{"id":"https://openalex.org/W2119512272","doi":"https://doi.org/10.1145/1376849.1376851","title":"Using checkpointing to recover from poor multi-site parallel job scheduling decisions","display_name":"Using checkpointing to recover from poor multi-site parallel job scheduling decisions","publication_year":2007,"publication_date":"2007-11-26","ids":{"openalex":"https://openalex.org/W2119512272","doi":"https://doi.org/10.1145/1376849.1376851","mag":"2119512272"},"language":"en","primary_location":{"id":"doi:10.1145/1376849.1376851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376849.1376851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th international workshop on Middleware for grid computing: held at the ACM/IFIP/USENIX 8th International Middleware Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062187807","display_name":"William M. Jones","orcid":"https://orcid.org/0000-0002-3796-6330"},"institutions":[{"id":"https://openalex.org/I189158971","display_name":"United States Naval Academy","ror":"https://ror.org/00znex860","country_code":"US","type":"education","lineage":["https://openalex.org/I1330347796","https://openalex.org/I189158971","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William M. Jones","raw_affiliation_strings":["United States Naval Academy, Annapolis, MD"],"affiliations":[{"raw_affiliation_string":"United States Naval Academy, Annapolis, MD","institution_ids":["https://openalex.org/I189158971"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062187807"],"corresponding_institution_ids":["https://openalex.org/I189158971"],"apc_list":null,"apc_paid":null,"fwci":1.0098,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80186228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7752623558044434},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6458843946456909},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.6160092949867249},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5959087610244751},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5285094380378723},{"id":"https://openalex.org/keywords/turnaround-time","display_name":"Turnaround time","score":0.5002336502075195},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.42185813188552856},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.41758620738983154},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.378586083650589},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1758366823196411},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10426199436187744},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.1038484275341034},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08525329828262329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752623558044434},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6458843946456909},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.6160092949867249},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5959087610244751},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5285094380378723},{"id":"https://openalex.org/C176553487","wikidata":"https://www.wikidata.org/wiki/Q7855819","display_name":"Turnaround time","level":2,"score":0.5002336502075195},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.42185813188552856},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.41758620738983154},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.378586083650589},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1758366823196411},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10426199436187744},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.1038484275341034},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08525329828262329},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.0},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1376849.1376851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376849.1376851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th international workshop on Middleware for grid computing: held at the ACM/IFIP/USENIX 8th International Middleware Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.8480","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.8480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.parl.clemson.edu/~wjones/papers/mgc2007.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5258918866","display_name":null,"funder_award_id":"NOOOI407WRZOI02","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1765050609","https://openalex.org/W1986400910","https://openalex.org/W2017838136","https://openalex.org/W2020990393","https://openalex.org/W2102336430","https://openalex.org/W2112168774","https://openalex.org/W2113052966","https://openalex.org/W2136277179","https://openalex.org/W2138358511","https://openalex.org/W2139250332","https://openalex.org/W2290831968","https://openalex.org/W3142050775","https://openalex.org/W4256312496","https://openalex.org/W4301762837"],"related_works":["https://openalex.org/W2941188264","https://openalex.org/W2159578300","https://openalex.org/W1949686329","https://openalex.org/W2368323020","https://openalex.org/W2281029826","https://openalex.org/W2035324862","https://openalex.org/W2138018478","https://openalex.org/W2547714048","https://openalex.org/W2188224146","https://openalex.org/W2151049026"],"abstract_inverted_index":{"Recent":[0],"research":[1,23],"in":[2,29,47,66],"multi-site":[3,39],"parallel":[4],"job":[5,11,18],"scheduling":[6,40,68],"leverages":[7],"user-provided":[8],"estimates":[9,31],"of":[10,27,50],"communication":[12],"characteristics":[13],"to":[14,78],"effectively":[15],"partition":[16],"the":[17,25,48],"across":[19],"multiple":[20],"clusters.":[21],"Previous":[22],"addressed":[24],"impact":[26],"inaccuracies":[28],"these":[30,44,54,63],"on":[32],"overall":[33],"system":[34],"performance":[35,83],"and":[36,84],"found":[37],"that":[38,70],"techniques":[41],"benefit":[42],"from":[43],"estimates,":[45],"even":[46],"presence":[49],"considerable":[51],"inaccuracy.":[52],"While":[53],"results":[55],"are":[56,59],"encouraging,":[57],"there":[58],"many":[60],"instances":[61],"where":[62],"errors":[64],"result":[65],"poor":[67],"decisions":[69],"cause":[71],"network":[72],"over-subscription.":[73],"This":[74],"situation":[75],"can":[76],"lead":[77],"significantly":[79],"degraded":[80],"application":[81],"runtime":[82],"turnaround":[85],"time.":[86]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
