{"id":"https://openalex.org/W2612649873","doi":"https://doi.org/10.1109/icde.2017.243","title":"Too Big to Eat: Boosting Analytics Data Ingestion from Object Stores with Scoop","display_name":"Too Big to Eat: Boosting Analytics Data Ingestion from Object Stores with Scoop","publication_year":2017,"publication_date":"2017-04-01","ids":{"openalex":"https://openalex.org/W2612649873","doi":"https://doi.org/10.1109/icde.2017.243","mag":"2612649873"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2017.243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5041553664","display_name":"Yosef Moatti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yosef Moatti","raw_affiliation_strings":["IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071262565","display_name":"Eran Rom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eran Rom","raw_affiliation_strings":["OpenStack Storlets Project"],"affiliations":[{"raw_affiliation_string":"OpenStack Storlets Project","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003865074","display_name":"Ra\u00fal Gracia-Tinedo","orcid":"https://orcid.org/0000-0003-1842-2976"},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universidad Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Raul Gracia-Tinedo","raw_affiliation_strings":["Universitat Rovira i Virgili, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Rovira i Virgili, Spain","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026549255","display_name":"Dalit Naor","orcid":"https://orcid.org/0009-0007-9628-312X"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dalit Naor","raw_affiliation_strings":["IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083581863","display_name":"Doron Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Doron Chen","raw_affiliation_strings":["IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084645226","display_name":"Josep Samp\u00e9","orcid":"https://orcid.org/0000-0002-6869-9765"},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universidad Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Sampe","raw_affiliation_strings":["Universitat Rovira i Virgili, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Rovira i Virgili, Spain","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023440534","display_name":"Marc S\u00e1nchez\u2010Artigas","orcid":"https://orcid.org/0000-0002-9700-7318"},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universidad Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marc Sanchez-Artigas","raw_affiliation_strings":["Universitat Rovira i Virgili, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Rovira i Virgili, Spain","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058391915","display_name":"Pedro Garc\u0131\u0301a-L\u00f3pez","orcid":"https://orcid.org/0000-0002-9848-1492"},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universidad Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pedro Garcia-Lopez","raw_affiliation_strings":["Universitat Rovira i Virgili, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Rovira i Virgili, Spain","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011970212","display_name":"Filip Gluszak","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Filip Gluszak","raw_affiliation_strings":["GridPocket, France"],"affiliations":[{"raw_affiliation_string":"GridPocket, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072410634","display_name":"Eric Deschdt","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Deschdt","raw_affiliation_strings":["GridPocket, France"],"affiliations":[{"raw_affiliation_string":"GridPocket, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414805","display_name":"Francesco Pace","orcid":"https://orcid.org/0000-0002-6560-5006"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Francesco Pace","raw_affiliation_strings":["Eurecom, France"],"affiliations":[{"raw_affiliation_string":"Eurecom, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054943182","display_name":"Daniele Venzano","orcid":"https://orcid.org/0000-0001-5381-5121"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Daniele Venzano","raw_affiliation_strings":["Eurecom, France"],"affiliations":[{"raw_affiliation_string":"Eurecom, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017009335","display_name":"Pietro Michiardi","orcid":"https://orcid.org/0000-0003-4675-7677"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pietro Michiardi","raw_affiliation_strings":["Eurecom, France"],"affiliations":[{"raw_affiliation_string":"Eurecom, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.655,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.77712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":83,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Big Data Technologies","score":0.9989,"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 Big Data