{"id":"https://openalex.org/W2113689712","doi":"https://doi.org/10.14778/1453856.1453961","title":"Online maintenance of very large random samples on flash storage","display_name":"Online maintenance of very large random samples on flash storage","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2113689712","doi":"https://doi.org/10.14778/1453856.1453961","mag":"2113689712"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453961","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453961","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5024224291","display_name":"Suman Nath","orcid":"https://orcid.org/0000-0001-7813-9756"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Suman Nath","raw_affiliation_strings":["Microsoft Research","Microsoft research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014824446","display_name":"Phillip B. Gibbons","orcid":"https://orcid.org/0000-0001-6967-2735"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Phillip B. Gibbons","raw_affiliation_strings":["Intel Research Pittsburgh","Intel Research Pittsburgh,"],"affiliations":[{"raw_affiliation_string":"Intel Research Pittsburgh","institution_ids":["https://openalex.org/I4210158342"]},{"raw_affiliation_string":"Intel Research Pittsburgh,","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024224291"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":14.4843,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.99044538,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"970","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8322943449020386},{"id":"https://openalex.org/keywords/flash-file-system","display_name":"Flash file system","score":0.7918748259544373},{"id":"https://openalex.org/keywords/flash-memory","display_name":"Flash memory","score":0.642630934715271},{"id":"https://openalex.org/keywords/flash","display_name":"Flash (photography)","score":0.6081987023353577},{"id":"https://openalex.org/keywords/flash-memory-emulator","display_name":"Flash memory emulator","score":0.48705413937568665},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4268644452095032},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4160914123058319},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3671499490737915},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34401094913482666},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.32341575622558594},{"id":"https://openalex.org/keywords/computer-memory","display_name":"Computer memory","score":0.17217129468917847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322943449020386},{"id":"https://openalex.org/C27670709","wikidata":"https://www.wikidata.org/wiki/Q5457555","display_name":"Flash file system","level":4,"score":0.7918748259544373},{"id":"https://openalex.org/C2776531357","wikidata":"https://www.wikidata.org/wiki/Q174077","display_name":"Flash memory","level":2,"score":0.642630934715271},{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.6081987023353577},{"id":"https://openalex.org/C96535780","wikidata":"https://www.wikidata.org/wiki/Q5457561","display_name":"Flash memory emulator","level":5,"score":0.48705413937568665},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4268644452095032},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4160914123058319},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3671499490737915},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34401094913482666},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32341575622558594},{"id":"https://openalex.org/C92855701","wikidata":"https://www.wikidata.org/wiki/Q5830907","display_name":"Computer memory","level":3,"score":0.17217129468917847},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/1453856.1453961","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453961","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.148.9239","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.148.9239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/people/sumann/vldbj10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.3073","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.3073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/76127/vldb2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.9570","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.9570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Edga/15-849/S09/papers//Nath-Gibbons-vldb08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W29