{"id":"https://openalex.org/W2105929610","doi":"https://doi.org/10.1109/reldis.2003.1238063","title":"Raptor: integrating checkpoints and thread migration for cluster management","display_name":"Raptor: integrating checkpoints and thread migration for cluster management","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2105929610","doi":"https://doi.org/10.1109/reldis.2003.1238063","mag":"2105929610"},"language":"en","primary_location":{"id":"doi:10.1109/reldis.2003.1238063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/reldis.2003.1238063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"22nd International Symposium on Reliable Distributed Systems, 2003. Proceedings.","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/A5010958864","display_name":"Hazim Shafi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Shafi","raw_affiliation_strings":["IBM Austin Research Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Austin Research Laboratory, USA","institution_ids":["https://openalex.org/I4210156936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073521684","display_name":"Evan W. Speight","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Speight","raw_affiliation_strings":["Computer Systems Laboratory, Cornell University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Systems Laboratory, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064483758","display_name":"John K. Bennett","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.K. Bennett","raw_affiliation_strings":["Department of Computer Science, University of Colorado, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4825,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62987824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"tr cs 98 1","issue":null,"first_page":"141","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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":0.8457438349723816},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.6232203245162964},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6029872894287109},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.6028484106063843},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46176308393478394},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41358309984207153},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3473235070705414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457438349723816},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.6232203245162964},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6029872894287109},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.6028484106063843},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46176308393478394},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41358309984207153},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3473235070705414}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/reldis.2003.1238063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/reldis.2003.1238063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"22nd International Symposium on Reliable Distributed Systems, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W126554001","https://openalex.org/W1495956870","https://openalex.org/W1529311848","https://openalex.org/W1537929875","https://openalex.org/W1538414448","https://openalex.org/W1542985837","https://openalex.org/W1559023493","https://openalex.org/W1579345337","https://openalex.org/W1863948217","https://openalex.org/W1911998402","https://openalex.org/W1966285605","https://openalex.org/W1982731142","https://openalex.org/W2026120091","https://openalex.org/W2032401773","https://openalex.org/W2037730929","https://openalex.org/W2046920165","https://openalex.org/W2062161320","https://openalex.org/W2079835745","https://openalex.org/W2100970777","https://openalex.org/W2108167744","https://openalex.org/W2109668944","https://openalex.org/W2112121929","https://openalex.org/W2116761791","https://openalex.org/W2118153508","https://openalex.org/W2136295287","https://openalex.org/W2140332639","https://openalex.org/W2140953143","https://openalex.org/W2149104472","https://openalex.org/W2242678157","https://openalex.org/W2543670216","https://openalex.org/W4205190765","https://openalex.org/W4232281662","https://openalex.org/W4254537978","https://openalex.org/W6605178103","https://openalex.org/W6629598324","https://openalex.org/W6631540460","https://openalex.org/W6631987640","https://openalex.org/W6632419953","https://openalex.org/W6633303746","https://openalex.org/W6640122196","https://openalex.org/W6662272791","https://openalex.org/W6690129670"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W2015567081","https://openalex.org/W4237177615","https://openalex.org/W2289257917"],"abstract_inverted_index":{"Software":[0],"distributed":[1],"shared-memory":[2,10],"(SDSM)":[3],"provides":[4],"the":[5,67,91,123,142],"abstraction":[6],"necessary":[7],"to":[8,36,39],"run":[9],"applications":[11],"on":[12,59,141],"cost-effective":[13],"parallel":[14],"platforms":[15],"such":[16,23],"as":[17,24],"clusters":[18],"of":[19,90,127],"workstations.":[20],"However,":[21],"problems":[22],"cluster":[25,29,55],"component":[26],"reliability":[27],"and":[28,61,70,82,119],"management,":[30],"which":[31],"are":[32,86],"not":[33],"directly":[34],"related":[35],"performance,":[37],"need":[38],"be":[40,46,105],"addressed":[41],"before":[42],"SDSM":[43,54,143],"solutions":[44],"can":[45],"widely":[47],"adopted.":[48],"This":[49],"paper":[50],"presents":[51],"Raptor,":[52],"an":[53],"management":[56],"system":[57,69],"based":[58],"checkpoint/recovery":[60],"thread":[62,113],"migration.":[63],"Raptor":[64],"checkpoints":[65],"decouple":[66],"runtime":[68],"application":[71,74,144],"data":[72,102],"from":[73,130],"threads,":[75],"allowing":[76],"efficient":[77],"load":[78],"balancing,":[79],"resource":[80],"allocation,":[81],"rollback":[83],"recovery.":[84],"There":[85],"two":[87],"important":[88],"features":[89],"system.":[92],"First,":[93],"it":[94,121],"reduces":[95],"checkpoint":[96],"overhead":[97],"by":[98,111],"only":[99],"saving":[100],"application-specific":[101],"that":[103],"cannot":[104],"recreated":[106],"at":[107,117],"recovery":[108],"time.":[109],"Second,":[110],"integrating":[112],"migration":[114],"capability":[115],"both":[116],"running":[118,132],"recovery,":[120],"allows":[122],"addition":[124],"or":[125,137],"removal":[126],"computing":[128],"resources":[129],"a":[131],"application,":[133],"while":[134],"adding":[135],"little":[136],"no":[138],"additional":[139],"burden":[140],"programmer.":[145]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
