Title
OpenSample: A Low-Latency, Sampling-Based Measurement Platform for Commodity SDN
Abstract
In this paper we propose, implement and evaluate Open Sample: a low-latency, sampling-based network measurement platform targeted at building faster control loops for software-defined networks. Open Sample leverages sFlow packet sampling to provide near-real-time measurements of both net-work load and individual flows. While Open Sample is useful in any context, it is particularly useful in an SDN environment where a network controller can quickly take action based on the data it provides. Using sampling for network monitoring allows Open Sample to have a 100 millisecond control loop rather than the 1-5 second control loop of prior polling-based approaches. We implement Open Sample in the Floodlight Open Flow controller and evaluate it both in simulation and on a test bed comprised of commodity switches. When used to inform traffic engineering, Open Sample provides up to a 150% throughput improvement over both static equal-cost multi-path routing and a polling-based solution with a one second control loop.
Year
DOI
Venue
2014
10.1109/ICDCS.2014.31
ICDCS
Keywords
Field
DocType
sflow packet sampling,commodity switches,static equal-cost multipath routing,network load,software defined networking,floodlight open flow controller,low-latency sampling-based network measurement platform,data center,throughput improvement,polling-based approaches,network monitoring,measurement,computer networks,packet sampling,software-defined networks,program control structures,commodity sdn,near-real-time measurements,telecommunication traffic,traffic engineering,telecommunication network routing,sdn environment,network controller,sflow,sflow, packet sampling, software defined networking, data center, traffic engineering, measurement,opensample,control loops
sFlow,Control theory,Computer science,Polling,Computer network,Real-time computing,Sampling (statistics),Throughput,Network monitoring,Software-defined networking,Network traffic control,Distributed computing
Conference
ISSN
Citations 
PageRank 
1063-6927
39
1.37
References 
Authors
18
5
Name
Order
Citations
PageRank
Junho Suh1453.30
Ted Taekyoung Kwon258435.90
Colin Dixon31375.39
Wes Felter459852.82
John B. Carter51785162.82