{"id":"https://openalex.org/W2976738393","doi":"https://doi.org/10.1109/infcomw.2019.8845043","title":"Efficient Estimation of Read Density when Caching for Big Data Processing","display_name":"Efficient Estimation of Read Density when Caching for Big Data Processing","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2976738393","doi":"https://doi.org/10.1109/infcomw.2019.8845043","mag":"2976738393"},"language":"en","primary_location":{"id":"doi:10.1109/infcomw.2019.8845043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2019.8845043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.scopus.com/inward/citedby.url?scp=85073235844&partnerID=8YFLogxK","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003364582","display_name":"Sacheendra Talluri","orcid":"https://orcid.org/0000-0003-3461-4919"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sacheendra Talluri","raw_affiliation_strings":["AtLarge Research and TU Delft, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AtLarge Research and TU Delft, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986556","display_name":"Alexandru Iosup","orcid":"https://orcid.org/0000-0001-8030-9398"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexandru Iosup","raw_affiliation_strings":["Vrije Universiteit, Amsterdam, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit, Amsterdam, the Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13637234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"502","last_page":"507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","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/T11478","display_name":"Caching and Content Delivery","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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.8832853436470032},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.804707944393158},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8039062023162842},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7121950387954712},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5900663733482361},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5582348108291626},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5063489675521851},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4451693594455719},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4300304651260376},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4137198030948639},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3814031481742859},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3716661036014557},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24811264872550964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8832853436470032},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.804707944393158},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8039062023162842},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7121950387954712},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5900663733482361},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5582348108291626},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5063489675521851},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4451693594455719},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4300304651260376},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4137198030948639},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3814031481742859},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3716661036014557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24811264872550964},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/infcomw.2019.8845043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2019.8845043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:publications/736df6f2-4d06-4c9d-9272-f67c622bf0ac","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/citedby.url?scp=85073235844&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400546","display_name":"Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Talluri, S & Iosup, A 2019, Efficient Estimation of Read Density when Caching for Big Data Processing. in Proceedings - IEEE INFOCOM 2019 : IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)., 8845043, INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 502-507, 2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019, Paris, France, 29/04/19. https://doi.org/10.1109/INFCOMW.2019.8845043","raw_type":"contributionToPeriodical"},{"id":"pmh:vu:oai:research.vu.nl:publications/736df6f2-4d06-4c9d-9272-f67c622bf0ac","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/736df6f2-4d06-4c9d-9272-f67c622bf0ac","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings - IEEE INFOCOM 2019: IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 502 - 507","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:research.vu.nl:publications/736df6f2-4d06-4c9d-9272-f67c622bf0ac","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/citedby.url?scp=85073235844&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400546","display_name":"Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Talluri, S & Iosup, A 2019, Efficient Estimation of Read Density when Caching for Big Data Processing. in Proceedings - IEEE INFOCOM 2019 : IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)., 8845043, INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 502-507, 2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019, Paris, France, 29/04/19. https://doi.org/10.1109/INFCOMW.2019.8845043","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1578858535","https://openalex.org/W1588407470","https://openalex.org/W1860107648","https://openalex.org/W1967373117","https://openalex.org/W2054308357","https://openalex.org/W2072853307","https://openalex.org/W2080234606","https://openalex.org/W2135916267","https://openalex.org/W2289797660","https://openalex.org/W2604771015","https://openalex.org/W2612838847","https://openalex.org/W2739832702","https://openalex.org/W2798520214","https://openalex.org/W2928834531","https://openalex.org/W2963554098","https://openalex.org/W2963979055","https://openalex.org/W3149866098","https://openalex.org/W4241687679","https://openalex.org/W4252238872","https://openalex.org/W6634647146","https://openalex.org/W6635217627","https://openalex.org/W6639025630","https://openalex.org/W6736175359","https://openalex.org/W6741503636","https://openalex.org/W6750798687"],"related_works":["https://openalex.org/W2147122795","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2167303720","https://openalex.org/W2268996566","https://openalex.org/W2109715593","https://openalex.org/W3161817247","https://openalex.org/W2012518269","https://openalex.org/W2068309140","https://openalex.org/W4239937081"],"abstract_inverted_index":{"Big":[0],"data":[1,41,95,202,227],"processing":[2],"systems":[3],"are":[4,14],"becoming":[5],"increasingly":[6],"more":[7,18],"present":[8],"in":[9,29,101],"cloud":[10],"workloads.":[11,84,96],"Consequently,":[12],"they":[13,48,70],"starting":[15],"to":[16,51,117,160,216],"incorporate":[17],"sophisticated":[19],"mechanisms":[20],"from":[21,181,205],"traditional":[22],"database":[23,83],"and":[24,62,78,82,186,208],"distributed":[25],"systems.":[26],"We":[27,97,104,140,173,194],"focus":[28],"this":[30,102],"work":[31],"on":[32,132,152],"the":[33,55,63,67,106,119,133,143,166,170,178,182,217],"use":[34,195],"of":[35,54,110,121,127,135,137,155,165],"caching":[36,86,179],"policies,":[37,111],"which":[38,112,146],"for":[39,200,225],"big":[40,94,201,226],"raise":[42],"important":[43],"new":[44,52],"challenges.":[45],"Not":[46],"only":[47],"must":[49,71],"respond":[50],"variants":[53],"trade-off":[56],"between":[57],"hit":[58],"rate,":[59],"response":[60],"time,":[61],"space":[64],"consumed":[65],"by":[66,169],"cache,":[68],"but":[69],"do":[72],"so":[73],"at":[74],"possibly":[75],"higher":[76],"volume":[77],"velocity":[79],"than":[80],"web":[81],"Previous":[85],"policies":[87,180],"have":[88],"not":[89],"been":[90],"tested":[91],"experimentally":[92],"with":[93,189,219],"address":[98],"these":[99],"challenges":[100],"work.":[103],"propose":[105],"Read":[107,183],"Density":[108,184],"family":[109,126],"is":[113,147],"a":[114,125,148],"principled":[115],"approach":[116],"quantify":[118],"utility":[120,128],"cached":[122],"objects":[123],"through":[124,175],"functions":[129],"that":[130],"depend":[131],"frequency":[134],"reads":[136],"an":[138,153],"object.":[139],"further":[141],"design":[142],"Approximate":[144],"Histogram,":[145],"policy-based":[149],"technique":[150,158],"based":[151],"array":[154],"counters.":[156],"This":[157],"promises":[159],"achieve":[161,213],"runtime-space":[162],"efficient":[163],"computation":[164],"metric":[167],"required":[168],"cache":[171],"policy.":[172],"evaluate":[174],"trace-based":[176],"simulation":[177],"family,":[185],"compare":[187],"them":[188],"over":[190],"ten":[191],"state-of-the-art":[192],"alternatives.":[193],"two":[196],"workload":[197],"traces":[198],"representative":[199],"processing,":[203],"collected":[204],"commercial":[206],"Spark":[207],"MapReduce":[209],"deployments.":[210],"While":[211],"we":[212],"comparable":[214],"performance":[215,223],"state-of-art":[218],"less":[220],"parameters,":[221],"meaningful":[222],"improvement":[224],"workloads":[228],"remain":[229],"elusive.":[230]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}