{"id":"https://openalex.org/W2133043855","doi":"https://doi.org/10.1109/clustr.2009.5289172","title":"DCR: A fully transparent checkpoint/restart framework for distributed systems","display_name":"DCR: A fully transparent checkpoint/restart framework for distributed systems","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2133043855","doi":"https://doi.org/10.1109/clustr.2009.5289172","mag":"2133043855"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2009.5289172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2009.5289172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Cluster Computing and 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/A5101021225","display_name":"Can Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Ma","raw_affiliation_strings":["National Research Center of Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy and Sciences, China","National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Center of Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy and Sciences, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029782045","display_name":"Zhigang Huo","orcid":"https://orcid.org/0000-0002-6488-5587"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Huo","raw_affiliation_strings":["National Research Center of Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy and Sciences, China","National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Center of Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy and Sciences, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101111982","display_name":"Jingnan Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingnan Cai","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, Beijing, CN","National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018703681","display_name":"Dan Meng","orcid":"https://orcid.org/0000-0001-6654-8552"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Meng","raw_affiliation_strings":["National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2703,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.47376354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1323","issue":null,"first_page":"1","last_page":"10"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9968000054359436,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9944000244140625,"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":0.8364677429199219},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5845551490783691},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5339366793632507},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4715442955493927},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3792221248149872},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3655358552932739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364677429199219},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5845551490783691},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5339366793632507},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4715442955493927},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3792221248149872},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3655358552932739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clustr.2009.5289172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2009.5289172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Cluster Computing and Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1524357507","https://openalex.org/W1571582830","https://openalex.org/W1923741182","https://openalex.org/W2064953307","https://openalex.org/W2095487435","https://openalex.org/W2100970777","https://openalex.org/W2115367411","https://openalex.org/W2116115793","https://openalex.org/W2117508157","https://openalex.org/W2118706534","https://openalex.org/W2131053137","https://openalex.org/W2133201251","https://openalex.org/W2148109481","https://openalex.org/W2150255127","https://openalex.org/W2155204206","https://openalex.org/W2155662278","https://openalex.org/W2157801087","https://openalex.org/W2161551433","https://openalex.org/W3141239549","https://openalex.org/W4255374438","https://openalex.org/W6640233066","https://openalex.org/W6681907482"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W2068121105","https://openalex.org/W3096519538","https://openalex.org/W1577886464","https://openalex.org/W2144438995","https://openalex.org/W2164896586","https://openalex.org/W1593559483","https://openalex.org/W2108334564","https://openalex.org/W2111125783","https://openalex.org/W2100367016"],"abstract_inverted_index":{"Checkpoint/restart":[0],"has":[1,22],"been":[2],"widely":[3,95],"used":[4],"in":[5,86,94],"computing":[6],"systems":[7],"for":[8],"fault":[9],"tolerance,":[10],"job":[11],"scheduling":[12],"and":[13,50,61,81,133],"system":[14,69],"maintenance":[15],"purposes.":[16],"However,":[17],"the":[18,44,76,82,116,125,131],"lack":[19],"of":[20,25,28,46,75,78,84,97,115,119,135],"transparency":[21],"hindered":[23],"adoptions":[24],"many":[26],"implementations":[27],"it.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"present":[34],"a":[35],"fully":[36,56],"transparent":[37,57],"parallel":[38,87],"checkpoint/restart":[39],"framework,":[40],"DCR,":[41],"which":[42,112],"takes":[43],"advantages":[45],"kernel-level":[47],"checkpointing":[48],"method":[49],"TCP":[51],"session":[52],"preservation.":[53],"DCR":[54,89,136],"is":[55,121],"to":[58,103,123],"application":[59],"programmers":[60],"users.":[62],"No":[63],"source":[64],"code":[65],"modifications,":[66],"recompilations,":[67],"or":[68],"call":[70],"interceptions":[71],"are":[72],"required.":[73],"Because":[74],"simplicity":[77],"its":[79],"design":[80],"dominance":[83],"TCP/IP":[85],"applications,":[88],"can":[90],"be":[91],"readily":[92],"deployed":[93],"scales":[96],"computers,":[98],"from":[99],"single":[100],"CPU":[101],"computers":[102],"large-scale":[104],"clusters.":[105],"A":[106],"new":[107],"on-demand":[108],"blocking":[109],"checkpoint":[110],"protocol,":[111],"makes":[113],"use":[114],"reliability":[117],"mechanism":[118],"TCP,":[120],"proposed":[122],"eliminate":[124],"global":[126],"synchronization.":[127],"We":[128],"have":[129],"demonstrated":[130],"effectiveness":[132],"efficiency":[134],"by":[137],"multiple":[138],"MPICH2":[139],"applications":[140],"running":[141],"on":[142],"Dawning":[143],"5000A.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
