{"id":"https://openalex.org/W2604336127","doi":"https://doi.org/10.1109/tkde.2017.2690431","title":"On Fault Tolerance for Distributed Iterative Dataflow Processing","display_name":"On Fault Tolerance for Distributed Iterative Dataflow Processing","publication_year":2017,"publication_date":"2017-04-03","ids":{"openalex":"https://openalex.org/W2604336127","doi":"https://doi.org/10.1109/tkde.2017.2690431","mag":"2604336127"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2017.2690431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2690431","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5100647359","display_name":"Chen Xu","orcid":"https://orcid.org/0000-0002-5452-9941"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Chen Xu","raw_affiliation_strings":["TU Berlin, Berlin, Germany","TU Berlin Berlin Germany"],"affiliations":[{"raw_affiliation_string":"TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"TU Berlin Berlin Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023111851","display_name":"Markus Holzemer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139189","display_name":"Hesse (Germany)","ror":"https://ror.org/041ppys11","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210139189"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Holzemer","raw_affiliation_strings":["Acellere, Frankfurt, Hessen, Germany"],"affiliations":[{"raw_affiliation_string":"Acellere, Frankfurt, Hessen, Germany","institution_ids":["https://openalex.org/I4210139189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052626178","display_name":"Manohar Kaul","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manohar Kaul","raw_affiliation_strings":["IIT Hyderabad, Telangana, India","IIT, Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"IIT Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIT, Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038969042","display_name":"Juan Soto","orcid":"https://orcid.org/0000-0002-5821-4533"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Juan Soto","raw_affiliation_strings":["TU Berlin, Berlin, Germany","TU Berlin Berlin Germany"],"affiliations":[{"raw_affiliation_string":"TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"TU Berlin Berlin Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002413906","display_name":"Volker Markl","orcid":"https://orcid.org/0009-0009-0964-026X"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Markl","raw_affiliation_strings":["TU Berlin, Berlin, Germany","TU Berlin Berlin Germany"],"affiliations":[{"raw_affiliation_string":"TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"TU Berlin Berlin Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100647359"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":4.0467,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94489815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":"8","first_page":"1709","last_page":"1722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980999827384949,"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":0.9980999827384949,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.996399998664856,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9053083658218384},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8993992805480957},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6958434581756592},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.631102442741394},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.602486252784729},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5802003741264343},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5166776180267334},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4781554639339447},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46981149911880493},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.4680445194244385},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3268930912017822},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2705150544643402},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17567682266235352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9053083658218384},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8993992805480957},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6958434581756592},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.631102442741394},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.602486252784729},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5802003741264343},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5166776180267334},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4781554639339447},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46981149911880493},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.4680445194244385},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3268930912017822},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2705150544643402},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17567682266235352}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2017.2690431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2690431","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:raiith.iith.ac.in:5317","is_oa":false,"landing_page_url":"http://raiith.iith.ac.in/5317/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G403265342","display_name":null,"funder_award_id":"01IS14013A","funder_id":"https://openalex.org/F4320334604","funder_display_name":"Banting