{"id":"https://openalex.org/W2242118751","doi":"https://doi.org/10.1109/issre.2015.7381808","title":"Experience report: An application-specific checkpointing technique for minimizing checkpoint corruption","display_name":"Experience report: An application-specific checkpointing technique for minimizing checkpoint corruption","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2242118751","doi":"https://doi.org/10.1109/issre.2015.7381808","mag":"2242118751"},"language":"en","primary_location":{"id":"doi:10.1109/issre.2015.7381808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/issre.2015.7381808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 26th International Symposium on Software Reliability Engineering (ISSRE)","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/A5025726299","display_name":"Guanpeng Li","orcid":"https://orcid.org/0000-0001-7773-7826"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Guanpeng Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of British Columbia (UBC), Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of British Columbia (UBC), Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073641368","display_name":"Karthik Pattabiraman","orcid":"https://orcid.org/0000-0003-2380-3415"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Karthik Pattabiraman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of British Columbia (UBC), Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of British Columbia (UBC), Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015839075","display_name":"Chen-Yong Cher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen-Yong Cher","raw_affiliation_strings":["IBM T.J. Watson Research Center, New York, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, New York, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009866527","display_name":"Pradip Bose","orcid":"https://orcid.org/0000-0002-1380-5671"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pradip Bose","raw_affiliation_strings":["IBM T.J. Watson Research Center, New York, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, New York, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025726299"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.9985,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80463274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"141","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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":0.9998000264167786,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.7776960134506226},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.776024580001831},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6630018949508667},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6263763904571533},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4956167936325073},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.48140740394592285},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.4150979518890381},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4113708734512329},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40512141585350037},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3899305462837219},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34103769063949585},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.28814440965652466},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22792398929595947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08302712440490723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776960134506226},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.776024580001831},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6630018949508667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6263763904571533},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4956167936325073},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.48140740394592285},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.4150979518890381},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4113708734512329},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40512141585350037},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3899305462837219},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34103769063949585},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.28814440965652466},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22792398929595947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08302712440490723},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/issre.2015.7381808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/issre.2015.7381808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 26th International Symposium on Software Reliability Engineering (ISSRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W120111160","https://openalex.org/W1573279165","https://openalex.org/W1965936844","https://openalex.org/W1972649107","https://openalex.org/W1997195086","https://openalex.org/W2010043262","https://openalex.org/W2012999187","https://openalex.org/W2032090095","https://openalex.org/W2034593585","https://openalex.org/W2043694663","https://openalex.org/W2047360090","https://openalex.org/W2063384380","https://openalex.org/W2096865422","https://openalex.org/W2100970777","https://openalex.org/W2101729333","https://openalex.org/W2116996243","https://openalex.org/W2125169487","https://openalex.org/W2130189691","https://openalex.org/W2132362854","https://openalex.org/W2135089235","https://openalex.org/W2145021036","https://openalex.org/W2150267144","https://openalex.org/W2153185479","https://openalex.org/W2156204788","https://openalex.org/W2160401437","https://openalex.org/W2162351670","https://openalex.org/W2166293939","https://openalex.org/W2169875292","https://openalex.org/W2273440736","https://openalex.org/W3008756550","https://openalex.org/W4244078624","https://openalex.org/W4246166885","https://openalex.org/W4246310005","https://openalex.org/W4250644124","https://openalex.org/W4255032011","https://openalex.org/W6604921527","https://openalex.org/W6684034536","https://openalex.org/W6694513646"],"related_works":["https://openalex.org/W2800642137","https://openalex.org/W1862835629","https://openalex.org/W2971479921","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W2157727563"],"abstract_inverted_index":{"Checkpointing":[0],"is":[1,163],"widely":[2],"deployed":[3],"in":[4,56,165],"computer":[5],"systems":[6],"to":[7,12,52,58,90],"recover":[8],"from":[9],"failures":[10],"due":[11],"both":[13],"hardware":[14],"and":[15,30,83,118],"software":[16],"errors.":[17],"However,":[18],"as":[19],"faults":[20],"propagate,":[21],"checkpoints":[22],"may":[23],"become":[24],"corrupted":[25],"by":[26,151],"saving":[27],"erroneous":[28],"states":[29],"make":[31],"errors":[32],"unrecoverable,":[33],"especially":[34],"at":[35,155],"aggressive":[36,157],"checkpoint":[37,54,60,64,81,137,158],"frequencies.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,66,96],"proposed":[43],"a":[44,49,69,99],"technique":[45],"that":[46,102,108,129,161],"automatically":[47,103],"analyzes":[48],"given":[50],"program":[51,106],"guide":[53],"strategies":[55],"order":[57],"minimize":[59],"corruptions.":[61,92],"To":[62],"understand":[63],"corruptions,":[65,82],"first":[67],"perform":[68],"large-scale":[70],"fault":[71,87,113],"injection":[72],"study":[73],"across":[74],"ten":[75],"benchmark":[76],"applications.":[77],"We":[78],"then":[79],"classify":[80],"comprehensively":[84],"characterize":[85],"the":[86,105,136,146,149],"propagations":[88],"leading":[89],"these":[91,94],"Leveraging":[93],"findings,":[95],"build":[97],"ReCov,":[98],"compiler-based":[100],"tool":[101],"identifies":[104],"locations":[107],"have":[109],"lowest":[110],"density":[111],"of":[112,135,148],"propagation":[114],"for":[115],"placing":[116],"checkpoints,":[117],"combines":[119],"it":[120,162],"with":[121,139],"low-overhead":[122],"protection":[123],"techniques.":[124],"Our":[125],"experimental":[126],"results":[127],"shows":[128],"ReCov":[130,144],"can":[131],"eliminate":[132],"nearly":[133],"92%":[134],"corruptions":[138],"about":[140],"5%":[141],"performance":[142],"overhead.":[143],"reduces":[145],"unavailability":[147],"system":[150],"8.25":[152],"times":[153],"even":[154],"very":[156],"frequencies,":[159],"showing":[160],"effective":[164],"practice.":[166]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
