Method for improving web performance by adapting servers based on client cluster characterization

• US 20030046343A1
• Filed: 08/07/2002
• Published: 03/06/2003
• Est. Priority Date: 08/27/1999
• Status: Active Grant

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Krishnamurthy, Balachander, Wills, Craig Ellis
• Granted Patent: US 7,296,089 B2
• Time in Patent Office: Days
• US Class Current: 709/203
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 45/74591 using content-addressable memories [CAM]
• CPC Class Codes: H04L 61/00 Network arrangements, protocols or services for addressing or naming
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: H04L 67/303 Terminal profiles
• 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 67/563 Data redirection of data network streams
• CPC Class Codes: H04L 67/565 Conversion or adaptation of application format or content adding application control or application functional data H04L67/561
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 67/5682 Policies or rules for updating, deleting or replacing the stored data
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

The present invention is a method for improving delivery of content to a client communicating with a server on the Web. Groups or clusters of clients are formed by processing the IP addresses of the clients according to a network-aware, radix-encoded trie classification process. The groups of clients are categorized based on information about one or more clients in each group that can be determined by the server. That information is used to help drive tailored actions on the part of Web servers. Users with poor connectivity may choose not to spend much time at a Web site if it takes a long time to receive a page, even if the Web server at the site is not the bottleneck. Retaining such clients may be of interest to a Web site. Better-connected clients may be able to receive enhanced representations of Web pages such as with higher quality images.

Once a group of clients is characterized as poor, a variety of server actions can be taken by the server, including altering the delivered content or the manner in which content is delivered, including guiding server policy decisions, aiding in caching decisions and deciding when to redirect the client to a mirror site. Clustering permits those actions to be taken even if no client-specific categorization is available.

Claims

1. A method for delivering content to a first client through a first connection, the method comprising the steps of:

forming a group of clients including the first client by processing the IP addresses of the clients according to a radix encoded trie classification process;

classifying the group of clients into a group classification according to at least one criterion indicative of at least one connection through which content is delivered to at least one member of the group other than the first client;

receiving a request from the first client to serve content through the first connection;

altering a response to the client request in accordance with the group classification; and

sending the response to the client.

2. The method as claimed in claim 1, wherein the step of altering the response comprises altering the content to be delivered.

3. The method as claimed in claim 1, wherein the step of altering the response comprises altering the manner in which the content is to be delivered.

4. The method as claimed in claim 3, wherein the step of altering the manner of delivery comprises redirecting the client to a mirror server.

5. The method as claimed in claim 3, wherein the step of altering the manner of delivery comprises altering meta-information delivered with the content.

6. The method as claimed in claim 5, wherein the step of altering meta-information results in extending a freshness lifetime of an object in the content.

7. The method as claimed in claim 5, wherein the step of altering meta-information results in altering a policy of including cache validation requests with other messages exchanged with a server.

8. The method as claimed in claim 3, wherein the step of altering the manner of delivery comprises increasing a length of allowed TCP sessions.

9. The method as claimed in claim 3, further comprising altering the requested content before delivery.

10. The method as claimed in claim 1, wherein the step of classifying the group of clients according to a connection criterion includes placing the group in one of a poor, a normal and a rich class.

11. The method as claimed in claim 10, wherein the group is initially placed in the normal class.

12. The method as claimed in claim 1, wherein the step of classifying the group of clients includes receiving client characterization information from at least one member of the group.

13. The method as claimed in claim 1, wherein the step of classifying the group of clients includes measuring a time between accepting a TCP connection from the member of the group and receipt of a first HTTP request from that member.

14. The method as claimed in claim 1, wherein the step of classifying the group of clients includes the steps of:

in response to a client request from a member of the group, sending a redirect response, and

measuring a time between the client request and a redirected client request from the member.

15. The method as claimed in claim 1, wherein the step of classifying the group of clients includes measuring a time between transmittal of a container document to a member of the group and receipt of a first request for an object in the document.

16. The method as claimed in claim 1, wherein the step of classifying the group of clients includes measuring a time between transmittal of a container document to a member of the group and receipt of a last request for an object in the document.

