{"id":"https://openalex.org/W2783759858","doi":"https://doi.org/10.1109/bigdata.2017.8258066","title":"A comparative analysis of state-of-the-art SQL-on-Hadoop systems for interactive analytics","display_name":"A comparative analysis of state-of-the-art SQL-on-Hadoop systems for interactive analytics","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783759858","doi":"https://doi.org/10.1109/bigdata.2017.8258066","mag":"2783759858"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.00224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038482926","display_name":"Ashish Tapdiya","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashish Tapdiya","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University,#TAB#"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University,#TAB#","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029954233","display_name":"Daniel Fabbri","orcid":"https://orcid.org/0000-0003-0530-2510"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fabbri","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University,#TAB#"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University,#TAB#","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038482926"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26632886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1349","last_page":"1356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.995199978351593,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/sql","display_name":"SQL","score":0.8386054039001465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8381592035293579},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6560310125350952},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5875782370567322},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5717208385467529},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.541689395904541},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49091798067092896},{"id":"https://openalex.org/keywords/stored-procedure","display_name":"Stored procedure","score":0.48055341839790344},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.47180047631263733},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4438445270061493},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.43038231134414673},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.39284396171569824},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19006970524787903},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1796313226222992},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.11425316333770752},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.09425511956214905}],"concepts":[{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.8386054039001465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381592035293579},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6560310125350952},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5875782370567322},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5717208385467529},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.541689395904541},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49091798067092896},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.48055341839790344},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.47180047631263733},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4438445270061493},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.43038231134414673},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.39284396171569824},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19006970524787903},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1796313226222992},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.11425316333770752},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.09425511956214905},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bigdata.2017.8258066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.00224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00224","pdf_url":"https://arxiv.org/pdf/1804.00224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2783759858","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.00224v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.00224","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.00224","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.00224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00224","pdf_url":"https://arxiv.org/pdf/1804.00224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2783759858.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1569570229","https://openalex.org/W1605782097","https://openalex.org/W1746258828","https://openalex.org/W2038412523","https://openalex.org/W2074935284","https://openalex.org/W2097484305","https://openalex.org/W2106625078","https://openalex.org/W2110086534","https://openalex.org/W2114303224","https://openalex.org/W2123866731","https://openalex.org/W2124851765","https://openalex.org/W2139072600","https://openalex.org/W2171094780","https://openalex.org/W2173213060","https://openalex.org/W2190012392","https://openalex.org/W2221398285","https://openalex.org/W2265297126","https://openalex.org/W2394680079","https://openalex.org/W6637806892","https://openalex.org/W6687322159","https://openalex.org/W6712120708"],"related_works":["https://openalex.org/W2963965822","https://openalex.org/W2106625078","https://openalex.org/W3018396859","https://openalex.org/W3004375626","https://openalex.org/W2029536873","https://openalex.org/W2433128352","https://openalex.org/W2087177601","https://openalex.org/W2946366829","https://openalex.org/W2756536429","https://openalex.org/W2407924219","https://openalex.org/W2889447213","https://openalex.org/W2618045710","https://openalex.org/W2108510805","https://openalex.org/W2783620457","https://openalex.org/W2079955672","https://openalex.org/W2580992973","https://openalex.org/W2016829627","https://openalex.org/W28784159","https://openalex.org/W2229578264","https://openalex.org/W2242303434"],"abstract_inverted_index":{"Hadoop":[0],"is":[1],"emerging":[2],"as":[3],"the":[4,13,25,39,44,80,87,91,109,115,135],"primary":[5],"data":[6,18],"hub":[7],"in":[8,35,108,114],"enterprises,":[9],"and":[10,55,77,86,146],"SQL":[11,76],"represents":[12],"de":[14],"facto":[15],"language":[16],"for":[17],"analysis.":[19],"This":[20],"combination":[21],"has":[22],"led":[23],"to":[24,138],"development":[26],"of":[27,30,47,68,125,130],"a":[28,65],"variety":[29],"SQL-on-Hadoop":[31,41,71],"systems":[32,42,72,106],"that":[33],"are":[34],"use":[36],"today.":[37],"While":[38],"various":[40],"target":[43],"same":[45],"class":[46],"analytical":[48],"workloads,":[49],"their":[50],"different":[51],"architectures,":[52],"design":[53],"decisions":[54],"implementations":[56],"impact":[57],"query":[58,147],"performance.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"perform":[64],"comparative":[66],"analysis":[67,129],"four":[69],"state-of-the-art":[70],"(Impala,":[73],"Drill,":[74],"Spark":[75],"Phoenix)":[78],"using":[79],"Web":[81],"Data":[82],"Analytics":[83],"micro":[84],"benchmark":[85,89],"TPC-H":[88,97],"on":[90,123],"Amazon":[92],"EC2":[93],"cloud":[94],"platform.":[95],"The":[96],"experiment":[98],"results":[99,137],"show":[100],"that,":[101],"although":[102],"Impala":[103],"outperforms":[104],"other":[105],"(4.41x-6.65x)":[107],"text":[110],"format,":[111,117],"trade-offs":[112],"exists":[113],"parquet":[116],"with":[118],"each":[119],"system":[120],"performing":[121],"best":[122],"subsets":[124],"queries.":[126],"A":[127],"comprehensive":[128],"execution":[131,148],"profiles":[132],"expands":[133],"upon":[134],"performance":[136,142,144],"provide":[139],"insights":[140],"into":[141],"variations,":[143],"bottlenecks":[145],"characteristics.":[149]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}