{"id":"https://openalex.org/W2151762340","doi":"https://doi.org/10.1109/hpcsim.2011.5999808","title":"Towards self-caring mapreduce: Proactively reducing fault-induced execution-time penalties","display_name":"Towards self-caring mapreduce: Proactively reducing fault-induced execution-time penalties","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2151762340","doi":"https://doi.org/10.1109/hpcsim.2011.5999808","mag":"2151762340"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2011.5999808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2011.5999808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on High Performance Computing &amp; Simulation","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/A5009398382","display_name":"Selvi Kadirvel","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Selvi Kadirvel","raw_affiliation_strings":["Advanced Computing and Information Systems Laboratory, University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems Laboratory, University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003181544","display_name":"J.A.B. Fortes","orcid":"https://orcid.org/0000-0001-8870-5205"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose A. B. Fortes","raw_affiliation_strings":["Advanced Computing and Information Systems Laboratory, University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems Laboratory, University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009398382"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":2.2169,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.91261805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9961000084877014,"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/T12127","display_name":"Software System Performance and Reliability","score":0.993399977684021,"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":0.8549621105194092},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7667479515075684},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6407480239868164},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6119152307510376},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5978389978408813},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5176746845245361},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.5123370885848999},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4183223247528076},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18096843361854553},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11348938941955566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8549621105194092},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7667479515075684},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6407480239868164},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6119152307510376},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5978389978408813},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5176746845245361},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.5123370885848999},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4183223247528076},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18096843361854553},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11348938941955566},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2011.5999808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2011.5999808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on High Performance Computing &amp; Simulation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574},{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W137316345","https://openalex.org/W193620207","https://openalex.org/W1861377444","https://openalex.org/W1996438407","https://openalex.org/W2007227498","https://openalex.org/W2015342263","https://openalex.org/W2048554864","https://openalex.org/W2057420573","https://openalex.org/W2070275167","https://openalex.org/W2098476679","https://openalex.org/W2102130607","https://openalex.org/W2121762798","https://openalex.org/W2122465391","https://openalex.org/W2126399065","https://openalex.org/W2131229759","https://openalex.org/W2145298408","https://openalex.org/W2302914195","https://openalex.org/W4211012425","https://openalex.org/W6605595552","https://openalex.org/W6607999007","https://openalex.org/W6639193275","https://openalex.org/W6649353803","https://openalex.org/W6654119168","https://openalex.org/W6662682235","https://openalex.org/W6697788245"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4244478748","https://openalex.org/W4245971243","https://openalex.org/W4223488648","https://openalex.org/W1922805944","https://openalex.org/W2134969820","https://openalex.org/W2163132667","https://openalex.org/W1975475533"],"abstract_inverted_index":{"Self-Caring":[0],"IT":[1],"systems":[2],"are":[3,24,128],"those":[4],"that":[5,194],"can":[6,197],"proactively":[7,176],"avoid":[8],"system":[9],"failures":[10,15,27,60,103,209,220],"rather":[11],"than":[12],"reactively":[13],"handle":[14],"after":[16],"they":[17],"have":[18],"occurred.":[19],"In":[20],"this":[21,72,81],"paper,":[22],"we":[23,192],"interested":[25],"in":[26,28,71,97,104,116,122,167,204,215],"which":[29],"a":[30,151,165,178],"MapReduce":[31,107,148],"job":[32,66,85,180,188],"is":[33,52,74,119],"unable":[34],"to":[35,64,75,169,202,213],"execute":[36],"within":[37],"an":[38],"SLA-based":[39],"completion":[40],"time.":[41],"The":[42],"existing":[43,143],"fault":[44],"tolerance":[45],"capability":[46,145],"provided":[47],"by":[48,130,140,200,211],"Map":[49],"Reduce":[50],"frameworks":[51],"simple":[53],"and":[54,87,174,189,210],"the":[55,78,95,105,111,142,147,161,205,216],"penalty":[56,82,96],"associated":[57,100],"with":[58,101],"handling":[59],"could":[61],"potentially":[62],"lead":[63],"excessive":[65],"execution":[67,98,117,171],"times.":[68],"Our":[69,134],"goal":[70],"paper":[73],"bring":[76],"out":[77],"severity":[79],"of":[80,146,164,207,218],"for":[83,186],"different":[84],"characteristics":[86],"configurable":[88],"framework":[89,149,190],"parameters.":[90],"We":[91],"first":[92],"quantitatively":[93],"evaluate":[94],"time":[99,118,172],"node":[102],"open-source":[106],"framework,":[108],"Hadoop":[109],"using":[110,150],"MRPerf":[112],"simulator.":[113],"This":[114,156],"increase":[115],"particularly":[120],"expensive":[121],"pay-as-you-go":[123],"cloud":[124],"infrastructures":[125],"where":[126],"users":[127],"charged":[129],"resource":[131,153,157],"usage":[132],"duration.":[133],"solution":[135],"minimizes":[136],"job-completion-time":[137],"SLA":[138],"violations":[139],"augmenting":[141],"fault-tolerance":[144],"dynamic":[152],"scaling":[154,158],"approach.":[155],"approach":[159,185],"leverages":[160],"elastic":[162],"properties":[163],"cloud,":[166],"order":[168],"mitigate":[170],"penalties":[173,196],"hence":[175],"avoids":[177],"potential":[179],"failure.":[181],"Using":[182],"our":[183],"proposed":[184],"various":[187],"parameters,":[191],"show":[193],"performance":[195],"be":[198],"decreased":[199],"up":[201,212],"78%":[203],"case":[206,217],"singlenode":[208],"100%":[214],"4-node":[219],"at":[221],"minimal":[222],"additional":[223],"cost.":[224]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