Technologies","score":0.9989,"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":"Distributed Storage Systems and Network Coding","score":0.9914,"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/T10273","display_name":"Internet of Things and Edge Computing","score":0.9907,"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/scoop","display_name":"SCOOP","score":0.9577265},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5233982},{"id":"https://openalex.org/keywords/distributed-storage","display_name":"Distributed Storage","score":0.50329},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.503055}],"concepts":[{"id":"https://openalex.org/C2779427698","wikidata":"https://www.wikidata.org/wiki/Q17146793","display_name":"SCOOP","level":2,"score":0.9577265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85770607},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6753231},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6407158},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5233982},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.47617215},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44649425},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4171247},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32059008},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08248934}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2017.243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W1519276763","https://openalex.org/W1540606052","https://openalex.org/W1575777113","https://openalex.org/W16186195","https://openalex.org/W1990084070","https://openalex.org/W1990240141","https://openalex.org/W2020105227","https://openalex.org/W2033610982","https://openalex.org/W2038412523","https://openalex.org/W2063499922","https://openalex.org/W2098638772","https://openalex.org/W2112485457","https://openalex.org/W2117734592","https://openalex.org/W2120989660","https://openalex.org/W2124256298","https://openalex.org/W2127861928","https://openalex.org/W2131975293","https://openalex.org/W2153889808","https://openalex.org/W2159761515","https://openalex.org/W2160967997","https://openalex.org/W2177227417","https://openalex.org/W2215904967","https://openalex.org/W2274638528","https://openalex.org/W2335452449","https://openalex.org/W2578298407","https://openalex.org/W2604940315","https://openalex.org/W848570255"],"related_works":["https://openalex.org/W4379407450","https://openalex.org/W4252667786","https://openalex.org/W3191926225","https://openalex.org/W2905107896","https://openalex.org/W2895375519","https://openalex.org/W2558523485","https://openalex.org/W2408437972","https://openalex.org/W2398226711","https://openalex.org/W2209833712","https://openalex.org/W1864929253"],"abstract_inverted_index":{"Extracting":[0],"value":[1],"from":[2,42,69,152],"data":[3,41,127,148],"stored":[4],"in":[5,25,128,142],"object":[6,44,109],"stores,such":[7],"as":[8],"OpenStack":[9],"Swift":[10],"and":[11,22,55,95,106,149],"Amazon":[12],"S3,":[13],"can":[14],"be":[15,122],"problematicin":[16],"common":[17],"scenarios":[18],"where":[19],"analytics":[20,35,80,132],"frameworks":[21,36],"objectstores":[23,74],"run":[24],"physically":[26],"disaggregated":[27],"clusters.":[28],"One":[29],"of":[30,73,79,88,134],"the":[31,43,48,70,77,86,92,101,126],"mainproblems":[32],"is":[33],"that":[34],"must":[37],"ingest":[38],"large":[39],"amountsof":[40],"store":[45],"prior":[46],"to":[47,67,75,91,100,121,125,161],"actual":[49],"computation;this":[50],"incurs":[51],"a":[52,104,135,143],"significant":[53],"resources":[54,72],"performance":[56],"overhead.":[57],"Toovercome":[58],"this":[59],"problem,":[60],"we":[61],"present":[62],"Scoop.":[63],"Scoop":[64,82,114],"enables":[65,115],"analyticsframeworks":[66],"benefit":[68],"computational":[71],"optimize":[76],"execution":[78,158],"jobs.":[81],"achievesthis":[83],"by":[84,96],"enabling":[85],"addition":[87],"ETL-type":[89],"actions":[90],"dataupload":[93],"path":[94],"offloading":[97],"querying":[98],"functions":[99],"objectstore":[102],"through":[103],"rich":[105],"extensible":[107],"active":[108],"storage":[110],"layer.":[111],"Asa":[112],"proof-of-concept,":[113],"Apache":[116],"Spark":[117],"SQL":[118,150],"selectionsand":[119],"projections":[120],"executed":[123],"close":[124],"OpenStackSwift":[129],"for":[130],"accelerating":[131],"workloads":[133],"smart":[136],"energy":[137],"gridcompany":[138],"(GridPocket).":[139],"Our":[140],"experiments":[141],"63-machine":[144],"clusterwith":[145],"real":[146],"IoT":[147],"queries":[151],"GridPocket":[153],"show":[154],"thatScoop":[155],"exhibits":[156],"query":[157],"times":[159],"up":[160],"30x":[162],"faster":[163],"than":[164],"thetraditional":[165],"\"ingest-then-compute\"":[166],"approach.":[167]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2612649873","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2024-10-11T09:18:50.544910","created_date":"2017-05-19"}
