{"id":"https://openalex.org/W28511425","doi":null,"title":"Scalable diskless checkpointing for large parallel systems","display_name":"Scalable diskless checkpointing for large parallel systems","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W28511425","mag":"28511425"},"language":"en","primary_location":{"id":"mag:28511425","doi":null,"is_oa":false,"landing_page_url":"https://ideals.illinois.edu/handle/2142/11054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5008222900","display_name":"Daniel A. Reed","orcid":"https://orcid.org/0000-0001-7331-1473","observed_orcids":["https://orcid.org/0000-0001-7331-1473"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel A. Reed","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":"https://orcid.org/0000-0001-7331-1473","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100882715","display_name":"Charng\u2010Da Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charng\u2010Da Lu","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.1788,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.92690866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"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":0.9291999936103821,"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":0.9291999936103821,"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":0.05490000173449516,"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":0.005499999970197678,"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/i-o-scalability","display_name":"I/O scalability","score":0.7279999852180481},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.5479999780654907},{"id":"https://openalex.org/keywords/reed-solomon-codes","display_name":"Reed-Solomon codes","score":0.9810000061988831},{"id":"https://openalex.org/keywords/parity-bits","display_name":"parity bits","score":0.5529999732971191},{"id":"https://openalex.org/keywords/node-partitioning","display_name":"node partitioning","score":0.6919999718666077},{"id":"https://openalex.org/keywords/checkpoint-recovery","display_name":"checkpoint recovery","score":0.6200000047683716},{"id":"https://openalex.org/keywords/parallel-scientific-applications","display_name":"parallel scientific applications","score":0.6539999842643738},{"id":"https://openalex.org/keywords/analytical-performance-model","display_name":"analytical performance model","score":0.6779999732971191},{"id":"https://openalex.org/keywords/i-o-bottleneck","display_name":"I/O bottleneck","score":0.4950000047683716},{"id":"https://openalex.org/keywords/massively-parallel-computers","display_name":"massively parallel computers","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847942590713501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7117248773574829},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6449723243713379},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.58695387840271},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49043819308280945},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4868842661380768},{"id":"https://openalex.org/C2781057727","wikidata":"https://www.wikidata.org/wiki/Q9941","display_name":"Parallel I/O","level":2,"score":0.46042323112487793},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4476034343242645},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4362748861312866},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.42107075452804565},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4183223247528076},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.273568332195282}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:28511425","doi":null,"is_oa":false,"landing_page_url":"https://ideals.illinois.edu/handle/2142/11054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W4871647","https://openalex.org/W21025594","https://openalex.org/W26797728","https://openalex.org/W50248055","https://openalex.org/W71644105","https://openalex.org/W132638985","https://openalex.org/W176967344","https://openalex.org/W191492107","https://openalex.org/W791531824","https://openalex.org/W1486339539","https://openalex.org/W1486947867","https://openalex.org/W1514171102","https://openalex.org/W1514634512","https://openalex.org/W1527235902","https://openalex.org/W1537929875","https://openalex.org/W1539055682","https://openalex.org/W1541582221","https://openalex.org/W1547423527","https://openalex.org/W1555915743","https://openalex.org/W1581312614","https://openalex.org/W1581374141","https://openalex.org/W1591141258","https://openalex.org/W1596936080","https://openalex.org/W1634121635","https://openalex.org/W1785729727","https://openalex.org/W1916709771","https://openalex.org/W1963726333","https://openalex.org/W1965351873","https://openalex.org/W1974401809","https://openalex.org/W1986009243","https://openalex.org/W1990911977","https://openalex.org/W1991750682","https://openalex.org/W1995365180","https://openalex.org/W1995516298","https://openalex.org/W1999667809","https://openalex.org/W2033656974","https://openalex.org/W2040932846","https://openalex.org/W2042038304","https://openalex.org/W2045879521","https://openalex.org/W2053352232","https://openalex.org/W2068975988","https://openalex.org/W2073965851","https://openalex.org/W2081612620","https://openalex.org/W2091327926","https://openalex.org/W2092787020","https://openalex.org/W2093123948","https