{"id":"https://openalex.org/W2415420807","doi":"https://doi.org/10.1109/ispass.2016.7482079","title":"Workload characterization and optimization of TPC-H queries on Apache Spark","display_name":"Workload characterization and optimization of TPC-H queries on Apache Spark","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2415420807","doi":"https://doi.org/10.1109/ispass.2016.7482079","mag":"2415420807"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2016.7482079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","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/A5041846557","display_name":"Tatsuhiro Chiba","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tatsuhiro Chiba","raw_affiliation_strings":["IBM Research - Tokyo, Chuo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, Chuo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001578514","display_name":"Tamiya Onodera","orcid":"https://orcid.org/0000-0002-6076-8236"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tamiya Onodera","raw_affiliation_strings":["IBM Research - Tokyo, Chuo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, Chuo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041846557"],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":19.9043,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.99220982,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987000226974487,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8786576986312866},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7133869528770447},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.6730210781097412},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5656483769416809},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5377232432365417},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4993157386779785},{"id":"https://openalex.org/keywords/garbage-collection","display_name":"Garbage collection","score":0.49516525864601135},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.45317843556404114},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45029518008232117},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4456329643726349},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34500935673713684},{"id":"https://openalex.org/keywords/garbage","display_name":"Garbage","score":0.1848679482936859},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1248759925365448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8786576986312866},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7133869528770447},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.6730210781097412},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5656483769416809},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5377232432365417},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4993157386779785},{"id":"https://openalex.org/C105122174","wikidata":"https://www.wikidata.org/wiki/Q322202","display_name":"Garbage collection","level":3,"score":0.49516525864601135},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.45317843556404114},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45029518008232117},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4456329643726349},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34500935673713684},{"id":"https://openalex.org/C75403996","wikidata":"https://www.wikidata.org/wiki/Q5521979","display_name":"Garbage","level":2,"score":0.1848679482936859},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1248759925365448},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass.2016.7482079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1976860187","https://openalex.org/W2013344760","https://openalex.org/W2038412523","https://openalex.org/W2040728701","https://openalex.org/W2064677427","https://openalex.org/W2071704971","https://openalex.org/W2106625078","https://openalex.org/W2114303224","https://openalex.org/W2120230074","https://openalex.org/W2131040110","https://openalex.org/W2131975293","https://openalex.org/W2150478767","https://openalex.org/W2170616854","https://openalex.org/W2189465200","https://openalex.org/W2190012392","https://openalex.org/W2256629785","https://openalex.org/W2913446311","https://openalex.org/W3004105989","https://openalex.org/W3104065274","https://openalex.org/W4250415899","https://openalex.org/W6679815717","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2005091774","https://openalex.org/W2114459515","https://openalex.org/W2060525997"],"abstract_inverted_index":{"Besides":[0],"being":[1],"an":[2],"in-memory-oriented":[3],"computing":[4,60,131],"framework,":[5],"Spark":[6,23,112,184],"runs":[7],"on":[8,72,118,196],"top":[9],"of":[10,54,91,129],"Java":[11,35],"Virtual":[12],"Machines":[13],"(JVMs),":[14],"so":[15,79],"JVM":[16,106,154,176],"parameters":[17,27,107],"must":[18],"be":[19,123],"tuned":[20],"to":[21,83,122,125,201],"improve":[22],"application":[24,55,115],"performance.":[25,31,185],"Misconfigured":[26],"and":[28,69,114,146,157,161,173,177,198],"settings":[29],"degrade":[30],"For":[32],"example,":[33],"using":[34],"heaps":[36],"that":[37],"are":[38,75],"too":[39],"large":[40],"often":[41],"causes":[42],"a":[43,98,165,187],"long":[44],"garbage":[45],"collection":[46],"pause":[47],"time,":[48],"which":[49],"accounts":[50],"for":[51,182],"over":[52],"10-20%":[53],"execution":[56],"time.":[57],"Moreover,":[58],"recent":[59],"nodes":[61],"have":[62],"many":[63,148],"cores":[64],"with":[65],"simultaneous":[66],"multi-threading":[67],"technology":[68],"the":[70,73,138,205],"processors":[71],"node":[74],"connected":[76],"via":[77],"NUMA,":[78],"it":[80],"is":[81,101,199],"difficult":[82],"exploit":[84],"best":[85],"performance":[86,166],"without":[87],"taking":[88],"into":[89],"account":[90],"these":[92],"hardware":[93,162],"features.":[94],"Thus,":[95],"optimization":[96,143,180,190],"in":[97,194],"full":[99,127],"stack":[100],"also":[102,109],"important.":[103],"Not":[104],"only":[105],"but":[108],"OS":[110,178],"parameters,":[111],"configuration,":[113],"code":[116],"based":[117],"CPU":[119],"characteristics":[120],"need":[121],"optimized":[124],"take":[126],"advantage":[128],"underlying":[130],"resources.":[132],"In":[133],"this":[134],"paper,":[135],"we":[136],"used":[137],"TPC-H":[139],"benchmark":[140],"as":[141,152],"our":[142,189],"case":[144],"study":[145],"gathered":[147],"perspective":[149],"logs":[150],"such":[151],"application,":[153],"(e.g.":[155],"GC":[156],"JIT),":[158],"system":[159],"utilization,":[160],"events":[163],"from":[164],"monitoring":[167],"unit.":[168],"We":[169],"discuss":[170],"current":[171],"problems":[172],"introduce":[174],"several":[175],"parameter":[179],"approaches":[181],"accelerating":[183],"As":[186],"result,":[188],"exhibits":[191],"30-40%":[192],"increase":[193],"speed":[195],"average":[197],"up":[200],"5x":[202],"faster":[203],"than":[204],"naive":[206],"configuration.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}