{"id":"https://openalex.org/W2001708197","doi":"https://doi.org/10.1145/1967422.1967427","title":"Optimizing intermediate data management in MapReduce computations","display_name":"Optimizing intermediate data management in MapReduce computations","publication_year":2011,"publication_date":"2011-04-10","ids":{"openalex":"https://openalex.org/W2001708197","doi":"https://doi.org/10.1145/1967422.1967427","mag":"2001708197"},"language":"en","primary_location":{"id":"doi:10.1145/1967422.1967427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1967422.1967427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Cloud Computing Platforms","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00574351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064457907","display_name":"Diana Moise","orcid":null},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Diana Moise","raw_affiliation_strings":["INRIA Rennes - Bretagne Atlantique/IRISA","INRIA Rennes - Bretagne Atlantique/IRISA#TAB#"],"affiliations":[{"raw_affiliation_string":"INRIA Rennes - Bretagne Atlantique/IRISA","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I2802519937","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Rennes - Bretagne Atlantique/IRISA#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004602856","display_name":"Thi-Thu-Lan Trieu","orcid":null},"institutions":[{"id":"https://openalex.org/I11559806","display_name":"\u00c9cole Normale Sup\u00e9rieure Paris-Saclay","ror":"https://ror.org/00hx6zz33","country_code":"FR","type":"education","lineage":["https://openalex.org/I11559806","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thi-Thu-Lan Trieu","raw_affiliation_strings":["ENS Cachan, Brittany/IRISA","ENS Cachan/Brittany, IRISA"],"affiliations":[{"raw_affiliation_string":"ENS Cachan, Brittany/IRISA","institution_ids":["https://openalex.org/I11559806","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"ENS Cachan/Brittany, IRISA","institution_ids":["https://openalex.org/I11559806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020271777","display_name":"Luc Boug\u00e9","orcid":"https://orcid.org/0000-0002-5510-4443"},"institutions":[{"id":"https://openalex.org/I11559806","display_name":"\u00c9cole Normale Sup\u00e9rieure Paris-Saclay","ror":"https://ror.org/00hx6zz33","country_code":"FR","type":"education","lineage":["https://openalex.org/I11559806","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Luc Boug\u00e9","raw_affiliation_strings":["ENS Cachan, Brittany/IRISA","ENS Cachan/Brittany, IRISA"],"affiliations":[{"raw_affiliation_string":"ENS Cachan, Brittany/IRISA","institution_ids":["https://openalex.org/I11559806","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"ENS Cachan/Brittany, IRISA","institution_ids":["https://openalex.org/I11559806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077818565","display_name":"Gabriel Antoniu","orcid":"https://orcid.org/0000-0001-6525-3736"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gabriel Antoniu","raw_affiliation_strings":["INRIA Rennes - Bretagne Atlantique/IRISA","INRIA Rennes - Bretagne Atlantique/IRISA#TAB#"],"affiliations":[{"raw_affiliation_string":"INRIA Rennes - Bretagne Atlantique/IRISA","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I2802519937","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Rennes - Bretagne Atlantique/IRISA#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064457907"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I4210133778"],"apc_list":null,"apc_paid":null,"fwci":7.6384,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96786959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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/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":0.8930322527885437},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6649043560028076},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.649834930896759},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6273918151855469},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4651058614253998},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.44650202989578247},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.43929582834243774},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.43724238872528076},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4201376438140869},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38969895243644714},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3724434971809387},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2858656346797943},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0925382673740387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8930322527885437},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6649043560028076},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.649834930896759},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6273918151855469},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4651058614253998},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.44650202989578247},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.43929582834243774},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.43724238872528076},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4201376438140869},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38969895243644714},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3724434971809387},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2858656346797943},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0925382673740387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1967422.1967427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1967422.1967427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Cloud Computing Platforms","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.220.4266","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.4266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/57/43/51/PDF/main.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.824.9897","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.824.9897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/inria-00574351/document/","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00574351v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00574351","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CloudCP 2011 -- 1st International Workshop on Cloud Computing Platforms, Held in conjunction with the ACM SIGOPS Eurosys 11 conference, Apr 2011, Salzburg, Austria","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00574351v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00574351","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CloudCP 2011 -- 1st International Workshop on Cloud Computing Platforms, Held in conjunction with the ACM SIGOPS Eurosys 11 conference, Apr 2011, Salzburg, Austria","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W193620207","https://openalex.org/W1968075755","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2111364199","https://openalex.org/W2119738171","https://openalex.org/W2154655801","https://openalex.org/W2173213060","https://openalex.org/W6607999007"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2338718585","https://openalex.org/W3147391527"],"abstract_inverted_index":{"Many":[0],"cloud":[1,30],"computations":[2],"process":[3],"large":[4,196],"datasets.":[5],"Programming":[6],"paradigms":[7],"have":[8],"been":[9],"proposed":[10],"to":[11,19,37,46,95,127,156],"design":[12],"this":[13,92,132,162,189],"type":[14],"of":[15,22,70,83,91,106,110,116,177,185,198,200,218],"applications,":[16],"so":[17,226],"as":[18,165,180],"take":[20],"advantage":[21],"the":[23,29,34,39,55,62,68,80,84,104,108,114,120,123,128,145,152,158,174,178,182,201,228],"huge":[24],"processing":[25],"and":[26,44,58,77,87],"storage":[27,98,141,176],"options":[28],"holds,":[31],"but":[32,220],"at":[33],"same":[35],"time,":[36],"provide":[38],"user":[40],"with":[41,103],"a":[42,97,137,166,195],"clean":[43],"easy":[45],"use":[47],"interface.":[48],"Among":[49],"these":[50],"programming":[51],"models,":[52],"we":[53,134,191],"consider":[54],"MapReduce":[56,111,154],"paradigm":[57],"its":[59],"reference":[60],"implementation,":[61],"Hadoop":[63,153],"framework.":[64],"We":[65,150,204],"focus":[66],"on":[67,122,136,144,194],"aspect":[69],"intermediate":[71,101,159,213],"data,":[72],"that":[73,206,227],"is":[74,94,233],"data":[75,102,140,147,160,214],"produced":[76],"transferred":[78],"between":[79],"two":[81],"stages":[82],"computation":[85],"(map":[86],"reduce).":[88],"The":[89],"goal":[90],"paper":[93],"propose":[96],"mechanism":[99],"for":[100,212],"purpose":[105],"optimizing":[107],"execution":[109],"applications":[112],"in":[113,161,181,216],"presence":[115],"failures,":[117,219],"while":[118],"keeping":[119],"impact":[121],"job":[124,230],"completion":[125,231],"time":[126,232],"minimum.":[129],"To":[130,187],"meet":[131],"goal,":[133],"rely":[135],"fault-tolerant,":[138],"concurrency-optimized":[139],"layer":[142,163],"based":[143],"BlobSeer":[146],"management":[148],"service.":[149],"modify":[151],"framework":[155],"store":[157],"(acting":[164],"BlobSeer-based":[167],"distributed":[168],"file":[169],"system)":[170],"rather":[171],"than":[172],"using":[173],"local":[175],"mappers,":[179],"vanilla":[183],"version":[184],"Hadoop.":[186],"validate":[188],"work,":[190],"perform":[192],"experiments":[193],"number":[197],"nodes":[199],"Grid'5000":[202],"testbed.":[203],"demonstrate":[205],"our":[207],"approach":[208],"not":[209],"only":[210],"provides":[211],"availability":[215],"case":[217],"also":[221],"efficiently":[222],"handles":[223],"read/write":[224],"accesses":[225],"overall":[229],"substantially":[234],"improved.":[235]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}