{"id":"https://openalex.org/W4384705386","doi":"https://doi.org/10.1109/ipdps54959.2023.00028","title":"Drill: Log-based Anomaly Detection for Large-scale Storage Systems Using Source Code Analysis","display_name":"Drill: Log-based Anomaly Detection for Large-scale Storage Systems Using Source Code Analysis","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4384705386","doi":"https://doi.org/10.1109/ipdps54959.2023.00028"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps54959.2023.00028","doi":"https://doi.org/10.1109/ipdps54959.2023.00028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps54959.2023.00028","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5046324058","display_name":"Di Zhang","orcid":"https://orcid.org/0000-0002-6913-5187","observed_orcids":["https://orcid.org/0000-0002-6913-5187"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Zhang","raw_affiliation_strings":["University of North Carolina at Charlotte,Computer Science Department","Computer Science Department, University of North Carolina at Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Computer Science Department","institution_ids":["https://openalex.org/I102149020"]},{"raw_affiliation_string":"Computer Science Department, University of North Carolina at Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066243096","display_name":"Chris Egersdoerfer","orcid":"https://orcid.org/0009-0004-7072-2209","observed_orcids":["https://orcid.org/0009-0004-7072-2209"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Egersdoerfer","raw_affiliation_strings":["University of North Carolina at Charlotte,Computer Science Department","Computer Science Department, University of North Carolina at Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Computer Science Department","institution_ids":["https://openalex.org/I102149020"]},{"raw_affiliation_string":"Computer Science Department, University of North Carolina at Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061218003","display_name":"Tabassum Mahmud","orcid":"https://orcid.org/0009-0009-5271-7066","observed_orcids":["https://orcid.org/0009-0009-5271-7066"]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tabassum Mahmud","raw_affiliation_strings":["Iowa State University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004195454","display_name":"Mai Zheng","orcid":"https://orcid.org/0000-0002-0741-3436","observed_orcids":["https://orcid.org/0000-0002-0741-3436"]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mai Zheng","raw_affiliation_strings":["Iowa State University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012002926","display_name":"Dong Dai","orcid":"https://orcid.org/0000-0003-4078-8149","observed_orcids":["https://orcid.org/0000-0003-4078-8149"]},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Dai","raw_affiliation_strings":["University of North Carolina at Charlotte,Computer Science Department","Computer Science Department, University of North Carolina at Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Computer Science Department","institution_ids":["https://openalex.org/I102149020"]},{"raw_affiliation_string":"Computer Science Department, University of North Carolina at Charlotte","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6943,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91343254,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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":1.0,"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":0.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/log-based-anomaly-detection","display_name":"log anomaly detection","score":0.9900000095367432},{"id":"https://openalex.org/keywords/distributed-storage","display_name":"distributed storage","score":0.875},{"id":"https://openalex.org/keywords/lustre","display_name":"Lustre","score":0.9340000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887737154960632},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6226800680160522},{"id":"https://openalex.org/C180699724","wikidata":"https://www.wikidata.org/wiki/Q1877782","display_name":"Lustre (file