{"id":"https://openalex.org/W2133676479","doi":null,"title":"The Design and Implementation of a Fault-Tolerant Cluster Manager","display_name":"The Design and Implementation of a Fault-Tolerant Cluster Manager","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2133676479","mag":"2133676479"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.4866","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.4866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucla.edu/~tamir/papers/ftct_tr.ps","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"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/A5114889733","display_name":"Daniel W. Goldberg","orcid":"https://orcid.org/0000-0002-5691-6988","observed_orcids":["https://orcid.org/0000-0002-5691-6988"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel W. Goldberg","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5691-6988","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351421","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-4073-0273","observed_orcids":["https://orcid.org/0000-0002-4073-0273","https://orcid.org/0000-0002-7852-0159","https://orcid.org/0000-0003-1849-8241"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4073-0273","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047975756","display_name":"Wenchao Tao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenchao Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076257646","display_name":"Yuval Tamir","orcid":"https://orcid.org/0009-0008-9977-4714","observed_orcids":["https://orcid.org/0009-0008-9977-4714"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuval Tamir","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-9977-4714","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4726,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81068792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"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":0.9916999936103821,"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":0.9916999936103821,"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":0.007300000172108412,"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":9.999999747378752e-05,"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/fault-detection-and-recovery","display_name":"fault detection and recovery","score":0.7120000123977661},{"id":"https://openalex.org/keywords/active-replication","display_name":"active replication","score":0.7120000123977661},{"id":"https://openalex.org/keywords/centralized-decision-making","display_name":"centralized decision-making","score":0.8989999890327454},{"id":"https://openalex.org/keywords/node-failure-recovery","display_name":"node failure recovery","score":0.7400000095367432},{"id":"https://openalex.org/keywords/out-of-band-signaling","display_name":"out-of-band signaling","score":0.972000002861023},{"id":"https://openalex.org/keywords/task-scheduling","display_name":"task scheduling","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.8367007970809937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758185863494873},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7406192421913147},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6287224292755127},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.5879001021385193},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5705222487449646},{"id":"https://openalex.org/C108074857","wikidata":"https://www.wikidata.org/wiki/Q3067360","display_name":"Fault management","level":3,"score":0.5159493088722229},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.48469260334968567},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4124259352684021},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4023256301879883},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.365525484085083},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26962733268737793},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.25668859481811523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13161444664001465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.4866","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.4866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucla.edu/~tamir/papers/ftct_tr.ps","raw_type":"text"},{"id":"mag:2133676479","doi":null,"is_oa":false,"landing_page_url":"https://web.cs.ucla.edu/~tamir/papers/ftct_tr.pdf","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1571292340","https://openalex.org/W1622265552","https://openalex.org/W1912168163","https://openalex.org/W1988819074","https://openalex.org/W2005216655","https://openalex.org/W2039230357","https://openalex.org/W2043381104","https://openalex.org/W2045362872","https://openalex.org/W2048185351","https://openalex.org/W2077409330","https://openalex.org/W2077982907","https://openalex.org/W2089138728","https://openalex.org/W2109781153","https://openalex.org/W2112049462","https://openalex.org/W2114728910","https://openalex.org/W2120510885","https://openalex.org/W2126087831","https://openalex.org/W2140332639","https://openalex.org/W2148811828","https://openalex.org/W2157335831","https://openalex.org/W2170404151"],"related_works":["https://openalex.org/W7100518808","https://openalex.org/W7097342722","https://openalex.org/W2538903612","https://openalex.org/W262504769","https://openalex.org/W1980984075","https://openalex.org/W1576667233","https://openalex.org/W7099954008","https://openalex.org/W2045561344","https://openalex.org/W1983128607","https://openalex.org/W7098892962"],"abstract_inverted_index":{"Cluster":[0,180],"management":[1,32,46,59,142,200],"middleware":[2,33,47,72,143,169],"schedules":[3],"tasks":[4,150],"on":[5,107,185],"a":[6,35,50,159],"cluster,":[7],"controls":[8],"access":[9],"to":[10,37,58,126,131,146],"shared":[11],"resources,":[12],"provides":[13],"for":[14,73,86,97,163],"task":[15],"submission":[16],"and":[17,19,66,94,123,134],"monitoring,":[18],"coordinates":[20],"the":[21,31,38,42,45,101,114,124,128,148,177,195,199],"cluster's":[22],"fault":[23,80,135,165],"tolerance":[24,136,166],"mechanisms.":[25,167],"Thus,":[26],"reliable":[27,39],"continuous":[28],"operation":[29,40],"of":[30,41,53,69,100,176,187,194],"is":[34,105,118,144],"prerequisite":[36],"cluster.":[43],"Hence,":[44],"should":[48],"tolerate":[49],"wide":[51],"class":[52],"faults":[54],"with":[55,151],"minimal":[56],"interruptions":[57],"operations.":[60],"This":[61],"paper":[62],"describes":[63],"design":[64],"considerations":[65],"implementation":[67],"details":[68],"cluster":[70],"mangement":[71],"high":[74],"performance":[75],"computing":[76],"in":[77],"space,":[78],"where":[79],"rates":[81],"are":[82],"significantly":[83],"higher":[84],"than":[85],"earth-bound":[87],"systems.":[88],"We":[89],"describe":[90],"key":[91,160],"detection,":[92],"recovery,":[93],"reconfiguration":[95],"mechanisms":[96],"different":[98],"components":[99],"system.":[102],"The":[103,141,168],"system":[104],"based":[106],"centralized":[108],"decision":[109,115,129],"making.":[110],"Unlike":[111],"other":[112],"systems,":[113],"making":[116],"capability":[117,155],"protected":[119],"by":[120,198],"active":[121],"replication":[122],"ability":[125],"restore":[127],"maker":[130],"full":[132],"operational":[133],"capabilities":[137],"following":[138],"node":[139],"failure.":[140],"used":[145],"provide":[147],"application":[149],"an":[152],"out-of-band":[153],"signaling":[154],"that":[156],"can":[157],"be":[158],"building":[161],"block":[162],"application-level":[164],"described":[170],"has":[171],"been":[172],"implemented":[173],"as":[174],"part":[175],"UCLA":[178],"FaultTolerant":[179],"Testbed":[181],"(FTCT)":[182],"project.":[183],"Based":[184],"measurements":[186],"this":[188],"implementation,":[189],"we":[190],"present":[191],"preliminary":[192],"evaluation":[193],"overheads":[196],"incurred":[197],"middleware.":[201],"1.":[202]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2016-06-24T00:00:00"}
