{"id":"https://openalex.org/W2129055634","doi":"https://doi.org/10.14778/1453856.1453960","title":"Scheduling shared scans of large data files","display_name":"Scheduling shared scans of large data files","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2129055634","doi":"https://doi.org/10.14778/1453856.1453960","mag":"2129055634"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453960","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453960","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5075956031","display_name":"Parag Agrawal","orcid":"https://orcid.org/0009-0005-0759-8484"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Parag Agrawal","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431144","display_name":"Daniel Kifer","orcid":"https://orcid.org/0000-0002-4611-7066"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Daniel Kifer","raw_affiliation_strings":["Yahoo! Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881550","display_name":"Christopher Olston","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Christopher Olston","raw_affiliation_strings":["Yahoo! Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075956031"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":7.6233,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.97404641,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"958","last_page":"969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8351290225982666},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7227541208267212},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5772857069969177},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.5357531309127808},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.501929521560669},{"id":"https://openalex.org/keywords/time-sharing","display_name":"Time-sharing","score":0.47304266691207886},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.4336188733577728},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34289854764938354},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2328965663909912},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.10460937023162842},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.08432480692863464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351290225982666},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7227541208267212},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5772857069969177},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.5357531309127808},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.501929521560669},{"id":"https://openalex.org/C38725249","wikidata":"https://www.wikidata.org/wiki/Q913876","display_name":"Time-sharing","level":2,"score":0.47304266691207886},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.4336188733577728},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34289854764938354},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2328965663909912},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10460937023162842},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.08432480692863464},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1453856.1453960","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453960","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.861","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~olston/publications/vldb08a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5600000023841858,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W49387520","https://openalex.org/W1501066815","https://openalex.org/W1968447145","https://openalex.org/W1984302977","https://openalex.org/W2016555341","https://openalex.org/W2056099894","https://openalex.org/W2098959416","https://openalex.org/W2100099053","https://openalex.org/W2100830825","https://openalex.org/W2112312025","https://openalex.org/W2115299891","https://openalex.org/W2117876074","https://openalex.org/W2118049966","https://openalex.org/W2118328307","https://openalex.org/W2120684426","https://openalex.org/W2130622824","https://openalex.org/W2173213060","https://openalex.org/W2561675875","https://openalex.org/W2743045177","https://openalex.org/W4211017838"],"related_works":["https://openalex.org/W1551794236","https://openalex.org/W2123989238","https://openalex.org/W2141653733","https://openalex.org/W2195904091","https://openalex.org/W2060624625","https://openalex.org/W44553394","https://openalex.org/W3043302551","https://openalex.org/W3138769541","https://openalex.org/W1904492679","https://openalex.org/W1576430908"],"abstract_inverted_index":{"We":[0,105,161],"study":[1],"how":[2],"best":[3],"to":[4,18,27,115,133,158],"schedule":[5,134],"scans":[6,38,136],"of":[7,14,22,32,39,69,73,75,83,101,110,138,152],"large":[8],"data":[9,61],"files,":[10,35],"in":[11,59,98],"the":[12,29,40,99,123,149],"presence":[13,100],"many":[15],"simultaneous":[16],"requests":[17,77],"a":[19,80,107],"common":[20],"set":[21,82],"files.":[23,84],"The":[24],"objective":[25],"is":[26,131,156],"maximize":[28],"overall":[30],"rate":[31,151],"processing":[33,62,76],"these":[34],"by":[36],"sharing":[37,103],"same":[41],"file":[42],"as":[43,45,65,92],"aggressively":[44],"possible,":[46],"without":[47],"imposing":[48],"undue":[49],"wait":[50],"time":[51],"on":[52],"individual":[53],"jobs.":[54],"This":[55],"scheduling":[56,89,111,119,181],"problem":[57],"arises":[58],"batch":[60],"environments":[63],"such":[64,91],"Map-Reduce":[66],"systems,":[67],"some":[68],"which":[70],"handle":[71],"tens":[72],"thousands":[74],"daily,":[78],"over":[79,167],"shared":[81],"As":[85],"we":[86],"demonstrate,":[87],"conventional":[88,180],"techniques":[90],"shortest-job-first":[93],"do":[94],"not":[95],"perform":[96],"well":[97],"cross-job":[102],"opportunities.":[104],"derive":[106],"new":[108],"family":[109],"policies":[112,120,164],"specifically":[113],"targeted":[114],"sharable":[116,153],"workloads.":[117],"Our":[118],"revolve":[121],"around":[122],"notion":[124],"that,":[125],"all":[126],"else":[127],"being":[128],"equal,":[129],"it":[130],"good":[132],"nonsharable":[135],"ahead":[137],"ones":[139],"that":[140],"can":[141],"share":[142],"IO":[143],"work":[144],"with":[145,179],"future":[146,154],"jobs,":[147],"if":[148],"arrival":[150],"jobs":[155],"expected":[157],"be":[159],"high.":[160],"evaluate":[162],"our":[163],"via":[165],"simulation":[166],"varied":[168],"synthetic":[169],"and":[170,173],"real":[171],"workloads,":[172],"demonstrate":[174],"significant":[175],"performance":[176],"gains":[177],"compared":[178],"approaches.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
