{"id":"https://openalex.org/W3109056343","doi":"https://doi.org/10.1145/3415958.3433046","title":"Event Management and Monitoring Framework for HPC Environments using ServiceNow and Prometheus","display_name":"Event Management and Monitoring Framework for HPC Environments using ServiceNow and Prometheus","publication_year":2020,"publication_date":"2020-11-02","ids":{"openalex":"https://openalex.org/W3109056343","doi":"https://doi.org/10.1145/3415958.3433046","mag":"3109056343"},"language":"en","primary_location":{"id":"doi:10.1145/3415958.3433046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3415958.3433046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/7ch6t25w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043623059","display_name":"Nitin Sukhija","orcid":"https://orcid.org/0000-0002-2083-1819"},"institutions":[{"id":"https://openalex.org/I169494899","display_name":"Slippery Rock University","ror":"https://ror.org/0369st156","country_code":"US","type":"education","lineage":["https://openalex.org/I169494899"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitin Sukhija","raw_affiliation_strings":["Department of Computer Science, Slippery Rock University of Pennsylvania, Slippery Rock, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Slippery Rock University of Pennsylvania, Slippery Rock, PA","institution_ids":["https://openalex.org/I169494899","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025254901","display_name":"Elizabeth Bautista","orcid":"https://orcid.org/0000-0001-5161-4967"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Bautista","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078120558","display_name":"Owen James","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Owen James","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048206382","display_name":"Daniel Gens","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gens","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002909582","display_name":"Siqi Deng","orcid":"https://orcid.org/0009-0004-2211-8322"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Deng","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039478250","display_name":"Yulok Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulok Lam","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029597260","display_name":"Tony Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tony Quan","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088471185","display_name":"Basil Lalli","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Basil Lalli","raw_affiliation_strings":["NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC, Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7848,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92568835,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.7278388738632202},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7030059099197388},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5692629814147949},{"id":"https://openalex.org/keywords/national-laboratory","display_name":"National laboratory","score":0.48015254735946655},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.44275838136672974},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3996519148349762},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.3472995162010193},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3393322825431824},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3276708126068115},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19409319758415222},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1563921868801117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278388738632202},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7030059099197388},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5692629814147949},{"id":"https://openalex.org/C2991948145","wikidata":"https://www.wikidata.org/wiki/Q16801175","display_name":"National laboratory","level":2,"score":0.48015254735946655},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.44275838136672974},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3996519148349762},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3472995162010193},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3393322825431824},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3276708126068115},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19409319758415222},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1563921868801117},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C61696701","wikidata":"https://www.wikidata.org/wiki/Q770766","display_name":"Engineering 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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3415958.3433046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3415958.3433046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt7ch6t25w","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7ch6t25w","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt7ch6t25w","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7ch6t25w","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W344292500","https://openalex.org/W1476683968","https://openalex.org/W1835640267","https://openalex.org/W2117411026","https://openalex.org/W2501089562","https://openalex.org/W2504051149","https://openalex.org/W2519997864","https://openalex.org/W2533137494","https://openalex.org/W2890042510","https://openalex.org/W2920975095","https://openalex.org/W2963251898","https://openalex.org/W2979133685","https://openalex.org/W2998311128","https://openalex.org/W3016092102"],"related_works":["https://openalex.org/W2341184295","https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2765823764","https://openalex.org/W306539506","https://openalex.org/W2227905990","https://openalex.org/W2079244304","https://openalex.org/W2140786083"],"abstract_inverted_index":{"The":[0,63,154],"challenge":[1],"of":[2,8,84,86,108,136,200],"monitoring":[3,61,129],"and":[4,20,24,27,52,88,94,104,128,160,170,177,208],"event":[5,126],"response":[6],"management":[7,127,207],"a":[9,197],"high":[10],"performance":[11],"computing":[12,118],"facility":[13,36],"grows":[14],"significantly":[15],"as":[16,182,184],"the":[17,30,34,39,49,56,72,82,106,115,133,137,142,157,167,192],"facilities":[18],"employs":[19],"orchestrates":[21],"more":[22,92,186],"complex":[23],"heterogeneous":[25],"systems":[26,140],"infrastructure.":[28],"As":[29],"computational":[31,40],"components":[32],"encompassing":[33],"HPC":[35],"system":[37],"increases,":[38],"staff":[41],"experiences":[42],"rise":[43],"in":[44,180],"alert":[45,89],"fatigue":[46],"due":[47],"to":[48,55,80,173],"false":[50],"alarms":[51],"noise":[53],"related":[54],"similar":[57],"events":[58,109],"generated":[59,113],"by":[60,114,191],"tools.":[62],"National":[64,75,145,147],"Energy":[65,148],"Research":[66,149],"Scientific":[67,150],"Computing":[68,151],"Center":[69,152],"(NERSC)":[70],"at":[71,141,164],"Lawrence":[73,143],"Berkeley":[74,144],"Laboratory":[76],"(LBNL)":[77],"has":[78],"begun":[79],"address":[81],"issues":[83],"duplication":[85],"alerts":[87],"remediation.":[90],"However,":[91],"automation":[93],"integration":[95],"is":[96],"needed":[97],"for":[98,203],"collecting,":[99],"aggregating,":[100],"correlating,":[101],"analyzing,":[102],"managing":[103],"visualizing":[105],"scale":[107],"that":[110,131,195],"will":[111],"be":[112],"emergent":[116],"hybrid":[117],"infrastructures.":[119],"In":[120],"this":[121],"paper,":[122],"we":[123],"present":[124],"an":[125,204],"framework":[130,155],"addresses":[132],"operational":[134],"needs":[135],"future":[138],"pre-exascale":[139],"Laboratory's":[146],"(NERSC).":[153],"integrates":[156],"Operations":[158],"Monitoring":[159],"Notification":[161],"Infrastructure":[162],"(OMNI)":[163],"NERSC":[165],"with":[166],"Prometheus,":[168],"Grafana":[169],"ServiceNow":[171],"platforms":[172],"help":[174],"identify,":[175],"diagnose,":[176],"resolve":[178],"incidents":[179],"real-time,":[181],"well":[183],"conduct":[185],"thorough":[187],"post-incident":[188],"reviews":[189],"enabled":[190],"intuitive":[193],"dashboards":[194],"provides":[196],"single":[198],"pane":[199],"glass":[201],"console":[202],"efficient":[205],"operations":[206],"real-time":[209],"proactive":[210],"monitoring.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}