{"id":"https://openalex.org/W2928834531","doi":"https://doi.org/10.1145/3297663.3310302","title":"Characterization of a Big Data Storage Workload in the Cloud","display_name":"Characterization of a Big Data Storage Workload in the Cloud","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2928834531","doi":"https://doi.org/10.1145/3297663.3310302","mag":"2928834531"},"language":"en","primary_location":{"id":"doi:10.1145/3297663.3310302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297663.3310302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.vu.nl/ws/files/87101046/Characterization_of_a_big_data_storage_workload_in_the_cloud.pdf","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":["Delft University of Technology & Databricks, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology & Databricks, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063586731","display_name":"Alicja \u0141uszczak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alicja \u0141uszczak","raw_affiliation_strings":["Databricks B.V., Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks B.V., Amsterdam, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071047865","display_name":"Cristina L. Abad","orcid":"https://orcid.org/0000-0002-9263-673X"},"institutions":[{"id":"https://openalex.org/I2135383","display_name":"Escuela Superior Politecnica del Litoral","ror":"https://ror.org/04qenc566","country_code":"EC","type":"education","lineage":["https://openalex.org/I2135383"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Cristina L. Abad","raw_affiliation_strings":["Escuela Superior Politecnica del Litoral, Guayaquil, Ecuador"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela Superior Politecnica del Litoral, Guayaquil, Ecuador","institution_ids":["https://openalex.org/I2135383"]}]},{"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, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"44"},"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":0.9962000250816345,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9872999787330627,"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/spark","display_name":"SPARK (programming language)","score":0.8834739923477173},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.8670241236686707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242800831794739},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8083498477935791},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7235464453697205},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.648088812828064},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4939790368080139},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4097149968147278},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4084126949310303},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3844965696334839},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3173275291919708}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8834739923477173},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.8670241236686707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242800831794739},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8083498477935791},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7235464453697205},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.648088812828064},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4939790368080139},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4097149968147278},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4084126949310303},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3844965696334839},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3173275291919708},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3297663.3310302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297663.3310302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:publications/b0f2a7a7-1594-4412-8719-a39c5196d0f1","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/b0f2a7a7-1594-4412-8719-a39c5196d0f1","pdf_url":"https://research.vu.nl/ws/files/87101046/Characterization_of_a_big_data_storage_workload_in_the_cloud.pdf","source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","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, Abad, C L, \u0141uszczak, A & Iosup, A 2019, Characterization of a big data storage workload in the cloud. in ICPE 2019 : Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering. Association for Computing Machinery, Inc, New York, NY, pp. 33-44, 10th ACM/SPEC International Conference on Performance Engineering, ICPE 2019, Mumbai, India, 7/04/19. https://doi.org/10.1145/3297663.3310302","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:research.vu.nl:openaire/b0f2a7a7-1594-4412-8719-a39c5196d0f1","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/b0f2a7a7-1594-4412-8719-a39c5196d0f1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","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, Abad, C L, \u0141uszczak, A & Iosup, A 2019, Characterization of a big data storage workload in the cloud. in ICPE 2019 : Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering. Association for Computing Machinery, Inc, New York, NY, pp. 33-44, 10th ACM/SPEC International Conference on Performance Engineering, ICPE 2019, Mumbai, India, 7/04/19. https://doi.org/10.1145/3297663.3310302","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:research.vu.nl:publications/b0f2a7a7-1594-4412-8719-a39c5196d0f1","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/b0f2a7a7-1594-4412-8719-a39c5196d0f1","pdf_url":"https://research.vu.nl/ws/files/87101046/Characterization_of_a_big_data_storage_workload_in_the_cloud.pdf","source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","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, Abad, C L, \u0141uszczak, A & Iosup, A 2019, Characterization of a big data storage workload in the cloud. in ICPE 2019 : Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering. Association for Computing Machinery, Inc, New York, NY, pp. 33-44, 10th ACM/SPEC International Conference on Performance Engineering, ICPE 2019, Mumbai, India, 7/04/19. https://doi.org/10.1145/3297663.3310302","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2928834531.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W8861657","https://openalex.org/W103650626","https://openalex.org/W1825603816","https://openalex.org/W1974534485","https://openalex.org/W2021171338","https://openalex.org/W2030315117","https://openalex.org/W2074899371","https://openalex.org/W2075771049","https://openalex.org/W2088443439","https://openalex.org/W2100618668","https://openalex.org/W2104993419","https://openalex.org/W2119565742","https://openalex.org/W2120751691","https://openalex.org/W2125901106","https://openalex.org/W2149140091","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2293392140","https://openalex.org/W2528650285","https://openalex.org/W2783985323","https://openalex.org/W2886990233","https://openalex.org/W2963436092","https://openalex.org/W2998553639","https://openalex.org/W3083700386","https://openalex.org/W4238584892"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2547038763","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"The":[0],"proliferation":[1,157],"of":[2,24,50,75,87,95,102,107,110,123,138,144,149,153,156,158],"big":[3,76,159],"data":[4,77,160],"processing":[5,78],"platforms":[6],"has":[7],"led":[8],"to":[9],"radically":[10],"different":[11],"system":[12],"designs,":[13],"such":[14,25,90],"as":[15,91],"MapReduce":[16,36],"and":[17,29,65,97,104,109,127,132,140,146,155],"the":[18,22,48,92,99,105,121,136,150],"newer":[19],"Spark.":[20],"Understanding":[21],"workloads":[23,37,52],"systems":[26,125],"facilitates":[27],"tuning":[28],"could":[30,119],"foster":[31],"new":[32,124],"designs.":[33,128],"However,":[34],"whereas":[35],"have":[38],"been":[39],"characterized":[40],"extensively,":[41],"relatively":[42],"little":[43],"public":[44],"knowledge":[45],"exists":[46],"about":[47],"characteristics":[49],"Spark":[51,69],"in":[53,60],"representative":[54],"environments.":[55],"To":[56],"address":[57],"this":[58,61],"problem,":[59],"work":[62],"we":[63,114],"collect":[64],"analyze":[66],"a":[67,72,85],"6-month":[68],"workload":[70],"from":[71],"major":[73],"provider":[74],"services,":[79],"Databricks.":[80],"Our":[81,129],"analysis":[82,134],"focuses":[83],"on":[84],"number":[86],"key":[88],"features,":[89],"long-term":[93],"trends":[94],"reads":[96],"modifications,":[98,154],"statistical":[100],"properties":[101],"reads,":[103],"popularity":[106],"clusters":[108],"file":[111],"formats.":[112,162],"Overall,":[113],"present":[115],"numerous":[116],"findings":[117],"that":[118],"form":[120],"basis":[122],"studies":[126],"quantitative":[130],"evidence":[131],"its":[133],"suggest":[135],"existence":[137],"daily":[139],"weekly":[141],"load":[142],"imbalances,":[143],"heavy-tailed":[145],"bursty":[147],"behaviour,":[148],"relative":[151],"rarity":[152],"specific":[161]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}