{"id":"https://openalex.org/W2132415006","doi":"https://doi.org/10.1109/ipdps.2010.5470432","title":"Scalable failure recovery for high-performance data aggregation","display_name":"Scalable failure recovery for high-performance data aggregation","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2132415006","doi":"https://doi.org/10.1109/ipdps.2010.5470432","mag":"2132415006"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084153776","display_name":"Dorian Arnold","orcid":"https://orcid.org/0000-0002-9425-1884"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorian C. Arnold","raw_affiliation_strings":["Department of Computer Science, University of New Mexico, Albuquerque, NM, USA","Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010187794","display_name":"Barton P. Miller","orcid":"https://orcid.org/0000-0002-9435-8315"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barton P. Miller","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin, Madison, WI, USA","Computer Sciences Department University of Wisconsin, Madison, Wisconsin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"Computer Sciences Department University of Wisconsin, Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.23789544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"11"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9968000054359436,"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":0.8248293399810791},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7114573121070862},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6976284384727478},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.49589356780052185},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.4509463310241699},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.31426918506622314},{"id":"https://openalex.org/keywords/wireless-sensor-network","display_name":"Wireless sensor network","score":0.16815143823623657},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16228356957435608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248293399810791},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7114573121070862},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6976284384727478},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.49589356780052185},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.4509463310241699},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.31426918506622314},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.16815143823623657},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16228356957435608},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2010.5470432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1598443221","https://openalex.org/W1609618519","https://openalex.org/W1997369208","https://openalex.org/W2043671329","https://openalex.org/W2046861417","https://openalex.org/W2057726682","https://openalex.org/W2089138728","https://openalex.org/W2094162326","https://openalex.org/W2099351934","https://openalex.org/W2100970777","https://openalex.org/W2106913893","https://openalex.org/W2119018856","https://openalex.org/W2119984085","https://openalex.org/W2120342738","https://openalex.org/W2126310747","https://openalex.org/W2129292927","https://openalex.org/W2140770199","https://openalex.org/W2141742398","https://openalex.org/W2143462372","https://openalex.org/W2144499729","https://openalex.org/W2148952547","https://openalex.org/W2150179825","https://openalex.org/W2153399951","https://openalex.org/W2167396179","https://openalex.org/W2171371822","https://openalex.org/W4248301666","https://openalex.org/W4285719527","https://openalex.org/W6673827415","https://openalex.org/W6682022027","https://openalex.org/W6686224502"],"related_works":["https://openalex.org/W595346907","https://openalex.org/W153296825","https://openalex.org/W598989511","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1824242903","https://openalex.org/W1493858311","https://openalex.org/W2155470929","https://openalex.org/W2111125783","https://openalex.org/W2394465510"],"abstract_inverted_index":{"Many":[0],"high-performance":[1],"tools,":[2],"applications":[3],"and":[4,15,25,91,94,116,127,144,148,160,172,205],"infrastructures,":[5],"such":[6],"as":[7],"Paradyn,":[8],"STAT,":[9],"TAU,":[10],"Ganglia,":[11],"SuperMon,":[12],"Astrolabe,":[13],"Borealis,":[14],"MRNet,":[16],"use":[17],"data":[18,23,27,45,113,136,154],"aggregation":[19,46,137,155],"to":[20,43,122,193],"synthesize":[21],"large":[22],"sets":[24],"reduce":[26],"volumes":[28],"while":[29],"retaining":[30],"relevant":[31],"information":[32,75],"content.":[33],"Hierarchical":[34],"or":[35],"tree-based":[36],"overlay":[37],"networks":[38],"(TBONs)":[39],"are":[40],"often":[41],"used":[42],"execute":[44],"operations":[47,156],"in":[48,77,98],"a":[49,60,111,131,173],"scalable,":[50],"piecewise":[51],"fashion.":[52],"In":[53,162],"this":[54,163,185],"paper,":[55,164],"we":[56,139,165],"present":[57],"state":[58,74,81,85,108,142,150,169,198],"compensation,":[59],"scalable":[61],"failure":[62],"recovery":[63,203],"model":[64,115],"for":[65,189],"high-bandwidth,":[66],"low-latency":[67],"TBON":[68,79,180],"computations.":[69],"By":[70],"leveraging":[71],"inherently":[72],"redundant":[73],"found":[76],"many":[78],"computations,":[80],"compensation":[82,109,143,151,170,199],"avoids":[83],"explicit":[84],"replication":[86],"(for":[87],"example,":[88],"process":[89],"checkpoints":[90],"message":[92],"logging)":[93],"incurs":[95],"no":[96],"overhead":[97],"the":[99,167,178],"absence":[100],"of":[101,134,195],"failures.":[102],"Further,":[103],"when":[104],"failures":[105,125],"do":[106],"occur,":[107],"uses":[110],"weak":[112],"consistency":[114],"localized":[117],"protocols":[118],"that":[119,153,188],"allow":[120],"processes":[121],"recover":[123],"from":[124],"independently":[126],"responsively.":[128],"Based":[129],"on":[130],"formal":[132],"specification":[133],"our":[135],"model,":[138],"have":[140],"validated":[141],"identified":[145],"its":[146],"assumptions":[147],"limitations:":[149],"requires":[152],"be":[157],"associative,":[158],"commutative":[159],"idempotent.":[161],"describe":[166],"fundamental":[168],"concepts":[171],"prototype":[174],"implementation":[175],"integrated":[176],"into":[177],"MRNet":[179],"infrastructure.":[181],"Our":[182],"experiments":[183],"with":[184],"framework":[186],"suggest":[187],"TBONs":[190],"supporting":[191],"up":[192],"millions":[194],"application":[196,207],"processes,":[197],"can":[200],"yield":[201],"millisecond":[202],"latencies":[204],"inconsequential":[206],"perturbation.":[208]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}