{"id":"https://openalex.org/W2727180277","doi":"https://doi.org/10.1145/3093338.3093351","title":"Insights into Research Computing Operations using Big Data-Powered Log Analysis","display_name":"Insights into Research Computing Operations using Big Data-Powered Log Analysis","publication_year":2017,"publication_date":"2017-07-05","ids":{"openalex":"https://openalex.org/W2727180277","doi":"https://doi.org/10.1145/3093338.3093351","mag":"2727180277"},"language":"en","primary_location":{"id":"doi:10.1145/3093338.3093351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093338.3093351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2017: Sustainability, Success and Impact","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/A5100453054","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0002-3383-2191"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fang Cherry Liu","raw_affiliation_strings":["Partnership for an Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883722","display_name":"Weijia Xu","orcid":"https://orcid.org/0000-0002-5134-6381"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijia Xu","raw_affiliation_strings":["Texas Advanced Computing Center, University of Texas, Austin, TX"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, University of Texas, Austin, TX","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078584378","display_name":"Mehmet Belgin","orcid":"https://orcid.org/0000-0001-8613-3485"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Belgin","raw_affiliation_strings":["Partnership for an Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057218817","display_name":"Ruizhu Huang","orcid":"https://orcid.org/0000-0003-3285-1945"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhu Huang","raw_affiliation_strings":["Texas Advanced Computing Center, University of Texas, Austin, TX"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, University of Texas, Austin, TX","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047933233","display_name":"Blake C. Fleischer","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blake C. Fleischer","raw_affiliation_strings":["Partnership for an Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Partnership for an Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100453054"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.4181,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91172921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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":0.9987999796867371,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761923611164093},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7023007869720459},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6889065504074097},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6815218925476074},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5431119799613953},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5337396860122681},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5260974168777466},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.5200297832489014},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5033895373344421},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4597582519054413},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42359912395477295},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3796009421348572},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3499342203140259},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2233067750930786},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16410091519355774},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14544597268104553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761923611164093},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7023007869720459},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6889065504074097},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6815218925476074},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5431119799613953},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5337396860122681},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5260974168777466},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.5200297832489014},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5033895373344421},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4597582519054413},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42359912395477295},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3796009421348572},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3499342203140259},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2233067750930786},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16410091519355774},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14544597268104553},{"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/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3093338.3093351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093338.3093351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2017: Sustainability, Success and Impact","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":0.550000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1968411163","https://openalex.org/W2120585109","https://openalex.org/W2189465200","https://openalex.org/W2212774021","https://openalex.org/W2507854792","https://openalex.org/W2519604594","https://openalex.org/W2519997864"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2799508461"],"abstract_inverted_index":{"Research":[0],"computing":[1,11,232],"centers":[2,60],"provide":[3],"a":[4,42,54,80,121,161],"wide":[5],"variety":[6],"of":[7,28,45,86,98,110,116,145,149,180,199,217,230],"services":[8,63],"including":[9],"large-scale":[10],"resources,":[12],"data":[13,68,100,123,141,150,189,193],"storage,":[14],"high-speed":[15],"interconnect":[16],"and":[17,32,72,128,137,212,225],"scientific":[18,49],"software":[19,213],"repositories":[20],"to":[21,53,78,159,168],"facilitate":[22],"continuous":[23],"competitive":[24],"research.":[25],"Efficient":[26],"management":[27,229],"these":[29],"complex":[30],"resources":[31],"services,":[33,73],"as":[34,36,166,185,187],"well":[35,186],"ensuring":[37],"their":[38],"fair":[39],"use":[40,61,109],"by":[41],"large":[43,84,147],"number":[44],"researchers":[46],"from":[47,70,93,152],"different":[48,183],"domains":[50],"are":[51,219],"key":[52],"center's":[55],"success.":[56],"Almost":[57],"all":[58,216],"research":[59,231],"monitoring":[62],"based":[64,125],"on":[65,83,126],"real":[66],"time":[67],"gathered":[69],"systems":[71,208],"but":[74],"often":[75],"lack":[76],"tools":[77,112],"perform":[79],"deeper":[81],"analysis":[82,163],"volumes":[85,148],"historical":[87],"logs":[88],"for":[89,107,113,227],"identifying":[90],"insightful":[91],"trends":[92],"recurring":[94],"events.":[95],"The":[96],"size":[97],"collected":[99,151],"can":[101],"be":[102],"massive,":[103],"posing":[104],"significant":[105],"challenges":[106],"the":[108,178,197],"conventional":[111,171],"this":[114,192],"kind":[115],"analysis.":[117],"This":[118,140],"paper":[119],"describes":[120],"big":[122],"pipeline":[124,142,175],"Hadoop":[127],"Spark":[129],"technologies,":[130],"developed":[131],"in":[132,164,182,222],"close":[133],"collaboration":[134],"between":[135],"TACC":[136],"Georgia":[138],"Tech.":[139],"is":[143],"capable":[144],"processing":[146],"schedulers":[153],"using":[154],"PBSTools,":[155],"making":[156],"it":[157],"possible":[158],"run":[160],"deep":[162],"minutes":[165],"opposed":[167],"hours":[169],"with":[170],"tools.":[172],"Our":[173],"component-based":[174],"design":[176],"adds":[177],"flexibility":[179],"plugging":[181],"components,":[184],"promotes":[188],"reuse.":[190],"Using":[191],"pipeline,":[194],"we":[195],"demonstrate":[196],"process":[198],"formulating":[200],"several":[201],"critical":[202,220],"operational":[203,210],"questions":[204],"around":[205],"researcher":[206],"behavior,":[207],"health,":[209],"aspects":[211],"usage":[214],"trends,":[215],"which":[218],"factors":[221],"determining":[223],"solutions":[224],"strategies":[226],"efficient":[228],"centers.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}