SYSTEM AND METHOD FOR SERVICE CHAIN LOAD BALANCING

• US 20170317932A1
• Filed: 04/29/2016
• Published: 11/02/2017
• Est. Priority Date: 04/29/2016
• Status: Active Grant

• Current Assignee: Citrix Systems, Inc. (Cloud Software Group)
• Original Assignee: Citrix Systems, Inc. (Cloud Software Group)
• Inventors: Paramasivam, Sankar Muthu
• Granted Patent: US 10,237,187 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 47/24 Traffic characterised by specific attributes, e.g. priority or QoS
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

The present disclosure is directed towards systems and methods of service chain load balancing. A controller intermediary to a client and computing infrastructure identifies a plurality of service chains. Each of the plurality of service chains include a path having an instance of a first service provided by the computing infrastructure and an instance of a second service provided by the computing infrastructure. The controller determines a path weight for each of the plurality of service chains. The path weight indicates a level of efficiency of delivering services in accordance with the service chain. The controller selects, based on a load balancing function and the path weight for each of the plurality of service chains, a service chain from the plurality of service chains to direct network traffic from a client.

Claims

1. A method of load balancing service chains, comprising:

identifying, by a controller intermediary to a client and computing infrastructure comprising one or more servers in one or more networked environments, a plurality of service chains, each of the plurality of service chains comprising a path having an instance of a first service provided by the computing infrastructure and an instance of a second service provided by the computing infrastructure;

determining, by the controller, a path weight for each of the plurality of service chains, the path weight indicating a level of efficiency of delivering services in accordance with the service chain; and

selecting, by the controller based on a load balancing function and the path weight for each of the plurality of service chains, a service chain from the plurality of service chains to direct network traffic from a client.

2. The method of claim 1, wherein identifying the plurality of service chains comprises:

generating, by the controller using a cloud application programming interface, one or more queries to identify each instance of the plurality of service chains; and

receiving, by the controller responsive to the one or more queries, an indication of a first service chain comprising a first path having a first instance of the first service and a first instance of the second service, and an indication of a second service chain comprising a second path having a second instance of the first service and a second instance of the second service.

3. The method of claim 1, comprising:

generating, by the controller using a cloud application programming interface, one or more queries to retrieve metadata for each instance of the plurality of service chains, the one or more queries configured to retrieve information for at least one of a placement, resource allocation, type of reservation, or type of connectivity.

4. The method of claim 1, comprising:

identifying, by the controller, the service chain of the plurality of service chains comprising a first path having a first instance of the first service and a first instance of the second service;

identifying, by the controller, a second service chain of the plurality of service chains comprising a second path having a second instance of the first service and a second instance of the second service;

receiving, by the controller using a cloud application programming interface, metadata for each of the first instance of the first service, the second instance of the first service, the first instance of the second service, and the second instance of the second service;

determining, by the controller based on the metadata, a first edge weight for the first instance of the first service, a second edge weight for the second instance of the first service, a third edge weight for the first instance of the second service, and a fourth edge weight for the second instance of the second service;

generating, by the controller, a first path weight for the first path based on a combination of the first edge weight with the third edge weight;

generating, by the controller, a second path weight for the second path based on a combination of the second edge weight with the fourth edge weight; and

selecting, by the controller, the service chain corresponding to the first path based on the first path weight ranking higher than the second path weight.

5. The method of claim 1, wherein selecting the service chain comprises:

ranking, by the controller, each service chain of the plurality of service chains based on the path weight for each of the plurality of service chains;

selecting, by the controller based on the ranking, a predetermined number of highest ranking service chains of the plurality of service chains to generate a subset of service chains; and

inputting, by the controller, the path weight for each of the subset of service chains into the load balancing function to select the service chain.

6. The method of claim 1, comprising:

ranking, by the controller, each service chain of the plurality of service chains based on the path weight for each of the plurality of service chains;

selecting, by the controller based on the ranking, a predetermined number of highest ranking service chains of the plurality of service chains to generate a subset of service chains;

identifying, by the controller, one or more instances of the first service that are missing from the subset of service chains; and

modifying, by the controller, the subset of service chains to include one or more additional service chains of the plurality of service chains, the one or more additional service chains comprising the one or more instances of the first service.

