{"id":"https://openalex.org/W2774555688","doi":"https://doi.org/10.1109/icacci.2017.8125977","title":"Shuffle phase optimization in spark","display_name":"Shuffle phase optimization in spark","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2774555688","doi":"https://doi.org/10.1109/icacci.2017.8125977","mag":"2774555688"},"language":"en","primary_location":{"id":"doi:10.1109/icacci.2017.8125977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2017.8125977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","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/A5112716896","display_name":"Vandana Vandana","orcid":null},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vandana","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita University, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita University, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049032243","display_name":"Monica Velamuri","orcid":null},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Velamuri Monica","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita University, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita University, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007716219","display_name":"Narendra Kumar Parambalath","orcid":null},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Narendra Kumar Parambalath","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita University, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita University, India","institution_ids":["https://openalex.org/I81556334"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112716896"],"corresponding_institution_ids":["https://openalex.org/I81556334"],"apc_list":null,"apc_paid":null,"fwci":0.4836,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75853083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1028","last_page":"1034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965999722480774,"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":0.9869999885559082,"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":0.8410899043083191},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.8081749677658081},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7021013498306274},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5553815364837646},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5289642214775085},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4962382912635803},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46469494700431824},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4138803482055664},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3953514099121094},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38754093647003174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410899043083191},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.8081749677658081},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7021013498306274},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5553815364837646},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5289642214775085},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4962382912635803},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46469494700431824},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4138803482055664},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3953514099121094},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38754093647003174},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icacci.2017.8125977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2017.8125977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1565405831","https://openalex.org/W1767603313","https://openalex.org/W2140838268","https://openalex.org/W2173213060","https://openalex.org/W2470997476","https://openalex.org/W2496033776","https://openalex.org/W2512245916","https://openalex.org/W3138367763","https://openalex.org/W6980612014"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W2045745654","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W2989751065","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4241304791","https://openalex.org/W2127306800"],"abstract_inverted_index":{"Data":[0,22,38,63,169],"is":[1,10,39,45,112,134,167,173,190],"continuously":[2],"increasing":[3],"in":[4,101,108,150,165],"volume,":[5],"variety":[6],"and":[7,9,14,36,67,116,123,139,143,160,214],"velocity":[8],"becoming":[11,40,46],"a":[12,180],"precious":[13],"an":[15],"irreplaceable":[16],"asset.":[17],"The":[18],"insights":[19],"drawn":[20],"from":[21,170,188],"analysis":[23],"are":[24],"used":[25],"to":[26,48,97,130],"transform":[27],"healthcare,":[28],"Engineering":[29],"of":[30,56,105,157,202,210],"products,":[31],"Cyber":[32],"Security,":[33],"National":[34],"intelligence":[35],"business.":[37],"extremely":[41],"large":[42,140,176],"that,":[43],"it":[44,88],"difficult":[47],"process":[49],"using":[50,136,183],"traditional":[51],"data":[52,59,78,187,211],"storage":[53],"systems,":[54],"because":[55],"their":[57],"centralized":[58],"processing":[60,79],"behavior.":[61,80],"Big":[62],"tools":[64],"like":[65],"Hadoop":[66],"Apache":[68],"Spark":[69,81],"use":[70],"MapReduce":[71],"as":[72,205,207],"programming":[73],"paradigm":[74],"which":[75,86,147],"has":[76],"decentralized":[77],"performs":[82],"in-memory":[83],"cluster":[84],"computing":[85],"makes":[87],"100x":[89],"times":[90],"faster":[91],"than":[92],"Hadoop.":[93],"This":[94,198,217],"paper":[95],"proposes":[96],"identify":[98],"various":[99],"inefficiencies":[100],"the":[102,155,193,200,221],"current":[103],"design":[104],"shuffle":[106,132],"phase":[107,111],"Spark.":[109],"Shuffle":[110],"all-to-all":[113],"communication":[114],"mechanism":[115],"can":[117],"potentially":[118],"introduce":[119],"network,":[120],"disk,":[121],"memory":[122],"CPU":[124,222],"scheduling":[125,223],"overheads.":[126],"A":[127],"simple":[128],"strategy":[129],"optimize":[131],"performance":[133,152],"by":[135,153,178,225,232],"NIO":[137,184,233],"buffers":[138],"buffer":[141,177,189],"read":[142,159,182],"writes":[144,161],"during":[145],"shuffling":[146],"would":[148],"result":[149],"better":[151],"reducing":[154],"number":[156,201],"disk":[158,203],"when":[162],"partition":[163],"size":[164],"spill":[166],"small.":[168],"input":[171],"channel":[172,195],"buffered":[174],"into":[175,192],"performing":[179],"single":[181],"buffer.":[185,234],"Then,":[186],"put":[191],"output":[194],"for":[196,229],"shuffling.":[197],"reduces":[199,220],"operations":[204],"well":[206],"multiple":[208],"copies":[209],"between":[212],"JVM":[213],"native":[215],"memory.":[216],"method":[218],"also":[219],"overheads":[224],"providing":[226],"non-blocking":[227],"modes":[228],"threads":[230],"provided":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}