Buffer Size Evaluation of OpenFlow Systems in Software-Defined Networks

Summary Burst traffic is a common traffic pattern in modern IP networks, and it may lead to the unfairness problem and seriously degrade the performance of switches and routers. From the perspective of switching mechanism, the majority of commercial switches adopt the on‐chip shared‐memory switching architecture, and high‐speed packet buffer with efficient queue management is required to deal with the unfairness and congestion problem. In this paper, the performance of a shared‐private buffer management scheme is analyzed in detail. In the proposed scheme, the total memory space is split into shared area and private area. Each output port has a private memory area that cannot be used by other ports. The shared area is completely shared among all output ports. A theoretical queuing model of the proposed scheme is formulated, and closed‐form formulas for multiple performance parameters are derived. Through the numerical studies, we demonstrate that a nearly optimal buffer partition policy can be obtained by setting an equally small amount of private area for each queue. This work is validated by simulations as well as hardware experiments. Software simulations show that the proposed scheme performs better than existing methods, and packet dropping caused by burst traffic can be significantly reduced. Besides, a prototype of the buffer management module is implemented and evaluated in field programmable gate array platform. The evaluation shows that the proposed scheme can ensure the efficiency and fairness while keeping a high throughput in real workload.

Section: Performance Analysis Of the Proposalmentioning

confidence: 93%

Section: Performance Analysis Of the Proposalmentioning

confidence: 99%

Section: Performance Analysis Of the Proposalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Performance analysis and hardware implementation of a nearly optimal buffer management scheme for high‐performance shared‐memory switches

Liu

Pan

et al. 2020

“…Although the shared buffer model simplifies the analysis, it is not realistic as there is an implicit assumption that the traffic forwarded to the controller is sent back to the switch and is threated in the same way as the new packets entering the switch. If the switch has finite buffers, 25 then there are concerns over preserving the Markovian property of the individual queues, which is necessary for product-form analysis. 26 The stationary behavior of this type of network cannot be modeled using product form analysis; however, the stationary behavior in this case can be modeled by using global-balance equations.…”

Section: Buffer Modeling For Of Switchmentioning

confidence: 99%

Performance analysis of handover delay and buffer capacity in mobile OpenFlow‐based networks

Panev¹,

Latkoski

2020

Summary Software‐defined networking (SDN) is a network concept that brings significant benefits for the mobile cellular operators. In an SDN‐based core network, the average service time of an OpenFlow switch is highly influenced by the total capacity and type of the output buffer, which is used for temporary storage of the incoming packets. In this work, the main goal is to model the handover delay due to the exchange of OpenFlow‐related messages in mobile SDN networks. The handover delay is defined as the overall delay experienced by the mobile node within the handover procedure, when reestablishing an ongoing session from the switch in the source eNodeB to the switch in the destination eNodeB. We propose a new analytical model, and we compare two systems with different SDN switch designs that model a continuous time Markov process by using quasi‐birth–death processes: (1) single shared buffer without priority (model SFB), used for all output ports for both control and user traffic, and (2) two isolated buffers with priority (model priority finite buffering [PFB]), one for control and the other for user plane traffic, where the control traffic is always prioritized. The two proposed systems are compared in terms of total handover delay and minimal buffer capacity needed to satisfy a certain packet error ratio imposed by the link. The mathematical modeling is verified via extensive simulations. In terms of handover delay, the results show that the model PFB outperforms the model SFB, especially for networks with high number of users and high probability of packet‐in messages. As for the buffer dimensioning analysis, for lower arrival rates, low number of users, and low probability of packet‐in messages, the model SFB has the advantage of requiring a smaller buffer size.

The intelligent multi‐domain service function chain deployment: Architecture, challenges and solutions

Zhang

Wang

Dong

et al. 2020

Network function virtualization (NFV) technology achieves flexible service deployment by replacing the middleboxes with virtual network functions (VNFs). In NFV, a set of VNFs are chained in a given order, called service function chain (SFC), and accordingly, data flow is steered to traverse all the VNFs in order to offer a service. With a large number of network devices and end users being connected into Internet, there is a growing demand for largescale multi-domain networks to dynamically deploy the SFC across multiple network domains, in order to support efficient service provisioning. To this end, in this paper, we first investigate the state of the art of multi-domain SFC deployment, and then propose an intelligent multi-domain SFC deployment (IMSD) architecture by leveraging software-defined networking (SDN), NFV, and deep learning technologies. Furthermore, we discuss the potential challenges to realize the IMSD and provide some promising solutions. K E Y W O R D S deep learning, multi-domain networks, SDN, SFC deployment 1 | INTRODUCTION Recently, a great variety of middleboxes have been designed to efficiently provide various network services. 1 However, the service provisioning method is not flexible and leads to large capital expenditure (CAPEX) and operational expenditure (OPEX) since the middleboxes are heavily dependent on specific hardware devices. Fortunately, the emergence of network function virtualization (NFV) technology provides a promising solution to address the issues. NFV decouples network functions from hardware devices and implements them in software, called virtual network functions (VNFs). 2,3 Unlike the middleboxes, the VNFs can be flexibly deployed in the commercial-off-the-shelf devices. NFV