An adaptive job scheduling scheme for mesh-connected multicomputers

Ismail Ababneh, Saad Bani-Mohammad, Mohamed Ould-Khaoua

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Allocating submeshes to jobs in mesh-connected multicomputers in an FCFS fashion leads to poor system performance because a large job at the head of the waiting queue can prevent the allocation of free submeshes to other smaller waiting jobs. However, serving jobs aggressively out-of-order can lead to excessive waiting delays for large jobs located at the head of the waiting queue. In this paper, we show that the ability of the job scheduling algorithm to bypass the head of the waiting queue should increase with the load, and we propose a scheduling scheme that can bypass the waiting queue head in a load-dependent adaptive fashion. Also, giving priority to large jobs because they are more difficult to accommodate is investigated. The performance of the proposed scheme has been compared to that of FCFS, aggressive out-of-order scheduling, and other previous job scheduling schemes. Extensive simulation results based on synthetic workloads and real workload traces indicate that our scheduling strategy is a good strategy when both average and maximum job waiting delays are considered. In particular, it is substantially superior to FCFS in terms of mean turnaround times, and to aggressive out-of-order scheduling in terms of maximum waiting delays.

Original languageEnglish
Pages (from-to)5-25
Number of pages21
JournalJournal of Supercomputing
Volume53
Issue number1
DOIs
Publication statusPublished - Jul 2010

Fingerprint

Adaptive Scheduling
Multicomputers
Job Scheduling
Queue
Scheduling
Mesh
Workload
Turnaround time
Scheduling Algorithm
System Performance
Scheduling algorithms
Trace
Dependent
Simulation
Strategy

Keywords

  • Contiguous submesh allocation
  • Job scheduling
  • Maximum waiting delay
  • Mesh
  • Multicomputer
  • Waiting delay

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Information Systems
  • Theoretical Computer Science

Cite this

An adaptive job scheduling scheme for mesh-connected multicomputers. / Ababneh, Ismail; Bani-Mohammad, Saad; Ould-Khaoua, Mohamed.

In: Journal of Supercomputing, Vol. 53, No. 1, 07.2010, p. 5-25.

Research output: Contribution to journalArticle

Ababneh, Ismail ; Bani-Mohammad, Saad ; Ould-Khaoua, Mohamed. / An adaptive job scheduling scheme for mesh-connected multicomputers. In: Journal of Supercomputing. 2010 ; Vol. 53, No. 1. pp. 5-25.
@article{5c04b16a652640139f0d7e5605fe5682,
title = "An adaptive job scheduling scheme for mesh-connected multicomputers",
abstract = "Allocating submeshes to jobs in mesh-connected multicomputers in an FCFS fashion leads to poor system performance because a large job at the head of the waiting queue can prevent the allocation of free submeshes to other smaller waiting jobs. However, serving jobs aggressively out-of-order can lead to excessive waiting delays for large jobs located at the head of the waiting queue. In this paper, we show that the ability of the job scheduling algorithm to bypass the head of the waiting queue should increase with the load, and we propose a scheduling scheme that can bypass the waiting queue head in a load-dependent adaptive fashion. Also, giving priority to large jobs because they are more difficult to accommodate is investigated. The performance of the proposed scheme has been compared to that of FCFS, aggressive out-of-order scheduling, and other previous job scheduling schemes. Extensive simulation results based on synthetic workloads and real workload traces indicate that our scheduling strategy is a good strategy when both average and maximum job waiting delays are considered. In particular, it is substantially superior to FCFS in terms of mean turnaround times, and to aggressive out-of-order scheduling in terms of maximum waiting delays.",
keywords = "Contiguous submesh allocation, Job scheduling, Maximum waiting delay, Mesh, Multicomputer, Waiting delay",
author = "Ismail Ababneh and Saad Bani-Mohammad and Mohamed Ould-Khaoua",
year = "2010",
month = "7",
doi = "10.1007/s11227-009-0333-2",
language = "English",
volume = "53",
pages = "5--25",
journal = "Journal of Supercomputing",
issn = "0920-8542",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - An adaptive job scheduling scheme for mesh-connected multicomputers

AU - Ababneh, Ismail

AU - Bani-Mohammad, Saad

AU - Ould-Khaoua, Mohamed

PY - 2010/7

Y1 - 2010/7

N2 - Allocating submeshes to jobs in mesh-connected multicomputers in an FCFS fashion leads to poor system performance because a large job at the head of the waiting queue can prevent the allocation of free submeshes to other smaller waiting jobs. However, serving jobs aggressively out-of-order can lead to excessive waiting delays for large jobs located at the head of the waiting queue. In this paper, we show that the ability of the job scheduling algorithm to bypass the head of the waiting queue should increase with the load, and we propose a scheduling scheme that can bypass the waiting queue head in a load-dependent adaptive fashion. Also, giving priority to large jobs because they are more difficult to accommodate is investigated. The performance of the proposed scheme has been compared to that of FCFS, aggressive out-of-order scheduling, and other previous job scheduling schemes. Extensive simulation results based on synthetic workloads and real workload traces indicate that our scheduling strategy is a good strategy when both average and maximum job waiting delays are considered. In particular, it is substantially superior to FCFS in terms of mean turnaround times, and to aggressive out-of-order scheduling in terms of maximum waiting delays.

AB - Allocating submeshes to jobs in mesh-connected multicomputers in an FCFS fashion leads to poor system performance because a large job at the head of the waiting queue can prevent the allocation of free submeshes to other smaller waiting jobs. However, serving jobs aggressively out-of-order can lead to excessive waiting delays for large jobs located at the head of the waiting queue. In this paper, we show that the ability of the job scheduling algorithm to bypass the head of the waiting queue should increase with the load, and we propose a scheduling scheme that can bypass the waiting queue head in a load-dependent adaptive fashion. Also, giving priority to large jobs because they are more difficult to accommodate is investigated. The performance of the proposed scheme has been compared to that of FCFS, aggressive out-of-order scheduling, and other previous job scheduling schemes. Extensive simulation results based on synthetic workloads and real workload traces indicate that our scheduling strategy is a good strategy when both average and maximum job waiting delays are considered. In particular, it is substantially superior to FCFS in terms of mean turnaround times, and to aggressive out-of-order scheduling in terms of maximum waiting delays.

KW - Contiguous submesh allocation

KW - Job scheduling

KW - Maximum waiting delay

KW - Mesh

KW - Multicomputer

KW - Waiting delay

UR - http://www.scopus.com/inward/record.url?scp=77953618134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953618134&partnerID=8YFLogxK

U2 - 10.1007/s11227-009-0333-2

DO - 10.1007/s11227-009-0333-2

M3 - Article

AN - SCOPUS:77953618134

VL - 53

SP - 5

EP - 25

JO - Journal of Supercomputing

JF - Journal of Supercomputing

SN - 0920-8542

IS - 1

ER -