{"id":"https://openalex.org/W2017194553","doi":"https://doi.org/10.1109/icde.2010.5447919","title":"Estimating the progress of MapReduce pipelines","display_name":"Estimating the progress of MapReduce pipelines","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2017194553","doi":"https://doi.org/10.1109/icde.2010.5447919","mag":"2017194553"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063728932","display_name":"Kristi Morton","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristi Morton","raw_affiliation_strings":["Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","Computer Science & Engineering Department, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Computer Science & Engineering Department, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077191191","display_name":"Abram L. Friesen","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abram Friesen","raw_affiliation_strings":["Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","Computer Science & Engineering Department, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Computer Science & Engineering Department, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064988079","display_name":"Magdalena Ba\u0142azi\u0144ska","orcid":"https://orcid.org/0000-0002-6805-0325"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Balazinska","raw_affiliation_strings":["Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","Computer Science & Engineering Department, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Computer Science & Engineering Department, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103045316","display_name":"Dan Grossman","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Grossman","raw_affiliation_strings":["Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","Computer Science & Engineering Department, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Computer Science & Engineering Department, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":15.2556,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.9962371,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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/T11106","display_name":"Data Management and Algorithms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8900657892227173},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6174240708351135},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4952491819858551},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.43650007247924805},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.42216843366622925},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3932393789291382},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36920446157455444},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.221700519323349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8900657892227173},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6174240708351135},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4952491819858551},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.43650007247924805},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.42216843366622925},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3932393789291382},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36920446157455444},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.221700519323349},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2010.5447919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.175.2866","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.175.2866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.washington.edu/homes/kmorton/ICDE10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2014375476","https://openalex.org/W2054681294","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2112847223","https://openalex.org/W2119414841","https://openalex.org/W2120451551","https://openalex.org/W2149666876","https://openalex.org/W2153231596","https://openalex.org/W2168910844","https://openalex.org/W2173213060","https://openalex.org/W2296677182","https://openalex.org/W4240511086","https://openalex.org/W6676947189","https://openalex.org/W6677690127"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"In":[0,44],"parallel":[1,42,56],"query-processing":[2],"environments,":[3],"accurate,":[4],"time-oriented":[5],"progress":[6,39,85],"indicators":[7],"could":[8],"provide":[9,37],"much":[10],"utility":[11],"given":[12],"that":[13],"inter-":[14],"and":[15,98,111,121],"intra-query":[16],"execution":[17,100],"times":[18],"can":[19],"have":[20,103],"high":[21],"variance.":[22],"However,":[23],"none":[24],"of":[25,71,74,86],"the":[26,35,50,61,84,93,108,118],"techniques":[27,81],"used":[28],"by":[29],"existing":[30],"tools":[31],"or":[32],"available":[33],"in":[34,63,107,125],"literature":[36],"non-trivial":[38],"estimation":[40],"for":[41,82],"queries.":[43],"this":[45,64],"paper,":[46],"we":[47],"introduce":[48],"Parallax,":[49],"first":[51],"such":[52],"indicator.":[53],"While":[54],"several":[55],"data":[57],"processing":[58],"systems":[59],"exist,":[60],"work":[62],"paper":[65],"targets":[66],"environments":[67],"where":[68],"queries":[69,123],"consist":[70],"a":[72,126],"series":[73],"MapReduce":[75],"jobs.":[76],"Parallax":[77],"builds":[78],"on":[79,92],"recently-developed":[80],"estimating":[83],"single-site":[87],"SQL":[88],"queries,":[89],"but":[90],"focuses":[91],"challenges":[94],"related":[95],"to":[96],"parallelism":[97],"variable":[99],"speeds.":[101],"We":[102],"implemented":[104],"our":[105],"estimator":[106],"Pig":[109],"system":[110],"demonstrate":[112],"its":[113],"performance":[114],"through":[115],"experiments":[116],"with":[117],"PigMix":[119],"benchmark":[120],"other":[122],"running":[124],"real,":[127],"small-scale":[128],"cluster.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":17}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}