{"id":"https://openalex.org/W4281868399","doi":"https://doi.org/10.1145/3514221.3517845","title":"Tastes Great! Less Filling! High Performance and Accurate Training Data Collection for Self-Driving Database Management Systems","display_name":"Tastes Great! Less Filling! High Performance and Accurate Training Data Collection for Self-Driving Database Management Systems","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281868399","doi":"https://doi.org/10.1145/3514221.3517845"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517845","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075481941","display_name":"Matthew Butrovich","orcid":"https://orcid.org/0000-0001-5148-3661"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Butrovich","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046462762","display_name":"Wan Shen Lim","orcid":"https://orcid.org/0000-0003-1508-2080"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wan Shen Lim","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072023220","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0001-9626-8754"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084548052","display_name":"John Rollinson","orcid":"https://orcid.org/0000-0001-5713-0832"},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Rollinson","raw_affiliation_strings":["Army Cyber Institute, West Point, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Cyber Institute, West Point, NY, USA","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101962788","display_name":"William Zhang","orcid":"https://orcid.org/0009-0000-8189-6782"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Zhang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102800438","display_name":"Yu Xia","orcid":"https://orcid.org/0009-0009-3130-5046"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Xia","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049165312","display_name":"Andrew Pavlo","orcid":"https://orcid.org/0000-0001-6040-6991"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Pavlo","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9980000257492065,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9980000257492065,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8651986122131348},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.7950284481048584},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4706401526927948},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3252184987068176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8651986122131348},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.7950284481048584},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4706401526927948},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3252184987068176}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3514221.3517845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517845","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/146274","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/146274","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Proceedings of the 2022 International Conference on Management of Data","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3514221.3517845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517845","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2816854815","display_name":"SPX: Collaborative Research: Distributed Database Management with Logical Leases and Hardware Transactional Memory","funder_award_id":"1822933","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5849404552","display_name":"CAREER: Self-Driving Database Management Systems","funder_award_id":"1846158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8666259691","display_name":null,"funder_award_id":"IIS-1846158, SPX-1822933","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281868399.pdf","grobid_xml":"https://content.openalex.org/works/W4281868399.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1985229168","https://openalex.org/W1989306170","https://openalex.org/W2020129682","https://openalex.org/W2068245803","https://openalex.org/W2070317073","https://openalex.org/W2106771621","https://openalex.org/W2112474496","https://openalex.org/W2140246545","https://openalex.org/W2240667924","https://openalex.org/W2613206411","https://openalex.org/W2775606259","https://openalex.org/W2911464154","https://openalex.org/W2918549777","https://openalex.org/W2930500175","https://openalex.org/W2939293933","https://openalex.org/W2948513753","https://openalex.org/W2962702521","https://openalex.org/W2970851599","https://openalex.org/W2988720726","https://openalex.org/W3006061521","https://openalex.org/W3037027022","https://openalex.org/W3105457604","https://openalex.org/W3131834909","https://openalex.org/W3137837084","https://openalex.org/W3174394491","https://openalex.org/W3176419577","https://openalex.org/W3196849431","https://openalex.org/W4238288622"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2990194547","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W1480123525","https://openalex.org/W2414054180"],"abstract_inverted_index":{"A":[0],"self-driving":[1,64,141],"database":[2],"management":[3],"system":[4],"(DBMS)":[5],"aims":[6],"to":[7,99,124,158,215,237],"configure,":[8],"deploy,":[9],"and":[10,55,85,88,92,115,168,211,222],"optimize":[11],"almost":[12],"all":[13,48],"aspects":[14],"of":[15,27],"itself":[16],"automatically":[17],"without":[18],"human":[19],"intervention":[20],"or":[21],"guidance.":[22],"Achieving":[23],"this":[24],"high":[25],"level":[26],"automation":[28],"relies":[29],"on":[30],"machine":[31],"learning":[32],"(ML)":[33],"models":[34,61,241],"that":[35,80,118,176,228],"predict":[36,125],"how":[37],"a":[38,63,71,104,152,170,208,234,247],"DBMS":[39,49,65,86,105,195,210,236],"will":[40],"behave":[41],"in":[42,207],"different":[43],"scenarios.":[44],"This":[45],"behavior":[46,60,128,202],"encompasses":[47],"runtime":[50],"operations,":[51],"including":[52],"query":[53],"execution":[54],"maintenance":[56],"tasks.":[57],"These":[58],"ML-based":[59],"for":[62,136,201,219,233],"require":[66],"low-level":[67],"training":[68,75,101,138,199,217,231],"data":[69,76,102,139,200,218,232],"about":[70],"DBMS's":[72,127,153],"internals.":[73],"Such":[74],"includes":[77],"(1)":[78],"features":[79],"describe":[81],"the":[82,120,126,132,160],"workload,":[83],"environment,":[84],"configuration,":[87],"(2)":[89],"both":[90,220],"DBMS-":[91],"hardware-level":[93],"metrics.":[94],"But":[95],"it":[96,107,111],"is":[97,108,145],"difficult":[98],"collect":[100,216],"from":[103,140,180],"while":[106],"running":[109],"because":[110],"can":[112],"introduce":[113],"performance":[114,185,249],"measurement":[116],"degradations":[117],"hinder":[119],"ML":[121],"models'":[122],"ability":[123,214],"correctly.":[129],"We":[130,204],"present":[131],"TScout":[133],"(TS)":[134],"framework":[135,144],"collecting":[137],"DBMSs.":[142],"Our":[143,225],"an":[146],"internal":[147,194],"approach":[148],"where":[149],"developers":[150],"annotate":[151],"source":[154],"code":[155],"with":[156,193,245],"hooks":[157,167],"monitor":[159],"system's":[161],"behavior.":[162],"TS":[163,189,206,229],"then":[164],"extracts":[165],"these":[166,191],"generates":[169,230],"kernel-level":[171],"program":[172],"(via":[173],"Linux's":[174],"BPF)":[175],"efficiently":[177],"captures":[178],"metrics":[179,192],"multiple":[181],"sources":[182],"(e.g.,":[183],"CPU":[184],"counters,":[186],"memory":[187],"allocators).":[188],"combines":[190],"state":[196],"observations,":[197],"generating":[198],"models.":[203],"integrated":[205],"PostgreSQL-compatible":[209],"measured":[212],"its":[213],"OLTP":[221],"OLAP":[223],"workloads.":[224],"results":[226],"show":[227],"deployed":[235],"train":[238],"more":[239],"accurate":[240],"than":[242],"previous":[243],"methods":[244],"only":[246],"7%":[248],"reduction.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}