Kumori: Steering Cloud traffic at IXPs to improve resiliency

Antoine Fressancourt , Cristel Pelsser and Maurice Gagnaire

Featured image for Kumori: Steering Cloud traffic at IXPs to improve resiliency
Download PDF Publisher Link

Abstract

After a few years of infancy, Cloud services have now gained enough maturity to be used to deliver an increasing number of critical services. To ensure the capacity of those services to survive failure events, major Cloud Services Providers (CSPs) deploy their platform in distant datacenters. The framework used to interconnect those datacenters is most of the time over-provisioned and costly to manage. In this paper, we present “Kumori”, a SDN-based overlay architecture designed to give CSPs back control on their inter-datacenter connectivity. Using the iPlane dataset, we compare our architecture with the Resilient Overlay Network (RON), considered as a seminal project on Internet resiliency for the last ten years. Our results show that, depending on the CSP's size and connectivity strategy, our architecture either gives significantly shorter paths than RON in terms of latency or provides a similar service using a smaller overlay in terms of number of overlay nodes.

Publication Details

Publication Type
Conference Paper
Publication Date
March 2016
Published In
2016 12th International Conference on the Design of Reliable Communication Networks (DRCN)
Pages
138--144
Publisher
IEEE
Location
Paris, France
Digital Object Identifier (DOI)
10.1109/DRCN.2016.7470848

Suggested citation

Antoine Fressancourt, Cristel Pelsser, and Maurice Gagnaire. 2016. Kumori: Steering Cloud traffic at IXPs to improve resiliency. In 2016 12th International Conference on the Design of Reliable Communication Networks (DRCN). IEEE, Paris, France, 138–144. https://doi.org/10.1109/DRCN.2016.7470848

BibTeX Citation

@inproceedings{Fressancourt2016,
	title        = {Kumori: Steering Cloud traffic at IXPs to improve resiliency},
	author       = {Antoine Fressancourt and Cristel Pelsser and Maurice Gagnaire},
	year         = 2016,
	month        = mar,
	journal      = {2016 12th International Conference on the Design of Reliable Communication Networks (DRCN)},
	booktitle    = {12th International Conference on the Design of Reliable Communication Networks, {DRCN} 2016},
	publisher    = {IEEE},
	address      = {Paris, France},
	pages        = {138--144},
	doi          = {10.1109/DRCN.2016.7470848},
	isbn         = {978-1-4673-8495-7},
	editor       = {Prosper Chemouil and Achille Pattavina and {\'{E}}ric Gourdin and Stefano Secci},
	abstract     = {After a few years of infancy, Cloud services have now gained enough maturity to be used to deliver an increasing number of critical services. To ensure the capacity of those services to survive failure events, major Cloud Services Providers (CSPs) deploy their platform in distant datacenters. The framework used to interconnect those datacenters is most of the time over-provisioned and costly to manage. In this paper, we present “Kumori”, a SDN-based overlay architecture designed to give CSPs back control on their inter-datacenter connectivity. Using the iPlane dataset, we compare our architecture with the Resilient Overlay Network (RON), considered as a seminal project on Internet resiliency for the last ten years. Our results show that, depending on the CSP's size and connectivity strategy, our architecture either gives significantly shorter paths than RON in terms of latency or provides a similar service using a smaller overlay in terms of number of overlay nodes.},
	bibsource    = {dblp computer science bibliography, https://dblp.org},
	biburl       = {https://dblp.org/rec/conf/drcn/FressancourtPG16.bib},
	eventdate    = {15-17 March 2016},
	eventtitleaddon = {Paris, France},
	file         = {:Fressancourt2016 - Kumori_ Steering Cloud Traffic at IXPs to Improve Resiliency.pdf:PDF},
	groups       = {International Conferences},
	keywords     = {Computer architecture, Peer-to-peer computing, Cloud computing, Routing, Overlay networks, SDN, Overlay, Resiliency, Performance evaluation},
	award        = {Best Paper Award}
}

Related publications