{"id":"https://openalex.org/W1977792483","doi":"https://doi.org/10.1109/cluster.2014.6968777","title":"Checkpoint/restart in practice: When &amp;#x2018;simple is better&amp;#x2019;","display_name":"Checkpoint/restart in practice: When &amp;#x2018;simple is better&amp;#x2019;","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1977792483","doi":"https://doi.org/10.1109/cluster.2014.6968777","mag":"1977792483"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2014.6968777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2014.6968777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-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/A5041608911","display_name":"Nosayba El-Sayed","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nosayba El-Sayed","raw_affiliation_strings":["Department of Computer Science, University of Toronto","Department of Computer Science University of Toronto, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science University of Toronto, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040893798","display_name":"Bianca Schroeder","orcid":"https://orcid.org/0000-0003-3289-1824"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bianca Schroeder","raw_affiliation_strings":["Department of Computer Science, University of Toronto","Department of Computer Science University of Toronto, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science University of Toronto, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041608911"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":2.0689,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87737992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"92"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8293963670730591},{"id":"https://openalex.org/keywords/rule-of-thumb","display_name":"Rule of thumb","score":0.7299525737762451},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.6296529769897461},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6140254139900208},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5860028266906738},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5430026650428772},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5412527918815613},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.536392331123352},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43254202604293823},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4320594072341919},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4157589375972748},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.33648839592933655},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3256193995475769},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18064215779304504},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15366709232330322},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13925445079803467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293963670730591},{"id":"https://openalex.org/C89246107","wikidata":"https://www.wikidata.org/wiki/Q1398821","display_name":"Rule of thumb","level":2,"score":0.7299525737762451},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.6296529769897461},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6140254139900208},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5860028266906738},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5430026650428772},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5412527918815613},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.536392331123352},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43254202604293823},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4320594072341919},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4157589375972748},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.33648839592933655},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3256193995475769},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18064215779304504},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15366709232330322},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13925445079803467},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2014.6968777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2014.6968777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Cluster Computing (CLUSTER)","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":23,"referenced_works":["https://openalex.org/W1558516248","https://openalex.org/W1870609547","https://openalex.org/W1998221613","https://openalex.org/W2033656974","https://openalex.org/W2064388050","https://openalex.org/W2081235423","https://openalex.org/W2089536264","https://openalex.org/W2113708023","https://openalex.org/W2116011221","https://openalex.org/W2121575774","https://openalex.org/W2133046454","https://openalex.org/W2155521027","https://openalex.org/W2161416813","https://openalex.org/W2166143798","https://openalex.org/W2254416046","https://openalex.org/W2317514805","https://openalex.org/W4285719527","https://openalex.org/W6633553838","https://openalex.org/W6639082569","https://openalex.org/W6666956023","https://openalex.org/W6670668349","https://openalex.org/W6691979229","https://openalex.org/W6699540517"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"Efficient":[0],"use":[1,102,161],"of":[2,28,42,48,72,126,206],"high-performance":[3],"computing":[4],"(HPC)":[5],"installations":[6],"critically":[7],"relies":[8],"on":[9,78,180],"effective":[10],"methods":[11,92,127],"for":[12,93,128,160,212],"fault":[13],"tolerance.":[14],"The":[15],"most":[16],"commonly":[17],"used":[18,193],"method":[19],"is":[20,51,89],"checkpoint/restart,":[21,49],"where":[22],"an":[23,124],"application":[24],"writes":[25],"periodic":[26],"checkpoints":[27],"its":[29,62],"state":[30],"to":[31,60,90,101,194],"stable":[32],"storage":[33],"that":[34,98,141,150,171,186],"it":[35,50],"can":[36,156,191],"restart":[37],"from":[38],"in":[39,57,103,162,200],"the":[40,46,65,95,107,119,130,197],"case":[41],"a":[43,69,151],"failure.":[44],"Despite":[45,68],"prevalence":[47],"still":[52,76],"not":[53],"very":[54,152],"well":[55,137],"understood":[56],"practice":[58,104,163],"how":[59],"set":[61],"key":[63],"parameter,":[64],"checkpoint":[66,131],"interval.":[67],"large":[70],"body":[71],"theoretical":[73],"work,":[74],"practitioners":[75],"rely":[77],"crude":[79],"rules-of-thumb":[80],"such":[81],"as":[82,136,138],"\u201ccheckpoint":[83],"once":[84],"every":[85],"hour\u201d.":[86],"Our":[87],"goal":[88],"identify":[91],"optimizing":[94,129],"checkpointing":[96],"process":[97],"are":[99],"easy":[100],"and":[105,164,203,210],"at":[106],"same":[108],"time":[109],"achieve":[110],"high":[111],"quality":[112],"solutions.":[113],"In":[114],"particular,":[115],"our":[116],"paper":[117],"makes":[118],"following":[120],"contributions:":[121],"We":[122,148,168,184],"evaluate":[123],"array":[125],"interval,":[132],"some":[133],"previously":[134],"known":[135],"new":[139],"ones":[140],"we":[142],"propose,":[143],"using":[144],"real-world":[145],"failure":[146],"logs.":[147],"show":[149,185],"simple":[153,187],"closed-form":[154],"solution":[155],"easily":[157],"be":[158,192],"adapted":[159],"achieves":[165],"near-optimal":[166],"performance.":[167],"also":[169],"find":[170],"more":[172],"complex":[173],"solutions":[174],"only":[175],"negligibly":[176],"improve":[177],"performance":[178],"based":[179],"real":[181],"world":[182],"traces.":[183],"back-of-the":[188],"envelope":[189],"formulas":[190],"accurately":[195],"estimate":[196],"wasted":[198],"work":[199],"HPC":[201,208],"systems,":[202],"make":[204],"projections":[205],"future":[207],"systems":[209],"requirements":[211],"their":[213],"efficient":[214],"use.":[215]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}
