{"id":"https://openalex.org/W2615246652","doi":"https://doi.org/10.1145/3078468.3078500","title":"Big data analysis of cloud storage logs using spark","display_name":"Big data analysis of cloud storage logs using spark","publication_year":2017,"publication_date":"2017-05-19","ids":{"openalex":"https://openalex.org/W2615246652","doi":"https://doi.org/10.1145/3078468.3078500","mag":"2615246652"},"language":"en","primary_location":{"id":"doi:10.1145/3078468.3078500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078468.3078500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Systems and Storage Conference","raw_type":"proceedings-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/A5028176674","display_name":"Shelly Garion","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Shelly Garion","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028032307","display_name":"Hillel Kolodner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hillel Kolodner","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014058894","display_name":"Allon Adir","orcid":"https://orcid.org/0000-0001-8128-6706"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Allon Adir","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072874959","display_name":"Ehud Aharoni","orcid":"https://orcid.org/0000-0002-3647-1440"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ehud Aharoni","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026541410","display_name":"Lev Greenberg","orcid":"https://orcid.org/0000-0002-1981-9775"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lev Greenberg","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028176674"],"corresponding_institution_ids":["https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":0.4144,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64423798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","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/T12127","display_name":"Software System Performance and Reliability","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9943000078201294,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8758881092071533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743442177772522},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.717413604259491},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6901031732559204},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6282737851142883},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5823956727981567},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5016965866088867},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.44470277428627014},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.42496609687805176},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41886311769485474},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39974138140678406},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28879135847091675},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17616376280784607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0796053409576416}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8758881092071533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743442177772522},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.717413604259491},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6901031732559204},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6282737851142883},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5823956727981567},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5016965866088867},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.44470277428627014},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42496609687805176},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41886311769485474},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39974138140678406},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28879135847091675},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17616376280784607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0796053409576416},{"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/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:10.1145/3078468.3078500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078468.3078500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Systems and Storage Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1974021852","https://openalex.org/W2091351040"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W3191926225","https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W4245701730","https://openalex.org/W2511794504"],"abstract_inverted_index":{"We":[0],"use":[1],"Apache":[2],"Spark":[3,114],"analytics":[4,64],"to":[5,16,73,117,131],"investigate":[6],"the":[7,85,107,133],"logs":[8],"of":[9,31,35,44,128],"an":[10],"operational":[11],"cloud":[12],"object":[13],"store":[14],"service":[15],"understand":[17],"how":[18],"it":[19],"is":[20,72],"being":[21],"used.":[22],"This":[23],"investigation":[24],"involves":[25],"going":[26,120],"over":[27,41,121,125],"very":[28],"large":[29],"amounts":[30],"historical":[32,122,134],"data":[33,109,123,138],"(PBs":[34],"records":[36],"in":[37,99,139],"some":[38],"cases)":[39],"collected":[40,124],"long":[42,76,126],"periods":[43,77,127],"time":[45,129],"retroactively.":[46],"Existing":[47],"tools,":[48],"such":[49,65,89],"as":[50,66,90],"Elasticsearch-Logstash-Kibana":[51],"(ELK),":[52],"are":[53],"mainly":[54],"used":[55],"for":[56,75],"presenting":[57],"short-term":[58],"metrics":[59],"and":[60,101,130,142],"can-not":[61],"perform":[62],"advanced":[63],"machine":[67],"learning.":[68],"A":[69],"possible":[70],"solution":[71],"save":[74],"only":[78],"certain":[79],"aggregations":[80],"or":[81,92],"calculations":[82],"produced":[83],"from":[84],"raw":[86,108],"log":[87],"data,":[88],"averages":[91],"histograms,":[93],"however":[94],"these":[95],"must":[96],"be":[97,103],"decided":[98],"advance,":[100],"cannot":[102],"changed":[104],"retroactively":[105],"since":[106],"has":[110],"already":[111],"been":[112],"discarded.":[113],"allows":[115],"us":[116],"gain":[118],"insights":[119],"apply":[132],"models":[135],"on":[136],"online":[137],"a":[140],"simple":[141],"efficient":[143],"way.":[144]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
