{"id":"https://openalex.org/W2042506452","doi":"https://doi.org/10.1109/tc.2014.2360536","title":"Fault Tolerance on Large Scale Systems using Adaptive Process Replication","display_name":"Fault Tolerance on Large Scale Systems using Adaptive Process Replication","publication_year":2014,"publication_date":"2014-09-26","ids":{"openalex":"https://openalex.org/W2042506452","doi":"https://doi.org/10.1109/tc.2014.2360536","mag":"2042506452"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2014.2360536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2014.2360536","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"type":"article","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/A5086773705","display_name":"Cijo George","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cijo George","raw_affiliation_strings":["NetApp Advanced Technology Group, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetApp Advanced Technology Group, Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078057384","display_name":"Sathish Vadhiyar","orcid":"https://orcid.org/0000-0002-5476-8328"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sathish Vadhiyar","raw_affiliation_strings":["Supercomputer Education and Research Centre of Indian Institute of Science, Bangalore, India","[Supercomputer Education and Research Centre of Indian Institute of Science, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Supercomputer Education and Research Centre of Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"[Supercomputer Education and Research Centre of Indian Institute of Science, Bangalore, India]","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.5015,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86382538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"64","issue":"8","first_page":"2213","last_page":"2225"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9932000041007996,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8478865623474121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8394233584403992},{"id":"https://openalex.org/keywords/replica","display_name":"Replica","score":0.8135920166969299},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.791304349899292},{"id":"https://openalex.org/keywords/mean-time-between-failures","display_name":"Mean time between failures","score":0.7490155100822449},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6081250905990601},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6067062616348267},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5806660056114197},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3790353536605835},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.33426743745803833},{"id":"https://openalex.org/keywords/failure-rate","display_name":"Failure rate","score":0.14862030744552612},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09001284837722778}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8478865623474121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394233584403992},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.8135920166969299},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.791304349899292},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.7490155100822449},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6081250905990601},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6067062616348267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5806660056114197},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3790353536605835},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.33426743745803833},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.14862030744552612},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09001284837722778},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tc.2014.2360536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2014.2360536","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:eprints.iisc.ac.in:52054","is_oa":false,"landing_page_url":"http://eprints.iisc.ac.in/52054/1/IEEE_Tra_On_Com_64-8_2213_2015.pdf","pdf_url":"http://eprints.iisc.ac.in/52054/1/IEEE_Tra_On_Com_64-8_2213_2015.pdf","source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.3395","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.3395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.serc.iisc.ernet.in/%7Evss/publications/cijo-adaptiveProcessReplication-tc2015.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1558516248","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1993660990","https://openalex.org/W2001495258","https://openalex.org/W2016411419","https://openalex.org/W2045152180","https://openalex.org/W2045611838","https://openalex.org/W2063924830","https://openalex.org/W2064388050","https://openalex.org/W2072672002","https://openalex.org/W2088552220","https://openalex.org/W2089536264","https://openalex.org/W2095157729","https://openalex.org/W2113036804","https://openalex.org/W2116115793","https://openalex.org/W2123646449","https://openalex.org/W2133046454","https://openalex.org/W2137512117","https://openalex.org/W2139244298","https://openalex.org/W2146306455","https://openalex.org/W2146854584","https://openalex.org/W2155118768","https://openalex.org/W2156629984","https://openalex.org/W2164463086","https://openalex.org/W2167899274","https://openalex.org/W2171007672","https://openalex.org/W2171371822","https://openalex.org/W2730583186","https://openalex.org/W3150262005","https://openalex.org/W4248195866","https://openalex.org/W4249923483","https://openalex.org/W6666956023","https://openalex.org/W6678359629","https://openalex.org/W6685186519"],"related_works":["https://openalex.org/W3013979739","https://openalex.org/W2655578171","https://openalex.org/W2577913821","https://openalex.org/W4296976839","https://openalex.org/W2460131733","https://openalex.org/W2953070151","https://openalex.org/W2372946558","https://openalex.org/W3126044086","https://openalex.org/W1520094959","https://openalex.org/W2086301695"],"abstract_inverted_index":{"Exascale":[0],"systems":[1],"of":[2,14,33,37,44,69,86,89,100],"the":[3,34,98,122],"future":[4],"are":[5],"predicted":[6],"to":[7,48,57,108,141],"have":[8,58,75,112,126],"mean":[9],"time":[10],"between":[11],"failures":[12,39],"(MTBF)":[13],"less":[15],"than":[16],"one":[17],"hour.":[18],"At":[19],"such":[20,51],"low":[21,30],"MTBFs,":[22],"employing":[23],"periodic":[24],"checkpointing":[25],"alone":[26],"will":[27],"result":[28],"in":[29,41,145],"efficiency":[31,147],"because":[32],"high":[35],"number":[36,68],"application":[38,90,146],"resulting":[40],"large":[42],"amount":[43],"lost":[45],"work":[46],"due":[47],"rollbacks.":[49],"In":[50,71],"scenarios,":[52],"it":[53],"is":[54],"highly":[55],"necessary":[56],"proactive":[59,80],"fault":[60,81,93],"tolerance":[61,82,94],"mechanisms":[62,138],"that":[63,119,128],"can":[64],"help":[65],"avoid":[66,109],"significant":[67],"failures.":[70,110],"this":[72],"work,":[73],"we":[74],"developed":[76,113],"a":[77,87],"mechanism":[78],"for":[79,149],"using":[83],"partial":[84],"replication":[85,134],"set":[88,99],"processes.":[91],"Our":[92],"framework":[95],"adaptively":[96],"changes":[97],"replicated":[101],"processes":[102],"periodically":[103],"based":[104],"on":[105],"failure":[106],"predictions":[107],"We":[111,125],"an":[114],"MPI":[115],"prototype":[116],"implementation,":[117],"PAREP-MPI":[118],"allows":[120],"changing":[121],"replica":[123],"set.":[124],"shown":[127],"our":[129],"strategy":[130],"involving":[131],"adaptive":[132],"process":[133],"significantly":[135],"outperforms":[136],"existing":[137],"providing":[139],"up":[140],"20":[142],"percent":[143],"improvement":[144],"even":[148],"exascale":[150],"systems.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}