{"id":"https://openalex.org/W2241684952","doi":"https://doi.org/10.1109/issre.2015.7381844","title":"Experience report: A characteristic study on out of memory errors in distributed data-parallel applications","display_name":"Experience report: A characteristic study on out of memory errors in distributed data-parallel applications","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2241684952","doi":"https://doi.org/10.1109/issre.2015.7381844","mag":"2241684952"},"language":"en","primary_location":{"id":"doi:10.1109/issre.2015.7381844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/issre.2015.7381844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 26th International Symposium on Software Reliability Engineering (ISSRE)","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/A5103731665","display_name":"Lijie Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijie Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023724495","display_name":"Wensheng Dou","orcid":"https://orcid.org/0000-0002-3323-0449"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wensheng Dou","raw_affiliation_strings":["State Key Lab of Computer Science, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Computer Science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100565154","display_name":"Feng Zhu","orcid":"https://orcid.org/0009-0008-4999-2780"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036073707","display_name":"Chushu Gao","orcid":"https://orcid.org/0000-0003-1397-4536"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chushu Gao","raw_affiliation_strings":["State Key Lab of Computer Science, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Computer Science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682444","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-8204-424X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["State Key Lab of Computer Science, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Computer Science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038920560","display_name":"Hua Zhong","orcid":"https://orcid.org/0000-0002-8535-8225"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Zhong","raw_affiliation_strings":["State Key Lab of Computer Science, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Computer Science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037779332","display_name":"Jun Wei","orcid":"https://orcid.org/0000-0002-1028-8509"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wei","raw_affiliation_strings":["State Key Lab of Computer Science, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Computer Science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103731665"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.3185,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93356988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"529"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9980000257492065,"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":0.8717825412750244},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5580362677574158},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.515363872051239},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5132749080657959},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5046366453170776},{"id":"https://openalex.org/keywords/memory-errors","display_name":"Memory errors","score":0.4530297815799713},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.44283345341682434},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4413355588912964},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.43136149644851685},{"id":"https://openalex.org/keywords/distributed-shared-memory","display_name":"Distributed shared memory","score":0.4270510971546173},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.4256126880645752},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40884387493133545},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.40471628308296204},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.39068514108657837},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3213304281234741},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.2113572359085083},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.20315846800804138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8717825412750244},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5580362677574158},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.515363872051239},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5132749080657959},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5046366453170776},{"id":"https://openalex.org/C119907115","wikidata":"https://www.wikidata.org/wiki/Q6815725","display_name":"Memory errors","level":3,"score":0.4530297815799713},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.44283345341682434},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4413355588912964},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.43136149644851685},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.4270510971546173},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.4256126880645752},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40884387493133545},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.40471628308296204},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.39068514108657837},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3213304281234741},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.2113572359085083},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.20315846800804138},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/issre.2015.7381844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/issre.2015.7381844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 26th International Symposium on Software Reliability Engineering (ISSRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W1448681276","https://openalex.org/W1984775394","https://openalex.org/W1991546210","https://openalex.org/W2000100269","https://openalex.org/W2006307164","https://openalex.org/W2039676055","https://openalex.org/W2082171780","https://openalex.org/W2088727885","https://openalex.org/W2100830825","https://openalex.org/W2114303224","https://openalex.org/W2126399065","https://openalex.org/W2131975293","https://openalex.org/W2132353061","https://openalex.org/W2154843497","https://openalex.org/W2154894831","https://openalex.org/W2160768644","https://openalex.org/W2166140339","https://openalex.org/W2168206938","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2290323698","https://openalex.org/W4242010563","https://openalex.org/W4251369193","https://openalex.org/W4254901924","https://openalex.org/W4300988640","https://openalex.org/W6603201521","https://openalex.org/W6628546715","https://openalex.org/W6679815717"],"related_works":["https://openalex.org/W254684032","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W4381884576","https://openalex.org/W233533876","https://openalex.org/W1848192231","https://openalex.org/W2781952239","https://openalex.org/W2066998387","https://openalex.org/W2959540566","https://openalex.org/W1560342753"],"abstract_inverted_index":{"Out":[0],"of":[1,41,112,223],"memory":[2,25,105,110,215,221],"(OOM)":[3],"errors":[4,70,82,120,142,165],"occur":[5],"frequently":[6],"in":[7,71,90,183,243],"data-intensive":[8],"applications":[9],"that":[10,95],"run":[11],"atop":[12],"distributed":[13,42],"data-parallel":[14],"frameworks,":[15],"such":[16,129],"as":[17,130],"MapReduce":[18],"and":[19,32,54,73,115,136,194,226],"Spark.":[20],"In":[21],"these":[22,56],"applications,":[23],"the":[24,30,36,39,51,86,91,103,109,113,124,170,188,209,220,224],"space":[26],"is":[27,45,97,247],"shared":[28],"by":[29,85,123,146,169],"framework":[31,37,114,225],"user":[33,116,148,196,227],"code.":[34,117],"Since":[35],"hides":[38],"details":[40],"execution,":[43],"it":[44,96],"challenging":[46],"for":[47,99],"users":[48,100,233],"to":[49,101,107,203,207,218],"pinpoint":[50],"root":[52],"causes":[53],"fix":[55,180],"OOM":[57,69,210],"errors.":[58],"This":[59],"paper":[60],"presents":[61],"a":[62,248],"comprehensive":[63],"characteristic":[64],"study":[65],"on":[66],"123":[67],"real-world":[68],"Hadoop":[72],"Spark":[74],"applications.":[75],"Our":[76,199],"major":[77],"findings":[78,200],"include:":[79],"(1)":[80,212],"12%":[81],"are":[83,121,144,166,177],"caused":[84,122,145,168],"large":[87,126,131,137,154,158,172,240],"data":[88,132,155,236,245],"buffered/cached":[89],"framework,":[92],"which":[93,150],"indicates":[94],"hard":[98],"configure":[102],"right":[104],"quota":[106],"balance":[108,219],"usage":[111,222],"(2)":[118,231],"37%":[119],"unexpected":[125,153,171],"runtime":[127,173,192],"data,":[128,193],"partition,":[133],"hotspot":[134],"key,":[135],"key/value":[138],"record.":[139],"(3)":[140],"Most":[141],"(64%)":[143],"memory-consuming":[147],"code,":[149],"carelessly":[151],"processes":[152],"or":[156],"generates":[157],"in-memory":[159,244],"computing":[160,241],"results.":[161],"Among":[162],"them,":[163],"13%":[164],"also":[167],"data.":[174],"(4)":[175],"There":[176],"three":[178],"common":[179,249],"patterns":[181],"(used":[182],"34%":[184],"errors),":[185],"namely":[186],"changing":[187],"memory/dataflow-related":[189],"configurations,":[190],"dividing":[191],"optimizing":[195],"code":[197,228],"logic.":[198],"inspire":[201],"us":[202],"propose":[204],"potential":[205],"solutions":[206],"avoid":[208],"errors:":[211],"providing":[213,232],"dynamic":[214],"management":[216],"mechanisms":[217],"at":[229],"runtime;":[230],"with":[234],"memory+disk":[235],"structures,":[237],"since":[238],"accumulating":[239],"results":[242],"structures":[246],"cause":[250],"(15%":[251],"errors).":[252]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
