{"id":"https://openalex.org/W2256629785","doi":"https://doi.org/10.14778/2824032.2824080","title":"Scaling spark in the real world","display_name":"Scaling spark in the real world","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2256629785","doi":"https://doi.org/10.14778/2824032.2824080","mag":"2256629785"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824080","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824080","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/A5073379366","display_name":"Michael Armbrust","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Michael Armbrust","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103417248","display_name":"Tathagata Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tathagata Das","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088886568","display_name":"A.R. Davidson","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Aaron Davidson","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035859","display_name":"Ali Ghodsi","orcid":"https://orcid.org/0000-0003-1866-246X"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Ghodsi","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028880316","display_name":"Andrew Or","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Or","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055061976","display_name":"Josh Rosen","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Josh Rosen","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041920173","display_name":"Ion Stoica","orcid":"https://orcid.org/0000-0002-5373-0088"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ion Stoica","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015907748","display_name":"Patrick Wendell","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Wendell","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000259060","display_name":"Reynold Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Reynold Xin","raw_affiliation_strings":["Databricks Inc"],"affiliations":[{"raw_affiliation_string":"Databricks Inc","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5073379366"],"corresponding_institution_ids":["https://openalex.org/I4401726825"],"apc_list":null,"apc_paid":null,"fwci":38.1408,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.99731721,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":"12","first_page":"1840","last_page":"1843"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9071517586708069},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6667174100875854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5428469777107239},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4858510196208954},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47012484073638916},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4655972421169281},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.45433834195137024},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4104361832141876},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.39980295300483704},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2365500032901764},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08705452084541321},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0810995101928711},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.07804733514785767},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.07306069135665894}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9071517586708069},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6667174100875854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5428469777107239},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4858510196208954},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47012484073638916},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4655972421169281},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.45433834195137024},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4104361832141876},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.39980295300483704},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2365500032901764},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08705452084541321},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0810995101928711},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07804733514785767},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.07306069135665894},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824080","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824080","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":[{"score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1448681276","https://openalex.org/W1976821017","https://openalex.org/W1989017925","https://openalex.org/W2002430341","https://openalex.org/W2013455564","https://openalex.org/W2018030107","https://openalex.org/W2038412523","https://openalex.org/W2100830825","https://openalex.org/W2131975293","https://openalex.org/W2170616854","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W4389670110","https://openalex.org/W2187546663","https://openalex.org/W2429057255","https://openalex.org/W148745890","https://openalex.org/W2611942503","https://openalex.org/W4315621326","https://openalex.org/W2899790217","https://openalex.org/W1576092969","https://openalex.org/W2598865957","https://openalex.org/W126953346"],"abstract_inverted_index":{"Apache":[0],"Spark":[1,37,65],"is":[2],"one":[3],"of":[4,24,42,70],"the":[5,27,56,81],"most":[6],"widely":[7],"used":[8],"open":[9],"source":[10],"processing":[11],"engines":[12],"for":[13],"big":[14],"data,":[15],"with":[16],"rich":[17],"language-integrated":[18],"APIs":[19],"and":[20,59,72,74],"a":[21,39,67],"wide":[22,40,68],"range":[23,41],"libraries.":[25],"Over":[26],"past":[28],"two":[29],"years,":[30],"our":[31,50],"group":[32],"has":[33],"worked":[34],"to":[35,38,66,80],"deploy":[36],"organizations":[43],"through":[44],"consulting":[45],"relationships":[46],"as":[47,49],"well":[48],"hosted":[51],"service,":[52],"Databricks.":[53],"We":[54],"describe":[55],"main":[57],"challenges":[58],"requirements":[60],"that":[61],"appeared":[62],"in":[63,83],"taking":[64],"set":[69],"users,":[71],"usability":[73],"performance":[75],"improvements":[76],"we":[77],"have":[78],"made":[79],"engine":[82],"response.":[84]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
