{"id":"https://openalex.org/W2141563029","doi":"https://doi.org/10.1145/2670979.2671005","title":"Wrangler","display_name":"Wrangler","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2141563029","doi":"https://doi.org/10.1145/2670979.2671005","mag":"2141563029"},"language":"en","primary_location":{"id":"doi:10.1145/2670979.2671005","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2670979.2671005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud 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/A5031510918","display_name":"Neeraja J. Yadwadkar","orcid":"https://orcid.org/0009-0007-7556-3069"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neeraja J. Yadwadkar","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031071237","display_name":"Ganesh Ananthanarayanan","orcid":"https://orcid.org/0000-0002-7479-1664"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ganesh Ananthanarayanan","raw_affiliation_strings":["Microsoft Research","Microsoft research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109560331","display_name":"Randy H. Katz","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randy Katz","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031510918"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":26.8226,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.994808,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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":0.9991999864578247,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9907000064849854,"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":0.8503438234329224},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6042940020561218},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5114647150039673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48461899161338806},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.10308271646499634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503438234329224},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6042940020561218},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5114647150039673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48461899161338806},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10308271646499634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2670979.2671005","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2670979.2671005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6200000047683716,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G7103680314","display_name":null,"funder_award_id":"FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8056273921","display_name":null,"funder_award_id":"CCF-1139158","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1506806321","https://openalex.org/W1512098439","https://openalex.org/W1549656520","https://openalex.org/W1563088657","https://openalex.org/W1579147384","https://openalex.org/W1618905105","https://openalex.org/W1663973292","https://openalex.org/W1750643891","https://openalex.org/W1780041672","https://openalex.org/W1846416616","https://openalex.org/W1861377444","https://openalex.org/W1903497807","https://openalex.org/W1943309769","https://openalex.org/W1982063824","https://openalex.org/W2002538706","https://openalex.org/W2022678927","https://openalex.org/W2041562692","https://openalex.org/W2053724458","https://openalex.org/W2096125134","https://openalex.org/W2100830825","https://openalex.org/W2103363198","https://openalex.org/W2103614420","https://openalex.org/W2104993419","https://openalex.org/W2110104287","https://openalex.org/W2119191234","https://openalex.org/W2133990480","https://openalex.org/W2135106139","https://openalex.org/W2139212933","https://openalex.org/W2140486418","https://openalex.org/W2140509629","https://openalex.org/W2148143831","https://openalex.org/W2154983209","https://openalex.org/W2160121678","https://openalex.org/W2163291889","https://openalex.org/W2173213060","https://openalex.org/W2230666400","https://openalex.org/W2322524800","https://openalex.org/W2811047940","https://openalex.org/W2987444521","https://openalex.org/W2999943684","https://openalex.org/W3193477162"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"Straggler":[0],"tasks":[1],"continue":[2],"to":[3,28,43,58,65,72,90,117,129,141,183,187,209],"be":[4],"a":[5,38,78,95,108,111,131,156,190],"major":[6],"hurdle":[7],"in":[8,144,159],"achieving":[9],"faster":[10],"completion":[11,163,179],"of":[12,110,152],"data":[13],"intensive":[14],"applications":[15],"running":[16],"on":[17,37,67,100],"modern":[18],"data-processing":[19],"frameworks.":[20],"Existing":[21,51,60],"straggler":[22,45,193],"mitigation":[23,194],"techniques":[24,53],"are":[25,63],"inefficient":[26,48],"due":[27,57,71],"their":[29],"reactive":[30],"and":[31,47,170],"replicative":[32],"nature":[33],"--":[34],"they":[35],"rely":[36,66],"wait-speculate-re-execute":[39],"mechanism,":[40],"thus":[41],"leading":[42],"delayed":[44],"detection":[46],"resource":[49,102,205],"utilization.":[50],"proactive":[52],"also":[54],"over-utilize":[55],"resources":[56],"replication.":[59],"modeling-based":[61],"approaches":[62],"hard":[64],"for":[68,150],"production-level":[69,166],"adoption":[70],"modeling":[73,120],"errors.":[74],"We":[75],"present":[76],"Wrangler,":[77],"system":[79],"that":[80,84],"proactively":[81],"avoids":[82],"situations":[83,93],"cause":[85],"stragglers.":[86],"Wrangler":[87,106,154,173,197],"automatically":[88],"learns":[89],"predict":[91],"such":[92],"using":[94,138],"statistical":[96],"learning":[97],"technique":[98],"based":[99],"cluster":[101],"utilization":[103],"counters.":[104],"Furthermore,":[105],"introduces":[107],"notion":[109],"confidence":[112,124],"measure":[113,125],"with":[114],"these":[115,139],"predictions":[116,140],"overcome":[118],"the":[119,148,160,175,204],"error":[121],"problems;":[122],"this":[123,199],"is":[126],"then":[127],"exploited":[128],"achieve":[130],"reliable":[132],"task":[133,145],"scheduling.":[134],"In":[135],"particular,":[136],"by":[137,181],"balance":[142],"delay":[143],"scheduling":[146],"against":[147],"potential":[149],"idling":[151],"resources,":[153],"achieves":[155,198],"speed":[157],"up":[158,182,208],"overall":[161],"job":[162,178],"time.":[164],"For":[165],"workloads":[167],"from":[168],"Facebook":[169],"Cloudera's":[171],"customers,":[172],"improves":[174],"99th":[176],"percentile":[177],"time":[180],"61%":[184],"as":[185],"compared":[186],"speculative":[188],"execution,":[189],"widely":[191],"used":[192],"technique.":[195],"Moreover,":[196],"speed-up":[200],"while":[201],"significantly":[202],"improving":[203],"consumption":[206],"(by":[207],"55%).":[210]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
