Job scheduling strategies for parallel processing : 8th International Workshop, JSSPP 2002, Edinburgh, Scotland, UK, July 24, 2002 : revised papers

This book constitutes the thoroughly refereed post-proceedings of the 8th International Workshop on Job Scheduling Strategies for Parallel Processing, JSSPP 2002, held in conjunction with HPDC-11 and FFG-5 in Edinburgh, Scotland in July 2002. The 12 revised full papers presented were carefully reviewed and selected during two rounds of reviewing and revision; they present state-of-the-art research results in the area with emphasis on classical massively parallel processing scheduling, in particular backfilling, and on scheduling in the context of grid computing. Thisvolumecontainsthepaperspresentedatthe8thworkshoponjobsched- Ingstrategiesforparallelprocessing,whichwasheldinconjunctionwith Hpdc11andggf5inedinburgh,uk,onjuly24,2002. Thepapershave Beenthroughacompletereviewprocess,withthefullversionbeingreadand Evaluatedby?vetosevenmembersoftheprogramcommittee. Wewouldliketo Takethisopportunitytothanktheprogramcommittee,andreaarpaci-dusseau, Walfredocirne,allendowney,wolfganggentzsch,allangottlieb,moejette, Richardlagerstrom,jensmache,cathymccann,reaganmoore,billnitzberg, Marksquillante,andjohntowns,foranexcellentjob. Thanksarealsodueto Theauthorsfortheirsubmissions,presentations,and?nalrevisionsforthisv- Ume. Finally,wewouldliketothankthemitlaboratoryforcomputerscience Andtheschoolofcomputerscienceandengineeringatthehebrewuniversity Fortheuseoftheirfacilitiesinthepreparationoftheseproceedings. Thisyearsawanemphasisontwomainthemes. The?rstwastheclassical Mppschedulingarea.^ Themainfocusinthisareawasonback?lling,including Severaladvancedvariationsonthebasicscheme. Itisalsonoteworthythatseveral Papersdiscussedtheuseofadaptivenessinjobscheduling. Thesecondmajor Themewasschedulinginthecontextofgridcomputing,whichisemergingasan Areaofmuchactivityandrapidprogress. Thesearecomplementedbyaninvited Paperprovidinganoverviewoftheschedulingandresourcemanagementareaof Theglobalgridforum(ggf)e?ort. Thiswastheeighthannualworkshopinthisseries,whichre?ectsthec- Tinuedinterestinthisarea. Theproceedingsofpreviousworkshopsareavailable Fromspringer-verlagaslncsvolumes949,1162,1291,1459,1659,1911,and 2221(andsince1998theyhavealsobeenavailableonline). Wehopeyou?ndthesepapersinterestinganduseful. September2002 Drorfeitelson Larryrudolph Uweschwiegelshohn Table Of Contents Aself-tuningjobschedulerfamilywithdynamicpolicyswitching . . . . . . . . 1 Achimstreit Preemptionbasedback?ll. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .^ 24 Quinno. Snell,markj. Clement,anddavidb. Jackson Jobschedulingforthebluegene/lsystem. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 Eliekrevat,jos ́eg. Castan ̃os,andjos ́ee. Moreira Selectivereservationstrategiesforback?lljobscheduling. . . . . . . . . . . . . . . . . 55 Srividyasrinivasan,rajkumarkettimuthu,vijaysubramani, Andponnuswamysadayappan Multiple-queueback?llingschedulingwithprioritiesandreservations Forparallelsystems. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72 Barryg. Lawsonandevgeniasmirni Schedulingjobsonparallelsystemsusingarelaxedback?llstrategy. . . . . 88 Williama. Ward,jr. ,carriel. Mahood,andjohne. West Theimpactofmoreaccuraterequestedruntimes Onproductionjobschedulingperformance. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103 Su-huichiang,andreaarpaci-dusseau,andmaryk. Vernon Economicschedulingingridcomputing. . . . . . . . . . . . . . . . . . . . . . . . .^ . . . . . . . . 128 Carstenernemann,volkerhamscher,andraminyahyapour Snap:aprotocolfornegotiatingservicelevelagreements Andcoordinatingresourcemanagementindistributedsystems. . . . . . . . . . 153 Karlczajkowski,ianfoster,carlkesselman,volkersander, Andsteventuecke Localversusglobalschedulerswithprocessorco-allocation Inmulticlustersystems. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 184 Ancai. D. Bucuranddickh. J. Epema Practicalheterogeneousplaceholderscheduling Inoverlaymetacomputers:earlyexperiences. . . . . . . . . . . . . . . . . . . . . . . . . . . . 205 Christopherpinchak,paullu,andmarkgoldenberg Currentactivitiesintheschedulingandresourcemanagementarea Oftheglobalgridforum. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 229 Billnitzbergandjenniferm. Schopf Author Index. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .^ . . . . . . 