{"id":"https://openalex.org/W2583701252","doi":"https://doi.org/10.1109/bigdata.2016.7840838","title":"Identifying performance bottlenecks in Hive: Use of processor counters","display_name":"Identifying performance bottlenecks in Hive: Use of processor counters","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583701252","doi":"https://doi.org/10.1109/bigdata.2016.7840838","mag":"2583701252"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big 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/A5063412256","display_name":"Alexander Cole Shulyak","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander C. Shulyak","raw_affiliation_strings":["The University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068885069","display_name":"Lizy K. John","orcid":"https://orcid.org/0000-0002-8747-5214"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lizy K. John","raw_affiliation_strings":["The University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063412256"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.3269,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8761242,"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":"2109","last_page":"2114"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9962999820709229,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9927999973297119,"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":0.8894875645637512},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5203373432159424},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5121440887451172},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4913081228733063},{"id":"https://openalex.org/keywords/online-transaction-processing","display_name":"Online transaction processing","score":0.4818202555179596},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4712422490119934},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4110185205936432},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34249764680862427},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3319590389728546},{"id":"https://openalex.org/keywords/transaction-processing","display_name":"Transaction processing","score":0.24231436848640442},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15526512265205383},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.10706701874732971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8894875645637512},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5203373432159424},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5121440887451172},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4913081228733063},{"id":"https://openalex.org/C191087605","wikidata":"https://www.wikidata.org/wiki/Q1501395","display_name":"Online transaction processing","level":4,"score":0.4818202555179596},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4712422490119934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4110185205936432},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34249764680862427},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3319590389728546},{"id":"https://openalex.org/C72108876","wikidata":"https://www.wikidata.org/wiki/Q844565","display_name":"Transaction processing","level":3,"score":0.24231436848640442},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15526512265205383},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.10706701874732971},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2013062050","https://openalex.org/W2097484305","https://openalex.org/W2106625078","https://openalex.org/W2158865579","https://openalex.org/W2171094780","https://openalex.org/W2173213060","https://openalex.org/W2199558228"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W2558523485","https://openalex.org/W4379407450","https://openalex.org/W2408437972","https://openalex.org/W2905107896","https://openalex.org/W2895375519"],"abstract_inverted_index":{"Distributed":[0],"SQL":[1],"Query":[2],"Engines,":[3],"like":[4,27],"Hive,":[5],"Spark,":[6],"and":[7,30,76,126,132,189],"Impala,":[8],"have":[9],"become":[10],"the":[11,83,87,90,116,120,124,157,164,174],"de-facto":[12],"database":[13,21,60,67],"set-up":[14],"for":[15],"Decision":[16],"Support":[17],"Systems":[18],"with":[19],"large":[20],"sizes.":[22],"Unlike":[23],"other":[24],"distributed":[25,58],"computing":[26],"graph":[28],"processing":[29],"OLTP":[31],"transactions,":[32],"DSS":[33],"queries":[34,100,183],"are":[35,135],"often":[36],"CPU":[37],"bound":[38,44],"as":[39],"opposed":[40],"to":[41,64,137,149,162],"Network":[42],"I/O":[43],"[8].":[45],"In":[46,160],"this":[47],"paper,":[48],"we":[49],"identify":[50],"apparent":[51],"anomalies":[52],"in":[53,142,185],"query":[54],"performance":[55,78,121],"on":[56],"a":[57,65,102,139,151,186],"Hive":[59,127,143,145],"setup,":[61],"comparing":[62],"it":[63],"traditional":[66],"(MySQL)":[68],"system.":[69],"We":[70,110],"found":[71],"MySQL":[72,125],"is":[73,79,146],"algorithmically":[74],"efficient,":[75],"micro-architectural":[77],"affected":[80],"only":[81],"by":[82,180,190],"computational":[84],"demands":[85],"of":[86,104,114,119],"query.":[88],"On":[89],"other-hand,":[91],"Hive's":[92],"generic":[93],"execution":[94,166],"framework":[95],"has":[96],"difficulty":[97],"converting":[98],"some":[99],"into":[101],"set":[103],"MapReduce":[105,172],"jobs,":[106],"increasing":[107],"algorithmic":[108],"in-efficency.":[109],"describe":[111],"our":[112],"experience":[113],"analyzing":[115],"root":[117],"causes":[118],"discrepancies":[122],"between":[123],"executions.":[128,144],"JVM":[129],"startup":[130],"overhead":[131],"context":[133],"switches":[134],"seen":[136,148],"be":[138,178],"major":[140],"bottleneck":[141],"also":[147],"use":[150],"larger":[152],"code":[153],"footprint":[154],"which":[155,168],"stresses":[156],"memory":[158],"hierarchy.":[159],"addition":[161],"using":[163],"Tez":[165],"engine,":[167],"reuses":[169],"containers":[170],"across":[171],"tasks,":[173],"aforementioned":[175],"costs":[176],"could":[177],"reduced":[179],"running":[181],"small":[182],"together":[184],"single":[187],"session,":[188],"forcing":[191],"one":[192],"process":[193],"per":[194],"available":[195],"physical":[196],"core.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}