17. The method as claimed in claim 1, wherein the step of classifying the group of clients includes measuring a criterion based on of a plurality of server requests.

18. The method as claimed in claim 17, wherein a criterion value E_first is adjusted based on a new measurement E_measured according to a formula:

E_first=α

E_first+(1−

α

)E_measured

wherein α

is a smoothing value in a range from 0 to 1.

19. The method as claimed in claim 1, wherein the client group comprises a cluster of clients under common administrative control.

20. The method as claimed in claim 1, further comprising the steps of generating a cookie containing a result of the classification step, and transmitting the cookie to the first client.

21. The method as claimed in claim 17 wherein the step of classifying the group of clients includes transmitting an executable to at least one of the clients for measuring the criterion indicative of the connection.

22. The method as claimed in claim 1, wherein the step of altering the response to the client request includes maintaining the content without alteration.

23. A server for delivering content to a first client through a connection, the server configured to perform the steps of:

forming a group of clients including the first client by processing the IP addresses of the clients according to a radix encoded trie classification process;

classifying the group of clients into a group classification according to at least one criterion indicative of at least one connection through which content is delivered to at least one member of the group other than the first client;

receiving a request from the first client to serve content through the first connection;

altering a response to the client request in accordance with the group classification; and

sending the response to the client.

24. The server as claimed in claim 23, wherein the step of altering the response comprises altering the content to be delivered.

25. The server as claimed in claim 23, wherein the step of altering the response comprises altering the manner in which the content is to be delivered.

26. The server as claimed in claim 25, wherein the step of altering the manner of delivery comprises redirecting the client to a mirror server.

27. The server as claimed in claim 25, wherein the step of altering the manner of delivery comprises altering meta-information delivered with the content.

28. The server as claimed in claim 27, wherein the step of altering meta-information results in extending a freshness lifetime of an object in the content.

29. The server as claimed in claim 27, wherein the step of altering meta-information results in altering a policy of including cache validation requests with other messages exchanged with a server.

30. The server as claimed in claim 25, wherein the step of altering the manner of delivery comprises increasing a length of allowed TCP sessions.

31. The server as claimed in claim 25, wherein the step of altering the response further comprises altering the requested content before delivery.

32. The server as claimed in claim 23, wherein the step of classifying the group of clients according to a connection criterion includes placing the group in one of a poor, a normal and a rich class.

33. The server as claimed in claim 32, wherein the group is initially placed in the normal class.

34. The server as claimed in claim 23, wherein the step of classifying the group of clients includes receiving client characterization information from at least one member of the group.

35. The server as claimed in claim 23, wherein the step of classifying the group of clients includes measuring a time between accepting a TCP connection from a member of the group and receipt of a first HTTP request from that member.

36. The server as claimed in claim 23, wherein the step of classifying the group of clients includes the steps of:

in response to a client request from a member of the group, sending a redirect response, and

measuring a time between the client request and a redirected client request from the member.

37. The server as claimed in claim 23, wherein the step of classifying the group of clients includes measuring a time between transmittal of a container document to a member of the group and receipt of a first request for an object in the document.

38. The server as claimed in claim 23, wherein the step of classifying the group of clients includes measuring a time between transmittal of a container document to a member of the group and receipt of a last request for an object in the document.

39. The server as claimed in claim 23, wherein the step of classifying the group of clients includes measuring a criterion based on of a plurality of server requests.

40. The server as claimed in claim 39, wherein a criterion value E_first is adjusted based on a new measurement E_measured according to a formula:

E_first=α

E_first+(1−

α

)E_measured

wherein α

is a smoothing value in a range from 0 to 1.

41. The server as claimed in claim 23, wherein the client group comprises a cluster of clients under common administrative control.

42. The server as claimed in claim 23, further configured to perform the steps of generating a cookie containing a result of the classification step, and transmitting the cookie to the first client.

43. The server as claimed in claim 23, wherein the step of classifying the group of clients includes transmitting an executable to at least one of the clients for measuring the criterion indicative of the connection.

44. The server as claimed in claim 23, wherein the step of altering the response to the client request includes maintaining the content without alteration.