{"id":"https://openalex.org/W2999028480","doi":"https://doi.org/10.1109/ipccc47392.2019.8958719","title":"Query optimization Approach with Shuffle Intermediate Cache Layer for Spark SQL","display_name":"Query optimization Approach with Shuffle Intermediate Cache Layer for Spark SQL","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2999028480","doi":"https://doi.org/10.1109/ipccc47392.2019.8958719","mag":"2999028480"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc47392.2019.8958719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc47392.2019.8958719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)","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/A5042336611","display_name":"Mingyu Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingyu Zhai","raw_affiliation_strings":["NARI Research Institute,NARI Technology,Nanjing,China","NARI Technology, NARI Research Institute, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"NARI Research Institute,NARI Technology,Nanjing,China","institution_ids":["https://openalex.org/I4210118629"]},{"raw_affiliation_string":"NARI Technology, NARI Research Institute, Nanjing, China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084604918","display_name":"Aibo Song","orcid":"https://orcid.org/0000-0003-4447-7305"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aibo Song","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China","School of Computer Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002624948","display_name":"Jingyi Qiu","orcid":"https://orcid.org/0000-0001-7014-8375"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Qiu","raw_affiliation_strings":["Southeast University,School of Cyber Science and Engineering,Nanjing,China","School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Cyber Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011713058","display_name":"Xuechun Ji","orcid":"https://orcid.org/0000-0003-3654-0204"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechun Ji","raw_affiliation_strings":["NARI Research Institute,NARI Technology,Nanjing,China","NARI Technology, NARI Research Institute, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"NARI Research Institute,NARI Technology,Nanjing,China","institution_ids":["https://openalex.org/I4210118629"]},{"raw_affiliation_string":"NARI Technology, NARI Research Institute, Nanjing, China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037599201","display_name":"Qingxi Wu","orcid":"https://orcid.org/0000-0003-4716-4144"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxi Wu","raw_affiliation_strings":["NARI Research Institute,NARI Technology,Nanjing,China","NARI Technology, NARI Research Institute, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"NARI Research Institute,NARI Technology,Nanjing,China","institution_ids":["https://openalex.org/I4210118629"]},{"raw_affiliation_string":"NARI Technology, NARI Research Institute, Nanjing, China","institution_ids":["https://openalex.org/I4210118629"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042336611"],"corresponding_institution_ids":["https://openalex.org/I4210118629"],"apc_list":null,"apc_paid":null,"fwci":0.6783,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79883103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9944000244140625,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8675537109375},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7832682132720947},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7530173063278198},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5908603668212891},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5532867908477783},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5313416719436646},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.4783432185649872},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.46570947766304016},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4389592409133911},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3489839434623718},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.1791573166847229},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.11065545678138733},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10761266946792603},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.10748600959777832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675537109375},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7832682132720947},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7530173063278198},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5908603668212891},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5532867908477783},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5313416719436646},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.4783432185649872},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.46570947766304016},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4389592409133911},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3489839434623718},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.1791573166847229},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.11065545678138733},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10761266946792603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.10748600959777832}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc47392.2019.8958719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc47392.2019.8958719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)","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":12,"referenced_works":["https://openalex.org/W1982003698","https://openalex.org/W2038412523","https://openalex.org/W2071989194","https://openalex.org/W2105947650","https://openalex.org/W2110086534","https://openalex.org/W2119738171","https://openalex.org/W2131166445","https://openalex.org/W2138474206","https://openalex.org/W2139072600","https://openalex.org/W2163961697","https://openalex.org/W2243803726","https://openalex.org/W2963288913"],"related_works":["https://openalex.org/W2955368753","https://openalex.org/W2391725132","https://openalex.org/W2384284661","https://openalex.org/W319014924","https://openalex.org/W2588167896","https://openalex.org/W1987288934","https://openalex.org/W2389888740","https://openalex.org/W2362460270","https://openalex.org/W2188347403","https://openalex.org/W2385089576"],"abstract_inverted_index":{"Spark":[0,20,39,63,119,135],"SQL":[1,110,136],"is":[2],"a":[3],"big":[4],"data":[5,10,29,52,139],"processing":[6],"tool":[7],"for":[8,88,99],"structured":[9],"query":[11,76,130,156],"and":[12,48,60,113,163],"analysis.":[13],"However,":[14],"due":[15],"to":[16,26,30,65,121],"the":[17,31,35,43,56,61,67,75,83,92,107,117,123,129,133,149,155,159,168],"execution":[18,36],"of":[19,38,69,85,167],"SQL,":[21],"there":[22],"are":[23],"multiple":[24],"times":[25],"write":[27],"intermediate":[28,51],"disk,":[32],"which":[33],"reduces":[34],"efficiency":[37],"SQL.":[40],"Targeting":[41],"on":[42],"existing":[44,134],"issues,":[45],"we":[46,79],"design":[47],"implement":[49],"an":[50],"cache":[53,86],"layer":[54,87],"between":[55],"underlying":[57],"file":[58],"system":[59,120],"upper":[62],"core":[64],"reduce":[66,158],"cost":[68,162],"random":[70],"disk":[71,160],"I/O.":[72],"By":[73],"using":[74],"pre-analysis":[77],"module,":[78],"can":[80,95,152],"dynamically":[81],"adjust":[82],"capacity":[84],"different":[89],"queries.":[90],"And":[91],"allocation":[93],"module":[94,112,151],"allocate":[96],"proper":[97],"memory":[98,170],"each":[100],"node":[101],"in":[102],"cluster.":[103],"This":[104,126],"paper":[105,127],"develops":[106],"SSO":[108,150],"(Spark":[109],"optimizer)":[111],"integrates":[114],"it":[115],"into":[116],"original":[118],"achieve":[122],"above":[124],"functions.":[125],"compares":[128],"performance":[131],"with":[132],"by":[137,141],"experiment":[138],"generated":[140],"TPC-H":[142],"tool.":[143],"The":[144],"experimental":[145],"results":[146],"show":[147],"that":[148],"effectively":[153],"improve":[154],"efficiency,":[157],"I/O":[161],"make":[164],"full":[165],"use":[166],"cluster":[169],"resources.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}