Blind, Adaptive and Robust Flow Segmentation in Datacenters

Abstract : —To optimize routing of flows in datacenters, SDN controllers receive a packet-in message whenever a new flow appears in the network. Unfortunately, flow arrival rates can peak to millions per second, impairing the ability of controllers to treat them on time. Flow scheduling copes with such sheer numbers by segmenting the traffic between elephant and mice flows and by treating elephant flows in priority, as they disrupt short lived TCP flows and create bottlenecks. We propose a learning algorithm called SOFIA and able to perform optimal online flow segmentation. Our solution, based on stochastic approximation techniques, is implemented at the switch level and updated by the controller, with minimal signaling over the control channel. SOFIA is blind, i.e., it is oblivious to the flow size distribution. It is also adaptive, since it can track traffic variations over time. We prove its convergence properties and its message complexity. Moreover, we specialize our solution to be robust to traffic classification errors. Extensive numerical experiments characterize the performance of our approach in vitro. Finally, results of the implementation in a real OpenFlow controller demonstrate the viability of SOFIA as a solution in production environments.
Type de document :
Communication dans un congrès
INFOCOM 2018 - IEEE International Conference on Computer Communications, Apr 2018, Honolulu, United States. 〈http://infocom2018.ieee-infocom.org/〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01666905
Contributeur : Damien Saucez <>
Soumis le : lundi 18 décembre 2017 - 19:26:06
Dernière modification le : lundi 22 janvier 2018 - 10:49:02

Identifiants

  • HAL Id : hal-01666905, version 1

Collections

Citation

Francesco De Pellegrini, Lorenzo Maggi, Antonio Massaro, Damien Saucez, Jeremie Leguay, et al.. Blind, Adaptive and Robust Flow Segmentation in Datacenters. INFOCOM 2018 - IEEE International Conference on Computer Communications, Apr 2018, Honolulu, United States. 〈http://infocom2018.ieee-infocom.org/〉. 〈hal-01666905〉

Partager

Métriques

Consultations de la notice

360