Connection management system and method

• US 7,346,691 B2
• Filed: 12/07/2005
• Issued: 03/18/2008
• Est. Priority Date: 10/05/2000
• Status: Expired due to Term

• Current Assignee: Juniper Networks Incorporated
• Original Assignee: Juniper Networks Incorporated
• Inventors: Peiffer, Christopher
• Primary Examiner(s): Dalencourt; Yves
• Application Number:
  US11/296,759
• Publication Number:
  US 20060089996A1
• Time in Patent Office: 832 Days
• Field of Search: None
• US Class Current: 709/227
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/10015 Access to distributed or replicated servers, e.g. using brokers
• 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 67/101 based on network conditions
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/14 Session management for real-time applications in data packet communications networks H04L65/1066
• CPC Class Codes: H04L 67/564 Enhancement of application control based on intercepted application data
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 69/14 Multichannel or multilink protocols
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

A system and method for managing connections between a server and a plurality of clients at a network connection management device is provided. The method comprises maintaining at least one connection to the server, receiving requests from the clients, transmitting the requests to the server, receiving responses to the requests from the server, and monitoring a server response time for a selected request sent to the server, the server response time for the selected request being the time elapsed between transmitting the selected request to the server and receiving a corresponding response from the server. A method according to the present invention may also include basing the number of connections to the server on the server response time.

Claims

1. A method of managing connections between a plurality of server and a plurality of clients at a connection management device, the connection management device being interposed between the server and the plurality of clients on a computer network, the method comprising:

maintaining one or more persistent connections from the connection management device to each of the servers;

distributing requests from the clients to the servers over the persistent connections;

monitoring server response times for the requests sent to the servers over the persistent connections; and

changing with the connection management device the number of persistent connections from the connection management device to the servers based on the monitored server response times.

2. The method of claim 1, wherein changing with the connection management device the number of connections comprises closing with the connection management device one or more of the connections when the server response time is below a first predetermined threshold.

3. The method of claim 1, further comprising seeking a selected connection with no pending requests before transmitting a received request to the server via the selected connection.

4. The method of claim 3, further comprising opening a new connection for transmission of the received request if no connection with no pending request is found.

5. The method of claim 1, wherein monitoring the server response time includes monitoring a performance indicator that is correlated to the server response time.

6. The method of claim 5, the performance indicator having a value, wherein changing with the connection management device the number of connections comprises changing the number of connections to the server if the value of the performance indicator falls outside a determined range of values.

7. The method of claim 6, further comprising continuously updating the determined range of values by periodically correlating the server response time to the performance indicator.

8. The method of claim 5, wherein the performance indicator is selected from the group consisting of a rate of formation of new client connections to the connection management device, a rate of client requests received, a type of request received, a client type, a client bandwidth, a resource URL, and a resource type requested.

9. A method of optimizing communication between a plurality of clients and a server at a connection management device, the connection management device being configured to connect to the clients and to the server to facilitate resource transfer between the clients and the server, the method comprising:

maintaining one or more persistent connections from the connection management device to the server;

monitoring a server response time for requests sent to the server for each of the persistent connections; and

dynamically decreasing the number of persistent connections from the connection management device to the server when the monitored server response time for one or more of the persistent connections falls below a threshold.

10. The method of claim 9, further comprising opening a new connection to the server and sending the request to the server on the new connection if a connection with no pending requests cannot be identified.

11. The method of claim 9, wherein the connections are persistent connections and a server response time elapses between sending the request to the server and receiving a corresponding response from the server, further comprising monitoring the server response time and changing the number of persistent connections to the server if the server response time falls outside of a predetermined range of times defined at least in part by the threshold.

12. The method of claim 11, wherein decreasing the connections comprises closing one or more of the connections if the server response time is faster than the predetermined range of times.

13. The method of claim 11, wherein a connection is opened if the server response time is slower than the predetermined range of times.

14. The method of claim 9, wherein a server response time elapses between sending the request to the server and receiving a corresponding response from the server, further comprising continuously monitoring a performance indicator correlated to the server response time.

15. The method of claim 14, the performance indicator having a value, further comprising changing the number of connections to the server if the value of the performance indicator falls outside a desired value range.

16. The method of claim 15, wherein the performance indicator is selected from the group consisting of a rate of formation of new client connections to the connection management device, a rate of client requests received, a type of request received, a client type, a client bandwidth, a resource URL, and a resource type requested.

17. The method of claim 15, further comprising continuously updating the desired value range by periodically correlating the server response time to selected values of the performance indicator.

18. The method of claim 17, wherein periodically correlating the server response time to selected values of the performance indicator includes calculating a historical average of server response times for selected values of the performance indicator.

19. The method of claim 9, the connection management device being configured to receive a plurality of requests from the clients and forward the plurality of requests to the server, wherein sending the request to the server includes storing information regarding the request to help identify a corresponding response from the server.

20. A connection management device configured to manage connections between at least one client and a server, the connection management device including a controller having a processor and volatile memory, a network interface configured to interface the connection management device to the computer network, and non-volatile memory, the non-volatile memory containing a communications program executable by the controller to:

maintain one or more persistent connections from the connection management device to the server;

monitor a server response time for requests sent to the server for each of the persistent connections; and

decrease the number of persistent connections from the connection management device to the server when the server response time is shorter than a predetermined range of response times.

21. The connection management device of claim 20, wherein the communications program is executable by the controller to periodically monitor a plurality of server response times for a plurality of requests.

22. The connection management device of claim 20, wherein the communications program is executable by the controller to increase the number of connections to the server when a selected server response time is longer than a predetermined range of response times.

23. The connection management device of claim 22, wherein the communications program is executable by the controller to correlate a performance indicator to the server response times.

24. The connection management device of claim 23, the performance indicator having a value, wherein the communications program is executable by the controller to base the number of connections to the server upon the value of the performance indicator.

25. The connection management device of claim 23, wherein the performance indicator is selected from the group consisting of a rate of formation of new client connections to the connection management device, a rate of client requests received, a type of request received, a client type, a client bandwidth, a resource URL, and a type of resource requested.

26. The connection management device of claim 23, wherein the communications program is executable by the controller to continuously update the correlation of the performance indicator to the server response times.