VNF‐Consensus: A virtual network function for maintaining a consistent distributed software‐defined network control plane

Abstract

Software-defined networks (SDN) usually rely on a centralized controller, which has limited availability and scalability by definition. Although a solution is to employ a distributed control plane, the main issue with this approach is how to maintain the consistency among multiple controllers. Consistency should be achieved with as low impact on network performance as possible and should be transparent for controllers, without requiring any change of the SDN protocols. In this work, we propose VNF-Consensus, a virtual network function that implements Paxos to ensure strong consistency among controllers of a distributed control plane. In our solution, controllers can perform their control plane activities without having to execute the expensive tasks required to keep consistency. Experimental results are presented showing the cost and benefits of the proposed solution, in particular in terms of low controller overhead. | INTRODUCTIONSoftware-defined networks (SDN) separate the control plane from the data plane, which improves their flexibility, programmability, and management. 1,2 The control plane is usually centralized, consisting of a single controller, while the data plane consists of numerous network devices distributed across the network. While a centralized approach is attractive as it is simpler to operate and manage, it represents a vulnerability as the controller is a single point of failure with a direct impact not only in terms of resilience (i.e., if the controller fails the whole network stops running) but also on performance and scalability 3 (i.e., the single controller has to process all requests from all switches). The solution is to distribute the control plane, employing multiple controllers that share responsibilities. 4 Several different distributed SDN control plane strategies have been proposed. 5,6 Although the advantages of employing multiple controllers should be clear, there is also a cost to pay: in order to employ a distributed control plane it is necessary to employ techniques to guarantee the consistency among the

Distributed Target Tracking in Sensor Networks by Consistency Algorithm and Semantic Moving Computing of Internet of Things

“…In this scheme, the controller could perform its control plane activities without the high consumption tasks required to maintain consistency. The experimental results showed that this scheme could effectively reduce costs and improve the actual benefits, especially in low controller overhead [14]. Hu and Liu reported that the Raft consistency algorithm was one of the typical consistency algorithms in distributed systems to manage the consistency of log replication.…”

NFV-COIN: Unleashing The Power of In-Network Computing with Virtualization Technologies

“…As early as 2015 (Turchetti and Duarte, 2015), an NFV-COIN service was implemented based on the classic failure detectors of distributed systems; that work was later expanded (Turchetti and Duarte Jr, 2017). Consensus was another distributed service implemented with NFV-COIN (Venâncio et al, 2021), used to maintain the consistency of a group of SDN (Software-Defined Networks) controllers. In yet another effort, the network was augmented with the ability to natively offer reliable and ordered broadcast services (Venâncio et al, 2019).…”

“…Existing solutions employ the controllers themselves to perform the synchronization tasks, or alternatively synchronize the data plane. In (Venâncio et al, 2021) the VNF-Consensus service is proposed to implement the Paxos consensus algorithm and to maintain the consistency of a distributed control plane that consists of multiple SDN controllers. VNF-Consensus does not require any modification of the data plane or the SDN protocol (in this case, again OpenFlow).…”

Uma Avaliação sobre a Tolerância a Falhas no Plano de Dados em Controladores SDN

“…Considerando funcionalidades para tolerância a falhas em redes SDN,é possível observar diversos outros trabalhos que incluem a sincronização consistente no plano de controle distribuído. Estas funcionalidades se traduzem em diferentes algoritmos, tais como: Paxos [Ho et al 2016, Venâncio et al 2018, Replicação de Máquina de Estados [Canini et al 2015, Mahajan et al 2016, Zookeeper [Koponen et al 2010], Raft [Medved et al 2014], entre outros algoritmos frequentemente empregados no contexto de tolerância a falhas em sistemas distribuídos. Também são encontradas soluções que procuram garantir a execução consistente do plano de dados.…”

“…Em uma rede SDN o controlador executa um papel fundamental. Por este motivo, pode-se observar diversos esforços concentrados no controlador no sentido de avaliar seu desempenho [Zulu et al 2018], torná-lo distribuído [Kohler et al 2018], escalável [Bianco et al 2017, Karakus andDurresi 2017], confiável [Curic et al 2018, Venâncio et al 2018, seguro e tolerante a falhas [Gonzalez et al 2016]. Estes atributos foram ou estão sendo implementados nos diversos controladores disponíveis para uso.…”