and Best Diabetes Centre, University of Toronto"}],"funders":[{"id":"https://openalex.org/F4320334604","display_name":"Banting and Best Diabetes Centre, University of Toronto","ror":"https://ror.org/03dbr7087"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W1448681276","https://openalex.org/W1524103123","https://openalex.org/W1603765807","https://openalex.org/W1970372442","https://openalex.org/W1976860187","https://openalex.org/W1994727615","https://openalex.org/W2009584448","https://openalex.org/W2013344760","https://openalex.org/W2016924386","https://openalex.org/W2033656974","https://openalex.org/W2035176107","https://openalex.org/W2036971997","https://openalex.org/W2043494924","https://openalex.org/W2060393849","https://openalex.org/W2090673017","https://openalex.org/W2096544401","https://openalex.org/W2100830825","https://openalex.org/W2116762767","https://openalex.org/W2121810937","https://openalex.org/W2122465391","https://openalex.org/W2131975293","https://openalex.org/W2170616854","https://openalex.org/W2189465200","https://openalex.org/W2214884049","https://openalex.org/W2263854845","https://openalex.org/W2266486761","https://openalex.org/W2357449897","https://openalex.org/W2435174210","https://openalex.org/W2566979091","https://openalex.org/W6603201521","https://openalex.org/W6628546715","https://openalex.org/W6642827211","https://openalex.org/W6652477910","https://openalex.org/W6665801690","https://openalex.org/W6679815717","https://openalex.org/W6687322159","https://openalex.org/W6693251527"],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W2077180914","https://openalex.org/W1989140795","https://openalex.org/W2521218765","https://openalex.org/W2403307847","https://openalex.org/W1981433684"],"abstract_inverted_index":{"Large-scale":[0],"graph":[1,57,105,128,200],"and":[2,27,50,58,84,106,122,193,224,275,281,288],"machine":[3,59,107,240],"learning":[4,60,108,241],"analytics":[5,13,61,109],"widely":[6],"employ":[7,245],"distributed":[8,31,113],"iterative":[9,178,199],"processing.":[10,201],"Typically,":[11],"these":[12,45],"are":[14,62,204],"a":[15,18,66,85,228,246,272],"part":[16],"of":[17,37,173],"comprehensive":[19],"workflow,":[20],"which":[21],"includes":[22],"data":[23,76],"preparation,":[24],"model":[25,28],"building,":[26],"evaluation.":[29],"General-purpose":[30],"dataflow":[32,114,179],"frameworks":[33],"execute":[34],"all":[35],"steps":[36],"such":[38],"workflows":[39],"holistically.":[40],"This":[41,188],"holistic":[42],"view":[43],"enables":[44,250],"systems":[46],"to":[47,64,118,154,206,226,252,257,263],"reason":[48],"about":[49],"automatically":[51],"optimize":[52],"the":[53,75,155,171,177,190,214],"entire":[54],"pipeline.":[55],"Here,":[56],"known":[63],"incur":[65],"long":[67],"runtime":[68],"since":[69],"they":[70,284],"require":[71],"multiple":[72],"passes":[73],"over":[74],"until":[77],"convergence":[78],"is":[79,91,184],"reached.":[80],"Thus,":[81],"fault":[82,266],"tolerance":[83,267],"fast-recovery":[86],"from":[87,231],"any":[88,259],"intermittent":[89],"failure":[90,124],"critical":[92],"for":[93,104,158,166,239],"efficient":[94],"analysis.":[95],"In":[96,152,233,261],"this":[97],"paper,":[98],"we":[99,169,203,235,244,269],"propose":[100,236],"novel":[101],"fault-tolerant":[102],"mechanisms":[103],"that":[110,134,146,162,216,249,283],"run":[111],"on":[112,221],"systems.":[115],"We":[116],"seek":[117],"reduce":[119],"checkpointing":[120,160,287],"costs":[121],"shorten":[123],"recovery":[125,238],"times.":[126],"For":[127],"processing,":[129],"rather":[130],"than":[131],"writing":[132],"checkpoints":[133,141,164,172],"block":[135],"downstream":[136],"operators,":[137],"our":[138,182,265],"mechanism":[139,183],"writes":[140],"in":[142],"an":[143],"unblocking":[144,159],"manner":[145],"does":[147],"not":[148],"break":[149],"pipelined":[150],"tasks.":[151],"contrast":[153],"conventional":[156],"approach":[157],"(e.g.,":[161],"manage":[163],"independently":[165],"immutable":[167],"datasets),":[168],"inject":[170],"mutable":[174],"datasets":[175],"into":[176],"itself.":[180],"Hence,":[181],"iteration-aware":[185],"by":[186,212],"design.":[187],"simplifies":[189],"system":[191],"architecture":[192],"facilitates":[194],"coordinating":[195],"checkpoint":[196],"creation":[197],"during":[198],"Moreover,":[202],"able":[205],"rapidly":[207],"rebound,":[208],"via":[209],"confined":[210],"recovery,":[211],"exploiting":[213],"fact":[215],"log":[217],"files":[218],"exist":[219],"locally":[220],"healthy":[222],"nodes":[223],"managing":[225],"avoid":[227],"complete":[229,289],"recomputation":[230],"scratch.":[232],"addition,":[234],"replica":[237],"algorithms,":[242],"whereby":[243],"broadcast":[247],"variable":[248],"us":[251],"quickly":[253],"recover":[254],"without":[255],"having":[256],"introduce":[258],"checkpoints.":[260],"order":[262],"evaluate":[264],"strategies,":[268],"conduct":[270],"both":[271],"theoretical":[273],"study":[274],"experimental":[276],"analyses":[277],"using":[278],"Apache":[279],"Flink":[280],"discover":[282],"outperform":[285],"blocking":[286],"recovery.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}