{"id":"https://openalex.org/W2598450937","doi":"https://doi.org/10.1109/iccnc.2017.7876175","title":"Improving Shuffle I/O performance for big data processing using hybrid storage","display_name":"Improving Shuffle I/O performance for big data processing using hybrid storage","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2598450937","doi":"https://doi.org/10.1109/iccnc.2017.7876175","mag":"2598450937"},"language":"en","primary_location":{"id":"doi:10.1109/iccnc.2017.7876175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccnc.2017.7876175","pdf_url":null,"source":{"id":"https://openalex.org/S4306498181","display_name":"2017 International Conference on Computing, Networking and Communications (ICNC)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Computing, Networking and Communications (ICNC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101639518","display_name":"Xiaojun Ruan","orcid":"https://orcid.org/0000-0002-9359-5319"},"institutions":[{"id":"https://openalex.org/I161171246","display_name":"West Chester University","ror":"https://ror.org/0053n5071","country_code":"US","type":"education","lineage":["https://openalex.org/I161171246"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojun Ruan","raw_affiliation_strings":["Department of Computer Science, West Chester University of Pennsylvania, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, West Chester University of Pennsylvania, PA, USA","institution_ids":["https://openalex.org/I161171246","https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117634641","display_name":"Haiquan Chen","orcid":"https://orcid.org/0000-0003-1689-0549"},"institutions":[{"id":"https://openalex.org/I102716817","display_name":"Valdosta State University","ror":"https://ror.org/04zjcaq85","country_code":"US","type":"education","lineage":["https://openalex.org/I102716817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiquan Chen","raw_affiliation_strings":["Department of Computer Science, Valdosta State University, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Valdosta State University, GA, USA","institution_ids":["https://openalex.org/I102716817"]}]}],"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":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2017","issue":null,"first_page":"476","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9990000128746033,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.995199978351593,"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":0.8467617034912109},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7841446399688721},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7154148817062378},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6704445481300354},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5213045477867126},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5117154121398926},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4517844617366791},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.41654375195503235},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3362116813659668},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3134433627128601},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2543566823005676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467617034912109},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7841446399688721},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7154148817062378},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6704445481300354},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5213045477867126},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5117154121398926},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4517844617366791},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.41654375195503235},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3362116813659668},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3134433627128601},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2543566823005676},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccnc.2017.7876175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccnc.2017.7876175","pdf_url":null,"source":{"id":"https://openalex.org/S4306498181","display_name":"2017 International Conference on Computing, Networking and Communications (ICNC)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Computing, Networking and Communications (ICNC)","raw_type":"proceedings-article"},{"id":"mag:2748731613","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/201702230247549669","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1420267637","https://openalex.org/W1568181892","https://openalex.org/W1746258828","https://openalex.org/W1967174607","https://openalex.org/W1996438407","https://openalex.org/W2045287414","https://openalex.org/W2119738171","https://openalex.org/W2121784101","https://openalex.org/W2122465391","https://openalex.org/W2124499489","https://openalex.org/W2131975293","https://openalex.org/W2165068957","https://openalex.org/W2168395296","https://openalex.org/W2208859287","https://openalex.org/W2221106743","https://openalex.org/W2282327192","https://openalex.org/W2396433687","https://openalex.org/W2995564009","https://openalex.org/W4210654460","https://openalex.org/W4239670432","https://openalex.org/W6633954485","https://openalex.org/W6637806892","https://openalex.org/W6649353803","https://openalex.org/W6679815717","https://openalex.org/W6684515133","https://openalex.org/W6688262612","https://openalex.org/W6712017604"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W3191926225"],"abstract_inverted_index":{"Nowadays":[0],"Big":[1,25,50],"Data":[2,26,51],"analytics":[3,52],"have":[4],"been":[5],"widely":[6],"used":[7],"in":[8,78,183],"many":[9],"domains,":[10],"e.g.,":[11],"weather":[12],"forecast,":[13],"social":[14],"network":[15],"analysis,":[16],"scientific":[17],"computing,":[18],"and":[19,47,129,151,170],"bioinformatics.":[20],"As":[21],"indispensable":[22],"part":[23],"of":[24,36,45,57,65,117],"analytics,":[27],"MapReduce":[28,104],"has":[29],"become":[30],"the":[31,37,42,55,62,74,79,85,90,97,109,184,189],"de":[32],"facto":[33],"standard":[34],"model":[35],"distributed":[38],"computing":[39,66],"framework.":[40],"With":[41],"growing":[43],"complexity":[44],"software":[46],"hardware":[48],"components,":[49],"systems":[53],"face":[54],"challenge":[56],"performance":[58,86,101,157,161,181],"bottleneck":[59,87],"when":[60],"handling":[61,118],"increasing":[63],"size":[64],"workloads.":[67],"In":[68],"our":[69,175],"study,":[70],"we":[71,134],"reveal":[72],"that":[73,96,108,141,174],"existing":[75],"Shuffle":[76,91,98,155,185],"mechanism":[77],"current":[80],"Spark":[81,192],"implementation":[82],"is":[83],"still":[84],"due":[88,122],"to":[89,123,158],"I/O":[92,132,156],"latency.":[93],"We":[94],"demonstrate":[95],"stage":[99,186],"causes":[100],"degradation":[102,162],"among":[103],"jobs.":[105],"By":[106],"observing":[107],"high-end":[110],"Solid":[111],"State":[112],"Disks":[113],"(SSDs)":[114],"are":[115],"capable":[116],"random":[119],"writes":[120],"well":[121],"efficient":[124],"flash":[125],"translation":[126],"layer":[127],"algorithms":[128],"larger":[130],"on-board":[131],"cache,":[133],"present":[135],"a":[136],"hybrid":[137,176],"storage":[138,150,177],"system-based":[139,178],"solution":[140],"uses":[142],"hard":[143],"drive":[144],"disks":[145],"(HDDs)":[146],"for":[147,153],"large":[148],"datasets":[149],"SSDs":[152],"improving":[154],"mitigate":[159],"this":[160],"issue.":[163],"Our":[164],"extensive":[165],"experiments":[166],"using":[167],"both":[168],"real-world":[169],"synthetic":[171],"workloads":[172],"show":[173],"approach":[179],"achieves":[180],"improvement":[182],"compared":[187],"with":[188],"original":[190],"HDD-based":[191],"implementation.":[193]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}