{"id":"https://openalex.org/W2156617232","doi":"https://doi.org/10.1109/icdcsw.2010.79","title":"Field Data Based Modeling of Sender Based Message Logging Protocols for Supercomputers Checkpointing","display_name":"Field Data Based Modeling of Sender Based Message Logging Protocols for Supercomputers Checkpointing","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2156617232","doi":"https://doi.org/10.1109/icdcsw.2010.79","mag":"2156617232"},"language":"en","primary_location":{"id":"doi:10.1109/icdcsw.2010.79","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcsw.2010.79","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 30th International Conference on Distributed Computing Systems Workshops","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052961846","display_name":"Domenico Cotroneo","orcid":"https://orcid.org/0000-0001-7103-592X"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Domenico Cotroneo","raw_affiliation_strings":["Dipartimento di Informatica e Sistemistica (DIS), Universit\u00e1 degli studi di Napoli Federico, Napoli, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Sistemistica (DIS), Universit\u00e1 degli studi di Napoli Federico, Napoli, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021964790","display_name":"Catello Di Martino","orcid":"https://orcid.org/0000-0003-4460-516X"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Catello Di Martino","raw_affiliation_strings":["Dipt. di Inf. e Sist. (DIS), Univ. degli studi di Napoli Federico II, Naples, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipt. di Inf. e Sist. (DIS), Univ. degli studi di Napoli Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I71267560"],"apc_list":null,"apc_paid":null,"fwci":0.2934,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52017982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"294","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9959999918937683,"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/communication-source","display_name":"Communication source","score":0.8546669483184814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7612071633338928},{"id":"https://openalex.org/keywords/logging","display_name":"Logging","score":0.6774414777755737},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6764494180679321},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4605945348739624},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4569845497608185}],"concepts":[{"id":"https://openalex.org/C198104137","wikidata":"https://www.wikidata.org/wiki/Q974688","display_name":"Communication source","level":2,"score":0.8546669483184814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612071633338928},{"id":"https://openalex.org/C125620115","wikidata":"https://www.wikidata.org/wiki/Q845249","display_name":"Logging","level":2,"score":0.6774414777755737},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6764494180679321},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4605945348739624},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4569845497608185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdcsw.2010.79","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcsw.2010.79","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 30th International Conference on Distributed Computing Systems Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W191492107","https://openalex.org/W1485650462","https://openalex.org/W1506585574","https://openalex.org/W2004885674","https://openalex.org/W2023917386","https://openalex.org/W2033656974","https://openalex.org/W2042203635","https://openalex.org/W2113052966","https://openalex.org/W2114967206","https://openalex.org/W2119018856","https://openalex.org/W2121968979","https://openalex.org/W2142234387","https://openalex.org/W2158907675","https://openalex.org/W2161537327","https://openalex.org/W2161833190","https://openalex.org/W2166293939","https://openalex.org/W3043348741","https://openalex.org/W6661186670"],"related_works":["https://openalex.org/W2993833576","https://openalex.org/W2776877297","https://openalex.org/W3125718803","https://openalex.org/W2127920220","https://openalex.org/W3119288169","https://openalex.org/W2945097178","https://openalex.org/W4388741024","https://openalex.org/W3122953031","https://openalex.org/W3123743600","https://openalex.org/W4320855289"],"abstract_inverted_index":{"Checkpointing":[0],"is":[1,30,60,81],"today\u2019s":[2],"common":[3],"mean":[4],"for":[5,126,130],"dealing":[6],"with":[7],"transient":[8],"failures":[9,24,97],"in":[10],"supercomputers.":[11],"However,":[12],"the":[13,21,39,70,74,99,107,110,119,124,127],"effectiveness":[14],"of":[15,38,56,76,89,109,112],"checkpointing":[16,40,100],"and":[17,41,87,101,132],"recovery":[18,42],"protocols":[19,49],"under":[20],"assumption":[22],"that":[23,114],"may":[25],"happen":[26],"during":[27,98],"their":[28],"operation":[29],"not":[31],"well":[32],"understood.":[33],"We":[34,51],"present":[35],"an":[36,63],"evaluation":[37],"based":[43],"on":[44,69,106],"Sender":[45],"Based":[46],"Message":[47],"Logging":[48],"(SBML).":[50],"evaluate":[52,84],"it":[53],"by":[54],"means":[55],"a":[57],"model":[58,80,93],"which":[59],"gathered":[61],"from":[62],"extensive":[64],"field":[65],"data":[66],"campaign":[67],"performed":[68],"SCOPE":[71],"supercomputer":[72],"at":[73],"University":[75],"Naples.":[77],"A":[78],"comprehensive":[79],"built":[82],"to":[83,118],"reliability,":[85],"scalability":[86],"performance":[88],"SBML.":[90],"The":[91],"proposed":[92],"takes":[94],"into":[95],"account":[96],"recovery.":[102],"Result":[103],"provide":[104],"insights":[105],"limit":[108],"number":[111],"nodes":[113],"can":[115],"be":[116],"allocated":[117],"same":[120],"job":[121],"considering":[122],"i)":[123],"overhead":[125],"distributed":[128],"coordination":[129],"rollback,":[131],"ii)":[133],"network":[134],"resources":[135],"(e.g.":[136],"bandwidth).":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}