{"id":"https://openalex.org/W3006437988","doi":"https://doi.org/10.1109/tpds.2020.2972882","title":"Crocus: Enabling Computing Resource Orchestration for Inline Cluster-Wide Deduplication on Scalable Storage Systems","display_name":"Crocus: Enabling Computing Resource Orchestration for Inline Cluster-Wide Deduplication on Scalable Storage Systems","publication_year":2020,"publication_date":"2020-02-11","ids":{"openalex":"https://openalex.org/W3006437988","doi":"https://doi.org/10.1109/tpds.2020.2972882","mag":"3006437988"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2972882","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5082900475","display_name":"Prince Hamandawana","orcid":"https://orcid.org/0000-0002-1030-3844"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"funder","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Prince Hamandawana","raw_affiliation_strings":["Department of Computer Engineering, Ajou University, Suwon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Ajou University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085960321","display_name":"Awais Khan","orcid":"https://orcid.org/0000-0003-2603-3516"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"funder","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Awais Khan","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016679769","display_name":"Chang-Gyu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"funder","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang-Gyu Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413142","display_name":"Sungyong Park","orcid":"https://orcid.org/0000-0002-0309-1820"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"funder","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungyong Park","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458491","display_name":"Youngjae Kim","orcid":"https://orcid.org/0000-0001-8786-3850"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"funder","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjae Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.275,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.765738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":85,"max":86},"biblio":{"volume":"31","issue":"8","first_page":"1740","last_page":"1753"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997,"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":0.9997,"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":0.9991,"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":0.9975,"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/data-deduplication","display_name":"Data deduplication","score":0.895198}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.895198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8915405},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6969599},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6226767},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5095418},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47500503},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.45533696},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4309262},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40096214},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36029956},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11038691},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2972882","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea","award_id":"NRF-2018R1A1A1A05079398"}],"datasets":[],"versions":[],"referenced_works_count":36,"referenced_works":["https://openalex.org/W136989616","https://openalex.org/W174289249","https://openalex.org/W1793325024","https://openalex.org/W186989516","https://openalex.org/W1871705262","https://openalex.org/W1963563622","https://openalex.org/W1969126835","https://openalex.org/W1999984505","https://openalex.org/W200233886","https://openalex.org/W2003696547","https://openalex.org/W2008185810","https://openalex.org/W2055899630","https://openalex.org/W2061537611","https://openalex.org/W2066818624","https://openalex.org/W2072362295","https://openalex.org/W2080592089","https://openalex.org/W2105717273","https://openalex.org/W2145299840","https://openalex.org/W2156468933","https://openalex.org/W2281363974","https://openalex.org/W2287453169","https://openalex.org/W2323587239","https://openalex.org/W2351279544","https://openalex.org/W24740120","https://openalex.org/W2475932436","https://openalex.org/W2574550978","https://openalex.org/W26020480","https://openalex.org/W2739791894","https://openalex.org/W2754499276","https://openalex.org/W2780813414","https://openalex.org/W2808357789","https://openalex.org/W2876349725","https://openalex.org/W2926596943","https://openalex.org/W2935106878","https://openalex.org/W2963108782","https://openalex.org/W4230077428"],"related_works":["https://openalex.org/W94000989","https://openalex.org/W2516240846","https://openalex.org/W2503642292","https://openalex.org/W2385146268","https://openalex.org/W2364921833","https://openalex.org/W2064105003","https://openalex.org/W1967954938","https://openalex.org/W1596201972","https://openalex.org/W1595151633","https://openalex.org/W123872086"],"abstract_inverted_index":{"Inline":[0],"deduplication":[1,15,73,106,128,164],"dramatically":[2],"improves":[3],"storage":[4,131,140],"space":[5],"utilization.":[6],"However,":[7],"it":[8],"degrades":[9],"I/O":[10,35,51],"throughput":[11,52],"due":[12],"to":[13,48,70,112,160],"computeintensive":[14],"operations":[16,107],"such":[17,84],"as":[18,85],"chunking,":[19],"fingerprinting":[20,150],"or":[21,41,191],"hashing":[22],"of":[23,44],"chunk":[24,157],"content,":[25],"and":[26,53,87,103,119,126,179],"redundant":[27],"lookup":[28],"I/Os":[29],"over":[30,188],"the":[31,34,39,49,149],"network":[32],"in":[33,108,123,137,176],"path.":[36],"In":[37,57,75],"particular,":[38,76],"fingerprint":[40],"hash":[42],"generation":[43],"content":[45],"contributes":[46],"largely":[47],"degraded":[50],"is":[54,116],"computationally":[55],"expensive.":[56],"this":[58],"article,":[59],"we":[60],"propose":[61],"CROCUS,":[62],"a":[63,109,189],"framework":[64],"that":[65,146],"enables":[66],"compute":[67,82,94,113],"resource":[68],"orchestration":[69],"enhance":[71],"cluster-wide":[72],"performance.":[74],"CROCUS":[77,115,136,147],"takes":[78],"into":[79],"account":[80],"all":[81],"resources":[83],"local":[86],"remote":[88],"{CPU,":[89],"GPU}":[90],"by":[91,152],"managing":[92],"decentralized":[93],"pools.":[95,114],"An":[96],"opportunistic":[97],"Load-Aware":[98],"Fingerprint":[99],"Scheduler":[100],"(LAFS),":[101],"distributes":[102],"offloads":[104],"compute-intensive":[105],"load-aware":[110],"fashion":[111],"highly":[117],"generic":[118],"can":[120],"be":[121],"adopted":[122],"both":[124],"inline":[125],"offline":[127],"with":[129,155,162],"different":[130,177],"tier":[132],"configurations.":[133],"We":[134],"implemented":[135],"Ceph":[138,161],"scale-out":[139],"system.":[141],"Our":[142,170],"extensive":[143],"evaluation":[144],"shows":[145],"reduces":[148],"overhead":[151],"86":[153],"percent":[154,186],"4KB":[156],"size":[158],"compared":[159],"baseline":[163],"while":[165],"maintaining":[166],"high":[167],"disk-space":[168],"savings.":[169],"proposed":[171],"LAFS":[172],"scheduler,":[173],"when":[174],"tested":[175],"internal":[178],"external":[180],"contention":[181],"scenarios":[182],"also":[183],"showed":[184],"54":[185],"improvement":[187],"fixed":[190],"static":[192],"scheduling":[193],"approach.":[194]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3006437988","counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-04-13T07:49:10.303316","created_date":"2020-02-24"}