{"id":"https://openalex.org/W4386585137","doi":"https://doi.org/10.1145/3569951.3604396","title":"Jobstats: A Slurm-Compatible Job Monitoring Platform for CPU and GPU Clusters","display_name":"Jobstats: A Slurm-Compatible Job Monitoring Platform for CPU and GPU Clusters","publication_year":2023,"publication_date":"2023-07-23","ids":{"openalex":"https://openalex.org/W4386585137","doi":"https://doi.org/10.1145/3569951.3604396"},"language":"en","primary_location":{"id":"doi:10.1145/3569951.3604396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3569951.3604396","pdf_url":null,"source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3569951.3604396","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092841083","display_name":"Josko Plazonic","orcid":"https://orcid.org/0009-0000-6648-3568"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Josko Plazonic","raw_affiliation_strings":["OIT Research Computing, Princeton University, USA"],"raw_orcid":"https://orcid.org/0009-0000-6648-3568","affiliations":[{"raw_affiliation_string":"OIT Research Computing, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036623197","display_name":"Jonathan D. Halverson","orcid":"https://orcid.org/0009-0000-4877-3836"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Halverson","raw_affiliation_strings":["Princeton Institute for Computational Science and Engineering, Princeton University, USA"],"raw_orcid":"https://orcid.org/0009-0000-4877-3836","affiliations":[{"raw_affiliation_string":"Princeton Institute for Computational Science and Engineering, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067605290","display_name":"Troy J. Comi","orcid":"https://orcid.org/0000-0002-3215-4026"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Troy Comi","raw_affiliation_strings":["OIT Research Computing &amp; Department of Chemical and Biological Engineering, Princeton University, USA"],"raw_orcid":"https://orcid.org/0000-0002-3215-4026","affiliations":[{"raw_affiliation_string":"OIT Research Computing &amp; Department of Chemical and Biological Engineering, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092841083"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.787,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73732679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","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/T10715","display_name":"Distributed and Parallel Computing Systems","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.718116283416748},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4656238257884979},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.42465314269065857},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41699787974357605},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3813592791557312},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.27696430683135986},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23147577047348022},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18534567952156067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718116283416748},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4656238257884979},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.42465314269065857},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41699787974357605},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3813592791557312},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.27696430683135986},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23147577047348022},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18534567952156067}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3569951.3604396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3569951.3604396","pdf_url":null,"source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3569951.3604396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3569951.3604396","pdf_url":null,"source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2151316504","https://openalex.org/W2154983209","https://openalex.org/W3205113394","https://openalex.org/W6969259846"],"related_works":["https://openalex.org/W2071296827","https://openalex.org/W1827514603","https://openalex.org/W2030707850","https://openalex.org/W2332345327","https://openalex.org/W2012928711","https://openalex.org/W2024548679","https://openalex.org/W4288452443","https://openalex.org/W2138990193","https://openalex.org/W2397581384","https://openalex.org/W3165899388"],"abstract_inverted_index":{"Job":[0],"monitoring":[1,25,105],"on":[2,57],"high-performance":[3],"computing":[4],"clusters":[5],"is":[6],"important":[7],"for":[8,48,98,112],"evaluating":[9],"hardware":[10],"performance,":[11],"troubleshooting":[12],"failed":[13],"jobs,":[14],"identifying":[15],"inefficient":[16],"jobs":[17],"and":[18,27,60,73,115,127,135],"more.":[19],"The":[20,102],"combination":[21],"of":[22,91],"the":[23,28,95,125],"Prometheus":[24,43,126],"framework":[26],"Grafana":[29],"visualization":[30],"toolkit":[31],"has":[32],"proven":[33],"successful":[34],"in":[35,94],"recent":[36],"years.":[37],"This":[38],"work":[39],"shows":[40],"how":[41],"four":[42],"exporters":[44],"can":[45,109],"be":[46,110],"configured":[47],"a":[49,89],"Slurm":[50,96,128],"cluster":[51],"to":[52,86,130],"provide":[53],"detailed":[54],"job-level":[55],"information":[56],"CPU/GPU":[58,61],"efficiencies":[59],"memory":[62],"usage":[63],"as":[64,66],"well":[65],"node-level":[67],"Network":[68],"File":[69,77],"System":[70,78],"(NFS)":[71],"statistics":[72],"cluster-level":[74],"General":[75],"Parallel":[76],"(GPFS)":[79],"activity.":[80],"A":[81],"novel":[82],"approach":[83],"was":[84],"devised":[85],"efficiently":[87],"store":[88],"summary":[90],"this":[92],"data":[93],"database":[97],"each":[99],"completed":[100],"job.":[101],"open-source":[103],"job":[104],"platform":[106],"introduced":[107],"here":[108],"used":[111],"batch,":[113],"interactive":[114],"Open":[116],"OnDemand":[117],"jobs.":[118],"Several":[119],"tools":[120],"are":[121],"presented":[122],"that":[123],"use":[124],"databases":[129],"create":[131],"dashboards,":[132],"utilization":[133],"reports":[134],"alerts.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
