Large scale bandwidth management of IP flows using a hierarchy of traffic shaping devices

• US 10,382,339 B2
• Filed: 03/30/2018
• Issued: 08/13/2019
• Est. Priority Date: 01/12/2015
• Status: Active Grant

• Current Assignee: Citrix Systems, Inc. (Cloud Software Group)
• Original Assignee: Citrix Systems, Inc. (Cloud Software Group)
• Inventors: Haran, Jeffrey, Wason, Ashwani, Stavrakos, Nicholas, Kotlyar, Grisha
• Primary Examiner(s): Holland, Jenee
• Application Number:
  US15/941,162
• Publication Number:
  US 20180227234A1
• Time in Patent Office: 501 Days
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 47/22 Traffic shaping
• CPC Class Codes: H04L 47/2483 involving identification of individual flows
• CPC Class Codes: H04L 47/35 by embedding flow control information in regular packets, e.g. piggybacking

Abstract

A computer network appliance may include a memory and a processor cooperating with the memory to run a classification kernel module performing traffic shaping on data packets based upon a first set of queuing disciplines (qdiscs). The processor may further run at least one virtual device also performing traffic shaping on the data packets based upon a second set of qdiscs different than the first set of qdiscs, and provide the data packets to a network interface.

Claims

1. A computer network appliance comprising:

a memory and a processor cooperating with the memory to run

a classification kernel module performing traffic shaping on data packets based upon a first set of queuing disciplines (qdiscs), and

at least one virtual device also performing traffic shaping on the data packets based upon a second set of qdiscs different than the first set of qdiscs, and providing the data packets to a network interface.

2. The computer network appliance of claim 1 wherein the classification kernel module further determines at least one traffic shaping rule associated with different data packets, and wherein the at least one virtual device selects respective qdiscs from among the second set of qdiscs for different data packets based upon the at least one traffic shaping rule determined by the classification kernel module.

3. The computer network appliance of claim 2 wherein the at least one traffic shaping rule comprises at least one of a subscriber traffic shaping rule and an application traffic shaping rule.

4. The computer network appliance of claim 1 wherein the at least one virtual device comprises at least one virtual subscriber device to perform traffic shaping based upon respective subscribers associated with the data packets.

5. The computer network appliance of claim 4 wherein the at least one virtual subscriber devices comprises a plurality of virtual subscriber devices;

and wherein the processor further runs a virtual subscriber multiplexer (mux) device for distributing the data packets from the classification kernel module to the plurality of virtual subscriber devices.

6. The computer network appliance of claim 1 wherein the at least one virtual device comprises a virtual application device to perform traffic shaping based upon a data type associated with the data packets from among a plurality of different data types.

7. The computer network appliance of claim 1 wherein the network interface comprises a wireless virtual local area network (VLAN) and an Internet VLAN;

and wherein the processor further runs a virtual wireless head to receive data packets from the classification kernel module designated for the wireless VLAN device, and an Internet head to receive data packets from the classification kernel designated for the Internet VLAN.

8. The computer network appliance of claim 7 wherein the processor further runs a VLAN multiplexer (mux) to route data packets to the wireless VLAN or Internet VLAN based upon the virtual wireless head and the virtual Internet head.

9. A computer network traffic shaping method comprising:

performing traffic shaping on data packets at a classification kernel module based upon a first set of queuing disciplines (qdiscs);

performing traffic shaping on the data packets also using at least one virtual device based upon a second set of qdiscs different than the first set of qdiscs; and

providing the data packets to a network interface after traffic shaping based upon the first and second sets of qdiscs.

10. The method of claim 9 further comprising:

determining at least one traffic shaping rule associated with different data packets at the classification kernel module; and

selecting respective qdiscs from among the second set of qdiscs for different data packets at the at least one virtual device based upon the at least one traffic shaping rule determined by the classification kernel module.

11. The method of claim 10 wherein the at least one traffic shaping rule comprises at least one of a subscriber traffic shaping rule and an application traffic shaping rule.

12. The method of claim 9 wherein the at least one virtual device comprises at least one virtual subscriber device to perform traffic shaping based upon respective subscribers associated with the data packets.

13. The method of claim 12 wherein the at least one virtual subscriber device comprises a plurality of virtual subscriber devices;

and further comprising distributing the data packets from the classification kernel module to the plurality of virtual subscriber devices using a virtual subscriber multiplexer (mux) device.

14. The method of claim 9 wherein the at least one virtual device comprises a virtual application device to perform traffic shaping based upon a data type associated with the data packets from among a plurality of different data types.

15. A non-transitory computer-readable medium for a computer network appliance running a classification kernel module and at least one virtual device, the non-transitory computer-readable medium having computer-executable instructions for causing the computer network appliance to perform steps comprising:

performing traffic shaping on data packets at the classification kernel module based upon a first set of queuing disciplines (qdiscs);

performing traffic shaping on the data packets also using the at least one virtual device based upon a second set of qdiscs different than the first set of qdiscs; and

providing the data packets to a network interface after traffic shaping based upon the first and second sets of qdiscs.

16. The non-transitory computer-readable medium of claim 15 further having computer-executable instructions for causing the computer network appliance to perform steps comprising:

determining at least one traffic shaping rule associated with different data packets at the classification kernel module; and

selecting respective qdiscs from among the second set of qdiscs for different data packets at the at least one virtual device based upon the at least one traffic shaping rule determined by the classification kernel module.

17. The non-transitory computer-readable medium of claim 16 wherein the at least one traffic shaping rule comprises at least one of a subscriber traffic shaping rule and an application traffic shaping rule.

18. The non-transitory computer-readable medium of claim 15 wherein the at least one virtual device comprises at least one virtual subscriber device to perform traffic shaping based upon respective subscribers associated with the data packets.

19. The non-transitory computer-readable medium of claim 18 wherein the at least one virtual subscriber device comprises a plurality of virtual subscriber devices;

and further having computer-executable instructions for causing the computer network appliance to run a virtual subscriber multiplexer (mux) device to distribute the data packets from the classification kernel module to the plurality of virtual subscriber devices.

20. The non-transitory computer-readable medium of claim 15 wherein the at least one virtual device comprises a virtual application device to perform traffic shaping based upon a data type associated with the data packets from among a plurality of different data types.