Minimising the execution of unknown Bag-of-Task jobs with deadlines on the Cloud

Long Thanh Thai; Blesson Varghese; Adam David Barker

doi:10.1145/2912152.2912153

Minimising the execution of unknown Bag-of-Task jobs with deadlines on the Cloud

Long Thanh Thai, Blesson Varghese, Adam David Barker

School of Computer Science

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

1 Citation (Scopus)

2 Downloads (Pure)

Abstract

Scheduling jobs with deadlines, each of which de nes the latest time that a job must be completed, can be challenging on the cloud due to incurred costs and unpredictable performance. This problem is further complicated when there
is not enough information to e ectively schedule a job such that its deadline is satis ed, and the cost is minimised. In this paper, we present an approach to schedule jobs, whose performance are unknown before execution, with deadlines on the cloud. By performing a sampling phase to collect
the necessary information about those jobs, our approach delivers the scheduling decision within 10% cost and 16% violation rate when compared to the ideal setting, which has complete knowledge about each of the jobs from the beginning. It is noted that our proposed algorithm outperforms existing approaches, which use a xed amount of resources by reducing the violation cost by at least two times.

Original language	English
Title of host publication	DIDC '16 Proceedings of the ACM International Workshop on Data-Intensive Distributed Computing
Publisher	ACM
Pages	3-10
ISBN (Print)	9781450343527
DOIs	https://doi.org/10.1145/2912152.2912153
Publication status	Published - 1 Jun 2016
Event	The 7th International Workshop on Data-intensive Distributed Computing (DIDC'16) - Kyoto, Japan Duration: 1 Jun 2016 → 1 Jun 2016 http://www.rci.rutgers.edu/~ey108/didc2016/home.html

Workshop

Workshop	The 7th International Workshop on Data-intensive Distributed Computing (DIDC'16)
Country/Territory	Japan
City	Kyoto
Period	1/06/16 → 1/06/16
Internet address	http://www.rci.rutgers.edu/~ey108/didc2016/home.html

Keywords

Bag of Task
Scheduling
Deadline
Cloud computing
Unknown

Access to Document

10.1145/2912152.2912153

2016.DIDC
© 2016, the Author(s). This work is made available online in accordance with the publisher’s policies. This is the author created, accepted version manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at dl.acm.org / https://dx.doi.org/10.1145/1235
Accepted author manuscript, 1.14 MB

Cite this

@inproceedings{493577503ad64ad987d370dde23c8a59,

title = "Minimising the execution of unknown Bag-of-Task jobs with deadlines on the Cloud",

abstract = "Scheduling jobs with deadlines, each of which de nes the latest time that a job must be completed, can be challenging on the cloud due to incurred costs and unpredictable performance. This problem is further complicated when thereis not enough information to e ectively schedule a job such that its deadline is satis ed, and the cost is minimised. In this paper, we present an approach to schedule jobs, whose performance are unknown before execution, with deadlines on the cloud. By performing a sampling phase to collectthe necessary information about those jobs, our approach delivers the scheduling decision within 10% cost and 16% violation rate when compared to the ideal setting, which has complete knowledge about each of the jobs from the beginning. It is noted that our proposed algorithm outperforms existing approaches, which use a xed amount of resources by reducing the violation cost by at least two times.",

keywords = "Bag of Task, Scheduling, Deadline, Cloud computing, Unknown",

author = "Thai, {Long Thanh} and Blesson Varghese and Barker, {Adam David}",

year = "2016",

month = jun,

day = "1",

doi = "10.1145/2912152.2912153",

language = "English",

isbn = "9781450343527",

pages = "3--10",

booktitle = "DIDC '16 Proceedings of the ACM International Workshop on Data-Intensive Distributed Computing",

publisher = "ACM",

address = "United States",

note = "The 7th International Workshop on Data-intensive Distributed Computing (DIDC'16) ; Conference date: 01-06-2016 Through 01-06-2016",

url = "http://www.rci.rutgers.edu/~ey108/didc2016/home.html",

}

Thai, LT, Varghese, B & Barker, AD 2016, Minimising the execution of unknown Bag-of-Task jobs with deadlines on the Cloud. in DIDC '16 Proceedings of the ACM International Workshop on Data-Intensive Distributed Computing. ACM, pp. 3-10, The 7th International Workshop on Data-intensive Distributed Computing (DIDC'16), Kyoto, Japan, 1/06/16. https://doi.org/10.1145/2912152.2912153

TY - GEN

T1 - Minimising the execution of unknown Bag-of-Task jobs with deadlines on the Cloud

AU - Thai, Long Thanh

AU - Varghese, Blesson

AU - Barker, Adam David

PY - 2016/6/1

Y1 - 2016/6/1

N2 - Scheduling jobs with deadlines, each of which de nes the latest time that a job must be completed, can be challenging on the cloud due to incurred costs and unpredictable performance. This problem is further complicated when thereis not enough information to e ectively schedule a job such that its deadline is satis ed, and the cost is minimised. In this paper, we present an approach to schedule jobs, whose performance are unknown before execution, with deadlines on the cloud. By performing a sampling phase to collectthe necessary information about those jobs, our approach delivers the scheduling decision within 10% cost and 16% violation rate when compared to the ideal setting, which has complete knowledge about each of the jobs from the beginning. It is noted that our proposed algorithm outperforms existing approaches, which use a xed amount of resources by reducing the violation cost by at least two times.

AB - Scheduling jobs with deadlines, each of which de nes the latest time that a job must be completed, can be challenging on the cloud due to incurred costs and unpredictable performance. This problem is further complicated when thereis not enough information to e ectively schedule a job such that its deadline is satis ed, and the cost is minimised. In this paper, we present an approach to schedule jobs, whose performance are unknown before execution, with deadlines on the cloud. By performing a sampling phase to collectthe necessary information about those jobs, our approach delivers the scheduling decision within 10% cost and 16% violation rate when compared to the ideal setting, which has complete knowledge about each of the jobs from the beginning. It is noted that our proposed algorithm outperforms existing approaches, which use a xed amount of resources by reducing the violation cost by at least two times.

KW - Bag of Task

KW - Scheduling

KW - Deadline

KW - Cloud computing

KW - Unknown

U2 - 10.1145/2912152.2912153

DO - 10.1145/2912152.2912153

M3 - Conference contribution

SN - 9781450343527

SP - 3

EP - 10

BT - DIDC '16 Proceedings of the ACM International Workshop on Data-Intensive Distributed Computing

PB - ACM

T2 - The 7th International Workshop on Data-intensive Distributed Computing (DIDC'16)

Y2 - 1 June 2016 through 1 June 2016

ER -

Minimising the execution of unknown Bag-of-Task jobs with deadlines on the Cloud

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this