{"id":"https://openalex.org/W2051505342","doi":"https://doi.org/10.1145/2287076.2287108","title":"Understanding the effects and implications of compute node related failures in hadoop","display_name":"Understanding the effects and implications of compute node related failures in hadoop","publication_year":2012,"publication_date":"2012-06-18","ids":{"openalex":"https://openalex.org/W2051505342","doi":"https://doi.org/10.1145/2287076.2287108","mag":"2051505342"},"language":"en","primary_location":{"id":"doi:10.1145/2287076.2287108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2287076.2287108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing","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/A5079167224","display_name":"Florin Dinu","orcid":"https://orcid.org/0009-0005-1514-2997"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Florin Dinu","raw_affiliation_strings":["Rice University, Houston, TX, USA","Rice Univ., Houston, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice Univ., Houston, TX, USA#TAB#","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075120727","display_name":"T. S. Eugene Ng","orcid":"https://orcid.org/0000-0003-2954-0767"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Eugene Ng","raw_affiliation_strings":["Rice University, Houston, TX, USA","Rice Univ., Houston, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice Univ., Houston, TX, USA#TAB#","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079167224"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":20.4896,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.99190291,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"198"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9977999925613403,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9976999759674072,"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":0.8459657430648804},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7778517603874207},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6693848371505737},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6372684836387634},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6271679401397705},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5837188363075256},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.508740246295929},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2864498496055603},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.18271556496620178},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17444419860839844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8459657430648804},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7778517603874207},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6693848371505737},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6372684836387634},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6271679401397705},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5837188363075256},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.508740246295929},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2864498496055603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.18271556496620178},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17444419860839844},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2287076.2287108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2287076.2287108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.9005","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.9005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rice.edu/~eugeneng/papers/HPDC12.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.2977","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.2977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rice.edu/%7Efd2/pdf/hpdc106-dinu.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W69713013","https://openalex.org/W91677537","https://openalex.org/W192446467","https://openalex.org/W1236737278","https://openalex.org/W1598064945","https://openalex.org/W1609755472","https://openalex.org/W1857009450","https://openalex.org/W1861377444","https://openalex.org/W1985419898","https://openalex.org/W1987932453","https://openalex.org/W1993892970","https://openalex.org/W2013344760","https://openalex.org/W2035543557","https://openalex.org/W2048554864","https://openalex.org/W2070275167","https://openalex.org/W2091765165","https://openalex.org/W2092643753","https://openalex.org/W2097926925","https://openalex.org/W2098935637","https://openalex.org/W2104171511","https://openalex.org/W2110104287","https://openalex.org/W2118676041","https://openalex.org/W2119528150","https://openalex.org/W2119638333","https://openalex.org/W2125775320","https://openalex.org/W2126969025","https://openalex.org/W2129424879","https://openalex.org/W2136717145","https://openalex.org/W2147470852","https://openalex.org/W2153704625","https://openalex.org/W2153889808","https://openalex.org/W2158733823","https://openalex.org/W2163291889","https://openalex.org/W2173213060","https://openalex.org/W2187146589","https://openalex.org/W2566481479","https://openalex.org/W2588083655","https://openalex.org/W2613694343","https://openalex.org/W2912802084","https://openalex.org/W4213221859"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4244478748","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757"],"abstract_inverted_index":{"Hadoop":[0,14,76,134,153],"has":[1],"become":[2],"a":[3,43,60],"critical":[4],"component":[5],"in":[6,48,59,107,126],"today's":[7],"cloud":[8,92],"environment.":[9],"Ensuring":[10],"good":[11],"performance":[12],"for":[13,17],"is":[15,132],"paramount":[16],"the":[18,66,91,121,157,168,189],"wide-range":[19],"of":[20,25,123,159,171,191,200],"applications":[21],"built":[22],"on":[23,136],"top":[24],"it.":[26],"In":[27],"this":[28,69],"paper":[29],"we":[30,73],"analyze":[31],"Hadoop's":[32,98,108],"behavior":[33],"under":[34],"failures":[35,113,161],"involving":[36],"compute":[37],"nodes.":[38],"We":[39,63,165,186],"find":[40,74],"that":[41,75,133,167],"even":[42],"single":[44],"failure":[45,148,173,180],"can":[46,86],"result":[47,103],"inflated,":[49],"variable":[50],"and":[51,139,194],"unpredictable":[52],"job":[53,127],"running":[54,128],"times,":[55],"all":[56],"undesirable":[57],"properties":[58],"distributed":[61],"system.":[62],"systematically":[64],"track":[65],"causes":[67,158,176],"underlying":[68],"distressing":[70],"behavior.":[71],"First,":[72],"makes":[77],"unrealistic":[78],"assumptions":[79,85],"about":[80],"task":[81,119],"progress":[82],"rates.":[83],"These":[84],"be":[87],"easily":[88],"invalidated":[89],"by":[90,97,117],"environment":[93],"and,":[94],"more":[95],"surprisingly,":[96],"own":[99],"design":[100],"decisions.":[101],"The":[102,130],"are":[104,114],"significant":[105],"inefficiencies":[106],"speculative":[109],"execution":[110],"algorithm.":[111],"Second,":[112],"re-discovered":[115],"individually":[116],"each":[118],"at":[120],"cost":[122],"great":[124],"degradation":[125],"time.":[129],"reason":[131],"focuses":[135],"extreme":[137],"scalability":[138],"thus":[140],"trades":[141],"off":[142],"possible":[143],"improvements":[144],"resulting":[145,169],"from":[146],"sharing":[147],"information":[149],"between":[150,162],"tasks.":[151,164,185],"Third,":[152],"does":[154],"not":[155],"consider":[156],"connection":[160,172],"its":[163],"show":[166],"overloading":[170],"semantics":[174],"unnecessarily":[175],"an":[177],"otherwise":[178],"localized":[179],"to":[181,183,197],"propagate":[182],"healthy":[184],"also":[187],"discuss":[188],"implications":[190],"our":[192],"findings":[193],"draw":[195],"attention":[196],"new":[198],"ways":[199],"improving":[201],"Hadoop-like":[202],"frameworks.":[203]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
