Near optimal service function path instantiation in a multi-datacenter environment

Abstract

Service Function Chaining (SFC) supports services/applications through linking an ordered list of service functions (such as firewalls, deep packet inspections and load balancers) in the network. Using Software Defined Networking (SDN) and Network Function Virtualization (NFV) provides a simpler and shorter SFC process. In order to provide high-availability on a multi-site SFC, it is required a flexible algorithm able to properly select Service Function instances while creating the Service Function Path (SFP). This paper presents a new service function selection algorithm providing a flexible tradeoff between the SFP distance and the loads per service function instances at the deployment stage. The flexible tradeoff provided in the algorithm can be adjusted by a parameter. This parameter value can differ among different types of SFCs based on the service/application (real time or non-real time) dedicated for its SFC. Matlab has been utilized for validating it with different scenarios. It is also compared to other existing algorithms such as, load balancing and shortest path. The results showed that the proposed algorithm could provide the best SFP end-to-end distance performance as the shortest path algorithm for the real time services/applications, and that will result a good Quality of Service (QoS) performance for real time services/applications. Furthermore, the proposed algorithm provides an acceptable load distribution over the available service functions instances better than shortest path algorithm and not far from and load balancing algorithms.