Client-side techniques for web server allocation

• US 6,175,869 B1
• Filed: 04/08/1998
• Issued: 01/16/2001
• Est. Priority Date: 04/08/1998
• Status: Expired due to Term

• Current Assignee: WSOU Investments, LLC (WSOU Holdings, LLC)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Korilis, Ioannis A., Karaul, Mehmet, Ahuja, Sudhir Raman
• Primary Examiner(s): Maung, Zarni
• Assistant Examiner(s): CALDWELL, ANDREW T
• Application Number:
  US09/057,274
• Time in Patent Office: 1,014 Days
• Field of Search: 709/201, 709/202, 709/203, 709/219, 709/226, 709/105
• US Class Current: 709/226
• 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 67/1019 Random or heuristic server selection

Abstract

A client request directed to a web site or other service hosted by a distributed pool of servers is processed by a client agent associated with the client. The client agent intercepts the client request and routes it to a particular one of the servers in the pool. The client agent bases its routing decision on address information regarding the individual servers of the pool and performance data regarding processing of previous client requests directed to the service. The address information may be retrieved by the client agent from a response to an initial client request directed to the service. The performance data may include response times for servicing previous client requests directed to the service, and the client agent may route the client request such that an average response time of multiple requests to the service is minimized. It may also make use of a probabilistic routing strategy which ensures that each of the servers in the pool receives at least one client request, such that accurate performance data may be maintained for all of the servers. A pricing manager associated with the server pool may be used to establish discount factors or other pricing information for each of the servers in the pool. This pricing information is communicated to the client agents and used in their routing decisions, so as to ensure that otherwise non-cooperating client agents will route their requests in a manner consistent with a target operating point established by the service provider.

Claims

1. A method of processing a client request directed from a client to a service hosted by a pool of servers, the method comprising the steps of:

intercepting a client request directed to the service hosted by the server pool; and

selecting a particular one ofthe servers in the server pool to which to route the client request based on address information and performance data regarding the servers, wherein at least a portion of the address information and the performance data is gathered by a given client agent associated with the client, the given client agent gathering the portion ofthe address information and the performance data by processing responses to one or more previous client requests generated by the corresponding client and directed by the client agent to servers of the server pool using a routing strategy which ensures that each of the servers in the server pool receives at least one client request, and further wherein the selecting step utilizes additional information received from an entity associated with the server pool such that a plurality of otherwise non-cooperating client agents including the given client agent route their requests in accordance with a target operating point for the server pool.

2. The method of claim 1 wherein the intercepting and selecting steps are implemented in the client agent associated with the client.

3. The method of claim 1 wherein upon an initial client request to the service hosted by the server pool, the client agent retrieves the address information from a response to the initial request received from a server in the server pool.

4. The method of claim 1 wherein the selecting step includes selecting a particular one of the servers based on performance data which includes performance data regarding a network over which the client requests are sent.

5. The method of claim 1 wherein the selecting step includes selecting a particular one of the servers based on performance data which includes average response times for at least a subset of the servers.

6. The method of claim 5 wherein the average response times are determined by monitoring previous client requests directed to the service.

7. The method of claim 6 wherein the average response time for at least one of the servers includes a weighted average response time, wherein more recent responses are weighted more heavily than less recent responses.

8. The method of claim 5 wherein the average response times are determined by utilizing probe messages sent by the client agent to the servers.

9. The method of claim 1 wherein the selecting step includes selecting a server in the server pool in accordance with a probabilistic routing strategy which routes client requests such that a server in the pool which provides the fastest response is more likely to receive subsequent client requests than a server in the pool which provides a slower response.

10. The method of claim 9 wherein the probabilistic routing strategy routes multiple client requests such that at least one client request is directed to each of the servers in the pool.

11. The method of claim 1 further including the step of delivering the address information and other server-site specific information to the client agent by a server agent associated with the server pool.

12. The method of claim 11 wherein the server agent determines whether the address information used by the client agent to route the client request is outdated by examining a timestamp transmitted by the client agent with the client request.

13. The method of claim 11 wherein the server agent provides updated address information in its response to the client request if it determines that the address information used by the client agent to route the request is outdated.

14. The method of claim 1 further including the step of transmitting at least a portion of the additional information in the form of pricing information to the client agent, wherein the pricing information establishes a service price associated with each of at least a subset of the servers in the server pool, based on the target operating point for the server pool.

15. The method of claim 14 wherein at least a portion of the pricing information is generated by a pricing manager and transmitted from the pricing manager to a server agent and from the server agent to the client agent.

16. The method of claim 14 wherein at least a portion of the pricing information is generated by server agents associated with the servers and transmitted from the server agents to the client agent.

17. The method of claim 14 wherein the pricing information includes a discount factor for each of the servers in the pool, and the discount factor for a given server reflects the relative sensitivity of the client agent to the responsiveness of that server.

18. The method of claim 17 wherein the selecting step includes selecting one of the servers based on performance data which includes an average response time of each server multiplied by its corresponding discount factor.

19. The method of claim 17 further including the step of updating the discount factors in accordance with an adaptive algorithm.

20. The method of claim 17 wherein a single set of discount factors are supplied to each of a plurality of client agents processing client requests directed to the service hosted by the server pool.

21. An apparatus for processing a client request directed to a service hosted by a pool of servers, the apparatus comprising:

a processor for implementing a given client agent which is operative to intercept a client request directed from a corresponding client to the service hosted by the server pool, and to select a particular one of the servers in the server pool to which to route the client request based on address information and performance data regarding the servers, the given client agent gathering at least a portion of the address information and the performance data by processing responses to one or more previous client requests generated by the corresponding client and directed by the client agent to servers of the server pool using a routing strategy which ensures that each of the servers in the server pool receives at least one client request, wherein the server selection operation further utilizes additional information received from an entity associated with the server pool such that a plurality of otherwise non-cooperating client agents including the given client agent route their requests in accordance with a target operating point for the server pool; and

a memory associated with the processor for storing at least a portion of the address information and performance data.

