses to pings.

5. The method of implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources of claim 1, further comprising updating or generating a cloud routing table based on the gathered metrics, wherein the cloud is determined in accordance with routing in the cloud routing table.

6. The method of implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources of claim 5, wherein the routing in the cloud routing table further depends on preferences of a customer.

7. The method of implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources of claim 1, wherein the efficiency threshold comprises a latency value between the user device and the edge server.

8. A computer-readable memory having sets of instructions stored thereon which, when executed by a computer, cause the computer to:

determine an edge server from a plurality of geographically distributed edge servers within a cloud to use to communicate with a user device based on an efficiency threshold, wherein a content delivery network comprises the plurality of geographically distributed edge servers;

receive, at the determined edge server, an application service request from a user device;

analyze the application service request to gather metrics about historical responses provided by applications in each of a plurality of clouds;

based on the gathered metrics, determine a cloud of the plurality of clouds to which to direct the application service request;

forward the application service request to a compute platform in the determined cloud;

capture a response to the application service request from the determined cloud; and

respond to the application service request.

9. The computer-readable memory of claim 8, wherein the cloud is also determined based on a business rule.

10. The computer-readable memory of claim 8, wherein the historical responses include responses to past application service requests from user devices.

11. The computer-readable memory of claim 8, wherein the historical responses include historical responses to pings.

12. The computer-readable memory of claim 8, wherein the instructions, when executed by the computer, further cause the computer to update or generate a cloud routing table based on the gathered metrics, wherein the cloud is determined in accordance with routing in the cloud routing table.

13. The computer-readable memory of claim 12, wherein the routing in the cloud routing table further depends on preferences of a customer.

14. The computer-readable memory of claim 8, wherein the efficiency threshold comprises a latency value between the user device and the edge server.

15. A system for implementing edge-based cloud computing including an edge server that communicates with end users and arranges application resources, the system comprising:

an edge server configured to receive an application service request from a user device, the edge server being of a plurality of geographically distributed edge servers within a cloud, a content delivery network comprising the plurality of geographically distributed edge servers, the edge server being selected from amongst the plurality of edge servers based on an efficiency threshold;

a cloud control unit configured to;

analyze an application service request received at the edge server from a user device to gather metrics about historical responses provided by applications in each of a plurality of clouds;

based on the gathered metrics, determine a cloud of the plurality of clouds to which to direct the application service request;

forward the application service request to a compute platform in the determined cloud; and

capture a response to the application service request from the determined cloud.

16. The system for implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources as in claim 15, wherein the edge server and the cloud control unit are within a single point of presence (PoP) in the content delivery network, the content delivery network comprising a plurality of points of presence.

17. The system for implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources as in claim 15, further comprising a request analysis unit that determines an application or service associated with the request, wherein the cloud control unit accesses a policy associated with the application or service, and wherein the cloud is determined at least in part based on the policy.

18. The system for implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources as in claim 15, further comprising a request analysis unit that determines a customer associated with the request, wherein the cloud control unit accesses a policy associated with customer, and wherein the cloud is determined at least in part based on the policy.

19. The system for implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources as in claim 15, wherein the historical responses include responses to past application service requests from user devices.

20. The system for implementing edge-based cloud computing including the edge server that communicates with end users and arranges application resources as in claim 15, wherein the historical responses include historical responses to pings.