Using hardware classification to improve PC-based OpenFlow switching

Tanyingyong, Voravit; Hidell, Markus; Sjödin, Peter

doi:10.1109/hpsr.2011.5986029

Cited by 27 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…when using 5-8 CPU cores) due to the contention among logical processors. We have observed the same behavior in previous experiments [10]. For the performance of 1-4 CPU cores, our architecture maintains the average throughput improvement of roughly 32% compared to unmodified Open vSwitch.…”

Section: A Baseline Performancesupporting

confidence: 67%

“…We believe that the architecture we proposed in our previous works [10], [12] is an important step in this direction. We intend to extend it further to provide a basis for a multipurpose PCbased router, which we call a combined router/server.…”

Section: Architectural Designmentioning

confidence: 99%

“…This Intel chipset offers a hardware classification support called Flow Director filter, which can direct received packets, according to their flows, to queues for classification purposes. We describe the operation of the Flow Director filter in more detail in [10]. We use the Flow Director filter to classify received packets into two types; matched flows and unmatched flows.…”

Section: Prototype Implementationmentioning

confidence: 99%

“…To offload the CPU from packet processing, we introduce a fast path in the lookup process to bypass the software based forwarding. This is done by caching active flow table entries in the on-board NIC classification hardware, which functions as a lookup accelerator [10]. In general, commodity NICs have no capability to forward the packet completely by themselves.…”

Section: Architectural Designmentioning

confidence: 99%

“…The idea for this work comes as a spin-off from our previous work [10] that aims at improving lookup performance of PCbased OpenFlow [11] using NIC hardware classification to offload the CPU from the lookup processing task. The rest of this paper is organized as follows; Section II describes the architecture for multipurpose PC-based router and motivation behind it.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving performance in a combined router/server

Tanyingyong

Hidell

Sjödin

2012

2012 IEEE 13th International Conference on High Performance Switching and Routing

Self Cite

View full text Add to dashboard Cite

Abstract-A modern PC-based router can provide as competitive service as a specialized hardware router while offering more flexibility and possibility to extend beyond routing. We focus on a use case in which the PC-based router also functions as a server. In this paper, we propose a multi-core based architecture for a combined router/server that efficiently provides simultaneous packet forwarding and server processing. We improve the overall performance by creating a fast path for packet forwarding through caching flow entries in on-board classification hardware on the NIC. We propose a generic design based on multicore processors and multi-queue network interface cards. We describe a prototype implementation and present an experimental evaluation of this design. We also devise a strategy for how to efficiently map packet forwarding and application processing tasks onto the multi-core architecture.

show abstract

Section: A Baseline Performancesupporting

confidence: 67%

Section: Architectural Designmentioning

confidence: 99%

Section: Prototype Implementationmentioning

confidence: 99%

Section: Architectural Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving performance in a combined router/server

Tanyingyong

Hidell

Sjödin

2012

2012 IEEE 13th International Conference on High Performance Switching and Routing

Self Cite

View full text Add to dashboard Cite

show abstract

Resource management in radio access and IP-based core networks for IMT Advanced and Beyond

Song

Hidell

Abrahamsson³

et al. 2013

Sci. China Inf. Sci.

Self Cite

View full text Add to dashboard Cite

Optimal resource allocation for transmission diversity in multi-radio access networks: a coevolutionary genetic algorithm approach SCIENCE CHINA Information Sciences 57, 022310 (2014); Efficient resource allocation scheme for multi-service based on interference mitigation in LTE-Advanced networks SCIENCE CHINA Information Sciences 57, 082304 (2014); Optimal remote radio head selection for cloud radio access networks SCIENCE CHINA Information Sciences 59, 102315 (2016); Novel spectrum sensing and access in cognitive radio networks SCIENCE CHINA Information Sciences 61, 089302 (2018);. RESEARCH PAPER .

show abstract

A Survey on Data Plane Flexibility and Programmability in Software-Defined Networking

et al. 2019

View full text Add to dashboard Cite

Software-defined networking (SDN) attracts the attention of the research community in recent years, as evidenced by a large number of survey and review papers. The architecture of SDN clearly recognizes three planes: application, control, and data plane. The application plane executes network applications; control plane regulates the rules for the entire network based on the requests generated by network applications; and based on the set rules, the controller configures the switches in the data plane. The role of the switch in the data plane is to simply forward packets based on the instructions given by the controller. By analyzing SDN-related research papers, it is observed that research, from the very beginning, is insufficiently focused on the data plane. Therefore, this paper gives a comprehensive overview of the data plane survey with particular emphasis on the problem of programmability and flexibility. The first part of the survey is dedicated to the evaluation of actual data plane architectures through several definitions and aspects of data plane flexibility and programmability. Then, an overview of SDN-related research was presented with the aim of identifying key factors influencing the gradual deviation from the original data plane architectures given with ForCES and OpenFlow specifications, which we called the data plane evolution. By establishing a correlation between the treated problem and the problem-solving approaches, the limitations of ForCES and OpenFlow data plane architectures were identified. Based on identified limitations, a generalization of approaches to addressing the problem of data plane flexibility and programmability is made. By examining generalized approaches, open issues have been identified, establishing the grounds for future research directions proposal.

show abstract

Using hardware classification to improve PC-based OpenFlow switching

Cited by 27 publications

References 19 publications

Improving performance in a combined router/server

Improving performance in a combined router/server

Resource management in radio access and IP-based core networks for IMT Advanced and Beyond

A Survey on Data Plane Flexibility and Programmability in Software-Defined Networking

Contact Info

Product

Resources

About