System and method for managing network traffic

• US 7,848,348 B2
• Filed: 04/13/2007
• Issued: 12/07/2010
• Est. Priority Date: 04/13/2007
• Status: Active Grant

• Current Assignee: Atlassian US, Inc. (Atlassian Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Chen, Kaiyan, Jiang, Baofeng, Van Slyke, John, Wu, Xidong, Savoor, Raghvendra, Park, Sun-Uk, Blackburn, Stuart L.
• Primary Examiner(s): Hoang; Thai D
• Application Number:
  US11/735,175
• Publication Number:
  US 20080253393A1
• Time in Patent Office: 1,334 Days
• Field of Search: 370449-457, 370/346
• US Class Current: 370/449
• CPC Class Codes: H04L 43/024 by adaptive sampling
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity

Abstract

A system and method for managing network traffic is disclosed. A system that incorporates teachings of the present disclosure may include, for example, a data switch having a controller element to transmit telemetry data representative of bandwidth usage by one or more users of the data switch. Traffic for the data switch can be managed based at least in part on the bandwidth usage by higher bandwidth users of the data switch. Additional embodiments are disclosed.

Claims

1. A non-transitory computer-readable storage medium in a network proxy of a communication system, the storage medium being embedded with computer instructions for causing a computing device to perform the steps of:

polling a data switch according to a polling frequency to determine bandwidth usage of one or more users of the communication system;

determining a peak bandwidth of each of the one or more users based at least in part on the bandwidth usage;

identifying higher bandwidth users of the one or more users based at least in part on the peak bandwidth;

increasing the polling frequency for at least one of the higher bandwidth users to determine an estimated bandwidth usage and to avoid a rollover of a telemetry counter; and

determining the at least one higher bandwidth users for increased polling frequency based at least in part on a differential in upstream and downstream data transfer rates for the one or more users.

2. The computer readable storage medium of claim 1, further comprising computer instructions for managing traffic for the data switch based at least in part on the estimated bandwidth usage.

3. The computer readable storage medium of claim 1, wherein the managing of traffic for the data switch comprises at least one among augmenting bandwidth of the data switch and transferring at least one of the one or more users to another data switch.

4. The computer readable storage medium of claim 3, wherein the at least one of the one or more users transferred to the other data switch is one or more of the at least one higher bandwidth users.

5. The computer readable storage medium of claim 1, further comprising computer instructions for:

monitoring other bandwidth usage of one or more other data switches; and

transferring at least one of the one or more users to the one or more other data switches based at least in part on the other bandwidth usage.

6. The computer readable storage medium of claim 5, further comprising computer instructions for:

polling one or more other data switches to determine the other bandwidth usage;

identifying other higher bandwidth users of the one or more other data switches; and

increasing the polling frequency for at least one of the other higher bandwidth users.

7. The computer readable storage medium of claim 1, further comprising computer instructions for:

determining whether a desired polling frequency exceeds a polling frequency limit; and

increasing the polling frequency for the at least one of the higher bandwidth users while the increased polling frequency is less than the polling frequency limit.

8. A data switch, comprising:

a counter for monitoring or collecting telemetry data for the data switch;

wherein the data switch is configured to transmit telemetry data representative of bandwidth usage by one or more users of the data switch,

wherein traffic for the data switch is managed based at least in part on the bandwidth usage by higher bandwidth users of the data switch, and

wherein at least one higher bandwidth user has an increased polling frequency based at least in part on a differential in upstream and downstream data transfer rates for the one or more users.

9. The data switch of claim 8, wherein a network proxy manages traffic for the data switch according to at least one among augmenting bandwidth of the data switch and transferring at least one of the one or more users to another data switch.

10. The data switch of claim 9, wherein other bandwidth usage of the another switch is monitored, and wherein the transferring of the at least one of the one or more users to the another data switch is based at least in part on the other bandwidth usage.

11. The data switch of claim 8, wherein a peak bandwidth of each of the one or more users is determined based at least in part on the bandwidth usage, and wherein the higher bandwidth users are determined based at least in part on the peak bandwidth.

12. The data switch of claim 8, wherein the telemetry data is transmitted in response to a request by a network proxy according to a polling frequency of the network proxy.

13. The data switch of claim 12, wherein a peak bandwidth of each of the one or more users is determined based at least in part on the bandwidth usage, wherein the higher bandwidth users are determined based at least in part on the peak bandwidth, and wherein the polling frequency is increased for at least one of the higher usage users so long as the polling frequency does not exceed a polling frequency limit.

14. A method of managing network traffic comprising:

with a counter, monitoring bandwidth usage of one or more users of a data switch to at least in part avoid a rollover of a telemetry counter;

performing traffic management based at least in part on the bandwidth usage monitored with the counter according to at least one among augmenting bandwidth of the data switch and transferring at least one of the one or more users to another data switch; and

determining a differential in upstream and downstream data transfer rates for the one or more users based at least in part on the peak bandwidth, wherein the at least one higher bandwidth users for increased polling frequency is determined based at least in part on the differential.

15. The method of claim 14, wherein the traffic management for the data switch is based at least in part on the bandwidth usage by higher bandwidth users of the one or more users of the data switch.

16. The method of claim 15, further comprising:

determining a peak bandwidth of each of the one or more users based at least in part on the bandwidth usage; and

determining the higher bandwidth users based at least in part on the peak bandwidth.

17. The method of claim 15, wherein the monitoring of the bandwidth usage comprises polling according to a polling frequency.

18. The method of claim 17, further comprising:

determining a peak bandwidth of each of the one or more users based at least in part on the bandwidth usage;

determining the higher bandwidth users based at least in part on the peak bandwidth; and

increasing the polling frequency for at least one of the higher bandwidth users while the polling frequency is less than a desired polling frequency.

19. The method of claim 18, further comprising:

determining whether the desired polling frequency exceeds a polling frequency limit; and

increasing the polling frequency for the at least one of the higher bandwidth users while the desired polling frequency is less than the polling frequency limit.

20. The method of claim 14, further comprising:

monitoring one or more other data switches for other bandwidth usage, wherein the transferring of the at least one of the one or more users to another data switch is based at least in part on the other bandwidth usage.

21. The method of claim 20, further comprising:

polling the one or more other data switches to determine the other bandwidth usage;

determining other higher bandwidth users of the one or more other data switches; and

increasing the polling frequency for at least one of the other higher bandwidth users.