Experimentation Environments for Data Center Routing Protocols: A Comprehensive Review

Alberro, Leonardo; Castro, Alberto; Grampín, Eduardo

doi:10.3390/fi14010029

Cited by 7 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a previous work [3], we experimented with data center routing protocols in emulated environments such as Kathara [4,5], Megalos [6], CORE [7] or Mininet [8], complementing the work presented in [9], where the Sibyl framework is used for evaluating implementation of routing protocols in fat-trees, including the Border Gateway Protocol (BGP) in the data center [10], Openfabric (IS-IS with flooding reduction) [11], and Routing in Fat Trees (RIFT) [12,13]. This framework presents wall-clock independent metrics, which permits us to normalize the results disregarding the underlying execution environment.…”

Section: Introductionmentioning

confidence: 90%

Experimenting with Routing Protocols in the Data Center: An ns-3 Simulation Approach

et al. 2022

Self Cite

View full text Add to dashboard Cite

Massive scale data centers (MSDC) have become a key component of current content-centric Internet architecture. With scales of up to hundreds of thousands servers, conveying traffic inside these infrastructures requires much greater connectivity resources than traditional broadband Internet transit networks. MSDCs use Fat-Tree type topologies, which ensure multipath connectivity and constant bisection bandwidth between servers. To properly use the potential advantages of these topologies, specific routing protocols are needed, with multipath support and low control messaging load. These infrastructures are enormously expensive, and therefore it is not possible to use them to experiment with new protocols; that is why scalable and realistic emulation/simulation environments are needed. Based on previous experiences, in this paper we present extensions to the ns-3 network simulator that allow executing the Free Range Routing (FRR) protocol suite, which support some of the specific MSDC routing protocols. Focused on the Border Gateway Protocol (BGP), we run a comprehensive set of control plane experiments over Fat-Tree topologies, achieving competitive scalability running on a single-host environment, which demonstrates that the modified ns-3 simulator can be effectively used for experimenting in the MSDC. Moreover, the validation was complemented with a theoretical analysis of BGP behavior over selected scenarios. The whole project is available to the community and fully reproducible.

show abstract

Section: Introductionmentioning

confidence: 90%

Experimenting with Routing Protocols in the Data Center: An ns-3 Simulation Approach

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Regarding the central tendency measurements, (8) exposes the average number of links among nodes in Leaf & Spine with 8 leaves and 2 spines:…”

Section: Leaf and Spine (Ls) With 8 Leaves And 2 Spinesmentioning

confidence: 99%

“…However, the implementation of the former is more complex as the forwarding process requires further resources because each host has more than one network, whilst the latter only have connection per host [8]. There are different papers in the literature within this field devoted to compare features of different network architectures in data centers.…”

Section: Introductionmentioning

confidence: 99%

Study on Data Center Network Topologies for Monitoring Data using Edge/Fog Computing

Roig,

Alcaraz,

Gılly

et al. 2024

Politeknik Dergisi

View full text Add to dashboard Cite

The election of an appropriate data center network topology is key when dealing with surveillance and monitoring processes, such as those devoted to obtaining relevant data for sensor data fusion in any type of remote computing environment so as to perform fault diagnosis and prevention. In this paper, some of the most commonly used topologies to interconnect nodes within a data center bound to edge/fog computing, representing either switch-centric ones or server-centric ones, are reviewed and analyzed from a statistical point of view in order to measure their performance, resulting in server-centric ones doing it better.

show abstract

“…loud computing is going through evolutions that make Internet architecture undergo notable restructuring. The restructuring will improve users' requests on the network and bring the network closer to its end users (Alberro, et al,2022). Consequently, our study examines the property of the Transmission Control Protocol (TCP) of the Internet architecture in order to propose a queueing model that supports its nonmemoryless property.…”

Section: Introductionmentioning

confidence: 99%

An Exact Method for a Class of Self-Similar M/Ga/1/K Queueing System of Internet Stream

Popoola¹,

Popoola²,

Olaniran³

2022

FUOYEJET

View full text Add to dashboard Cite

In Internet stream monitoring, computing the expected parameters and distributions for the stream process under self-similarity and long-range dependency requires appropriate and exact methods queueing analyses to obtain performance of the Internet. Our method avoids fitting a non-heavy tailed distribution to Internet stream data by specifically fitting Gamma distribution to its service time process, which enhances the features of correlated events that explain self-similarity and long-range dependency compared to the classical memoryless assumptions of standard Poisson arrival and Exponential service. We propose the specific expectations of the parameters for a class of M/Ga/1/k queueing system (‘M’ represents a Markovian arrival process that follows Poisson distribution, ‘Ga’ represents a Gamma distribution service process, ‘1’ represents a single server, ‘k’ represents the buffer size) in an exact closed-form derivations using the Pollaczek Khintchine formulae alongside the Laplace transform to obtain the performance of queue. The adequacy of the proposed model was confirmed using simulated data of Internet traffic. Keywords- Gamma distribution, Internet stream, M/Ga/1/K model, Self-similarity, heavy-tail distribution

show abstract

Experimentation Environments for Data Center Routing Protocols: A Comprehensive Review

Cited by 7 publications

References 26 publications

Experimenting with Routing Protocols in the Data Center: An ns-3 Simulation Approach

Experimenting with Routing Protocols in the Data Center: An ns-3 Simulation Approach

Study on Data Center Network Topologies for Monitoring Data using Edge/Fog Computing

An Exact Method for a Class of Self-Similar M/Ga/1/K Queueing System of Internet Stream

Contact Info

Product

Resources

About