237 Aself-tuningjobschedulerfamily Withdynamic Policyswitching Achim Streit 2 Pc - Paderborn Center For Parallel Computing, Paderborn University 33102 Paderborn, Germany Streit@upb. De Http://www. Upb. De/pc2 Abstract. The Performance Of Job Scheduling Policies Strongly Depends On The Properties Of The Incoming Jobs. If The Job Characteristics Often Change, The Scheduling Policy Should Follow These Changes. For This P- Pose The Dynp Job Scheduler Family Has Been Developed. The Idea Is To Dynamically Switch The Scheduling Policy During Runtime. In A Basic V- Sion The Policy Switching Is Controlled By Two Parameters. The Basic Concept Of Theself-tuning Dynp Scheduler Is To Compute Virtual Schedules For Each Policy In Every Scheduling Step. That Policy Is Chosen Which Generates The ’best’ Schedule. The Performance Of The Self-tuning Dynp Scheduler No Longer Depends On A Adequate Setting Of The Input Parameters. A Self-tuning Job Scheduler Family With Dynamic Policy Switching / Achim Streit -- Preemption Based Backfill / Quinn O. Snell, Mark J. Clement, And David B. Jackson -- Job Scheduling For The Bluegene/l System / Elie Krevat, José G. Castaños, And José E. Moreira -- Selective Reservation Strategies For Backfill Job Scheduling / Srividya Srinivasan [and Others] -- Multiple-queue Backfilling Scheduling With Priorities And Reservations For Parallel Systems / Barry G. Lawson And Evgenia Smirni -- Scheduling Jobs On Parallel Systems Using A Relaxed Backfill Strategy / William A. Ward, Jr., Carrie L. Mahood, And John E. West -- The Impact Of More Accurate Requested Runtimes On Production Job Scheduling Performance / Su-hui Chiang, Andrea Arpaci-dusseau, And Mary K. Vernon -- Economic Scheduling In Grid Computing / Carsten Ernemann, Volker Hamscher, And Ramin Yahyapour -- Snap: A Protocol For Negotiating Service Level Agreements And Coordinating Resource Management In Distributed Systems / Karl Czajkowski [and Others] -- Local Versus Global Schedulers With Processor Co-allocation In Multicluster Systems / Anca I.d. Bucur And Dick H.j. Epema -- Practical Heterogeneous Placeholder Scheduling In Overlay Metacomputers: Early Experiences / Christopher Pinchak, Paul Lu, And Mark Goldenberg -- Current Activities In The Scheduling And Resource Management Area Of The Global Grid Forum / Bill Nitzberg And Jennifer M. Schopf. Dror G. Feitelson, Larry Rudolph, Uwe Schwiegelshohn (eds.). Includes Bibliographical References And Index. A Self-Tuning Job Scheduler Family with Dynamic Policy Switching....Pages 1-23 Preemption Based Backfill....Pages 24-37 Job Scheduling for the BlueGene/L System....Pages 38-54 Selective Reservation Strategies for Backfill Job Scheduling....Pages 55-71 Multiple-Queue Backfilling Scheduling with Priorities and Reservations for Parallel Systems....Pages 72-87 Scheduling Jobs on Parallel Systems Using a Relaxed Backfill Strategy....Pages 88-102 The Impact of More Accurate Requested Runtimes on Production Job Scheduling Performance....Pages 103-127 Economic Scheduling in Grid Computing....Pages 128-152 SNAP: A Protocol for Negotiating Service Level Agreements and Coordinating Resource Management in Distributed Systems....Pages 153-183 Local versus Global Schedulers with Processor Co-allocation in Multicluster Systems....Pages 184-204 Practical Heterogeneous Placeholder Scheduling in Overlay Metacomputers: Early Experiences....Pages 205-228 Current Activities in the Scheduling and Resource Management Area of the Global Grid Forum....Pages 229-235 Job Scheduling Strategies for Parallel Processing: 7th International Workshop, JSSPP 2001 Cambridge, MA, USA, June 16, 2001 Revised Papers Author: Dror G. Feitelson, Larry Rudolph Published by Springer Berlin Heidelberg ISBN: 978-3-540-42817-6 DOI: 10.1007/3-540-45540-X Table of Contents: Performance Evaluation with Heavy Tailed Distributions SRPT Scheduling for Web Servers An Efficient and Scalable Coscheduling Technique for Large Symmetric Multiprocessor Clusters Coscheduling under Memory Constraints in a NOW Environment The Influence of Communication on the Performance of Co-allocation Core Algorithms of the Maui Scheduler On the Development of an Efficient Coscheduling System Effects of Memory Performance on Parallel Job Scheduling An Integrated Approach to Parallel Scheduling Using Gang-Scheduling, Backfilling, and Migration Characteristics of a Large Shared Memory Production Workload Metrics for Parallel Job Scheduling and Their Convergence Compiled from the post-proceedings of the 8th International Workshop on Job Scheduling Strategies for Parallel Processing, this volume contains 12 papers. They present research results in the area, with emphasis on classical massively parallel processing scheduling and grid computing. This book constitutes the thoroughly refereed proceedings of the 16th International Workshop on Job Scheduling Strategies for Parallel Processing, JSSPP 2012, which was held in Shanghai, China, in May 2012. The papers cover the following topics: parallel batch scheduling;