Method and apparatus for dynamic data flow control using prioritization of data requests

• US 7,454,457 B1
• Filed: 06/08/2000
• Issued: 11/18/2008
• Est. Priority Date: 02/07/2000
• Status: Expired due to Fees

• Current Assignee: Parallel Networks, LLC (epicRealm Licensing LP)
• Original Assignee: Parallel Networks, LLC (epicRealm Licensing LP)
• Inventors: Saxena, Avinash C., Lowery, Keith A., Davidson, David K.
• Primary Examiner(s): Flynn; Nathan
• Assistant Examiner(s): BOUTAH, ALINA A
• Application Number:
  US09/592,486
• Time in Patent Office: 3,085 Days
• Field of Search: 709201-203, 709223-226, 709217-219, 709/231, 709/235, 709/232, 711/113
• US Class Current: 709/203
• CPC Class Codes: H04L 43/0817 by checking functioning
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04L 47/10 Flow control; Congestion control
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources
• CPC Class Codes: H04L 63/101 Access control lists [ACL]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

A data center (14) receives a request (22) for content from a browser (12) on a client (11). The data center determines whether the requested content is available at the data center. The content is available when the content is both present at the data center and current. The content may be expired and marked as non-available in response to an expiration command (24). When the requested content is available at the data center, the data center returns the requested content to the data center. When the requested content is locally unavailable at the data center, the requested content is retrieved from an origin server (18). The retrieval of the content from the origin server may be delayed based on the processing load at the origin server. When retrieval of the content is delayed, the request is prioritized and placed in a queue for handling by the origin server based on the priority of the request. Also, when retrieval of the content is delayed, a status page may be communicated to the browser to inform a user of the delay and provide alternate content (139) and status information related to the request determined as a function of the request or the current state of the origin server.

Claims

1. A method for data processing comprising:

receiving from a cache server in a data center an initial request message, the initial request message including a request for data and requesting permission to forward the request for data to an origin server;

determining whether the origin server is available to process the request;

determining a state associated with the request for data in response to the origin server not being available to process the request for data;

assigning a priority to the request for data according to the state and according to priority criteria associated with the state in response to the origin server not being available to process the request for data;

queuing the request for data as a function of the priority associated with the request in response to the origin server not being available to process the request for data;

determining that the origin server becomes available to process the request for data;

returning the request for data and a permission indicator to the cache server in order to retrieve data associated with the request for data from the origin server for delivery to a client computer.

2. The method for data processing according to claim 1, further comprising:

automatically adjusting the priority criteria;

dynamically updating the priority of the request to send data to the client computer in response to the adjusted priority criteria.

3. The method for data processing according to claim 1 further comprising:

determining a load associated with the origin server;

granting permission to the cache server to retrieve data when the load associated with the origin server is below a threshold; and

denying permission to the cache server to retrieve data when the load associated with the origin server is above the threshold.

4. The method for data processing according to claim 3, wherein the threshold is determined as a function of the load of the origin server.

5. The method for data processing according to claim 1 further comprising instructing the cache server to communicate alternate content to the client computer, the alternate content comprising a status page, the status page comprising an automatic re-submission time for re-issuing the request.

6. The method for data processing according to claim 5, wherein the alternate content comprises the status page and wherein the status page is communicated when the load at the origin server exceeds a predetermined threshold.

7. The method for data processing according to claim 5, wherein communicating the alternate content comprises:

associating a queue delay time with the request for data;

determining whether the queue delay time exceeds a threshold;

instructing the cache server to return the alternate content to the client computer in response to the queue delay time exceeding the threshold.

8. The method for data processing according to claim 7, wherein the request for data is generated at the client computer remote from the data center and wherein generating the alternate content comprises instructing the cache server to select the alternate content as a function of the bandwidth available to the client computer.

9. The method for data processing according to claim 8, further comprising determining the amount of bandwidth available to the client computer, wherein the amount of bandwidth comprises one of high-bandwidth, medium-bandwidth and low-bandwidth.

10. The method for data processing according to claim 7, wherein the cache server is instructed to return the alternate content based on the queue delay time and the predetermined criteria.

11. The method for data processing according to claim 7, wherein the predetermined criteria comprises information associated with the request for data.

12. The method for data processing according to claim 7, wherein the predetermined criteria comprises external information associated with a user associated with the request.

13. The method for data processing according to claim 12, wherein the external information comprises historical shopping information associated with the user associated with the request for data.

14. The method for data processing according to claim 5, wherein the alternate content comprises the status page and further including resubmitting the data request to the data center by a browser to update the status page.

15. The method for data processing according to claim 14, wherein resubmitting the request for data is performed automatically by the browser.

16. The method for data processing according to claim 1, wherein assigning the priority to the request for data comprises determining whether the request for data is prioritizable, and wherein the priority is a first priority when the request for data is non-prioritizable and wherein the priority is a second priority when the request for data is prioritizable.

17. The method for data processing according to claim 16, wherein the first priority is a default priority and wherein the second priority is determined as a function of the data requested by the request for data.

18. The method for data processing according to claim 1 further comprising determining the load on an origin server by comparing a load metric associated with the origin server to a predetermined threshold.

19. The method for data processing according to claim 18, wherein the load metric comprises the number of requests being handled by the origin server.

