{"id":"https://openalex.org/W1976306141","doi":"https://doi.org/10.1109/cluster.2013.6702685","title":"Distributed data provenance for large-scale data-intensive computing","display_name":"Distributed data provenance for large-scale data-intensive computing","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W1976306141","doi":"https://doi.org/10.1109/cluster.2013.6702685","mag":"1976306141"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2013.6702685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5101671477","display_name":"Dongfang Zhao","orcid":"https://orcid.org/0000-0002-0677-634X"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Zhao","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology","Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111480538","display_name":"Chen Shou","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Shou","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology","Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098586263","display_name":"Tanu Maliky","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanu Maliky","raw_affiliation_strings":["Computation Institute, The University of Chicago, USA","Comput. Inst., Univ. of Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computation Institute, The University of Chicago, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Comput. Inst., Univ. of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030599558","display_name":"Ioan Raicu","orcid":"https://orcid.org/0000-0002-5477-439X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioan Raicu","raw_affiliation_strings":["Math and Computer Science Division, Argonne National Laboratory","Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Math and Computer Science Division, Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#","institution_ids":["https://openalex.org/I180949307"]}]}],"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":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976999759674072,"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/metadata","display_name":"Metadata","score":0.8847477436065674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8438358306884766},{"id":"https://openalex.org/keywords/metadata-management","display_name":"Metadata management","score":0.7370365858078003},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7121194005012512},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.6036267876625061},{"id":"https://openalex.org/keywords/torrent-file","display_name":"Torrent file","score":0.5717432498931885},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5398698449134827},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.49878382682800293},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.47165337204933167},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.43683061003685},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.4330641031265259},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.4282892346382141},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4246959984302521},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.41914474964141846},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38783344626426697},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.2922237515449524},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25565966963768005},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.24361908435821533},{"id":"https://openalex.org/keywords/journaling-file-system","display_name":"Journaling file system","score":0.1697406768798828},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.09917792677879333}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8847477436065674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438358306884766},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.7370365858078003},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7121194005012512},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.6036267876625061},{"id":"https://openalex.org/C40350719","wikidata":"https://www.wikidata.org/wiki/Q2451637","display_name":"Torrent file","level":4,"score":0.5717432498931885},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5398698449134827},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.49878382682800293},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.47165337204933167},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.43683061003685},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.4330641031265259},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.4282892346382141},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4246959984302521},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.41914474964141846},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38783344626426697},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.2922237515449524},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25565966963768005},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.24361908435821533},{"id":"https://openalex.org/C2225880","wikidata":"https://www.wikidata.org/wiki/Q579047","display_name":"Journaling file system","level":3,"score":0.1697406768798828},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.09917792677879333},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/cluster.2013.6702685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.414.838","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://datasys.cs.iit.edu/publications/2013_Cluster13_Provenance.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1751644051","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3075337988","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G3723637003","display_name":"CAREER: Avoiding Achilles' Heel in Exascale Computing with Distributed File Systems","funder_award_id":"1054974","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4245805214","display_name":null,"funder_award_id":"OCI-1054974","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4790718960","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5085543421","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7351994996","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W100800462","https://openalex.org/W114584783","https://openalex.org/W168132470","https://openalex.org/W1536870558","https://openalex.org/W1544888650","https://openalex.org/W1559528097","https://openalex.org/W1734799737","https://openalex.org/W1846570396","https://openalex.org/W1858703999","https://openalex.org/W1986794659","https://openalex.org/W2006887358","https://openalex.org/W2019438923","https://openalex.org/W2033728896","https://openalex.org/W2047899835","https://openalex.org/W2055120144","https://openalex.org/W2056441794","https://openalex.org/W2078455494","https://openalex.org/W2090575249","https://openalex.org/W2096945381","https://openalex.org/W2097351435","https://openalex.org/W2107759909","https://openalex.org/W2108841814","https://openalex.org/W2112582917","https://openalex.org/W2119565742","https://openalex.org/W2119738171","https://openalex.org/W2130304121","https://openalex.org/W2131304484","https://openalex.org/W2135377936","https://openalex.org/W2141005805","https://openalex.org/W2146917903","https://openalex.org/W2150697658","https://openalex.org/W2153704625","https://openalex.org/W2158049821","https://openalex.org/W2168067900","https://openalex.org/W2394621848","https://openalex.org/W2999097477","https://openalex.org/W3125398447","https://openalex.org/W3139073351","https://openalex.org/W3215028506","https://openalex.org/W4239670432","https://openalex.org/W4285719527","https://openalex.org/W6604616335","https://openalex.org/W6606869816","https://openalex.org/W6632436052","https://openalex.org/W6637631891","https://openalex.org/W6674500115"],"related_works":["https://openalex.org/W345350539","https://openalex.org/W3164148116","https://openalex.org/W2110546525","https://openalex.org/W2767725805","https://openalex.org/W2404084198","https://openalex.org/W2273516505","https://openalex.org/W2047852519","https://openalex.org/W1968075755","https://openalex.org/W2869909795","https://openalex.org/W3042737680"],"abstract_inverted_index":{"It":[0],"has":[1,154],"become":[2],"increasingly":[3],"important":[4],"to":[5,92,124,156,158,174,177],"capture":[6,171],"and":[7,11,31,45,59,116,129,153,160],"understand":[8],"the":[9,22,38,65],"origins":[10],"derivation":[12],"of":[13,24,40,100],"data":[14,25,128],"(its":[15],"provenance).":[16],"A":[17],"key":[18],"issue":[19],"in":[20,52],"evaluating":[21],"feasibility":[23,39],"provenance":[26,60,68,127,151,170],"is":[27,145,172],"its":[28,165],"performance,":[29],"overheads,":[30],"scalability.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"explore":[37],"a":[41,77,106,121,139,146],"general":[42],"metadata":[43,54,69,79,93,109],"storage":[44,80,167],"management":[46,110],"layer":[47,168],"for":[48,133,169],"parallel":[49],"file":[50,57,78,108],"systems,":[51],"which":[53,104,119],"includes":[55],"both":[56],"operations":[58],"metadata.":[61],"We":[62,82],"experimentally":[63],"investigate":[64],"design":[66],"optimality\u2014whether":[67],"should":[70],"be":[71],"loosely-coupled":[72],"or":[73],"tightly":[74],"integrated":[75],"with":[76,149,164],"systems.":[81],"consider":[83],"two":[84],"systems":[85],"that":[86,143],"have":[87],"applied":[88],"similar":[89],"distributed":[90,107,113,131],"concepts":[91],"management,":[94],"but":[95],"focusing":[96],"singularly":[97],"on":[98,112,138,180],"kind":[99],"metadata:":[101],"(i)":[102],"FusionFS,":[103],"implements":[105],"based":[111],"hash":[114],"tables,":[115],"(ii)":[117],"SPADE,":[118],"uses":[120],"graph":[122],"database":[123],"store":[125],"audited":[126],"provides":[130],"module":[132],"querying":[134],"provenance.":[135],"Our":[136],"results":[137],"32-node":[140],"cluster":[141],"show":[142],"FusionFS+SPADE":[144],"promising":[147],"prototype":[148],"negligible":[150],"overhead":[152],"promise":[155],"scale":[157,175],"petascale":[159],"beyond.":[161],"Furthermore,":[162],"FusionFS":[163],"own":[166],"able":[173],"up":[176],"1K":[178],"nodes":[179],"BlueGene/P":[181],"supercomputer.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}
