Autonomic management of client concurrency in a distributed storage service

Markus Gerhard Tauber; Graham Njal Cameron Kirby; Alan Dearle

doi:10.1109/INM.2011.5990521

Autonomic management of client concurrency in a distributed storage service

Markus Gerhard Tauber, Graham Njal Cameron Kirby, Alan Dearle

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A distributed autonomic system adapts its constituent components to a changing environment. This paper reports on the application of autonomic management to a distributed storage service. We developed a simple analytic model which suggested potential benefit from tuning the degree of concurrency used in data retrieval operations, to suit dynamic conditions. We then validated this experimentally by developing an autonomic manager to control the degree of concurrency. We compared the resulting data retrieval performance with non-autonomic versions, using various combinations of network capacity, membership churn and workload patterns. Overall, autonomic management yielded improved retrieval performance. It also produced a distinct but not significant increase in network usage relative to one non-autonomic configuration, and a significant reduction relative to another.

Original language	English
Title of host publication	2011 IFIP/IEEE International Symposium on Integrated Network Management (IM 2011)
Publisher	IEEE
Pages	1109-1115
ISBN (Electronic)	978-1-4244-9220-6
ISBN (Print)	978-1-4244-9219-0
DOIs	https://doi.org/10.1109/INM.2011.5990521
Publication status	Published - 2011
Event	4th IFIP/IEEE Distributed Autonomous Management Systems Workshop (DANMS 2011) - Dublin, Ireland Duration: 27 May 2011 → …

Conference

Conference	4th IFIP/IEEE Distributed Autonomous Management Systems Workshop (DANMS 2011)
Country/Territory	Ireland
City	Dublin
Period	27/05/11 → …

Access to Document

10.1109/INM.2011.5990521

Cite this

@inproceedings{8fdbb2fcd7ce48b28bba01a64c9dfdfb,

title = "Autonomic management of client concurrency in a distributed storage service",

abstract = "A distributed autonomic system adapts its constituent components to a changing environment. This paper reports on the application of autonomic management to a distributed storage service. We developed a simple analytic model which suggested potential benefit from tuning the degree of concurrency used in data retrieval operations, to suit dynamic conditions. We then validated this experimentally by developing an autonomic manager to control the degree of concurrency. We compared the resulting data retrieval performance with non-autonomic versions, using various combinations of network capacity, membership churn and workload patterns. Overall, autonomic management yielded improved retrieval performance. It also produced a distinct but not significant increase in network usage relative to one non-autonomic configuration, and a significant reduction relative to another.",

author = "Tauber, {Markus Gerhard} and Kirby, {Graham Njal Cameron} and Alan Dearle",

note = "Submitted for publication 21/12/2010; 4th IFIP/IEEE Distributed Autonomous Management Systems Workshop (DANMS 2011) ; Conference date: 27-05-2011",

year = "2011",

doi = "10.1109/INM.2011.5990521",

language = "English",

isbn = "978-1-4244-9219-0",

pages = "1109--1115",

booktitle = "2011 IFIP/IEEE International Symposium on Integrated Network Management (IM 2011)",

publisher = "IEEE",

}

Tauber, MG, Kirby, GNC & Dearle, A 2011, Autonomic management of client concurrency in a distributed storage service. in 2011 IFIP/IEEE International Symposium on Integrated Network Management (IM 2011) . IEEE, pp. 1109-1115, 4th IFIP/IEEE Distributed Autonomous Management Systems Workshop (DANMS 2011), Dublin, Ireland, 27/05/11. https://doi.org/10.1109/INM.2011.5990521

TY - GEN

T1 - Autonomic management of client concurrency in a distributed storage service

AU - Tauber, Markus Gerhard

AU - Kirby, Graham Njal Cameron

AU - Dearle, Alan

N1 - Submitted for publication 21/12/2010

PY - 2011

Y1 - 2011

N2 - A distributed autonomic system adapts its constituent components to a changing environment. This paper reports on the application of autonomic management to a distributed storage service. We developed a simple analytic model which suggested potential benefit from tuning the degree of concurrency used in data retrieval operations, to suit dynamic conditions. We then validated this experimentally by developing an autonomic manager to control the degree of concurrency. We compared the resulting data retrieval performance with non-autonomic versions, using various combinations of network capacity, membership churn and workload patterns. Overall, autonomic management yielded improved retrieval performance. It also produced a distinct but not significant increase in network usage relative to one non-autonomic configuration, and a significant reduction relative to another.

AB - A distributed autonomic system adapts its constituent components to a changing environment. This paper reports on the application of autonomic management to a distributed storage service. We developed a simple analytic model which suggested potential benefit from tuning the degree of concurrency used in data retrieval operations, to suit dynamic conditions. We then validated this experimentally by developing an autonomic manager to control the degree of concurrency. We compared the resulting data retrieval performance with non-autonomic versions, using various combinations of network capacity, membership churn and workload patterns. Overall, autonomic management yielded improved retrieval performance. It also produced a distinct but not significant increase in network usage relative to one non-autonomic configuration, and a significant reduction relative to another.

UR - http://www.danms.org/

U2 - 10.1109/INM.2011.5990521

DO - 10.1109/INM.2011.5990521

M3 - Conference contribution

SN - 978-1-4244-9219-0

SP - 1109

EP - 1115

BT - 2011 IFIP/IEEE International Symposium on Integrated Network Management (IM 2011)

PB - IEEE

T2 - 4th IFIP/IEEE Distributed Autonomous Management Systems Workshop (DANMS 2011)

Y2 - 27 May 2011

ER -

Autonomic management of client concurrency in a distributed storage service

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Autonomic management of maintenance scheduling in Chord

Self-adaptation applied to peer-set maintenance in Chord via a generic autonomic management framework

Cite this