SmartOS: towards automated learning and user-adaptive resource allocation in operating systems

Sepideh Goodarzy; Maziyar Nazari; Richard Han; Eric Keller; Eric Rozner

doi:10.1145/3476886.3477519

SmartOS: towards automated learning and user-adaptive resource allocation in operating systems

Sepideh Goodarzy^*, Maziyar Nazari, Richard Han, Eric Keller, Eric Rozner

^*Corresponding author for this work

School of Computing

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

2 Citations (Scopus)

58 Downloads (Pure)

Abstract

Today's operating systems typically apply a one-size-fits-all approach to resource management, such as applying a scheduler that treats all processes of equal importance. The goal of this paper is to explore a learning-based approach to resource management in modern operating systems in which the OS automatically learns what tasks the user deems to be most important at that time and seamlessly adjusts allocation of CPU, memory, I/O, and network bandwidth to prioritize user preferences on demand. We demonstrate an implementation of such a learning-based OS in Linux and present evaluation results showing that a reinforcement learning-based approach can rapidly learn and adjust system resources to meet user demands.

Original language	English
Title of host publication	APSys 2021 - Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems
Place of Publication	New York, NY
Publisher	Association for Computing Machinery
Pages	48-55
Number of pages	8
ISBN (Electronic)	9781450386982
DOIs	https://doi.org/10.1145/3476886.3477519
Publication status	Published - 2021
Event	12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys) - Online Duration: 24 Aug 2021 → 25 Aug 2021

Conference

Conference	12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)
Period	24/08/21 → 25/08/21

Bibliographical note

Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

Operating systems
Reinforcement learning
Human computer interaction

Access to Document

10.1145/3476886.3477519

Publisher version (open access)Final published version, 847 KBLicence: CC BY

Cite this

@inproceedings{499517db2d604a55906c685bbd95f139,

title = "SmartOS: towards automated learning and user-adaptive resource allocation in operating systems",

abstract = "Today's operating systems typically apply a one-size-fits-all approach to resource management, such as applying a scheduler that treats all processes of equal importance. The goal of this paper is to explore a learning-based approach to resource management in modern operating systems in which the OS automatically learns what tasks the user deems to be most important at that time and seamlessly adjusts allocation of CPU, memory, I/O, and network bandwidth to prioritize user preferences on demand. We demonstrate an implementation of such a learning-based OS in Linux and present evaluation results showing that a reinforcement learning-based approach can rapidly learn and adjust system resources to meet user demands.",

keywords = "Operating systems, Reinforcement learning, Human computer interaction",

author = "Sepideh Goodarzy and Maziyar Nazari and Richard Han and Eric Keller and Eric Rozner",

note = "Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.; 12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys) ; Conference date: 24-08-2021 Through 25-08-2021",

year = "2021",

doi = "10.1145/3476886.3477519",

language = "English",

pages = "48--55",

booktitle = "APSys 2021 - Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems",

publisher = "Association for Computing Machinery",

}

Goodarzy, S, Nazari, M, Han, R, Keller, E & Rozner, E 2021, SmartOS: towards automated learning and user-adaptive resource allocation in operating systems. in APSys 2021 - Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems. Association for Computing Machinery, New York, NY, pp. 48-55, 12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys), 24/08/21. https://doi.org/10.1145/3476886.3477519

SmartOS: towards automated learning and user-adaptive resource allocation in operating systems. / Goodarzy, Sepideh; Nazari, Maziyar; Han, Richard et al.
APSys 2021 - Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems. New York, NY: Association for Computing Machinery, 2021. p. 48-55.

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

TY - GEN

T1 - SmartOS

T2 - 12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)

AU - Goodarzy, Sepideh

AU - Nazari, Maziyar

AU - Han, Richard

AU - Keller, Eric

AU - Rozner, Eric

N1 - Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2021

Y1 - 2021

N2 - Today's operating systems typically apply a one-size-fits-all approach to resource management, such as applying a scheduler that treats all processes of equal importance. The goal of this paper is to explore a learning-based approach to resource management in modern operating systems in which the OS automatically learns what tasks the user deems to be most important at that time and seamlessly adjusts allocation of CPU, memory, I/O, and network bandwidth to prioritize user preferences on demand. We demonstrate an implementation of such a learning-based OS in Linux and present evaluation results showing that a reinforcement learning-based approach can rapidly learn and adjust system resources to meet user demands.

AB - Today's operating systems typically apply a one-size-fits-all approach to resource management, such as applying a scheduler that treats all processes of equal importance. The goal of this paper is to explore a learning-based approach to resource management in modern operating systems in which the OS automatically learns what tasks the user deems to be most important at that time and seamlessly adjusts allocation of CPU, memory, I/O, and network bandwidth to prioritize user preferences on demand. We demonstrate an implementation of such a learning-based OS in Linux and present evaluation results showing that a reinforcement learning-based approach can rapidly learn and adjust system resources to meet user demands.

KW - Operating systems

KW - Reinforcement learning

KW - Human computer interaction

UR - http://www.scopus.com/inward/record.url?scp=85118172914&partnerID=8YFLogxK

U2 - 10.1145/3476886.3477519

DO - 10.1145/3476886.3477519

M3 - Conference proceeding contribution

SP - 48

EP - 55

BT - APSys 2021 - Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems

PB - Association for Computing Machinery

CY - New York, NY

Y2 - 24 August 2021 through 25 August 2021

ER -

SmartOS: towards automated learning and user-adaptive resource allocation in operating systems

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this