A Fault-Tolerant and Consistent SDN Controller

Abstract

Abstract-Software-Defined Networking (SDN) is a new paradigm that promises to enhance network flexibility and innovation. However, operators need to thoroughly assess its advantages and threats before they can implement it. Robustness and fault tolerance are among the main criteria to be considered in such assessment. The currently available SDN controllers offer different fault tolerance mechanisms, but there are still many open issues, especially regarding the trade-off between consistency and performance in a fault-tolerant SDN platform. In this paper, we describe existing fault-tolerant SDN controller solutions, and propose a mechanism to design a consistent and fault-tolerant Master-Slave SDN controller that is able to balance consistency and performance. The main objective of this paper is to bring the performance of an SDN Master-Slave controller as close as possible to the one offered by a single controller. This is obtained by introducing a simple replication scheme, combined with a consistency check and a correction mechanism, that influence the performance only during the few intervals when it is needed, instead of being active during the entire operation time.

Dependability of the NFV Orchestrator: State of the Art and Research Challenges

“…The NFVO should take a central role in solving this issue. Finally, having a consistent distributed system state image may be technically feasible, but will come with a cost of reduced performance due to the extra time needed for synchronisation [71]. Therefore, the selected solutions have to be planned according to the performance needed and the implied speed of the consistency-guard mechanisms.…”

“…The basic SDN architecture depicts the controller as a potential single point of failure [71]. Therefore, control plane must be fault-tolerant.…”

“…Based on the general considerations used in the design of distributed systems [72]- [74], and more specifically in NFV systems [6], [16], [28], we want to increase the awareness of the importance of designing a dependable NFVO, by analysing those general principles and mapping them to specific NFVO scenarios, which is still unexplored. Avoid Single Point-of-Failure [6], [15], [16], [28], [72], [73] [74] Stateless vs Stateful [71], [75], [76], [77], [78] Consistency vs Performance [52], [71], [79], [80] Distributed-Load vs Master/Slave [81], [82], [83], [84], [85] Failure-Independent Domains [6], [28], [72], [73], [74] Monitoring and Failure Detection in Controller and Orchestrator Systems [15], [36], [43], [44], [45], [54], [55], [75] could cause overall operation to fail. The same principle should be applied to the NFVO, and basically implies that the NFVO cannot be implemented as an individual element, but it needs to be deployed in such a robust way that a failure does not produce the unavailability of the orchestration functionalities.…”

“…The dependability of this kind of stateful subsystems/modules needs the implementation of reliable and distributed storage systems and its respective synchronisation mechanisms in addition to the redundant instances and fail-over mechanisms. In the literature there are several works that attempt to designs such mechanisms [71], [75], [76], [77], and [78]. However, as mentioned in Section V-B, this is still an open challenge.…”

Orchestration and Control in Software‐Defined 5G Networks: Research Challenges

“…Through the years, many of those tests have been successful, but each case must be tested separately, based on the specific technical characteristics and requirements. Performance issues need to be assessed at both the control plane [71] and the data plane, where, for instance, the need to meet the performance requirements has promoted the introduction of acceleration modules, such as DPDK (Data Plane Development Kit) [72,73]. However, challenges such as increased complexity, the respective VNF validation, and the live migration implementation when using DPDK still need to be investigated.…”