On the performance of SDN controllers: A reality check

Zhao, Yimeng; Iannone, Luigi; Riguidel, Michel

doi:10.1109/nfv-sdn.2015.7387410

Cited by 64 publications

(46 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We compared the latency of the single thread ONOS and OpenDaylight in our study with prior work [99]. Table 4.13 shows the average flow setup latency of ONOS Blackbird release in the previous study, and compares it with Goldeneye release in our study.…”

Section: Thread Scalability Resultsmentioning

confidence: 99%

“…OpenDaylight latency is about the same, but ONOS latency has improved by 50%. We also compared the flow setup latency of ONOS and OpenDaylight in our study with the flow setup latency of some other controllers studied in previous work [99]. Each controller used only one thread, and the number of connected switches is one.…”

Section: Latency Resultsmentioning

confidence: 99%

“…We compared the throughput of the single thread ONOS in our study with prior work [99]. Table 4.13 compares the average throughput of two different releases of ONOS with one connected switch.…”

Section: Thread Scalability Resultsmentioning

confidence: 99%

“…We employed a similar benchmarking methodology to prior studies [80] [83] [85] [90] [99] to ensure the accuracy of our results. Our methodology studies performance and thread scalability.…”

Section: Methodology and Metricsmentioning

confidence: 99%

See 3 more Smart Citations

Experimental evaluation of two OpenFlow controllers

Darianian¹,

Williamson²,

Haque³

2017

2017 IEEE 25th International Conference on Network Protocols (ICNP)

View full text Add to dashboard Cite

Section: Thread Scalability Resultsmentioning

confidence: 99%

Section: Latency Resultsmentioning

confidence: 99%

Section: Thread Scalability Resultsmentioning

confidence: 99%

“…We employed a similar benchmarking methodology to prior studies [80] [83] [85] [90] [99] to ensure the accuracy of our results. Our methodology studies performance and thread scalability.…”

Section: Methodology and Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Experimental evaluation of two OpenFlow controllers

Darianian¹,

Williamson²,

Haque³

2017

2017 IEEE 25th International Conference on Network Protocols (ICNP)

View full text Add to dashboard Cite

“…Esses trabalhos geralmente comparam vários controladores de código aberto, apresentando uma análise quantitativa de rendimento e tempo de resposta. Os cenários quase sempre compreendem a variação do número de switches e threads com o propósito de avaliar a escalabilidade do controlador como em (TOOTOONCHIAN et al, 2012), (SHALIMOV et al, 2013), (ERICKSON, 2013), (ZHAO et al, 2015) (SALMAN et al, 2016). Outras investigações tiveram foco em ferramentas de benchmark, como o trabalho desenvolvido por (JARSCHEL et al, 2012), que propôs uma ferramenta de benchmark flexível de controladores OpenFlow capaz de criar switches virtuais customizáveis.…”

Section: Trabalhos Relacionadosunclassified

Avaliação de desempenho de um controlador SDN implementado como uma VNF

Ramos¹

2017

Anais Do Workshop Pré-Ietf (WPIETF)

View full text Add to dashboard Cite

No presente trabalho, realizamos experimentos com um controlador SDN implementado como uma função de rede virtual nos hypervisores de código aberto KVM e XEN e comparamos os parâmetros de desempenho mais críticos em relação a um cenário nativo com o propósito de mensurar a degradação de desempenho causada pela virtualização. Utilizamos Cbench para emular redes SDN e avaliar o desempenho e a latência do controlador Floodlight. Descobrimos que a virtualização do controlador no ambiente KVM resultou na degradação do processamento de fluxos em 29%, apresentou um aumento do tempo de resposta de 22% e utilizou bem menos o processador em relação ao ambiente Xen, que apesar de ter sobrecarregado a CPU em 25%, foi capaz de atingir o melhor desempenho, tempo de resposta e a menor utilização de memória RAM.

show abstract

DMoiSDN: A defensive mechanism of object integrity for SDN

Alsalamh,

Al‐Mutairi,

Humayed

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummarySoftware‐defined network (SDN) technology is widely used for computer networks, especially in enterprise data centers and virtualized networking. However, SDN networks encounter severe challenges to security. One such challenge comes from third‐party applications that contain malicious logic and security vulnerabilities, resulting in controller integrity attacks. In this paper, we propose a defensive mechanism of object integrity for SDN (DMoiSDN) to mitigate the issue known as Cross‐App Poisoning (CAP). Our results contribute to increasing the integrity level of the controller's resources by conducting a potential risk analysis, which showed a decrease of 57% in the risk factor for potential attacks. We further examined the results of comparing DMoiSDN's performance with related work that uses information flow control (IFC) policies. The best results among the three conducted scenarios were as follows: we found that decreased latency in our system ranged from 12% to 90%, with an average of 59%, when encountering an increase in requests. It ranged from 78% to 49%, with an average of 63%, when receiving a variable number of total permissions for each application. DMoiSDN is expected to show a perceptible but reasonable latency and, to some extent, be able to avoid a critical impact on performance.

show abstract

On the performance of SDN controllers: A reality check

Cited by 64 publications

References 8 publications

Experimental evaluation of two OpenFlow controllers

Experimental evaluation of two OpenFlow controllers

Avaliação de desempenho de um controlador SDN implementado como uma VNF

DMoiSDN: A defensive mechanism of object integrity for SDN

Contact Info

Product

Resources

About