Abstract
In classical monolithic router architecture, the Border Gateway Protocol (BGP) engine is implemented as a multiprocess centralized function within the controller entity. This architecture does not scale well and its performance decreases when the load increases, forcing multiple processes to compete for the same controller processor. In addition only a limited number of peer connections can be handled. In this paper, we propose a novel scalable distributed architecture for the BGP engine without modifying the core of the BGP protocol as defined in RFC 4271. The proposed architecture is designed according to the “Master-Slave” task separation along with the replication of the Routing Information Base (RIB) on multiple controller cards. In addition, we design a new consistency algorithm for the RIB replication. Simulations show an acceptable trade-off between the scalability to a large number of peer sessions and the overhead caused by the communication latency. Furthermore, simulations show that the proposed architecture handily outperforms the actual BGP processing capacity. Accordingly, we conclude that our approach increases considerably both scalability and reliability thanks to the replication of the RIB.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
