Abstract

Applications running in modern datacenters interact with the underlying network in complex ways, making administrators run multiple traffic management tasks to tune the system. However, today’s traffic management solutions are limited by an artificial division between the hosts and the network. While network devices only have knowledge of the network layer, the hosts can provide more visibility into how applications interact with the network. This paper proposes to extend the scope of traffic management to the end-host network stack. We present a software-defined networking platform for joint HOst-NEtwork (HONE) traffic management. HONE presents a uniform view of a diverse collection of measurement data, minimizes measurement overhead by performing lazy materialization of fine-grained statistics, and scales the analysis by processing data locally on the end hosts. HONE offers a simple and expressive programming framework for network and service administrators. We evaluate HONE by implementing several canonical traffic management applications, measuring its efficiency with micro-benchmarks, and demonstrating its scalability with larger experiments on Amazon EC2.

Original languageEnglish (US)
Pages (from-to)374-399
Number of pages26
JournalJournal of Network and Systems Management
Volume23
Issue number2
DOIs
StatePublished - Jan 1 2015

Fingerprint

Network layers
Visibility
Scalability
Software
Traffic management
Statistics
Experiments
Software defined networking
Benchmark
Networking
Amazon
Programming
Experiment

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications
  • Strategy and Management

Cite this

@article{6fd60c33d1fa4266867f0c2396293c62,
title = "HONE: Joint Host-Network Traffic Management in Software-Defined Networks",
abstract = "Applications running in modern datacenters interact with the underlying network in complex ways, making administrators run multiple traffic management tasks to tune the system. However, today’s traffic management solutions are limited by an artificial division between the hosts and the network. While network devices only have knowledge of the network layer, the hosts can provide more visibility into how applications interact with the network. This paper proposes to extend the scope of traffic management to the end-host network stack. We present a software-defined networking platform for joint HOst-NEtwork (HONE) traffic management. HONE presents a uniform view of a diverse collection of measurement data, minimizes measurement overhead by performing lazy materialization of fine-grained statistics, and scales the analysis by processing data locally on the end hosts. HONE offers a simple and expressive programming framework for network and service administrators. We evaluate HONE by implementing several canonical traffic management applications, measuring its efficiency with micro-benchmarks, and demonstrating its scalability with larger experiments on Amazon EC2.",
author = "Peng Sun and Minlan Yu and Freedman, {Michael Joseph} and Rexford, {Jennifer L.} and Walker, {David P.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1007/s10922-014-9321-9",
language = "English (US)",
volume = "23",
pages = "374--399",
journal = "Journal of Network and Systems Management",
issn = "1064-7570",
publisher = "Springer New York",
number = "2",

}

HONE : Joint Host-Network Traffic Management in Software-Defined Networks. / Sun, Peng; Yu, Minlan; Freedman, Michael Joseph; Rexford, Jennifer L.; Walker, David P.

In: Journal of Network and Systems Management, Vol. 23, No. 2, 01.01.2015, p. 374-399.

Research output: Contribution to journalArticle

TY - JOUR

T1 - HONE

T2 - Joint Host-Network Traffic Management in Software-Defined Networks

AU - Sun, Peng

AU - Yu, Minlan

AU - Freedman, Michael Joseph

AU - Rexford, Jennifer L.

AU - Walker, David P.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Applications running in modern datacenters interact with the underlying network in complex ways, making administrators run multiple traffic management tasks to tune the system. However, today’s traffic management solutions are limited by an artificial division between the hosts and the network. While network devices only have knowledge of the network layer, the hosts can provide more visibility into how applications interact with the network. This paper proposes to extend the scope of traffic management to the end-host network stack. We present a software-defined networking platform for joint HOst-NEtwork (HONE) traffic management. HONE presents a uniform view of a diverse collection of measurement data, minimizes measurement overhead by performing lazy materialization of fine-grained statistics, and scales the analysis by processing data locally on the end hosts. HONE offers a simple and expressive programming framework for network and service administrators. We evaluate HONE by implementing several canonical traffic management applications, measuring its efficiency with micro-benchmarks, and demonstrating its scalability with larger experiments on Amazon EC2.

AB - Applications running in modern datacenters interact with the underlying network in complex ways, making administrators run multiple traffic management tasks to tune the system. However, today’s traffic management solutions are limited by an artificial division between the hosts and the network. While network devices only have knowledge of the network layer, the hosts can provide more visibility into how applications interact with the network. This paper proposes to extend the scope of traffic management to the end-host network stack. We present a software-defined networking platform for joint HOst-NEtwork (HONE) traffic management. HONE presents a uniform view of a diverse collection of measurement data, minimizes measurement overhead by performing lazy materialization of fine-grained statistics, and scales the analysis by processing data locally on the end hosts. HONE offers a simple and expressive programming framework for network and service administrators. We evaluate HONE by implementing several canonical traffic management applications, measuring its efficiency with micro-benchmarks, and demonstrating its scalability with larger experiments on Amazon EC2.

UR - http://www.scopus.com/inward/record.url?scp=84924222201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924222201&partnerID=8YFLogxK

U2 - 10.1007/s10922-014-9321-9

DO - 10.1007/s10922-014-9321-9

M3 - Article

VL - 23

SP - 374

EP - 399

JO - Journal of Network and Systems Management

JF - Journal of Network and Systems Management

SN - 1064-7570

IS - 2

ER -