國立虎尾科技大學 |

Fair Scheduling in High Performance Computing Environments

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Fair Scheduling in High Performance Computing Environments/ by Art Sedighi, Milton Smith.
Author:	Sedighi, Art.
other author:	Smith, Milton.
Description:	XI, 132 p. 77 illus., 74 illus. in color.online resource. :
Contained By:	Springer Nature eBook
Subject:	Algorithms. -
Online resource:	https://doi.org/10.1007/978-3-030-14568-2
ISBN:	9783030145682

Fair Scheduling in High Performance Computing Environments
Sedighi, Art.

Fair Scheduling in High Performance Computing Environments[electronic resource] /by Art Sedighi, Milton Smith. - 1st ed. 2019. - XI, 132 p. 77 illus., 74 illus. in color.online resource.

Chapter 1 Introduction 1 -- Chapter 2 Financial Market Risk 9 -- Chapter 3 Scheduling in High Performance Computing 24 -- Chapter 4 Fairshare Scheduling 33 -- Chapter 5 Multi-Criteria Scheduling: A Mathematical Model 43 -- Chapter 6 Simulation & Methodology 56 -- Chapter 7 DSIM 67 -- Chapter 8 Simulation Scenarios 73 -- Chapter 9 Overview of Results 90 -- Chapter 10 Class A Results and Analysis 101 -- Chapter 11 Class B Results and Analysis 118 -- Chapter 12 Class C Results and Analysis 139 -- Chapter 13 Class D Results and Simulations 153 -- Chapter 14 Conclusion 173. .

This book introduces a new scheduler to fairly and efficiently distribute system resources to many users of varying usage patterns compete for them in large shared computing environments. The Rawlsian Fair scheduler developed for this effort is shown to boost performance while reducing delay in high performance computing workloads of certain types including the following four types examined in this book: i. Class A – similar but complementary workloads ii. Class B – similar but steady vs intermittent workloads iii. Class C – Large vs small workloads iv. Class D – Large vs noise-like workloads This new scheduler achieves short-term fairness for small timescale demanding rapid response to varying workloads and usage profiles. Rawlsian Fair scheduler is shown to consistently benefit workload Classes C and D while it only benefits Classes A and B workloads where they become disproportionate as the number of users increases. A simulation framework, dSim, simulates the new Rawlsian Fair scheduling mechanism. The dSim helps achieve instantaneous fairness in High Performance Computing environments, effective utilization of computing resources, and user satisfaction through the Rawlsian Fair scheduler.

ISBN: 9783030145682

Standard No.: 10.1007/978-3-030-14568-2doiSubjects--Topical Terms:

527865
Algorithms.

LC Class. No.: QA76.9.A43

Dewey Class. No.: 005.1

Fair Scheduling in High Performance Computing Environments
LDR:03154nam a22003975i 4500 001 1007917
003 DE-He213
005 20200701071923.0
007 cr nn 008mamaa
008 210106s2019 gw | s |||| 0|eng d
020 $a 9783030145682 $9 978-3-030-14568-2
024 7 $a 10.1007/978-3-030-14568-2 $2 doi
035 $a 978-3-030-14568-2
050 4 $a QA76.9.A43
072 7 $a UMB $2 bicssc
072 7 $a COM051300 $2 bisacsh
072 7 $a UMB $2 thema
082 0 4 $a 005.1 $2 23
100 1 $a Sedighi, Art. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1225850
245 1 0 $a Fair Scheduling in High Performance Computing Environments $h [electronic resource] / $c by Art Sedighi, Milton Smith.
250 $a 1st ed. 2019.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2019.
300 $a XI, 132 p. 77 illus., 74 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
505 0 $a Chapter 1 Introduction 1 -- Chapter 2 Financial Market Risk 9 -- Chapter 3 Scheduling in High Performance Computing 24 -- Chapter 4 Fairshare Scheduling 33 -- Chapter 5 Multi-Criteria Scheduling: A Mathematical Model 43 -- Chapter 6 Simulation & Methodology 56 -- Chapter 7 DSIM 67 -- Chapter 8 Simulation Scenarios 73 -- Chapter 9 Overview of Results 90 -- Chapter 10 Class A Results and Analysis 101 -- Chapter 11 Class B Results and Analysis 118 -- Chapter 12 Class C Results and Analysis 139 -- Chapter 13 Class D Results and Simulations 153 -- Chapter 14 Conclusion 173. .
520 $a This book introduces a new scheduler to fairly and efficiently distribute system resources to many users of varying usage patterns compete for them in large shared computing environments. The Rawlsian Fair scheduler developed for this effort is shown to boost performance while reducing delay in high performance computing workloads of certain types including the following four types examined in this book: i. Class A – similar but complementary workloads ii. Class B – similar but steady vs intermittent workloads iii. Class C – Large vs small workloads iv. Class D – Large vs noise-like workloads This new scheduler achieves short-term fairness for small timescale demanding rapid response to varying workloads and usage profiles. Rawlsian Fair scheduler is shown to consistently benefit workload Classes C and D while it only benefits Classes A and B workloads where they become disproportionate as the number of users increases. A simulation framework, dSim, simulates the new Rawlsian Fair scheduling mechanism. The dSim helps achieve instantaneous fairness in High Performance Computing environments, effective utilization of computing resources, and user satisfaction through the Rawlsian Fair scheduler.
650 0 $a Algorithms. $3 527865
650 0 $a Computers. $3 565115
650 0 $a Microprocessors. $3 632481
650 1 4 $a Algorithm Analysis and Problem Complexity. $3 593923
650 2 4 $a Information Systems and Communication Service. $3 669203
650 2 4 $a Processor Architectures. $3 669787
700 1 $a Smith, Milton. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1225851
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030145675
776 0 8 $i Printed edition: $z 9783030145699
776 0 8 $i Printed edition: $z 9783030145705
856 4 0 $u https://doi.org/10.1007/978-3-030-14568-2
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)