system)","level":3,"score":0.5687804818153381},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5608025789260864},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5115717053413391},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.503389298915863},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42643195390701294},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33134371042251587},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.23817121982574463},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2065129280090332},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20308804512023926},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0924842357635498},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps54959.2023.00028","doi":"https://doi.org/10.1109/ipdps54959.2023.00028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps54959.2023.00028","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1520857056","https://openalex.org/W1540258466","https://openalex.org/W1919179112","https://openalex.org/W1924770834","https://openalex.org/W1965626898","https://openalex.org/W2039157918","https://openalex.org/W2079735306","https://openalex.org/W2094924503","https://openalex.org/W2096017373","https://openalex.org/W2105454049","https://openalex.org/W2114554028","https://openalex.org/W2130678025","https://openalex.org/W2131774270","https://openalex.org/W2173213060","https://openalex.org/W2187358498","https://openalex.org/W2250539671","https://openalex.org/W2401686019","https://openalex.org/W2560021099","https://openalex.org/W2583874385","https://openalex.org/W2626778328","https://openalex.org/W2753478887","https://openalex.org/W2754665629","https://openalex.org/W2767094836","https://openalex.org/W2767346922","https://openalex.org/W2807975761","https://openalex.org/W2890169599","https://openalex.org/W2896457183","https://openalex.org/W2947815220","https://openalex.org/W2953498285","https://openalex.org/W2963341956","https://openalex.org/W2965838158","https://openalex.org/W3080528907","https://openalex.org/W3095840026","https://openalex.org/W3175109846","https://openalex.org/W3185152627","https://openalex.org/W4205965165","https://openalex.org/W4220730878","https://openalex.org/W4320060562"],"related_works":["https://openalex.org/W1978232743","https://openalex.org/W2560021099","https://openalex.org/W3185152627","https://openalex.org/W4405778637","https://openalex.org/W4385621806","https://openalex.org/W7163543695","https://openalex.org/W4409729599","https://openalex.org/W7214662090","https://openalex.org/W4386176731","https://openalex.org/W2804315071"],"abstract_inverted_index":{"Large-scale":[0],"storage":[1,130,150],"systems,":[2,9,42],"a":[3,88,114,176],"critical":[4,28],"part":[5],"of":[6,40,101,108,124,146],"modern":[7],"computing":[8],"are":[10],"subject":[11],"to":[12,93,119,163],"various":[13],"runtime":[14,25,34,125],"bugs,":[15],"failures,":[16],"and":[17,31,69,97,135,154],"anomalies":[18,23],"in":[19,64,82],"production.":[20],"Identifying":[21],"their":[22],"at":[24],"is":[26,87,175],"thus":[27],"for":[29,50,179],"users":[30],"administrators.":[32],"Since":[33],"logs":[35,126],"record":[36],"the":[37,41,83,98,102,106,140],"important":[38],"status":[39],"log-based":[43,57],"anomaly":[44,58,170,181],"detection":[45,59,171],"has":[46],"been":[47],"studied":[48],"extensively":[49],"timely":[51],"identifying":[52],"system":[53],"malfunctions.":[54],"However,":[55],"existing":[56,109],"solutions":[60],"share":[61],"common":[62,89],"limitations":[63],"representing":[65],"log":[66,76,116,136],"entries":[67,77],"accurately":[68],"robustly,":[70],"hence":[71],"can":[72,160],"not":[73,80],"effectively":[74],"handle":[75],"that":[78,158],"were":[79],"seen":[81],"historical":[84],"logs,":[85],"which":[86],"real-world":[90],"scenario":[91],"due":[92],"logs'":[94],"inherent":[95],"rarity":[96],"continuous":[99],"evolution":[100],"systems.":[103],"To":[104],"address":[105],"issues":[107],"methods,":[110],"we":[111,156],"propose":[112],"Drill,":[113],"new":[115],"pre-processing":[117],"method":[118],"generate":[120],"high-quality":[121],"vector":[122],"representation":[123],"by":[127],"leveraging":[128],"both":[129],"system-specific":[131],"sentiment-classifying":[132],"language":[133],"models":[134],"contexts":[137],"built":[138],"from":[139],"source":[141],"code.":[142],"Through":[143],"extensive":[144],"evaluations":[145],"two":[147],"representative":[148],"distributed":[149],"systems":[151],"(Apache":[152],"HDFS":[153],"Lustre),":[155],"show":[157],"Drill":[159],"achieve":[161],"up":[162],"41%":[164],"improvement":[165],"when":[166],"compared":[167],"with":[168],"state-of-the-art":[169],"solutions,":[172],"showing":[173],"it":[174],"promising":[177],"solution":[178],"general":[180],"detection.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-07-20T00:00:00"}