Data Center Network Virtualization: A Survey

Bari, Md. Faizul; Boutaba, Raouf; Esteves, Rafael Pereira; Granville, Lisandro Zambenedetti; Podlesny, Maxim; Rabbani, Golam; Zhang, Qi; Zhani, Mohamed Faten

doi:10.1109/surv.2012.090512.00043

Cited by 576 publications

(253 citation statements)

References 38 publications

Supporting

Mentioning

245

Contrasting

Unclassified

Order By: Relevance

“…It would appear that there might be scope for a better use of the actual host topology in virtualization tools such as SecondNet and Oktopus. This remark is also made in [5] where it is noted that the network utilization of SecondNet varies according to the underlying host topology; indeed, the authors of [5] remark upon the current lack of a consideration of embeddings on DCN design and mention this topic explicitly as a future research direction.…”

Section: Oktopusmentioning

confidence: 91%

“…We look again at aspects of symmetry in DCNs that aid virtualization but we do this in tandem with a new methodology to enable virtualization in server-centric DCNs. In so far as we are aware, this is the first real attempt to, first, consider virtualization in (non-tree-based) server-centric DCNs, and, second, explicitly use the underlying DCN topology when embedding virtual DCNs (so addressing a specific direction for future research as proposed in [5]). However, as we explain later, our methodology is not as topology specific as one might think as it exploits properties of symmetry inherent within many server-centric DCNs, and also highlights properties we would wish of new DCNs in order that virtualization is better supported.…”

Section: A New Virtualization Methodologymentioning

confidence: 99%

“…The reader is referred to a plethora of review articles for a general background as regards datacenters and issues only touched upon or not mentioned here (e.g. [1,[5][6][7]34,41,51,53,59,63,64]). …”

Section: Datacenter Network Designmentioning

confidence: 99%

“…-We outline the first generic virtualization methodology for application within server-centric DCNs (the omission of such a consideration was noted in [5] and suggested as a direction for further research; in so far as we are aware, our methodology is the first to be proposed). -We show that support for datacenter usage and intrinsic communication patterns is closely correlated with certain topological aspects of DCNs that we identify as symmetry.…”

Section: Our Contributionsmentioning

confidence: 99%

“…The bandwidth of this physical path of links needs to be shared between the two virtual datacenters; moreover, the actual physical bandwidth needs to be enough to accommodate the required bandwidths for the two virtual links (of course, the path links might also be currently used by other virtual datacenter embeddings). Implementing full-blown virtualization is incredibly difficult to achieve and is a vibrant area of research, with embedding just one aspect of virtualization (albeit a significant one); there are many other (more practical) aspects to consider too such as scalability, fault tolerance, security, performance isolation, and monitoring (the reader is referred to recent surveys [5,56,60] for detailed accounts of the current state of the art as regards datacenter virtualization).…”

Section: Virtualizationmentioning

confidence: 99%

See 4 more Smart Citations

The influence of datacenter usage on symmetry in datacenter network design

Stewart

Erickson

2017

J Supercomput

View full text Add to dashboard Cite

We undertake the first formal analysis of the role of symmetry, interpreted broadly, in the design of server-centric datacenter networks. Although symmetry has been mentioned by other researchers, we explicitly relate it to various specific, structural, graph-theoretic properties of datacenter networks. Our analysis of symmetry is motivated by the need to ascertain the usefulness of a datacenter network as regards the support of network virtualization and prevalent communication patterns in multitenanted clouds. We argue that a number of structural concepts relating to symmetry from general interconnection networks, such as recursive-definability, the existence and dynamic construction of spanning trees, pancyclicity, and variations in Hamiltonicity, are appropriate topological metrics to use in this regard. In relation to symmetry, we highlight the relevance of algebraic properties and algebraic constructions within datacenter network design. Built upon our analysis of symmetry, we outline the first technique to embed guest datacenter networks in a host datacenter network that is specifically oriented towards server-centric datacenter networks. In short, we provide the graph-theoretic foundations for the design of server-centric datacenter networks so as to support network virtualization and communication patterns in cloud computing.

show abstract

Section: Oktopusmentioning

confidence: 91%

Section: A New Virtualization Methodologymentioning

confidence: 99%

Section: Datacenter Network Designmentioning

confidence: 99%

Section: Our Contributionsmentioning

confidence: 99%

Section: Virtualizationmentioning

confidence: 99%

See 3 more Smart Citations

The influence of datacenter usage on symmetry in datacenter network design

Stewart

Erickson

2017

J Supercomput

View full text Add to dashboard Cite

show abstract

Network Virtualization and Network Hypervisors

Blenk

Kellerer

2022

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Modern communication networks have to deal with dynamically changing requirements of emerging applications. In order to support such heterogeneous requirements on the same substrate network, concepts for network abstraction and network programmability are essential to offer applications that individually tailored views on the network. Network virtualization is the basic concept to provide an abstraction of a substrate network that can be offered to a network application provider. Here, a network hypervisor realizes the level of indirection between substrate network and virtual network(s). Additional programmability can be offered through the concept of Software‐Defined Networking (SDN). SDN provides a network abstraction based on a centralized view on a network to program individual features such as forwarding rules inside a network. This chapter gives an overview of the networking concept of network virtualization as the example of the virtualization of SDN‐based networks. The combination of network virtualization and Software‐Defined Networking provides full network abstraction and adaptability. We detail the basic features of a network hypervisor, abstraction and isolation, and provide the example of FlowVisor as a prominent network hypervisor example in the state of the art.

show abstract