{"id":"https://openalex.org/W3216052173","doi":"https://doi.org/10.1109/mascots53633.2021.9614284","title":"Towards Efficient I/O Scheduling for Collaborative Multi-Level Checkpointing","display_name":"Towards Efficient I/O Scheduling for Collaborative Multi-Level Checkpointing","publication_year":2021,"publication_date":"2021-11-03","ids":{"openalex":"https://openalex.org/W3216052173","doi":"https://doi.org/10.1109/mascots53633.2021.9614284","mag":"3216052173"},"language":"en","primary_location":{"id":"doi:10.1109/mascots53633.2021.9614284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots53633.2021.9614284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03344362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049218913","display_name":"Avinash Maurya","orcid":"https://orcid.org/0000-0002-8200-0148"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Avinash Maurya","raw_affiliation_strings":["Rochester Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085745891","display_name":"Bogdan Nicolae","orcid":"https://orcid.org/0000-0002-0661-7509"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bogdan Nicolae","raw_affiliation_strings":["Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054011637","display_name":"M. Mustafa Rafique","orcid":"https://orcid.org/0000-0002-5034-2880"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Mustafa Rafique","raw_affiliation_strings":["Rochester Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051568476","display_name":"Thierry Tonellot","orcid":"https://orcid.org/0000-0003-2214-1173"},"institutions":[{"id":"https://openalex.org/I4210143841","display_name":"Saudi Aramco (Saudi Arabia)","ror":"https://ror.org/03ypap427","country_code":"SA","type":"company","lineage":["https://openalex.org/I4210143841"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Thierry Tonellot","raw_affiliation_strings":["Exploration and Petroleum Engineering Advanced Research Center, Saudi Aramco, Dhahran, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Exploration and Petroleum Engineering Advanced Research Center, Saudi Aramco, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I4210143841"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049218913"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":1.12,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79959025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9983000159263611,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9958999752998352,"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":0.8530870676040649},{"id":"https://openalex.org/keywords/spare-part","display_name":"Spare part","score":0.6511627435684204},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6430208683013916},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5862343907356262},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5706334710121155},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.569778561592102},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5046137571334839},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.47868043184280396},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23151090741157532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8530870676040649},{"id":"https://openalex.org/C194648553","wikidata":"https://www.wikidata.org/wiki/Q1364774","display_name":"Spare part","level":2,"score":0.6511627435684204},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6430208683013916},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5862343907356262},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5706334710121155},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.569778561592102},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5046137571334839},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.47868043184280396},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23151090741157532},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mascots53633.2021.9614284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots53633.2021.9614284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03344362v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03344362","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MASCOTS'21: 29th IEEE International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, Nov 2021, Virtual, Portugal","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03344362v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03344362","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MASCOTS'21: 