7. The method of claim 1, comprising:

pruning, by the controller using a machine learning technique, the plurality of service chains to generate a subset of the plurality of service chains; and

selecting, by the controller based on the load balancing function and the path weight for each of the subset of the plurality of service chains, the service chain from the subset of the plurality of service chains.

8. The method of claim 1, comprising:

determining the path weight for each of the plurality of service chains based on an edge weight of each instance of each of the plurality of service chains, the path weight based on at least one of latency, resource overhead, throughput, or resource cost.

9. The method of claim 1, wherein each of the plurality of service chains comprise a different path and provide same services.

10. The method of claim 1, comprising:

forwarding, by the controller, network traffic from the client to the first instance of the selected service chain.

11. A system to load balance service chains, comprising:

a controller intermediary to a client and computing infrastructure comprising one or more servers in one or more networked environments configured to;

identify a plurality of service chains, each of the plurality of service chains comprising a path having an instance of a first service provided by the computing infrastructure and an instance of a second service provided by the computing infrastructure;

determine a path weight for each of the plurality of service chains, the path weight indicating a level of efficiency of delivering services in accordance with the service chain; and

select, based on a load balancing function and the path weight for each of the plurality of service chains, a service chain from the plurality of service chains to direct network traffic from a client.

12. The system of claim 11, wherein the controller is further configured to:

generate, based on a cloud application programming interface, one or more queries to identify each instance of the plurality of service chains; and

receive, responsive to the one or more queries, an indication of a first service chain comprising a first path having a first instance of the first service and a first instance of the second service, and an indication of a second service chain comprising a second path having a second instance of the first service and a second instance of the second service.

13. The system of claim 11, wherein the controller is further configured to:

generate, based on a cloud application programming interface, one or more queries to retrieve metadata for each instance of the plurality of service chains, the one or more queries configured to retrieve information for at least one of a placement, resource allocation, type of reservation, or type of connectivity.

14. The system of claim 11, wherein the controller is further configured to:

identify the service chain of the plurality of service chains comprising a first path having a first instance of the first service and a first instance of the second service;

identify a second service chain of the plurality of service chains comprising a second path having a second instance of the first service and a second instance of the second service;

receive, via a cloud application programming interface, metadata for each of the first instance of the first service, the second instance of the first service, the first instance of the second service, and the second instance of the second service;

determine, based on the metadata, a first edge weight for the first instance of the first service, a second edge weight for the second instance of the first service, a third edge weight for the first instance of the second service, and a fourth edge weight for the second instance of the second service;

generate a first path weight for the first path based on a combination of the first edge weight with the third edge weight;

generate a second path weight for the second path based on a combination of the second edge weight with the fourth edge weight; and

select the service chain corresponding to the first path based on the first path weight ranking higher than the second path weight.

15. The system of claim 11, wherein the controller is further configured to:

rank each service chain of the plurality of service chains based on the path weight for each of the plurality of service chains;

select, based on the rank, a predetermined number of highest ranking service chains of the plurality of service chains to generate a subset of service chains; and

input the path weight for each of the subset of service chains into the load balancing function to select the service chain.

16. The system of claim 11, wherein the controller is further configured to:

rank each service chain of the plurality of service chains based on the path weight for each of the plurality of service chains;

select, based on the rank, a predetermined number of highest ranking service chains of the plurality of service chains to generate a subset of service chains;

identify one or more instances of the first service that are missing from the subset of service chains; and

modify the subset of service chains to include one or more additional service chains of the plurality of service chains, the one or more additional service chains comprising the one or more instances of the first service.

17. The system of claim 11, wherein the controller is further configured to:

prune, based on a machine learning technique, the plurality of service chains to generate a subset of the plurality of service chains; and

select, based on the load balancing function and the path weight for each of the subset of the plurality of service chains, the service chain from the subset of the plurality of service chains.

18. The system of claim 11, wherein the controller is further configured to:

determine the path weight for each of the plurality of service chains based on an edge weight of each instance of each of the plurality of service chains, the path weight based on at least one of latency, resource overhead, throughput, or resource cost.

19. The system of claim 11, wherein each of the plurality of service chains comprise a different path and provide same services.

20. The system of claim 11, wherein the controller is further configured to:

forward network traffic from the client to the first instance of the selected service chain.