{"id":"https://openalex.org/W5335935","doi":"https://doi.org/10.5555/1960475.1960477","title":"Tradeoffs in scalable data routing for deduplication clusters","display_name":"Tradeoffs in scalable data routing for deduplication clusters","publication_year":2011,"publication_date":"2011-02-15","ids":{"openalex":"https://openalex.org/W5335935","doi":"https://doi.org/10.5555/1960475.1960477","mag":"5335935"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.4983","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.4983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.usenix.org/events/fast11/tech/full_papers/Dong.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5086692495","display_name":"Wei Dong","orcid":"https://orcid.org/0000-0003-3067-8720","observed_orcids":["https://orcid.org/0000-0003-3067-8720"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Dong","raw_affiliation_strings":["Princeton University#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-3067-8720","affiliations":[{"raw_affiliation_string":"Princeton University#TAB#","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069996857","display_name":"Fred Douglis","orcid":"https://orcid.org/0000-0003-2472-0339","observed_orcids":["https://orcid.org/0000-0003-2472-0339"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fred Douglis","raw_affiliation_strings":["EMC;"],"raw_orcid":"https://orcid.org/0000-0003-2472-0339","affiliations":[{"raw_affiliation_string":"EMC;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399870","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-2095-7024","observed_orcids":["https://orcid.org/0000-0002-2095-7024","https://orcid.org/0000-0002-0517-2392"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Princeton University and EMC#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-2095-7024","affiliations":[{"raw_affiliation_string":"Princeton University and EMC#TAB#","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079487698","display_name":"Hugo Patterson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Patterson","raw_affiliation_strings":["EMC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EMC;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102028704","display_name":"Sazzala Reddy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sazzala Reddy","raw_affiliation_strings":["EMC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EMC;","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091766663","display_name":"Philip Shilane","orcid":"https://orcid.org/0000-0003-1235-0502","observed_orcids":["https://orcid.org/0000-0003-1235-0502"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip Shilane","raw_affiliation_strings":["EMC;"],"raw_orcid":"https://orcid.org/0000-0003-1235-0502","affiliations":[{"raw_affiliation_string":"EMC;","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.6164,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":{"value":0.9950962,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.00019999999494757503,"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":0.7440000176429749},{"id":"https://openalex.org/keywords/data-routing","display_name":"data routing","score":0.6890000104904175},{"id":"https://openalex.org/keywords/stateless-routing","display_name":"stateless routing","score":0.718999981880188},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.4729999899864197},{"id":"https://openalex.org/keywords/throughput","display_name":"throughput","score":0.7139999866485596},{"id":"https://openalex.org/keywords/data-backup-and-recovery","display_name":"data backup and recovery","score":0.6150000095367432},{"id":"https://openalex.org/keywords/data-compression","display_name":"data compression","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9555764198303223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143590688705444},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7085323333740234},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.700188934803009},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.6828712224960327},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.6548222899436951},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.6102457046508789},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5168407559394836},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45106130838394165},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4487369656562805},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28769731521606445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1889723539352417},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.4983","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.4983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.usenix.org/events/fast11/tech/full_papers/Dong.pdf","raw_type":"text"},{"id":"mag:5335935","doi":"https://doi.org/10.5555/1960475.1960477","is_oa":false,"landing_page_url":"https://static.usenix.org/events/fast11/tech/full_papers/Dong.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418422","display_name":"File and Storage Technologies","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"File and Storage Technologies","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7207000255584717,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W24740120","https://openalex.org/W69510097","https://openalex.org/W162607394","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1576397915","https://openalex.org/W1599186236","https://openalex.org/W1609518033","https://openalex.org/W1929726975","https://openalex.org/W1966085032","https://openalex.org/W1969126835","https://openalex.org/W1975868314","https://openalex.org/W2007842132","https://openalex.org/W2047484077","https://openalex.org/W2053449578","https://openalex.org/W2056980397","https://openalex.org/W2107745473","https://openalex.org/W2110298485","https://openalex.org/W2121133177","https://openalex.org/W2123845384","https://openalex.org/W2128912667","https://openalex.org/W2132627996","https://openalex.org/W2140733653","https://openalex.org/W2149993626","https://openalex.org/W2585172182","https://openalex.org/W2907710321"],"related_works":["https://openalex.org/W2014310906","https://openalex.org/W2583728456","https://openalex.org/W3202016598","https://openalex.org/W26020480","https://openalex.org/W2085553210","https://openalex.org/W2003696547","https://openalex.org/W2103275940","https://openalex.org/W2055899630","https://openalex.org/W12581771","https://openalex.org/W2076964673"],"abstract_inverted_index":{"As":[0],"data":[1,7,26,79,130],"have":[2,140],"been":[3,162],"growing":[4],"rapidly":[5],"in":[6,15,112,155,164],"centers,":[8],"deduplication":[9,40,45,89,98,150,175],"storage":[10,41,46,114,184],"systems":[11],"continuously":[12],"face":[13],"challenges":[14],"providing":[16],"the":[17,113],"corresponding":[18],"throughputs":[19],"and":[20,29,56,107,136,177],"capacities":[21],"necessary":[22],"to":[23,36,52,77,101,180],"move":[24],"backup":[25,28],"within":[27],"recovery":[30],"window":[31],"times.":[32],"One":[33],"approach":[34,160],"is":[35,51,76],"build":[37],"a":[38,66,87,104,109,165],"cluster":[39],"system":[42,47,90,168],"with":[43,65,94,121,133],"multiple":[44],"nodes.":[48,118],"The":[49,72,158],"goal":[50],"achieve":[53],"scalable":[54],"throughput":[55,176],"capacity":[57],"using":[58],"extremely":[59],"highthroughput":[60],"(e.g.":[61],"1.5":[62],"GB/s)":[63],"nodes,":[64,124],"minimal":[67],"loss":[68],"of":[69,103,116,123,183],"compression":[70],"ratio.":[71],"key":[73],"technical":[74],"issue":[75],"route":[78],"intelligently":[80],"at":[81],"an":[82],"appropriate":[83],"granularity.":[84],"We":[85],"present":[86],"cluster-based":[88],"that":[91,102,139,146,169],"can":[92,147],"deduplicate":[93],"high":[95],"throughput,":[96],"support":[97],"ratios":[99],"comparable":[100],"single":[105],"system,":[106],"maintain":[108],"low":[110,134],"variation":[111],"utilization":[115],"individual":[117],"In":[119],"experiments":[120],"dozens":[122],"we":[125],"examine":[126],"tradeoffs":[127],"between":[128],"stateless":[129,159],"routing":[131],"approaches":[132,138],"overhead":[135,142],"stateful":[137],"higher":[141],"but":[143],"avoid":[144],"imbalances":[145],"adversely":[148],"affect":[149],"effectiveness":[151],"for":[152,173],"some":[153],"datasets":[154],"large":[156],"clusters.":[157],"has":[161],"deployed":[163],"two-node":[166],"commercial":[167],"achieves":[170],"3":[171],"GB/s":[172],"multi-stream":[174],"currently":[178],"scales":[179],"5.6":[181],"PB":[182],"(assuming":[185],"20X":[186],"total":[187],"compression).":[188],"1":[189]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":21}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
