{"id":"https://openalex.org/W2048957547","doi":"https://doi.org/10.1145/2518017.2518019","title":"Performance Modeling and Optimization of Deadline-Driven Pig Programs","display_name":"Performance Modeling and Optimization of Deadline-Driven Pig Programs","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2048957547","doi":"https://doi.org/10.1145/2518017.2518019","mag":"2048957547"},"language":"en","primary_location":{"id":"doi:10.1145/2518017.2518019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2518017.2518019","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"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":"ACM Transactions on Autonomous and Adaptive Systems","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/A5011774662","display_name":"Zhuoyao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoyao Zhang","raw_affiliation_strings":["HP Labs and University of Pennsylvania","HP Labs and University of Pennsylvania#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs and University of Pennsylvania","institution_ids":["https://openalex.org/I1324840837","https://openalex.org/I79576946"]},{"raw_affiliation_string":"HP Labs and University of Pennsylvania#TAB#","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016669578","display_name":"Ludmila Cherkasova","orcid":"https://orcid.org/0000-0002-9333-4901"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludmila Cherkasova","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090056582","display_name":"Abhishek Verma","orcid":"https://orcid.org/0000-0002-0491-178X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Verma","raw_affiliation_strings":["HP Labs and University of Illinois at Urbana-Champaign","HP Labs and University of Illinois at Urbana-Champaign#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs and University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"HP Labs and University of Illinois at Urbana-Champaign#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090052860","display_name":"Boon Thau Loo","orcid":"https://orcid.org/0000-0002-4757-1746"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boon Thau Loo","raw_affiliation_strings":["University of Pennsylvania","#N# * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]},{"raw_affiliation_string":"#N# * University of Pennsylvania","institution_ids":["https://openalex.org/I36788626","https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.461,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9676844,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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/T12127","display_name":"Software System Performance and Reliability","score":0.991100013256073,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9904999732971191,"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":0.9201257228851318},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.592094361782074},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4640219807624817},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43103542923927307},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4155266284942627},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3187951445579529},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2800436317920685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9201257228851318},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.592094361782074},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4640219807624817},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43103542923927307},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4155266284942627},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3187951445579529},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2800436317920685},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2518017.2518019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2518017.2518019","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"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":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.431.4146","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.431.4146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Lucy_Cherkasova/papers/Pig-TAAS-cr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G1950092492","display_name":null,"funder_award_id":"CNS-1117185, CNS-0845552, IIS-0812270, CCF-0964471","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G3366251988","display_name":null,"funder_award_id":"CNS-1117185, CNS-0845552, IIS-0812270, CCF-0964471","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