{"id":"https://openalex.org/W2076164405","doi":"https://doi.org/10.1145/2391229.2391233","title":"Sailfish","display_name":"Sailfish","publication_year":2012,"publication_date":"2012-10-14","ids":{"openalex":"https://openalex.org/W2076164405","doi":"https://doi.org/10.1145/2391229.2391233","mag":"2076164405"},"language":"en","primary_location":{"id":"doi:10.1145/2391229.2391233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2391229.2391233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third ACM Symposium on Cloud Computing","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/A5070183492","display_name":"Sriram Rao","orcid":"https://orcid.org/0000-0002-3265-6165"},"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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Sriram Rao","raw_affiliation_strings":["Microsoft Corp","MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]},{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051301731","display_name":"Raghu Ramakrishnan","orcid":"https://orcid.org/0009-0007-5086-7664"},"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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Raghu Ramakrishnan","raw_affiliation_strings":["Microsoft Corp","MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]},{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002175828","display_name":"Adam Silberstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Silberstein","raw_affiliation_strings":["LinkedIn","LinkedIn#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LinkedIn","institution_ids":["https://openalex.org/I1316064682"]},{"raw_affiliation_string":"LinkedIn#TAB#","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043577377","display_name":"Mike Ovsiannikov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mike Ovsiannikov","raw_affiliation_strings":["Quantcast Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantcast Corp","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065339265","display_name":"Damian Reeves","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Damian Reeves","raw_affiliation_strings":["Quantcast Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantcast Corp","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0899,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.98804898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8686038255691528},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5907169580459595},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.589585542678833},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46080565452575684},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4308125376701355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4151294529438019},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37376824021339417},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3553859293460846},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24601203203201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8686038255691528},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5907169580459595},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.589585542678833},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46080565452575684},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4308125376701355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4151294529438019},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37376824021339417},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3553859293460846},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24601203203201294},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2391229.2391233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2391229.2391233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W65853127","https://openalex.org/W100509257","https://openalex.org/W1493893823","https://openalex.org/W1524103123","https://openalex.org/W1834532152","https://openalex.org/W2010279913","https://openalex.org/W2035543557","https://openalex.org/W2044490410","https://openalex.org/W2050315205","https://openalex.org/W2081804145","https://openalex.org/W2090452820","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2110086534","https://openalex.org/W2110104287","https://openalex.org/W2114103324","https://openalex.org/W2114303224","https://openalex.org/W2119565742","https://openalex.org/W2122465391","https://openalex.org/W2141267666","https://openalex.org/W2144518192","https://openalex.org/W2157355837"],"related_works":["https://openalex.org/W2045155990","https://openalex.org/W4313163053","https://openalex.org/W3045811229","https://openalex.org/W4300973204","https://openalex.org/W1483408780","https://openalex.org/W4284884309","https://openalex.org/W2908749798","https://openalex.org/W4243842598","https://openalex.org/W2105980483","https://openalex.org/W1514435881"],"abstract_inverted_index":{"In":[0],"this":[1,189],"paper,":[2],"we":[3,56,112],"present":[4,99],"Sailfish,":[5],"a":[6,121],"new":[7],"Map-Reduce":[8,82],"framework":[9],"for":[10,49,89,170,173],"large":[11],"scale":[12],"data":[13,25,51,69,91,145],"processing.":[14],"The":[15],"Sailfish":[16,79,104,136,178],"design":[17,137],"is":[18],"centered":[19],"around":[20],"aggregating":[21],"intermediate":[22],"data,":[23],"specifically":[24],"produced":[26],"by":[27,33,39,71,76],"map":[28,93],"tasks":[29,94],"and":[30,53,74,127,147,180],"consumed":[31],"later":[32],"reduce":[34,96],"tasks,":[35],"to":[36,66,86,95,115,165],"improve":[37],"performance":[38,106,119],"batching":[40],"disk":[41],"I/O.":[42],"We":[43,98,131],"introduce":[44],"an":[45,60,153],"abstraction":[46],"called":[47],"I-files":[48,88],"supporting":[50],"aggregation,":[52],"describe":[54],"how":[55],"implemented":[57],"it":[58],"as":[59,186,194],"extension":[61],"of":[62,107,124,157,188],"the":[63,81,135,181],"distributed":[64],"filesystem,":[65],"efficiently":[67],"batch":[68],"written":[70],"multiple":[72,77],"writers":[73],"read":[75],"readers.":[78],"adapts":[80],"layer":[83],"in":[84,110,144,160],"Hadoop":[85],"use":[87],"transporting":[90],"from":[92],"tasks.":[97],"experimental":[100],"results":[101],"demonstrating":[102],"that":[103,134,141],"improves":[105],"standard":[108],"Hadoop;":[109],"particular,":[111],"show":[113],"20%":[114],"5":[116],"times":[117],"faster":[118],"on":[120,163],"representative":[122],"mix":[123],"real":[125],"jobs":[126],"datasets":[128],"at":[129],"Yahoo!.":[130],"also":[132],"demonstrate":[133],"enables":[138],"auto-tuning":[139],"functionality":[140],"handles":[142],"changes":[143],"volume":[146],"skewed":[148],"distributions":[149],"effectively,":[150],"thereby":[151],"addressing":[152],"important":[154],"practical":[155],"drawback":[156],"Hadoop,":[158],"which":[159],"contrast":[161],"relies":[162],"programmers":[164],"configure":[166],"system":[167],"parameters":[168],"appropriately":[169],"each":[171,174],"job,":[172],"input":[175],"dataset.":[176],"Our":[177],"implementation":[179],"other":[182],"software":[183],"components":[184],"developed":[185],"part":[187],"paper":[190],"has":[191],"been":[192],"released":[193],"open":[195],"source.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}
