Network multi-source inbound quality of service methods and systems

• US 10,574,528 B2
• Filed: 11/13/2017
• Issued: 02/25/2020
• Est. Priority Date: 02/11/2017
• Status: Active Grant

• Current Assignee: Nicira Incorporated (Broadcom, Inc.)
• Original Assignee: Nicira Incorporated (Broadcom, Inc.)
• Inventors: Mayya, Ajit Ramachandra, Thakore, Parag Pritam, Connors, Stephen Craig, Woo, Steven Michael, Mukundan, Sunil, Srihari, Mukamala Swaminathan
• Primary Examiner(s): Abu Roumi, Mahran Y
• Application Number:
  US15/811,329
• Publication Number:
  US 20180302286A1
• Time in Patent Office: 834 Days
• Field of Search: 709224
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity

Abstract

A computerized method useful for implementing a Multi-Source Inbound QoS (Quality of Service) process in a computer network includes the step of calculating a current usage rate of a provider entity. The provider entity is classified by a network traffic priority; implementing a fair sharing policy among a set of provider entities. The method includes the step of adjusting any excess bandwidth among a set of provider entities. The method includes the step of implementing link sharing at a provider-entity level.

Claims

1. A method for implementing a multi-source inbound QoS (Quality of Service) process for use on network traffic transmitted from a set of provider entities to a particular receiver entity in a computer network, wherein each of the provider entities in the set of provider entities shares at least one link with the particular receiver entity, the method comprising:

at the particular receiver entity,

receiving, from each provider entity in the set of provider entities, at least one usage score based on a quantity of network traffic transmitted by the provider entity to the receiver entity, wherein the particular receiver entity receives from a particular provider entity (i) a first usage score that relates to a quantity of network traffic transmitted by the particular provider entity at a first priority level and (ii) a second usage score that relates to a quantity of network traffic transmitted by the particular provider entity at a second priority level that is different from the first priority level;

storing the received usage scores in a bandwidth accumulator;

based on the stored usage scores, calculating a current usage rate for each provider entity in the set of provider entities in order to determine bandwidth needs for each provider entity; and

allocating bandwidth for the priority levels to each provider entity of the set of provider entities based on the determined bandwidth needs.

2. The method of claim 1, wherein the at least one usage score received from each provider entity in the set of provider entities comprises a total requirement for the provider entity to send computer network traffic to the particular receiver entity without dropping any data packets.

3. The method of claim 1, wherein the calculated current usage rate of each provider entity in the set of provider entities comprises a sum of all received usage scores stored in the bandwidth accumulator from any particular provider entity.

4. The method of claim 1 further comprising implementing a provider-entity-level link-sharing policy for each provider entity in the set of provider entities by configuring a link scheduler at each provider entity such that path selection policies are honored.

5. The method of claim 1, wherein network traffic is transmitted at one of a high-priority level, a normal-priority level, and a low-priority level.

6. The method of claim 5 further comprising calculating a usage score for each network traffic priority level, wherein the usage score for a particular network traffic priority level is the sum of all received usage scores at the particular network traffic priority level.

7. The method of claim 1 further comprising:

when the determined bandwidth needs for a particular provider entity are less than a total link bandwidth specified for the receiver entity, allocating the total determined amount of needed bandwidth to the particular provider entity; and

when the determined bandwidth needs for the particular provider entity are greater than a total link bandwidth specified for the receiver entity, allocating, for each network traffic priority level, a minimum required bandwidth to the particular provider entity.

8. The method of claim 1 further comprising computing a minimum required bandwidth for a provider entity by dividing the total link bandwidth specified for the receiver entity by a number of provider entities in the set of provider entities.

9. The method of claim 1, wherein each provider entity in the set of provider entities comprises any one of (i) a multipath protocol endpoint, (ii) an Internet host, and (iii) a multipath hub in an enterprise datacenter.

10. The method of claim 1 further comprising when excess bandwidth is found after allocating bandwidth for the priority levels to each provider entity of the set of provider entities, allocating the excess bandwidth among the set of provider entities.

11. The method of claim 10, wherein allocating the excess bandwidth among the set of provider entities comprises:

iterating through each provider entity and assigning the excess bandwidth to a first provider entity that still requires more bandwidth.

12. A computer system comprising:

a set of one or more processing units; and

a non-transitory machine readable medium storing a program which when executed by at least one of the processing units, implements a multi-source inbound Quality of Service (QoS) process for use on network traffic transmitted from a set of provider entities to a particular receiver entity in a computer network, wherein each of the provider entities in the set of provider entities shares at least one link with the particular receiver entity, the program comprising a set of instructions for;

at the particular receiver entity;

receiving, from each provider entity in the set of provider entities, at least one usage score based on a quantity of network traffic transmitted by the provider entity to the receiver entity, wherein the particular receiver entity receives from a particular provider entity (i) a first usage score that relates to a quantity of network traffic transmitted by the particular provider entity at a first priority level and (ii) a second usage score that relates to a quantity of network traffic transmitted by the particular provider entity at a second priority level that is different from the first priority level;

storing the received usage scores in a bandwidth accumulator;

based on the stored usage scores, calculating a current usage rate for each provider entity in the set of provider entities in order to determine bandwidth needs for each provider entity;

allocating bandwidth for the priority levels to each provider entity of the set of provider entities based on the determined bandwidth needs.

13. The computerized system of claim 12, wherein the at least one usage score received from each provider entity in the set of provider entities comprises a total requirement for the provider entity to send computer network traffic to the particular receiver entity without dropping any data packets.

14. The computerized system of claim 12, wherein the calculated current usage rate of each provider entity in the set of provider entities comprises a sum of all received usage scores stored in the bandwidth accumulator from any particular provider entity.

15. The computerized system of claim 12, wherein the program comprises a set of instructions for implementing a provider-entity-level link-sharing policy for each provider entity in the set of provider entities by configuring a link scheduler at each provider entity such that path selection policies are honored.

16. The computerized system of claim 12, wherein each provider entity in the set of provider entities comprises any one of (i) a multipath protocol endpoint, (ii) an Internet host, and (iii) a multipath hub in an enterprise datacenter.