This paper proposes a novel latency monitoring method for software-defined networks (SDNs) called LLDP-looping, which uses LLDP packets injected repeatedly in the control plane to determine latency between switches. It provides accurate and continuous latency monitoring without involving any dedicated network infrastructure, while avoiding potential measurement failures that can occur in the existing method of timestamping data packets as probe packets, and overcoming the major factors that decrease the measurement accuracy in many existing methods for monitoring SDN latency. We formulate an optimization problem to enable LLDP-looping to minimize its workload on both control and data planes, and propose a novel greedy algorithm to solve this problem efficiently. Evaluations over the tree-based network topologies demonstrate that LLDP-looping can effectively minimize its overhead, and provide measurement accuracy higher than 90% against the round trip time measured by Ping over an SDN with link latency as small as 0.05 ms. The advantages of LLDP-looping can be realized with minimal modifications to SDN switches and this technique can be generalized to other networking scenarios.
1 December 2020 in Journal of Parallel and Distributed Computing
Cloud‐based virtual networking environments are required to provide fine‐grained quality of service (QoS) control without sacrificing scalability. However, no single approach can currently achieve these two goals simultaneously. FlowVisor is a building block to virtualise networks with fine‐grained QoS support; however, scalability issues caused by the OpenFlow protocol and the centralised control model are a major concern. This study introduces a distributed FlowVisor (DFVisor) platform to address these scalability issues. The proposed DFVisor uses a layered overlay mechanism to improve network addressing space and switch capacity. DFVisor uses a distributed synchronised two‐level database system with a synchronisation mechanism to enable the centralised control functions in the current FlowVisor platform in distributed control modules within the virtual network controllers. Therefore it removes a single point of failure in the network and reduces the flow setup latency without sacrificing the centralised network configuration and management capabilities. More importantly, the proposed DFVisor platform enables an advanced push‐based flow setup and statistics collection mechanism to address scalability issues caused by the current pull‐based flow setup and statistics collection method. A DFVisor prototype and an evaluation of this distributed synchronised two‐level database are presented, and key issues for future research are discussed.
This paper proposes flow entry timeout hopping strategies to defend against flow table Low-rate Denial of Service (LDoS) attacks in Software-Defined Networks (SDNs). By introducing uncertainty in the flow entry timeout, SDNs can avoid their flow entry timeout from being synchronized by attackers in the LDoS attack cycle, thereby effectively preventing their flow table from overflowing. Three different strategies are introduced, including a random hopping strategy, a strategy that hops the flow entry timeout based on the packet_in rate, and a strategy that hops the flow entry timeout based on the feedback of the packet_in rate. The evaluations are conducted on SDNs emulated by Mininet. The results show that all three hopping strategies significantly reduce flow table occupancy during attacks while consuming reasonable controller CPU resources, they effectively prevent flow table overflows and improve system stability.
1 August 2025 in Digital Communications and Networks