556861","https://openalex.org/W1503287972","https://openalex.org/W1513366578","https://openalex.org/W1564774435","https://openalex.org/W1578513732","https://openalex.org/W1990946453","https://openalex.org/W2006803879","https://openalex.org/W2022942700","https://openalex.org/W2035712985","https://openalex.org/W2037701287","https://openalex.org/W2040793975","https://openalex.org/W2046441184","https://openalex.org/W2068739275","https://openalex.org/W2070991879","https://openalex.org/W2074953519","https://openalex.org/W2106264466","https://openalex.org/W2109464129","https://openalex.org/W2112400233","https://openalex.org/W2112479717","https://openalex.org/W2113046370","https://openalex.org/W2114828666","https://openalex.org/W2119764208","https://openalex.org/W2119885577","https://openalex.org/W2125154238","https://openalex.org/W2154165046","https://openalex.org/W2165068957","https://openalex.org/W2169982181","https://openalex.org/W2403319904","https://openalex.org/W2405586383","https://openalex.org/W3003688632"],"related_works":["https://openalex.org/W1937038249","https://openalex.org/W2391055460","https://openalex.org/W164278522","https://openalex.org/W2082353818","https://openalex.org/W1691732600","https://openalex.org/W2291767606","https://openalex.org/W2104588025","https://openalex.org/W2606330551","https://openalex.org/W1994190181","https://openalex.org/W2378293894"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,14,166,186,212,273],"flash":[3,33,52,98,146,184,228,263,277],"media":[4,34,147,229],"have":[5],"made":[6],"it":[7],"an":[8,86,142,219,225],"attractive":[9],"alternative":[10],"for":[11,46,97,145,215],"data":[12,42,71,113],"storage":[13],"a":[15,102,112,155,163,173,203,213,216],"wide":[16],"spectrum":[17],"of":[18,75,111,116,218,237,255,258,283],"computing":[19],"devices,":[20],"such":[21,125],"as":[22,61,63,126],"embedded":[23],"sensors,":[24],"mobile":[25],"phones,":[26],"PDA's,":[27],"laptops,":[28],"and":[29,69,129,152,178,191,205,240,249,286],"even":[30],"servers.":[31],"However,":[32],"has":[35,172],"many":[36,262],"unique":[37],"characteristics":[38],"that":[39,90,122,230,268],"make":[40],"existing":[41],"management/analytics":[43],"algorithms":[44,124,264],"designed":[45,180],"magnetic":[47],"disks":[48],"perform":[49],"poorly":[50],"with":[51,183,202,227],"storage.":[53],"For":[54],"example,":[55],"while":[56],"random":[57,66,109,290],"(page)":[58,67],"reads":[59],"are":[60,73,132,234,279],"fast":[62],"sequential":[64,79],"reads,":[65],"writes":[68,270],"in-place":[70],"updates":[72],"orders":[74,236,282],"magnitude":[76,238,284],"slower":[77],"than":[78,243,289],"writes.":[80,291],"In":[81],"this":[82],"paper,":[83],"we":[84,120,139,195,223],"consider":[85],"important":[87],"fundamental":[88],"problem":[89],"would":[91],"seem":[92],"to":[93,136,148,160,181,188,198,206,261],"be":[94,158],"particularly":[95],"challenging":[96],"storage:":[99],"efficiently":[100,161],"maintaining":[101],"very":[103],"large":[104,164,209],"(100":[105],"MBs":[106],"or":[107],"more)":[108],"sample":[110,165,210],"stream":[114],"(e.g.,":[115],"sensor":[117],"readings).":[118],"First,":[119],"show":[121,153],"previous":[123],"reservoir":[127,247],"sampling":[128,248],"geometric":[130,250],"file":[131],"not":[133],"readily":[134],"adapted":[135],"flash.":[137,167],"Second,":[138],"propose":[140],"B-FILE,":[141],"energy-efficient":[143,242,288],"abstraction":[144],"store":[149],"self-expiring":[150],"items,":[151],"how":[154],"B-FILE":[156,204,214],"can":[157],"used":[159],"maintain":[162,199],"Our":[168],"solution":[169],"is":[170,179,267],"simple,":[171],"small":[174],"(RAM)":[175],"memory":[176],"footprint,":[177],"cope":[182],"constraints":[185],"order":[187],"reduce":[189],"latency":[190],"energy":[192],"consumption.":[193],"Third,":[194],"provide":[196],"techniques":[197,233],"biased":[200],"samples":[201],"query":[207],"the":[208,274],"stored":[211],"subsample":[217],"arbitrary":[220],"size.":[221],"Finally,":[222],"present":[224],"evaluation":[226],"shows":[231],"our":[232,256],"several":[235],"faster":[239,285],"more":[241,287],"(flash-friendly":[244],"versions":[245],"of)":[246],"file.":[251],"A":[252],"key":[253],"finding":[254],"study,":[257],"potential":[259],"use":[260],"beyond":[265],"sampling,":[266],"\"semi-random\"":[269],"(as":[271],"defined":[272],"paper)":[275],"on":[276],"cards":[278],"over":[280],"two":[281]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}