{"id":"https://openalex.org/W2985290192","doi":"https://doi.org/10.1145/3357223.3365870","title":"Lessons from Large-Scale Software as a Service at Databricks","display_name":"Lessons from Large-Scale Software as a Service at Databricks","publication_year":2019,"publication_date":"2019-11-11","ids":{"openalex":"https://openalex.org/W2985290192","doi":"https://doi.org/10.1145/3357223.3365870","mag":"2985290192"},"language":"en","primary_location":{"id":"doi:10.1145/3357223.3365870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357223.3365870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","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/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005554337"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.0174,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83638103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9969000220298767,"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":0.9969000220298767,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.980400025844574,"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":0.7539045214653015},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7525311708450317},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6417107582092285},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6198066473007202},{"id":"https://openalex.org/keywords/software-as-a-service","display_name":"Software as a service","score":0.6006448268890381},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.533966600894928},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.509196937084198},{"id":"https://openalex.org/keywords/software-analytics","display_name":"Software analytics","score":0.48642492294311523},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4622717797756195},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4574955403804779},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44602715969085693},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.44320523738861084},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4327229857444763},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.35077381134033203},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3448091745376587},{"id":"https://openalex.org/keywords/component-based-software-engineering","display_name":"Component-based software engineering","score":0.22737032175064087},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08885982632637024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539045214653015},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7525311708450317},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6417107582092285},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6198066473007202},{"id":"https://openalex.org/C175133352","wikidata":"https://www.wikidata.org/wiki/Q1254596","display_name":"Software as a service","level":4,"score":0.6006448268890381},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.533966600894928},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.509196937084198},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.48642492294311523},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4622717797756195},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4574955403804779},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44602715969085693},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.44320523738861084},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4327229857444763},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.35077381134033203},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3448091745376587},{"id":"https://openalex.org/C174683762","wikidata":"https://www.wikidata.org/wiki/Q609588","display_name":"Component-based software engineering","level":4,"score":0.22737032175064087},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08885982632637024}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357223.3365870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357223.3365870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1864280877","https://openalex.org/W3173750053","https://openalex.org/W4206347313","https://openalex.org/W2935682778","https://openalex.org/W2186039352","https://openalex.org/W4386159400","https://openalex.org/W2170955077","https://openalex.org/W2098734934","https://openalex.org/W2794238232","https://openalex.org/W2371222978"],"abstract_inverted_index":{"The":[0],"cloud":[1,127,199],"has":[2,29,189],"become":[3],"one":[4],"of":[5,40,67,89,109,133,153,157,165,172,183,217],"the":[6,116,173,184,198,220],"most":[7],"attractive":[8],"ways":[9,186],"for":[10,87,124,142,197,206],"enterprises":[11],"to":[12,71],"purchase":[13],"software,":[14,27],"but":[15],"it":[16],"requires":[17],"building":[18,99],"products":[19],"in":[20,34,95,151,219],"a":[21,49,53,58,100,211],"very":[22],"different":[23],"way":[24],"from":[25],"traditional":[26],"which":[28],"not":[30],"been":[31],"heavily":[32],"studied":[33],"research.":[35],"I":[36],"will":[37],"explain":[38],"some":[39,171,182],"these":[41],"challenges":[42,93,138,175],"based":[43],"on":[44,60,215],"my":[45],"experience":[46],"at":[47,111],"Databricks,":[48],"startup":[50],"that":[51,105,176,187],"provides":[52],"data":[54,73,117,143,160],"analytics":[55,144,195],"platform":[56],"as":[57],"service":[59],"AWS":[61],"and":[62,75,84,113,181,191,209],"Azure.":[63],"Databricks":[64,188],"manages":[65],"millions":[66],"VMs":[68,158],"per":[69],"day":[70],"run":[72],"engineering":[74],"machine":[76],"learning":[77],"workloads":[78,145],"using":[79],"Apache":[80,122,207],"Spark,":[81],"TensorFlow,":[82],"Python":[83],"other":[85],"software":[86,119,196],"thousands":[88,108],"customers.":[90],"Two":[91],"main":[92,185],"arise":[94],"this":[96],"context:":[97],"(1)":[98],"reliable,":[101],"scalable":[102],"control":[103],"plane":[104],"can":[106],"manage":[107],"customers":[110],"once":[112],"(2)":[114],"adapting":[115],"processing":[118],"itself":[120],"(e.g.":[121,155],"Spark)":[123],"an":[125,203],"elastic":[126],"environment":[128,200],"(for":[129],"instance,":[130],"autoscaling":[131,204],"instead":[132],"assuming":[134],"static":[135],"clusters).":[136],"These":[137],"are":[139],"especially":[140],"significant":[141],"whose":[146],"users":[147],"constantly":[148],"push":[149],"boundaries":[150],"terms":[152],"scale":[154],"number":[156,164],"used,":[159],"size,":[161,163],"metadata":[162],"concurrent":[166],"users,":[167],"etc).":[168],"I'll":[169],"describe":[170],"common":[174],"our":[177],"new":[178],"services":[179],"face":[180],"extended":[190],"modified":[192],"open":[193,223],"source":[194,224],"(e.g.,":[201],"designing":[202],"engine":[205],"Spark":[208],"creating":[210],"transactional":[212],"storage":[213],"layer":[214],"top":[216],"S3":[218],"Delta":[221],"Lake":[222],"product).":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
