Extending TCP for accelerating replication on cluster file systems over sdns

Sungheon Lim, Hyogon Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper explores the changes required of TCP to efficiently support cluster file systems such as Hadoop Distributed File System (HDFS) where the storage nodes are connected through a software defined networking (SDN). Traditional chain replications in these file systems incur large delay and cause inefficient network use. But SDN can cooperate with the cluster file systems to address the problems by pre-Arranging a distribution tree, which opens the possibility of parallel replication. Unfortunately, it cannot be realized without extending TCP, to accommodate the parallel transfer on the transport layer. This paper discusses how to extend TCP to make it possible, and demonstrates the feasibility by implementing a prototype in the Linux kernel. The prototype saves the data replication time by 25% while substantially reducing network use.

Original languageEnglish
Title of host publicationProceedings of the 2019 IEEE Conference on Network Softwarization
Subtitle of host publicationUnleashing the Power of Network Softwarization, NetSoft 2019
EditorsFilip De Turck, Flavio Esposito, Prosper Chemouil, Olivier Festor, Stefano Secci, Christian Jacquenet, Walter Cerroni
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages48-53
Number of pages6
ISBN (Electronic)9781538693766
DOIs
Publication statusPublished - 2019 Jun 1
Event5th IEEE Conference on Network Softwarization, NetSoft 2019 - Paris, France
Duration: 2019 Jun 242019 Jun 28

Publication series

NameProceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019

Conference

Conference5th IEEE Conference on Network Softwarization, NetSoft 2019
CountryFrance
CityParis
Period19/6/2419/6/28

Fingerprint

Software defined networking
Linux

Keywords

  • cluster file system
  • data replication
  • HDFS
  • network utilization
  • Software Defined Networking (SDN)
  • TCP extension

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications
  • Software

Cite this

Lim, S., & Kim, H. (2019). Extending TCP for accelerating replication on cluster file systems over sdns. In F. De Turck, F. Esposito, P. Chemouil, O. Festor, S. Secci, C. Jacquenet, & W. Cerroni (Eds.), Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019 (pp. 48-53). [8806672] (Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NETSOFT.2019.8806672

Extending TCP for accelerating replication on cluster file systems over sdns. / Lim, Sungheon; Kim, Hyogon.

Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019. ed. / Filip De Turck; Flavio Esposito; Prosper Chemouil; Olivier Festor; Stefano Secci; Christian Jacquenet; Walter Cerroni. Institute of Electrical and Electronics Engineers Inc., 2019. p. 48-53 8806672 (Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lim, S & Kim, H 2019, Extending TCP for accelerating replication on cluster file systems over sdns. in F De Turck, F Esposito, P Chemouil, O Festor, S Secci, C Jacquenet & W Cerroni (eds), Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019., 8806672, Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019, Institute of Electrical and Electronics Engineers Inc., pp. 48-53, 5th IEEE Conference on Network Softwarization, NetSoft 2019, Paris, France, 19/6/24. https://doi.org/10.1109/NETSOFT.2019.8806672
Lim S, Kim H. Extending TCP for accelerating replication on cluster file systems over sdns. In De Turck F, Esposito F, Chemouil P, Festor O, Secci S, Jacquenet C, Cerroni W, editors, Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 48-53. 8806672. (Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019). https://doi.org/10.1109/NETSOFT.2019.8806672
Lim, Sungheon ; Kim, Hyogon. / Extending TCP for accelerating replication on cluster file systems over sdns. Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019. editor / Filip De Turck ; Flavio Esposito ; Prosper Chemouil ; Olivier Festor ; Stefano Secci ; Christian Jacquenet ; Walter Cerroni. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 48-53 (Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019).
@inproceedings{73de1ad8b21a45f4a6611612a25eda94,
title = "Extending TCP for accelerating replication on cluster file systems over sdns",
abstract = "This paper explores the changes required of TCP to efficiently support cluster file systems such as Hadoop Distributed File System (HDFS) where the storage nodes are connected through a software defined networking (SDN). Traditional chain replications in these file systems incur large delay and cause inefficient network use. But SDN can cooperate with the cluster file systems to address the problems by pre-Arranging a distribution tree, which opens the possibility of parallel replication. Unfortunately, it cannot be realized without extending TCP, to accommodate the parallel transfer on the transport layer. This paper discusses how to extend TCP to make it possible, and demonstrates the feasibility by implementing a prototype in the Linux kernel. The prototype saves the data replication time by 25{\%} while substantially reducing network use.",
keywords = "cluster file system, data replication, HDFS, network utilization, Software Defined Networking (SDN), TCP extension",
author = "Sungheon Lim and Hyogon Kim",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/NETSOFT.2019.8806672",
language = "English",
series = "Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "48--53",
editor = "{De Turck}, Filip and Flavio Esposito and Prosper Chemouil and Olivier Festor and Stefano Secci and Christian Jacquenet and Walter Cerroni",
booktitle = "Proceedings of the 2019 IEEE Conference on Network Softwarization",

}

TY - GEN

T1 - Extending TCP for accelerating replication on cluster file systems over sdns

AU - Lim, Sungheon

AU - Kim, Hyogon

PY - 2019/6/1

Y1 - 2019/6/1

N2 - This paper explores the changes required of TCP to efficiently support cluster file systems such as Hadoop Distributed File System (HDFS) where the storage nodes are connected through a software defined networking (SDN). Traditional chain replications in these file systems incur large delay and cause inefficient network use. But SDN can cooperate with the cluster file systems to address the problems by pre-Arranging a distribution tree, which opens the possibility of parallel replication. Unfortunately, it cannot be realized without extending TCP, to accommodate the parallel transfer on the transport layer. This paper discusses how to extend TCP to make it possible, and demonstrates the feasibility by implementing a prototype in the Linux kernel. The prototype saves the data replication time by 25% while substantially reducing network use.

AB - This paper explores the changes required of TCP to efficiently support cluster file systems such as Hadoop Distributed File System (HDFS) where the storage nodes are connected through a software defined networking (SDN). Traditional chain replications in these file systems incur large delay and cause inefficient network use. But SDN can cooperate with the cluster file systems to address the problems by pre-Arranging a distribution tree, which opens the possibility of parallel replication. Unfortunately, it cannot be realized without extending TCP, to accommodate the parallel transfer on the transport layer. This paper discusses how to extend TCP to make it possible, and demonstrates the feasibility by implementing a prototype in the Linux kernel. The prototype saves the data replication time by 25% while substantially reducing network use.

KW - cluster file system

KW - data replication

KW - HDFS

KW - network utilization

KW - Software Defined Networking (SDN)

KW - TCP extension

UR - http://www.scopus.com/inward/record.url?scp=85072033690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072033690&partnerID=8YFLogxK

U2 - 10.1109/NETSOFT.2019.8806672

DO - 10.1109/NETSOFT.2019.8806672

M3 - Conference contribution

T3 - Proceedings of the 2019 IEEE Conference on Network Softwarization: Unleashing the Power of Network Softwarization, NetSoft 2019

SP - 48

EP - 53

BT - Proceedings of the 2019 IEEE Conference on Network Softwarization

A2 - De Turck, Filip

A2 - Esposito, Flavio

A2 - Chemouil, Prosper

A2 - Festor, Olivier

A2 - Secci, Stefano

A2 - Jacquenet, Christian

A2 - Cerroni, Walter

PB - Institute of Electrical and Electronics Engineers Inc.

ER -