{"id":"https://openalex.org/W2470592085","doi":"https://doi.org/10.1109/msst.2016.7897074","title":"Pfimbi: Accelerating big data jobs through flow-controlled data replication","display_name":"Pfimbi: Accelerating big data jobs through flow-controlled data replication","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2470592085","doi":"https://doi.org/10.1109/msst.2016.7897074","mag":"2470592085"},"language":"en","primary_location":{"id":"doi:10.1109/msst.2016.7897074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2016.7897074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 32nd Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/218542","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069280173","display_name":"Simbarashe Dzinamarira","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Simbarashe Dzinamarira","raw_affiliation_strings":["Rice University, United States of America"],"affiliations":[{"raw_affiliation_string":"Rice University, United States of America","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079167224","display_name":"Florin Dinu","orcid":"https://orcid.org/0009-0005-1514-2997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florin Dinu","raw_affiliation_strings":["EPFLT"],"affiliations":[{"raw_affiliation_string":"EPFLT","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075120727","display_name":"T. S. Eugene Ng","orcid":"https://orcid.org/0000-0003-2954-0767"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. S. Eugene Ng","raw_affiliation_strings":["Rice University, United States of America"],"affiliations":[{"raw_affiliation_string":"Rice University, United States of America","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069280173"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":1.3857,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86473927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"13"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10772","display_name":"Distributed systems and fault tolerance","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8374958038330078},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.6796011924743652},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6008792519569397},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5765976309776306},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5598210096359253},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5227158665657043},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.506442666053772},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4949776530265808},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4738074839115143},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.4267508387565613},{"id":"https://openalex.org/keywords/flow-control","display_name":"Flow control (data)","score":0.4135363698005676},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4119328260421753},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.352131724357605},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.34169360995292664},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20152148604393005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374958038330078},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6796011924743652},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6008792519569397},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5765976309776306},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5598210096359253},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5227158665657043},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.506442666053772},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4949776530265808},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4738074839115143},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4267508387565613},{"id":"https://openalex.org/C186766456","wikidata":"https://www.wikidata.org/wiki/Q612457","display_name":"Flow control (data)","level":2,"score":0.4135363698005676},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4119328260421753},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.352131724357605},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34169360995292664},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20152148604393005},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msst.2016.7897074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2016.7897074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 32nd Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:218542","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/218542","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:218542","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/218542","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1550151291","https://openalex.org/W1742682033","https://openalex.org/W2038157364","https://openalex.org/W2058819785","https://openalex.org/W2099602864","https://openalex.org/W2104993419","https://openalex.org/W2119565742","https://openalex.org/W2119738171","https://openalex.org/W2131975293","https://openalex.org/W2155072926","https://openalex.org/W2163931546","https://openalex.org/W2189465200","https://openalex.org/W2240943048","https://openalex.org/W2482213519","https://openalex.org/W4239670432","https://openalex.org/W6632933440","https://openalex.org/W6637704723","https://openalex.org/W6687322159","https://openalex.org/W6996886134"],"related_works":["https://openalex.org/W986318368","https://openalex.org/W2000785801","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,17,34,126],"HDFS":[3,54],"is":[4,31,40,119],"critical":[5],"to":[6,53,107,121],"big":[7],"data":[8,38,62],"software":[9],"stacks":[10],"and":[11,23,59,76,104],"has":[12,65],"been":[13],"at":[14],"the":[15,21,24,32,50,98,110,124],"forefront":[16],"recent":[18],"efforts":[19],"from":[20,92],"industry":[22],"open":[25],"source":[26],"community.":[27],"A":[28],"key":[29],"problem":[30],"lack":[33],"flexibility":[35],"in":[36,109,135,139],"how":[37],"replication":[39],"performed.":[41],"To":[42],"address":[43],"this":[44,46],"problem,":[45],"paper":[47],"presents":[48],"Pfimbi,":[49],"first":[51],"alternative":[52],"that":[55,86,116],"supports":[56,77],"both":[57],"synchronous":[58],"flow-controlled":[60],"asynchronous":[61,127],"replication.":[63],"Pfimbi":[64,96],"numerous":[66],"benefits:":[67],"It":[68],"accelerates":[69],"jobs,":[70],"exploits":[71],"under-utilized":[72],"storage":[73,79],"I/O":[74,80],"bandwidth,":[75],"hierarchical":[78],"bandwidth":[81],"allocation":[82],"policies.":[83],"We":[84,113],"demonstrate":[85,115],"for":[87],"a":[88,93,136],"job":[89,100,140],"trace":[90],"derived":[91],"Facebook":[94],"workload,":[95],"improves":[97],"average":[99],"runtime":[101],"by":[102,105],"18%":[103],"up":[106],"46%":[108],"best":[111],"case.":[112],"also":[114],"flow":[117,131],"control":[118,132],"crucial":[120],"fully":[122],"exploiting":[123],"benefits":[125],"replication;":[128],"removing":[129],"Pfimbi's":[130],"mechanisms":[133],"resulted":[134],"2.7\u00d7":[137],"increase":[138],"runtime.":[141]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
