{"id":"https://openalex.org/W2047793712","doi":"https://doi.org/10.1109/reldis.2004.1353012","title":"Skewed checkpointing for tolerating multi-node failures","display_name":"Skewed checkpointing for tolerating multi-node failures","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2047793712","doi":"https://doi.org/10.1109/reldis.2004.1353012","mag":"2047793712"},"language":"en","primary_location":{"id":"doi:10.1109/reldis.2004.1353012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/reldis.2004.1353012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd IEEE International Symposium on Reliable Distributed Systems, 2004.","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/A5090578339","display_name":"Hiroshi Nakamura","orcid":"https://orcid.org/0009-0005-6505-1903"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Nakamura","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060660833","display_name":"Takuro Hayashida","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Hayashida","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103017591","display_name":"Masaaki Kondo","orcid":"https://orcid.org/0000-0002-6025-8738"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Kondo","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111947392","display_name":"Y. Tajima","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Tajima","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031743517","display_name":"Mizuho Imai","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Imai","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073211567","display_name":"Takashi Nanya","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Nanya","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Res. Center for Adv. Sci. & Tech., Tokyo Univ., Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1608,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.42473594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":null,"first_page":"116","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","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/T10772","display_name":"Distributed systems and fault tolerance","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9901000261306763,"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/T12288","display_name":"Optimization and Search Problems","score":0.9879000186920166,"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/redundancy","display_name":"Redundancy (engineering)","score":0.8485920429229736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8321086764335632},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.610710620880127},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6056368350982666},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5909709930419922},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5795098543167114},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5273545384407043},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5056138038635254},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.47626087069511414},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23508012294769287},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1537049114704132}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.8485920429229736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321086764335632},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.610710620880127},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6056368350982666},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5909709930419922},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5795098543167114},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5273545384407043},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5056138038635254},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.47626087069511414},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23508012294769287},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1537049114704132},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/reldis.2004.1353012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/reldis.2004.1353012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd IEEE International Symposium on Reliable Distributed Systems, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1538291993","https://openalex.org/W1862835629","https://openalex.org/W1884410818","https://openalex.org/W1993143336","https://openalex.org/W2000131617","https://openalex.org/W2004885674","https://openalex.org/W2043522772","https://openalex.org/W2048894106","https://openalex.org/W2081413727","https://openalex.org/W2082498963","https://openalex.org/W2100970777","https://openalex.org/W2126071114","https://openalex.org/W2129231125","https://openalex.org/W2131053137","https://openalex.org/W2146942047","https://openalex.org/W2155568297","https://openalex.org/W2157960977","https://openalex.org/W2160123909","https://openalex.org/W2171453084","https://openalex.org/W4206909927","https://openalex.org/W6631615826","https://openalex.org/W6679533656"],"related_works":["https://openalex.org/W2153096481","https://openalex.org/W2148616436","https://openalex.org/W2102525122","https://openalex.org/W4245282135","https://openalex.org/W4306316843","https://openalex.org/W2130594209","https://openalex.org/W2036953450","https://openalex.org/W4300955944","https://openalex.org/W2170004886","https://openalex.org/W2108317625"],"abstract_inverted_index":{"Large":[0],"cluster":[1,21,149,169],"systems":[2,22],"have":[3],"become":[4],"widely":[5],"utilized":[6],"because":[7,37],"they":[8],"achieve":[9],"a":[10,30,66,84,148],"good":[11],"performance/cost":[12],"ratio":[13],"especially":[14,166],"in":[15,73],"high":[16,35],"performance":[17,79,140],"computing.":[18],"Although":[19,99],"these":[20],"are":[23,41],"distributed":[24],"memory":[25],"systems,":[26],"coordinated":[27,86],"checkpointing":[28,87,94,101,111,156],"is":[29,71,95,125,145],"promising":[31],"way":[32],"to":[33,44,78,147],"maintain":[34],"availability":[36],"the":[38,49,56,121,132,139,161],"computing":[39,52],"nodes":[40,53,124],"tightly":[42],"connected":[43],"one":[45,105],"another.":[46],"However,":[47],"as":[48],"number":[50,122],"of":[51,58,69,107,118,123,138,163],"gets":[54],"larger,":[55],"probability":[57],"multi-node":[59,64],"failures":[60],"increases.":[61],"To":[62],"tolerate":[63],"failures,":[65],"large":[67,168],"degree":[68,106],"redundancy":[70,119],"required":[72],"checkpointing,":[74],"but":[75],"this":[76,92,109,128,143],"leads":[77],"degradation.":[80],"Thus,":[81],"we":[82,130],"propose":[83],"new":[85],"called":[88],"skewed":[89,96,110],"checkpointing.":[90],"In":[91,127],"method,":[93,165],"every":[97],"time.":[98],"each":[100],"itself":[102],"contains":[103],"only":[104],"redundancy,":[108],"ensures":[112],"/spl":[113],"lfloor/log/sub":[114],"2/N/spl":[115],"rfloor/":[116],"degrees":[117],"when":[120],"N.":[126],"paper,":[129],"present":[131],"proposed":[133],"method":[134,144],"and":[135,151],"an":[136],"analysis":[137],"overhead.":[141],"Then,":[142],"applied":[146],"system":[150],"compared":[152],"with":[153],"other":[154],"conventional":[155],"schemes.":[157],"The":[158],"results":[159],"reveal":[160],"superiority":[162],"our":[164],"for":[167],"systems.":[170]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
