{"id":"https://openalex.org/W2583118803","doi":"https://doi.org/10.1109/bigdata.2016.7840608","title":"Efficient data access strategies for Hadoop and Spark on HPC cluster with heterogeneous storage","display_name":"Efficient data access strategies for Hadoop and Spark on HPC cluster with heterogeneous storage","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583118803","doi":"https://doi.org/10.1109/bigdata.2016.7840608","mag":"2583118803"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840608","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/A5112525485","display_name":"Nusrat Sharmin Islam","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nusrat Sharmin Islam","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University","Department of Computer Science and Engineering, The Ohio State University,#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University,#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064789593","display_name":"Md. Wasi-ur-Rahman","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md. Wasi-ur-Rahman","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University","Department of Computer Science and Engineering, The Ohio State University,#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University,#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067748041","display_name":"Xiaoyi Lu","orcid":"https://orcid.org/0000-0001-7581-8905"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Lu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University","Department of Computer Science and Engineering, The Ohio State University,#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University,#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. D K Panda","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University","Department of Computer Science and Engineering, The Ohio State University,#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University,#TAB#","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112525485"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.8411,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95566299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"232"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9947999715805054,"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/spark","display_name":"SPARK (programming language)","score":0.8519481420516968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8217604160308838},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7489911317825317},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7399977445602417},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.6796722412109375},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.5369401574134827},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.5212962627410889},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5208697319030762},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.4818643033504486},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4551742374897003}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8519481420516968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217604160308838},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7489911317825317},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7399977445602417},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.6796722412109375},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5369401574134827},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.5212962627410889},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5208697319030762},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.4818643033504486},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4551742374897003},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840608","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":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1502383304","https://openalex.org/W1579147384","https://openalex.org/W1581677478","https://openalex.org/W1968781019","https://openalex.org/W2038157364","https://openalex.org/W2057746399","https://openalex.org/W2059628440","https://openalex.org/W2082047517","https://openalex.org/W2089098642","https://openalex.org/W2105947650","https://openalex.org/W2122465391","https://openalex.org/W2126022651","https://openalex.org/W2131975293","https://openalex.org/W2158865579","https://openalex.org/W2189465200","https://openalex.org/W2208735439","https://openalex.org/W2277359368","https://openalex.org/W2294312748","https://openalex.org/W2496453903","https://openalex.org/W4234905039","https://openalex.org/W6634769544","https://openalex.org/W6679815717","https://openalex.org/W6687322159","https://openalex.org/W6694713699"],"related_works":["https://openalex.org/W2953559629","https://openalex.org/W3009037395","https://openalex.org/W4313272304","https://openalex.org/W2019177710","https://openalex.org/W2890987641","https://openalex.org/W2026548343","https://openalex.org/W3110864498","https://openalex.org/W2374861481","https://openalex.org/W3048252901","https://openalex.org/W2785349009"],"abstract_inverted_index":{"The":[0,160,177],"most":[1],"popular":[2],"Big":[3,27],"Data":[4,28],"processing":[5],"frameworks":[6,29],"of":[7,44,147,163,179],"these":[8,25],"days":[9],"are":[10,83,168,184],"Hadoop":[11,15,31,114,164,180],"MapReduce":[12,32],"and":[13,33,74,108,115,121,165,175,181],"Spark.":[14],"Distributed":[16],"File":[17],"System":[18],"(HDFS)":[19],"is":[20],"the":[21,42,104,129,137,144,155],"primary":[22],"storage":[23,46,53,65,76,98,122],"for":[24,106,113],"frameworks.":[26],"like":[30],"Spark":[34,116,166,182],"launch":[35],"tasks":[36],"based":[37],"on":[38],"data":[39,57,92,119,139,158],"locality.":[40],"In":[41],"presence":[43],"heterogeneous":[45],"devices,":[47],"when":[48,70],"different":[49,52],"nodes":[50],"have":[51],"characteristics,":[54],"only":[55],"locality-aware":[56,157],"access":[58,93,131,140],"cannot":[59],"always":[60],"guarantee":[61],"optimal":[62],"performance.":[63],"Rather,":[64],"type":[66,99],"becomes":[67],"important,":[68],"specially":[69],"high":[71,80,109],"performance":[72,81,110,146],"SSD":[73],"in-memory":[75],"devices":[77],"along":[78],"with":[79],"interconnects":[82],"available.":[84],"Therefore,":[85],"in":[86],"this":[87],"paper,":[88],"we":[89],"propose":[90],"efficient":[91],"strategies":[94,141],"(e.g.":[95],"Greedy":[96],"(prioritizes":[97],"over":[100],"locality),":[101],"Hybrid":[102],"(balances":[103],"load":[105],"locality":[107,120],"storage),":[111],"etc.)":[112],"considering":[117],"both":[118],"types.":[123],"We":[124],"re-design":[125],"HDFS":[126,148],"to":[127,151,154,173,189],"accommodate":[128],"enhanced":[130],"strategies.":[132],"Our":[133],"evaluations":[134],"show":[135],"that,":[136],"proposed":[138],"can":[142],"improve":[143],"read":[145],"by":[149,171,187],"up":[150,172,188],"33%":[152],"compared":[153],"default":[156],"access.":[159],"execution":[161],"times":[162],"Sort":[167],"also":[169,185],"reduced":[170],"32%":[174],"17%.":[176],"performances":[178],"TeraSort":[183],"improved":[186],"11%":[190],"through":[191],"our":[192],"design.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-05T07:30:30.508283","created_date":"2025-10-10T00:00:00"}