On the efficacy of fine-grained traffic splitting protocols in data center networks

Authors:
Advait Abhay Dixit;Pawan Prakash;Ramana Rao Kompella;Charlie Hu
Affiliations:
Purdue University, West Lafayette, IN, USA;Purdue University, West Lafayette, IN, USA;Purdue University, West Lafayette, IN, USA;Purdue University, West Lafayette, IN, USA
Venue:
Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer Systems
Year:
2012

Citing 4
Cited 0

A scalable, commodity data center network architecture

Proceedings of the ACM SIGCOMM 2008 conference on Data communication
VL2: a scalable and flexible data center network

Proceedings of the ACM SIGCOMM 2009 conference on Data communication
Hedera: dynamic flow scheduling for data center networks

NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Data center networking with multipath TCP

Hotnets-IX Proceedings of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Current multipath routing techniques split traffic at a per-flow level because, according to conventional wisdom, forwarding packets of a TCP flow along different paths leads to packet reordering which is detrimental to TCP. In this paper, we revisit this "myth" in the context of cloud data center networks which have regular topologies such as multi-rooted trees. We argue that due to the symmetry in the multiple equal-cost paths in such networks, simply spraying packets of a given flow among all equal-cost paths, leads to balanced queues across multiple paths, and consequently little packet reordering. Using a testbed comprising of NetFPGA switches, we show how cloud applications benefit from better network utilization in data centers.