G8947014938","display_name":null,"funder_award_id":"CNS-1117185, CNS-0845552, IIS-0812270, CCF-0964471","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W137316345","https://openalex.org/W1834532152","https://openalex.org/W2002472616","https://openalex.org/W2017194553","https://openalex.org/W2024085737","https://openalex.org/W2058047606","https://openalex.org/W2100830825","https://openalex.org/W2110086534","https://openalex.org/W2112013978","https://openalex.org/W2119208045","https://openalex.org/W2119400430","https://openalex.org/W2123537546","https://openalex.org/W2138440835","https://openalex.org/W2142031898","https://openalex.org/W2173213060","https://openalex.org/W2294316975","https://openalex.org/W2336006182","https://openalex.org/W2911595481","https://openalex.org/W4239429564"],"related_works":["https://openalex.org/W2893716391","https://openalex.org/W3189604146","https://openalex.org/W2166247150","https://openalex.org/W4243252198","https://openalex.org/W3216885170","https://openalex.org/W2118300983","https://openalex.org/W2112962394","https://openalex.org/W3137189469","https://openalex.org/W4235530921","https://openalex.org/W3160136729"],"abstract_inverted_index":{"Many":[0],"applications":[1,35],"associated":[2],"with":[3,145,207,260,276],"live":[4],"business":[5],"intelligence":[6],"are":[7,182],"written":[8],"as":[9,120,173],"complex":[10],"data":[11,66],"analysis":[12,76],"programs":[13,94,259],"defined":[14,172],"by":[15,196],"directed":[16],"acyclic":[17],"graphs":[18],"of":[19,33,60,72,82,116,123,130,134,176,185,201,227,294,306],"MapReduce":[20,61,84,177],"jobs,":[21,209],"for":[22,39,63,78,92,140,166,243,257],"example,":[23],"using":[24,285],"Pig,":[25],"Hive,":[26],"or":[27],"Scope":[28],"frameworks.":[29],"An":[30],"increasing":[31],"number":[32,133],"these":[34,249],"have":[36],"additional":[37],"requirements":[38],"completion":[40,114,160,180,216],"time":[41,115,161],"guarantees.":[42],"In":[43],"this":[44,210],"article,":[45],"we":[46,151,190,251],"consider":[47],"the":[48,100,107,113,128,186,198,214,232,277],"popular":[49],"Pig":[50,93,118,143,168,193,233,244,258],"framework":[51],"that":[52,95,157,170],"provides":[53],"a":[54,70,88,117,121,142,146,153,167,174,192,238,253,286,291,304],"high-level":[55],"SQL-like":[56],"abstraction":[57],"on":[58,248],"top":[59],"engine":[62],"processing":[64],"large":[65],"sets.":[67],"There":[68],"is":[69,171],"lack":[71],"performance":[73,80,89,155,241,255],"models":[74],"and":[75,103,136,162,235,290,300],"tools":[77],"automated":[79],"management":[81],"such":[83],"jobs.":[85,204,262],"We":[86,281],"offer":[87],"modeling":[90],"environment":[91],"automatically":[96],"profiles":[97],"jobs":[98],"from":[99],"past":[101],"runs":[102],"aims":[104],"to":[105,267],"solve":[106],"following":[108],"inter-related":[109],"problems:":[110],"(i)":[111],"estimating":[112,127],"program":[119,144,169,194,215],"function":[122],"allocated":[124],"resources;":[125],"(ii)":[126],"amount":[129],"resources":[131],"(a":[132],"map":[135],"reduce":[137],"slots)":[138],"required":[139,163],"completing":[141],"given":[147],"(soft)":[148],"deadline.":[149],"First,":[150],"design":[152],"basic":[154],"model":[156,242,256],"accurately":[158],"predicts":[159],"resource":[164,269],"allocation":[165],"sequence":[175],"jobs:":[178],"predicted":[179],"times":[181],"within":[183],"10%":[184],"measured":[187],"ones.":[188],"Second,":[189],"optimize":[191],"execution":[195,230],"enforcing":[197],"optimal":[199],"schedule":[200],"its":[202],"concurrent":[203,208,228,261],"For":[205],"DAGs":[206],"optimization":[211],"helps":[212],"reducing":[213],"time:":[217],"10%--27%":[218],"in":[219,231,272],"our":[220,273,283],"experiments.":[221],"Moreover,":[222],"it":[223],"eliminates":[224],"possible":[225],"nondeterminism":[226],"jobs\u2019":[229],"program,":[234],"therefore,":[236],"enables":[237],"more":[239],"accurate":[240],"programs.":[245],"Third,":[246],"based":[247],"optimizations,":[250],"propose":[252],"refined":[254],"The":[263],"proposed":[264],"approach":[265],"leads":[266],"significant":[268],"savings":[270],"(20%--60%":[271],"experiments)":[274],"compared":[275],"original,":[278],"unoptimized":[279],"solution.":[280],"validate":[282],"solution":[284],"66-node":[287],"Hadoop":[288],"cluster":[289],"diverse":[292],"set":[293],"workloads:":[295],"PigMix":[296],"benchmark,":[297],"TPC-H":[298],"queries,":[299],"customized":[301],"queries":[302],"mining":[303],"collection":[305],"HP":[307],"Labs\u2019":[308],"web":[309],"proxy":[310],"logs.":[311]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