29th IEEE International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, Nov 2021, Virtual, Portugal","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1565405831","https://openalex.org/W1572669544","https://openalex.org/W1969150237","https://openalex.org/W1983383464","https://openalex.org/W1994595608","https://openalex.org/W2061872629","https://openalex.org/W2078349455","https://openalex.org/W2108314995","https://openalex.org/W2122485954","https://openalex.org/W2125916088","https://openalex.org/W2153958596","https://openalex.org/W2153985054","https://openalex.org/W2165751385","https://openalex.org/W2486202470","https://openalex.org/W2792247833","https://openalex.org/W2886094133","https://openalex.org/W2902032749","https://openalex.org/W2942275892","https://openalex.org/W2953498285","https://openalex.org/W2954279981","https://openalex.org/W2961595369","https://openalex.org/W3006348265","https://openalex.org/W3042760775","https://openalex.org/W3043066357","https://openalex.org/W3082705249","https://openalex.org/W3115029474","https://openalex.org/W3163165976","https://openalex.org/W4231384169","https://openalex.org/W6764791836","https://openalex.org/W6780373310","https://openalex.org/W6787673396"],"related_works":["https://openalex.org/W2376859990","https://openalex.org/W2912704652","https://openalex.org/W2381161177","https://openalex.org/W2319226115","https://openalex.org/W830772239","https://openalex.org/W2970750595","https://openalex.org/W2366601680","https://openalex.org/W2392193501","https://openalex.org/W2738649048","https://openalex.org/W2277714805"],"abstract_inverted_index":{"Efficient":[0],"checkpointing":[1,40],"of":[2,21,51,68,76,92,143,152,175,187,202],"distributed":[3,45],"data":[4,53,178],"structures":[5],"periodically":[6],"at":[7],"key":[8],"moments":[9],"during":[10],"runtime":[11],"is":[12,41,111,124],"a":[13,18,42,64,215],"recurring":[14],"fundamental":[15],"pattern":[16],"in":[17,114,158,196,206,246],"large":[19],"number":[20],"uses":[22],"cases:":[23],"fault":[24],"tolerance":[25],"based":[26,213,221],"on":[27,134,214,222],"checkpoint-restart,":[28],"in-situ":[29],"or":[30],"post-analytics,":[31],"reproducibility,":[32],"adjoint":[33],"computations,":[34],"etc.":[35],"In":[36,145],"this":[37,108,122,146,156,168],"context,":[38],"multilevel":[39,251],"popular":[43],"technique:":[44],"processes":[46,88,128,191],"can":[47],"write":[48],"their":[49],"shard":[50],"the":[52,73,83,87,103,118,135,150,190,200,219],"independently":[54],"to":[55,63,96,99,102,116,154,160,179,189,198],"fast":[56,77,136],"local":[57],"storage":[58],"tiers,":[59,137],"then":[60],"flush":[61],"asynchronously":[62],"shared,":[65],"slower":[66],"tier":[67],"higher":[69],"capacity.":[70],"However,":[71],"given":[72],"limited":[74],"capacity":[75,132,195],"tiers":[78],"(e.g.":[79],"GPU":[80],"memory)":[81],"and":[82,94,218,233],"increasing":[84],"checkpoint":[85,119,247],"frequency,":[86],"often":[89,112],"run":[90,141],"out":[91,142,186],"space":[93,188],"need":[95],"fall":[97],"back":[98],"blocking":[100,205],"writes":[101],"slow":[104],"tiers.":[105],"To":[106,167],"mitigate":[107],"problem,":[109],"compression":[110],"applied":[113],"order":[115,159,197],"reduce":[117,161],"sizes.":[120],"Unfortunately,":[121],"reduction":[123],"not":[125],"uniform:":[126],"some":[127],"will":[129],"have":[130,193],"spare":[131,194],"left":[133],"while":[138],"others":[139],"still":[140],"space.":[144],"paper,":[147],"we":[148,170],"study":[149],"problem":[151,174],"how":[153,176],"leverage":[155],"imbalance":[157],"I/O":[162],"overheads":[163],"for":[164],"multi-level":[165],"checkpointing.":[166,252],"end,":[169],"solve":[171],"an":[172],"optimization":[173],"much":[177],"send":[180],"from":[181],"each":[182],"process":[183],"that":[184,192,240],"runs":[185],"minimize":[199],"amount":[201],"time":[203],"spent":[204],"I/O.":[207],"We":[208,227],"propose":[209],"two":[210],"algorithms:":[211],"one":[212],"greedy":[216],"approach":[217],"other":[220],"modified":[223],"minimum":[224],"cost":[225],"flows.":[226],"evaluate":[228],"our":[229],"proposal":[230],"using":[231],"synthetic":[232],"real-life":[234],"application":[235],"traces.":[236],"Our":[237],"evaluation":[238],"shows":[239],"both":[241],"algorithms":[242],"achieve":[243],"significant":[244],"improvements":[245],"performance":[248],"over":[249],"traditional":[250]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}