22. The apparatus of claim 21 wherein at least a portion of the performance data is gathered by the client agent.

23. The apparatus of claim 21 wherein the processor is implemented at least in part within the client.

24. The apparatus of claim 21 wherein the processor is co-located with the client.

25. The apparatus of claim 21 wherein the processor is directly coupled to the client.

26. The apparatus of claim 21 wherein upon an initial client request to the service hosted by the server pool, the client agent retrieves the address information from a response to the initial request received from a server in the server pool.

27. The apparatus of claim 21 wherein the processor is operative to select a particular one of the servers based on performance data which includes performance data regarding a network over which the client requests are sent.

28. The apparatus of claim 21 wherein the processor is operative to select a particular one of the servers based on performance data which includes average response times for at least a subset of the servers.

29. The apparatus of claim 28 wherein the average response times are determined by monitoring previous client requests directed to the service.

30. The apparatus of claim 29 wherein the average response time for at least one of the servers includes a weighted average response time, wherein more recent responses are weighted more heavily than less recent responses.

31. The apparatus of claim 28 wherein the average response times are determined by utilizing probe messages sent by the client agent to the servers.

32. The apparatus of claim 21 wherein the client agent is operative to select a server in the server pool in accordance with a probabilistic routing strategy which routes client requests such that a server in the pool which provides the fastest response is more likely to receive subsequent client requests than a server in the pool which provides a slower response.

33. The apparatus of claim 32 wherein the probabilistic routing strategy routes multiple client requests such that at least one client request is directed to each of the servers in the pool.

34. The apparatus of claim 21 wherein the address information and other server-site specific information are delivered to the client agent by a server agent associated with the server pool.

35. The apparatus of claim 21 wherein client agent transmits a timestamp with the client request, such that a server agent associated with the server pool can determine whether the address information used by the client agent to route the client request is outdated.

36. The apparatus of claim 21 wherein the client agent is operative to retrieve updated address information for the servers of the server pool from a response to the client request.

37. The apparatus of claim 21 wherein the client agent is further operative to receive at least a portion of the additional information in the form of pricing information associated with the server pool, wherein the pricing information establishes a service price associated with each of at least a subset of the servers in the server pool, based on the target operating point for the server pool.

38. The apparatus of claim 37 wherein at least a portion of the pricing information is generated by a pricing manager and transmitted from the pricing manager to a server agent and from the server agent to the client agent.

39. The apparatus of claim 37 wherein at least a portion of the pricing information is generated by server agents associated with the servers and transmitted from the server agents to the client agent.

40. The apparatus of claim 37 wherein the pricing information includes a discount factor for each of the servers in the pool, wherein the discount factor for a given server reflects the relative sensitivity of the client agent to the responsiveness of that server.

41. The apparatus of claim 40 wherein the client agent selects one of the servers based on performance data which includes an average response time of each server multiplied by its corresponding discount factor.

42. An apparatus for processing a client request directed to a service hosted by a pool of servers, comprising:

means for intercepting a client request directed to the service hosted by the server pool; and

means for selecting a particular one ofthe servers in the server pool to which to route the client request based on address information and performance data regarding the servers, wherein at least a portion of the address information and the performance data is gathered by a given client agent associated with the client, the given client agent gathering the portion of the address information and the performance data by processing responses to one or more previous client requests generated by the corresponding client and directed by the client agent to servers of the server pool using a routing strategy which ensures that each of the servers in the server pool receives at least one client request, and further wherein the selecting means utilizes additional information received from an entity associated with the server pool such that a plurality of otherwise non-cooperating client agents including the given client agent route their requests in accordance with a target operating point for the server pool.

43. A method of processing a client request directed from a client to a service hosted by a pool of servers, the method comprising the steps of:

generating pricing information which establishes a service price associated with each of at least a subset of the servers in the server pool, based on a target operating point for the server pool; and

transmitting the pricing information to the client, such that a client agent associated with the client is enabled to select a particular one of the servers in the server pool to which to route the client request based at least in part on the pricing information, the client agent gathering address information and performance data used in the select operation by processing responses to one or more previous client requests generated by the client and directed by the client agent to servers of the server pool using a routing strategy which ensures that each of the servers in the server pool receives at least one client request.

44. The method of claim 43 wherein at least a portion of the pricing information is generated by a pricing manager associated with the server pool and transmitted from the pricing manager to a client agent associated with the client.

45. The method of claim 43 wherein at least a portion of the pricing information is generated by server agents associated with the servers and transmitted from the server agents to a client agent associated with the client.

46. The method of claim 43 wherein the pricing information includes a discount factor for each of the servers in the pool, wherein the discount factor for a given server reflects the relative sensitivity of the client agent to the responsiveness of that server.

47. A method of processing a client request directed from a client to a service hosted by a pool of servers, the method comprising the steps of:

intercepting a client request directed to the service hosted by the server pool; and

selecting a particular one of the servers in the server pool to which to route the client request based on address information and performance data regarding the servers, wherein the intercepting and selecting steps are implemented in a client agent associated with the client, the client agent gathering at least a portion of the address information and the performance data by processing responses to one or more previous client requests generated by the corresponding client and directed by the client agent to servers of the server pool using a routing strategy which ensures that each of the servers in the server pool receives at least one client request, and further wherein the selecting step utilizes additional information received from an entity associated with the server pool such that a plurality of otherwise non-cooperating client agents including the given client agent route their requests in accordance with a target operating point for the server pool.