{"id":"https://openalex.org/W3198638494","doi":"https://doi.org/10.14778/3476311.3476388","title":"SparkCruise","display_name":"SparkCruise","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3198638494","doi":"https://doi.org/10.14778/3476311.3476388","mag":"3198638494"},"language":"en","primary_location":{"id":"doi:10.14778/3476311.3476388","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476388","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/A5102756987","display_name":"Abhishek Roy","orcid":"https://orcid.org/0009-0002-3569-7621"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abhishek Roy","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079846990","display_name":"Alekh Jindal","orcid":"https://orcid.org/0000-0001-8844-8165"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alekh Jindal","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067305697","display_name":"Priyanka Gomatam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Priyanka Gomatam","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022611095","display_name":"Xiating Ouyang","orcid":"https://orcid.org/0000-0001-5214-4688"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiating Ouyang","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062222915","display_name":"Ashit Gosalia","orcid":"https://orcid.org/0009-0003-7939-6692"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashit Gosalia","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112524865","display_name":"Nishkam Ravi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nishkam Ravi","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080077704","display_name":"Swinky Mann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Swinky Mann","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101072855","display_name":"Prakhar Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prakhar Jain","raw_affiliation_strings":["Databricks"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3859,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85487801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"12","first_page":"3122","last_page":"3134"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987999796867371,"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/T11106","display_name":"Data Management and Algorithms","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/spark","display_name":"SPARK (programming language)","score":0.8671435713768005},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.8635515570640564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8390015363693237},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6815071702003479},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6348385214805603},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5338256359100342},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4288378357887268},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.42849424481391907},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39257514476776123},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3720465898513794},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28400224447250366}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8671435713768005},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.8635515570640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390015363693237},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6815071702003479},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6348385214805603},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5338256359100342},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4288378357887268},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.42849424481391907},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39257514476776123},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3720465898513794},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28400224447250366},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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":1,"locations":[{"id":"doi:10.14778/3476311.3476388","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476388","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2038412523","https://openalex.org/W2119400430","https://openalex.org/W2139072600","https://openalex.org/W2139135093","https://openalex.org/W2189465200","https://openalex.org/W2766000922","https://openalex.org/W2799060872","https://openalex.org/W2799237774","https://openalex.org/W2911540814","https://openalex.org/W2913631065","https://openalex.org/W2970373351","https://openalex.org/W2985275869","https://openalex.org/W3005908620","https://openalex.org/W3007706798","https://openalex.org/W3028867501","https://openalex.org/W3030387435","https://openalex.org/W3032560301","https://openalex.org/W3086150815","https://openalex.org/W3176550827"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2558523485","https://openalex.org/W4379407450","https://openalex.org/W2408437972","https://openalex.org/W2905107896","https://openalex.org/W3191926225"],"abstract_inverted_index":{"Today":[0],"cloud":[1,31],"companies":[2],"offer":[3],"fully":[4],"managed":[5],"Spark":[6,68,82,138,168],"services.":[7],"This":[8],"has":[9,18],"made":[10],"it":[11,87],"easy":[12],"to":[13,40,66,78,88,101,161],"onboard":[14],"new":[15],"customers":[16],"but":[17],"also":[19,131],"increased":[20],"the":[21,36,67,90,94,108,133,144,151,158,163],"volume":[22],"of":[23,110,136,147,153,165],"users":[24,34],"and":[25,33,38,56,80,85,112,140],"their":[26],"workload":[27,58,124],"sizes.":[28],"However,":[29],"both":[30],"providers":[32],"lack":[35],"tools":[37],"time":[39],"optimize":[41,57],"these":[42],"massive":[43],"workloads.":[44,170],"To":[45,150],"solve":[46],"this":[47,72,156],"problem,":[48],"we":[49,74],"designed":[50],"SparkCruise":[51],"that":[52],"can":[53],"help":[54],"understand":[55],"instances":[59],"by":[60],"adding":[61],"a":[62],"workload-driven":[63],"feedback":[64,115],"loop":[65],"query":[69,83],"optimizer.":[70],"In":[71],"paper,":[73],"present":[75],"our":[76,154],"approach":[77],"collecting":[79],"representing":[81],"workloads":[84,111,139],"use":[86],"improve":[89],"overall":[91],"performance":[92],"on":[93],"workload,":[95],"all":[96],"without":[97],"requiring":[98],"any":[99],"access":[100],"user":[102],"data.":[103],"These":[104],"methods":[105],"scale":[106],"with":[107,143],"number":[109],"apply":[113],"learned":[114],"in":[116],"an":[117],"online":[118],"fashion.":[119],"We":[120,130],"explain":[121],"one":[122],"specific":[123],"optimization":[125],"developed":[126],"for":[127],"computation":[128],"reuse.":[129],"share":[132,162],"detailed":[134],"analysis":[135,146,164],"production":[137,167],"contrast":[141],"them":[142],"corresponding":[145],"TPC-DS":[148],"benchmark.":[149],"best":[152],"knowledge,":[155],"is":[157],"first":[159],"study":[160],"large-scale":[166],"SQL":[169]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-09-13T00:00:00"}