{"id":"https://openalex.org/W2119528150","doi":"https://doi.org/10.1145/1807167.1807278","title":"Data warehousing and analytics infrastructure at facebook","display_name":"Data warehousing and analytics infrastructure at facebook","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2119528150","doi":"https://doi.org/10.1145/1807167.1807278","mag":"2119528150"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-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/A5086564678","display_name":"Ashish Thusoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashish Thusoo","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112120488","display_name":"Zheng Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Shao","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017926637","display_name":"Suresh Anthony","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suresh Anthony","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015429075","display_name":"Dhruba Borthakur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruba Borthakur","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059659735","display_name":"Namit Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Namit Jain","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027100524","display_name":"Joydeep Sen Sarma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joydeep Sen Sarma","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041172869","display_name":"Raghotham Murthy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghotham Murthy","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458888","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-3026-478X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Facebook, Palo Alto, CA, USA","Facebook, Palo Alto, CA., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Palo Alto, CA., USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5086564678"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":47.7203,"has_fulltext":false,"cited_by_count":433,"citation_normalized_percentile":{"value":0.9994071,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1013","last_page":"1020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615150809288025},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6816391944885254},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.6537207961082458},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6452546119689941},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6347478628158569},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.623156726360321},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5484583377838135},{"id":"https://openalex.org/keywords/business-analytics","display_name":"Business analytics","score":0.5132722854614258},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4297488331794739},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4255080223083496},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41442710161209106},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34252989292144775},{"id":"https://openalex.org/keywords/business-model","display_name":"Business model","score":0.18683314323425293},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1557658612728119},{"id":"https://openalex.org/keywords/electronic-business","display_name":"Electronic business","score":0.13072532415390015},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.09170177578926086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615150809288025},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6816391944885254},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.6537207961082458},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6452546119689941},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6347478628158569},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.623156726360321},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5484583377838135},{"id":"https://openalex.org/C37952496","wikidata":"https://www.wikidata.org/wiki/Q5001829","display_name":"Business analytics","level":4,"score":0.5132722854614258},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4297488331794739},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4255080223083496},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41442710161209106},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34252989292144775},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.18683314323425293},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1557658612728119},{"id":"https://openalex.org/C65257409","wikidata":"https://www.wikidata.org/wiki/Q734253","display_name":"Electronic business","level":3,"score":0.13072532415390015},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.09170177578926086},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1807167.1807278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W110612056","https://openalex.org/W1993892970","https://openalex.org/W2119565742","https://openalex.org/W2122465391","https://openalex.org/W2130642985","https://openalex.org/W2139274913","https://openalex.org/W4238584892"],"related_works":["https://openalex.org/W4367856707","https://openalex.org/W3068949829","https://openalex.org/W2048156096","https://openalex.org/W2107023905","https://openalex.org/W2150941767","https://openalex.org/W3033964479","https://openalex.org/W3123352720","https://openalex.org/W3130756120","https://openalex.org/W1490270786","https://openalex.org/W2782627424"],"abstract_inverted_index":{"Scalable":[0],"analysis":[1,28],"on":[2,51,86],"large":[3,53],"data":[4,30,54,166,174,185],"sets":[5],"has":[6],"been":[7],"core":[8],"to":[9,69,79,112,121,163],"the":[10,40,66,87,136,139,193,199,204],"functions":[11],"of":[12,15,29,33,44,83,91,115,138,173,183,201],"a":[13,42,93,100,113,165],"number":[14,43,114],"teams":[16],"at":[17,125,146],"Facebook":[18,67],"-":[19],"both":[20],"engineering":[21],"and":[22,31,110,131,143,160,178,213,216],"non-engineering.":[23],"Apart":[24],"from":[25,59],"ad":[26],"hoc":[27],"creation":[32],"business":[34],"intelligence":[35],"dashboards":[36],"by":[37],"analysts":[38],"across":[39],"company,":[41],"Facebook's":[45],"site":[46],"features":[47,57],"are":[48,220],"also":[49],"based":[50],"analyzing":[52],"sets.":[55],"These":[56,127],"range":[58],"simple":[60],"reporting":[61],"applications":[62],"like":[63],"Insights":[64],"for":[65],"Advertisers,":[68],"more":[70,170,180],"advanced":[71],"kinds":[72],"such":[73],"as":[74],"friend":[75],"recommendations.":[76],"In":[77,148],"order":[78,120],"support":[80],"this":[81,149,202],"diversity":[82],"use":[84],"cases":[85],"ever":[88],"increasing":[89],"amount":[90],"data,":[92],"flexible":[94],"infrastructure":[95,145],"that":[96,168,206,218],"scales":[97],"up":[98],"in":[99,119,209],"cost":[101],"effective":[102],"manner,":[103],"is":[104],"critical.":[105],"We":[106,191],"have":[107,157],"leveraged,":[108],"authored":[109],"contributed":[111],"open":[116],"source":[117],"technologies":[118],"address":[122],"these":[123,155],"requirements":[124],"Facebook.":[126,147],"include":[128],"Scribe,":[129],"Hadoop":[130],"Hive":[132],"which":[133],"together":[134,159],"form":[135],"cornerstones":[137],"log":[140],"collection,":[141],"storage":[142],"analytics":[144],"paper":[150],"we":[151,207,219],"will":[152],"present":[153],"how":[154],"systems":[156],"come":[158],"enabled":[161],"us":[162],"implement":[164],"warehouse":[167],"stores":[169],"than":[171,181],"15PB":[172],"(2.5PB":[175],"after":[176,187],"compression)":[177,188],"loads":[179],"60TB":[182],"new":[184],"(10TB":[186],"every":[189],"day.":[190],"discuss":[192],"motivations":[194],"behind":[195],"our":[196],"design":[197],"choices,":[198],"capabilities":[200,215],"solution,":[203],"challenges":[205],"face":[208],"day":[210],"today":[211],"operations":[212],"future":[214],"improvements":[217],"working":[221],"on.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":36},{"year":2016,"cited_by_count":42},{"year":2015,"cited_by_count":50},{"year":2014,"cited_by_count":48},{"year":2013,"cited_by_count":55},{"year":2012,"cited_by_count":53}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