://openalex.org/W2098996511","https://openalex.org/W2100970777","https://openalex.org/W2101395364","https://openalex.org/W2101666697","https://openalex.org/W2102469268","https://openalex.org/W2103815459","https://openalex.org/W2104162910","https://openalex.org/W2104458739","https://openalex.org/W2105039796","https://openalex.org/W2106618588","https://openalex.org/W2107635250","https://openalex.org/W2113375596","https://openalex.org/W2114035455","https://openalex.org/W2114728910","https://openalex.org/W2114739461","https://openalex.org/W2120299349","https://openalex.org/W2120876718","https://openalex.org/W2121098551","https://openalex.org/W2123669573","https://openalex.org/W2124213351","https://openalex.org/W2126071114","https://openalex.org/W2126177294","https://openalex.org/W2126637194","https://openalex.org/W2129585587","https://openalex.org/W2130252115","https://openalex.org/W2131053137","https://openalex.org/W2131613942","https://openalex.org/W2131645490","https://openalex.org/W2133287150","https://openalex.org/W2136390693","https://openalex.org/W2140332639","https://openalex.org/W2142395340","https://openalex.org/W2144984544","https://openalex.org/W2146265738","https://openalex.org/W2148602057","https://openalex.org/W2151080836","https://openalex.org/W2151745115","https://openalex.org/W2154817671","https://openalex.org/W2155204206","https://openalex.org/W2155713541","https://openalex.org/W2156447886","https://openalex.org/W2160123909","https://openalex.org/W2161537327","https://openalex.org/W2163755682","https://openalex.org/W2165022815","https://openalex.org/W2167181671","https://openalex.org/W2168110206","https://openalex.org/W2168886965","https://openalex.org/W2171453084","https://openalex.org/W2172408677","https://openalex.org/W2296772319","https://openalex.org/W2480965226","https://openalex.org/W2729569041","https://openalex.org/W2970040153","https://openalex.org/W3141978889","https://openalex.org/W4232225775"],"related_works":["https://openalex.org/W2163295644","https://openalex.org/W2296772319","https://openalex.org/W7097883547","https://openalex.org/W1973963067","https://openalex.org/W7061363118","https://openalex.org/W1984564341","https://openalex.org/W2102469268","https://openalex.org/W1847743802","https://openalex.org/W63848143","https://openalex.org/W1991726467"],"abstract_inverted_index":{"Parallel":[0],"scientific":[1,52,194],"applications":[2,53],"deal":[3],"with":[4,188,248,253],"machine":[5],"unreliability":[6],"by":[7,132,152],"periodic":[8],"checkpointing,":[9],"in":[10,23,84,121],"which":[11,142],"all":[12],"processes":[13,63],"coordinate":[14],"to":[15,18,92,228],"dump":[16],"memory":[17,122],"stable":[19],"storage":[20,40,106],"simultaneously.":[21],"However,":[22],"systems":[24,58,90,210,247],"comprising":[25],"tens":[26],"of":[27,29,51,61,75,124,134,164,215,232,242,250,256],"thousands":[28,249],"nodes,":[30,251,257],"the":[31,37,62,73,78,117,230,240,258],"total":[32],"data":[33,118],"volume":[34],"can":[35,54,80,261],"overwhelm":[36],"network":[38],"and":[39,71,86,104,128,155,170,173,181,184,192,203,252],"farm,":[41],"creating":[42],"an":[43,225],"I/O":[44,148,190,201],"bottleneck.":[45],"Furthermore,":[46],"a":[47,98,178,212,218],"very":[48],"large":[49,89,213],"class":[50],"fail":[55,93],"on":[56,145,246],"these":[57],"if":[59],"one":[60],"dies.":[64],"\r\nPoor":[65],"checkpointing":[66,69,96,180],"performance":[67,187],"limits":[68],"frequency":[70],"increases":[72],"time-to-solution":[74],"applications.":[76,195],"Also,":[77],"application":[79,260],"spend":[81],"more":[82],"time":[83],"recovery":[85,182],"restart":[87],"because":[88],"tend":[91],"often.":[94],"\r\nDiskless":[95],"is":[97,119,130,149,244],"viable":[99],"approach":[100],"that":[101,239],"provides":[102],"high-performance":[103],"reliable":[105],"for":[107,211],"intermediate":[108],"or":[109,139],"temporary":[110],"data,":[111],"such":[112],"as":[113],"checkpoint":[114],"files.":[115],"First,":[116],"stored":[120,144],"instead":[123],"disk.":[125],"Second,":[126],"reliability":[127],"recoverability":[129],"guaranteed":[131],"use":[133],"redundancy":[135,167],"codes":[136,168],"(parity":[137],"bits":[138],"Reed-Solomon":[140],"codes),":[141],"are":[143],"spares.":[146],"Third,":[147],"made":[150],"scalable":[151],"partitioning":[153,255],"nodes":[154],"spares":[156],"into":[157],"small":[158,245],"groups.":[159],"Each":[160],"group":[161],"takes":[162],"care":[163],"its":[165,186],"own":[166],"generation":[169],"node":[171],"failure":[172],"recovery.":[174],"\r\nWe":[175],"have":[176,222],"implemented":[177],"diskless":[179,233],"system":[183],"assessed":[185],"both":[189],"benchmarks":[191],"real":[193],"The":[196],"results":[197],"show":[198],"much":[199],"greater":[200],"scalability":[202],"higher":[204],"throughput":[205],"than":[206],"disk-based":[207],"parallel":[208],"file":[209],"number":[214],"clients.":[216],"\r\nAs":[217],"technology":[219],"projection,":[220],"we":[221],"also":[223],"developed":[224],"analytical":[226],"model":[227,236],"investigate":[229],"performability":[231],"checkpointing.":[234],"Our":[235],"evaluation":[237],"shows":[238],"overhead":[241],"checkpoint/recovery":[243],"appropriate":[254],"user":[259],"survive":[262],"several":[263],"times":[264],"longer.":[265]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}