20. The method for data processing according to claim 18, wherein the load metric comprises the number of network connections being supported by the origin server.

21. The method for data processing according to claim 18, wherein the load metric comprises the delay associated with retrieving a predetermined web page from the origin server.

22. The method for data processing according to claim 1, wherein the request for data is a first request for data and wherein queuing the request for data comprises:

storing the first request for data in a queue associated with the data center, the queue having therein a plurality of second requests for data distinct from the first request for data, each of the second requests for data having a respective priority associated therewith;

sorting the queue as a function of the respective priority associated with the first request for data and each of the second requests for data; and

processing the highest priority request for data in the queue.

23. The method for data processing according to claim 1, wherein the data center comprises a plurality of data centers and wherein receiving the request for data comprises:

determining a network distance between the client computer and at least one of the data centers;

determining the closest data center to the client computer;

resolving a destination address associated with the request for data to the closest data center; and

routing the request for data to the closest data center.

24. A system for dynamic flow control comprising:

a cache server operable to receive a request for content and retrieve content from an origin server in response thereto, the request received from a client computer requesting the content; and

a flow control server having an associated queue and coupled to the cache server, the flow control server operable to;

receive an initial request message from the cache server, the initial request message including a request for data and requesting permission to forward the request for data to an origin server;

determine whether the origin server is available to process the request;

determine a state associated with the request for data in response to the origin server not being available to process the request for data;

assign a priority to the request for data according to the state associated with the request for data and according to priority criteria associated with the state in response to the origin server not being available to process the request for data;

store the prioritized request for data in the queue as a function of the priority associated with the request for data in response to the origin server not being available to process the request for data;

determine that the origin server becomes available to process the request for data;

return the request for data and a permission indicator to the cache server in order to retrieve data associated with the request for data from the origin server for delivery to a client computer.

25. The system for dynamic flow control according to claim 24, wherein the flow control server is further operable to

automatically adjust the priority criteria;

dynamically update the priority of the request for data to send data to the client computer in response to the adjusted priority criteria.

26. The system for dynamic flow control according to claim 24, wherein the flow control server is further operable to associate a priority with the request for data based on the content requested by the request for data and determine a processing load associated with the origin server.

27. The system for dynamic flow control according to claim 24, wherein the flow control server is further operable to associated a priority with the request for data based on external information associated with the request for data.

28. The system for dynamic flow control according to claim 27, wherein the external information comprises historical information associated with a user associated with the request for data.

29. A method for dynamic flow control comprising:

receiving a request for data, the request for data received from a client computer requesting data;

determining a state associated with the request for data in response to a protected source not being available to process the request for data;

associating a priority with the request for data according to the state associated with the request for data and according to priority criteria associated with the state in response to the protected source not being available to process the request for data;

storing the request for data in a queue as a function of the priority associated with the request for data in response to the protected source not being available to process the request for data; and

returning the request for data and a permission indicator for retrieving the data requested by the request for data from the protected resource in response to the protected source becoming available to process the request for data.

30. The method for dynamic flow control according to claim 29 further comprising determining a load at the protected resource, and wherein associating a priority with the request for data comprises associating the priority with the request for data when the load at the protected resource exceeds a predetermined threshold and wherein storing the request for data comprises queuing the request for data when the load at the protected resource exceeds the predetermined threshold.

31. The method for dynamic flow control according to claim 30 further comprising indicating status information to be returned to the client computer requesting data.

32. The method for dynamic flow control according to claim 30 further comprising indicating alternate content to be returned to the client computer requesting data.

33. The method for dynamic flow control according to claim 32 further comprising determining the alternate content as a function of the bandwidth associated with the client computer.

34. The method for dynamic flow control according to claim 31, wherein the status information comprises a status web page and wherein indicating status information comprises selecting the status page based on priority criteria associated with the protected resource.

35. The method for dynamic flow control according to claim 34 further comprising resubmitting the data request after a predetermined time interval.

36. The method for dynamic flow control according to claim 35, wherein resubmitting the data request is performed automatically.

37. The method for dynamic flow control according to claim 34 further comprising delaying communication of the status page indication for a predetermined time interval based on the priority criteria.

38. The method for dynamic flow control according to claim 37, wherein delaying communication of the status page comprises delaying communication of the status page indication based on an expected delay associated with the protected resource.

39. The method for dynamic flow control according to claim 30, wherein receiving the data request for data comprises receiving the request for data from a flow controlled device.

40. The method for dynamic flow control according to claim 30, wherein returning the request for data comprises:

removing at least one prioritized request for data from the queue when the load at the protected resource is below the predetermined threshold;

communicating the at least one removed prioritized request for data to the protected resource;

retrieving the requested data from the protected resource; and

communicating the requested data to a flow controlled device associated with the request for data.

41. The method for dynamic flow control according to claim 40, wherein removing at least one prioritized request for data comprises removing the highest priority request for data.

42. The method for dynamic flow control according to claim 40, wherein associating the priority with the request for data comprises determining whether the request for data is prioritizable, and wherein the priority is a first priority when the request for data is non-prioritizable and wherein the priority is a second priority when the request for data is prioritizable.

43. The method for data processing according to claim 42, wherein the first priority is a default priority and wherein the second priority is determined as a function of the request for data.