Interference resolver in shared storage systems to provide fairness to I/O intensive applications

Ramya Prabhakar, Mahmut Kandemir, Padma Raghavan, Myoungsoo Jung

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

Abstract

Most of the prior mechanisms on managing shared storage resources manage each individual shared resource without considering the interplay between different resources, leading to low fairness and loss of performance. Therefore, a coordinated mechanism that provides fairness in the entire shared storage system is desirable. This paper proposes a strategy to control inter-Application interference by dynamically adjusting the aggressiveness of the shared storage cache and I/O bandwidth accesses made by multiple, concurrently-executing applications, in a coordinated fashion. Our interference resolver eliminates the need for complicated individual resource-based partitioning mechanisms implemented independently in each resource and that require coordination. It ensures fairness among high performance applications that access the underlying storage system, while best utilizing the available resources. In our experimental evaluation, we use both trace-driven simulations and an implementation in the Linux kernel 2.6.32, and show that our interference resolver can significantly increase system performance and provide fairness to concurrently-executing applications.

Original languageEnglish
Title of host publicationProceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013
PublisherIEEE Computer Society
Pages1971-1980
Number of pages10
ISBN (Print)9780769549798
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 IEEE 37th Annual Computer Software and Applications Conference, COMPSAC 2013 - Boston, MA, Japan
Duration: 2013 Jul 222013 Jul 26

Publication series

NameProceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013

Conference

Conference2013 IEEE 37th Annual Computer Software and Applications Conference, COMPSAC 2013
CountryJapan
CityBoston, MA
Period13/7/2213/7/26

Fingerprint

Storage System
Fairness
Interference
Resources
Linux
Bandwidth
Experimental Evaluation
Cache
System Performance
Partitioning
Eliminate
High Performance
Trace
Entire
kernel
Simulation

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Software
  • Theoretical Computer Science

Cite this

Prabhakar, R., Kandemir, M., Raghavan, P., & Jung, M. (2013). Interference resolver in shared storage systems to provide fairness to I/O intensive applications. In Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013 (pp. 1971-1980). [6651101] (Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013). IEEE Computer Society. https://doi.org/10.1109/IPDPSW.2013.158
Prabhakar, Ramya ; Kandemir, Mahmut ; Raghavan, Padma ; Jung, Myoungsoo. / Interference resolver in shared storage systems to provide fairness to I/O intensive applications. Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013. IEEE Computer Society, 2013. pp. 1971-1980 (Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013).
@inproceedings{4ae7ebc86c69477fb56935198ca99625,
title = "Interference resolver in shared storage systems to provide fairness to I/O intensive applications",
abstract = "Most of the prior mechanisms on managing shared storage resources manage each individual shared resource without considering the interplay between different resources, leading to low fairness and loss of performance. Therefore, a coordinated mechanism that provides fairness in the entire shared storage system is desirable. This paper proposes a strategy to control inter-Application interference by dynamically adjusting the aggressiveness of the shared storage cache and I/O bandwidth accesses made by multiple, concurrently-executing applications, in a coordinated fashion. Our interference resolver eliminates the need for complicated individual resource-based partitioning mechanisms implemented independently in each resource and that require coordination. It ensures fairness among high performance applications that access the underlying storage system, while best utilizing the available resources. In our experimental evaluation, we use both trace-driven simulations and an implementation in the Linux kernel 2.6.32, and show that our interference resolver can significantly increase system performance and provide fairness to concurrently-executing applications.",
author = "Ramya Prabhakar and Mahmut Kandemir and Padma Raghavan and Myoungsoo Jung",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/IPDPSW.2013.158",
language = "English",
isbn = "9780769549798",
series = "Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013",
publisher = "IEEE Computer Society",
pages = "1971--1980",
booktitle = "Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013",
address = "United States",

}

Prabhakar, R, Kandemir, M, Raghavan, P & Jung, M 2013, Interference resolver in shared storage systems to provide fairness to I/O intensive applications. in Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013., 6651101, Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013, IEEE Computer Society, pp. 1971-1980, 2013 IEEE 37th Annual Computer Software and Applications Conference, COMPSAC 2013, Boston, MA, Japan, 13/7/22. https://doi.org/10.1109/IPDPSW.2013.158

Interference resolver in shared storage systems to provide fairness to I/O intensive applications. / Prabhakar, Ramya; Kandemir, Mahmut; Raghavan, Padma; Jung, Myoungsoo.

Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013. IEEE Computer Society, 2013. p. 1971-1980 6651101 (Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013).

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

TY - GEN

T1 - Interference resolver in shared storage systems to provide fairness to I/O intensive applications

AU - Prabhakar, Ramya

AU - Kandemir, Mahmut

AU - Raghavan, Padma

AU - Jung, Myoungsoo

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Most of the prior mechanisms on managing shared storage resources manage each individual shared resource without considering the interplay between different resources, leading to low fairness and loss of performance. Therefore, a coordinated mechanism that provides fairness in the entire shared storage system is desirable. This paper proposes a strategy to control inter-Application interference by dynamically adjusting the aggressiveness of the shared storage cache and I/O bandwidth accesses made by multiple, concurrently-executing applications, in a coordinated fashion. Our interference resolver eliminates the need for complicated individual resource-based partitioning mechanisms implemented independently in each resource and that require coordination. It ensures fairness among high performance applications that access the underlying storage system, while best utilizing the available resources. In our experimental evaluation, we use both trace-driven simulations and an implementation in the Linux kernel 2.6.32, and show that our interference resolver can significantly increase system performance and provide fairness to concurrently-executing applications.

AB - Most of the prior mechanisms on managing shared storage resources manage each individual shared resource without considering the interplay between different resources, leading to low fairness and loss of performance. Therefore, a coordinated mechanism that provides fairness in the entire shared storage system is desirable. This paper proposes a strategy to control inter-Application interference by dynamically adjusting the aggressiveness of the shared storage cache and I/O bandwidth accesses made by multiple, concurrently-executing applications, in a coordinated fashion. Our interference resolver eliminates the need for complicated individual resource-based partitioning mechanisms implemented independently in each resource and that require coordination. It ensures fairness among high performance applications that access the underlying storage system, while best utilizing the available resources. In our experimental evaluation, we use both trace-driven simulations and an implementation in the Linux kernel 2.6.32, and show that our interference resolver can significantly increase system performance and provide fairness to concurrently-executing applications.

UR - http://www.scopus.com/inward/record.url?scp=84899710145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899710145&partnerID=8YFLogxK

U2 - 10.1109/IPDPSW.2013.158

DO - 10.1109/IPDPSW.2013.158

M3 - Conference contribution

AN - SCOPUS:84899710145

SN - 9780769549798

T3 - Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013

SP - 1971

EP - 1980

BT - Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013

PB - IEEE Computer Society

ER -

Prabhakar R, Kandemir M, Raghavan P, Jung M. Interference resolver in shared storage systems to provide fairness to I/O intensive applications. In Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013. IEEE Computer Society. 2013. p. 1971-1980. 6651101. (Proceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013). https://doi.org/10.1109/IPDPSW.2013.158