{"id":"https://openalex.org/W2333167668","doi":"https://doi.org/10.1109/ictc.2014.6983331","title":"TS-Hadoop: Handling access skew in MapReduce by using tiered storage infrastructure","display_name":"TS-Hadoop: Handling access skew in MapReduce by using tiered storage infrastructure","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2333167668","doi":"https://doi.org/10.1109/ictc.2014.6983331","mag":"2333167668"},"language":"en","primary_location":{"id":"doi:10.1109/ictc.2014.6983331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc.2014.6983331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5029227867","display_name":"Zhanye Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanye Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337101","display_name":"Jing Li","orcid":"https://orcid.org/0000-0003-3265-014X"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957591","display_name":"Tao Xu","orcid":"https://orcid.org/0000-0001-5362-8588"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352646","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0001-6939-0850"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450575","display_name":"Dongsheng Wang","orcid":"https://orcid.org/0000-0001-5779-9026"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6408,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89623779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"911","last_page":"916"},"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":0.9930999875068665,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8701732158660889},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7381315231323242},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7135584950447083},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.5249440670013428},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5146949887275696},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4825522303581238},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47675761580467224},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.43668821454048157},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4350108504295349},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.43449246883392334},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4221961200237274},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3472277522087097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08123520016670227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8701732158660889},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7381315231323242},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7135584950447083},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.5249440670013428},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5146949887275696},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4825522303581238},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47675761580467224},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.43668821454048157},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4350108504295349},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.43449246883392334},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4221961200237274},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3472277522087097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08123520016670227},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc.2014.6983331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc.2014.6983331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1576397915","https://openalex.org/W1967436269","https://openalex.org/W2003829707","https://openalex.org/W2096125134","https://openalex.org/W2104993419","https://openalex.org/W2114303224","https://openalex.org/W2119738171","https://openalex.org/W2173213060","https://openalex.org/W6634463810"],"related_works":["https://openalex.org/W4290802965","https://openalex.org/W97789383","https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W2727156679","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2139670306","https://openalex.org/W1556216397"],"abstract_inverted_index":{"Over":[0],"the":[1,49,78,82,126,156,169],"last":[2],"few":[3],"years,":[4],"MapReduce":[5,39,83,92,174],"systems":[6],"has":[7,115],"become":[8],"popular":[9],"for":[10],"processing":[11],"large-scale":[12],"data":[13,23,50,60,72,127,143,158],"sets":[14],"and":[15,25,141,148,153],"are":[16,61],"increasingly":[17],"being":[18],"used":[19],"in":[20,45,128,133,159,176],"web":[21],"indexing,":[22],"mining,":[24],"machine":[26],"learning.":[27],"Unlike":[28],"simple":[29],"application":[30],"scenarios":[31],"such":[32],"as":[33],"word":[34],"count,":[35],"many":[36],"applications":[37],"of":[38,59,81,102,173],"exhibit":[40],"strong":[41],"skewed":[42],"access":[43,51,187],"patterns":[44],"real":[46],"production":[47],"environment,":[48],"is":[52,74,104,178],"non-uniform,":[53],"often":[54],"only":[55],"a":[56,91,116],"small":[57],"portion":[58],"accessed":[62],"far":[63],"more":[64],"frequently":[65],"than":[66,181],"others.":[67],"Clearly,":[68],"handling":[69],"these":[70],"hot":[71,140,157],"efficiently":[73],"quite":[75],"critical":[76],"to":[77],"overall":[79],"performance":[80],"computation.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88],"present":[89],"TS-Hadoop,":[90],"system":[93],"based":[94,144],"on":[95,145],"Apache":[96],"Hadoop.":[97],"The":[98],"most":[99],"significant":[100],"feature":[101],"TS-Hadoop":[103,113,137,177],"that":[105,125,168],"it":[106,121],"utilizes":[107],"tiered":[108],"storage":[109],"infrastructure,":[110],"besides":[111],"HDFS,":[112],"also":[114],"shared-disk":[117],"cluster":[118],"called":[119],"HCache,":[120],"can":[122],"be":[123,131,163],"guaranteed":[124],"HCache":[129,152,160],"could":[130,161],"processed":[132,164],"highly":[134],"parallel":[135],"way.":[136],"automatically":[138],"distinguish":[139],"cold":[142],"current":[146],"workload,":[147],"move":[149],"them":[150],"into":[151],"HDFS":[154],"respectively,":[155],"would":[162],"efficiently.":[165],"Experiments":[166],"show":[167],"average":[170],"execution":[171],"time":[172],"jobs":[175],"much":[179],"faster":[180],"traditional":[182],"Hadoop":[183],"platform":[184],"when":[185],"facing":[186],"skew":[188],"workloads.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
