{"id":"https://openalex.org/W1985102977","doi":"https://doi.org/10.1145/1274971.1274975","title":"Scalability of the Nutch search engine","display_name":"Scalability of the Nutch search engine","publication_year":2007,"publication_date":"2007-06-17","ids":{"openalex":"https://openalex.org/W1985102977","doi":"https://doi.org/10.1145/1274971.1274975","mag":"1985102977"},"language":"en","primary_location":{"id":"doi:10.1145/1274971.1274975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1274975","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 annual international conference on Supercomputing","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/A5055326969","display_name":"Jos\u00e9 E. Moreira","orcid":"https://orcid.org/0000-0001-7029-6327"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 E. Moreira","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013890585","display_name":"Maged M. Michael","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maged M. Michael","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045204301","display_name":"Dilma Da Silva","orcid":"https://orcid.org/0000-0001-6538-2888"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilma Da Silva","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049583570","display_name":"Doron Shiloach","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doron Shiloach","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110042006","display_name":"Parijat Dube","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parijat Dube","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425431","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-7293-8119"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"49","issue":null,"first_page":"3","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9932000041007996,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9932000041007996,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9923999905586243,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9819999933242798,"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/scalability","display_name":"Scalability","score":0.8875351548194885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8152060508728027},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.7044069766998291},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5865129232406616},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5666773915290833},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5658822059631348},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45068541169166565},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4170973300933838},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39215588569641113},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24682310223579407},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.18893420696258545}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8875351548194885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8152060508728027},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.7044069766998291},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5865129232406616},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5666773915290833},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5658822059631348},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45068541169166565},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4170973300933838},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39215588569641113},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24682310223579407},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.18893420696258545},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1274971.1274975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1274975","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 annual international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1527781663","https://openalex.org/W1976044247","https://openalex.org/W1980771010","https://openalex.org/W1990998971","https://openalex.org/W2013723863","https://openalex.org/W2017361020","https://openalex.org/W2018570519","https://openalex.org/W2064037464","https://openalex.org/W2104332750","https://openalex.org/W2122465391","https://openalex.org/W2131645490","https://openalex.org/W2135936812","https://openalex.org/W2139731740","https://openalex.org/W2154148563","https://openalex.org/W2492294785","https://openalex.org/W6666384160"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W4231814374","https://openalex.org/W2155964760","https://openalex.org/W2043380045","https://openalex.org/W2099557065"],"abstract_inverted_index":{"Nutch":[0,17,121],"is":[1,8,122],"an":[2],"open":[3],"source":[4],"search":[5,40,56,65],"engine":[6],"that":[7,120],"gaining":[9],"increasing":[10,43,72],"popularity":[11],"in":[12,69,115],"the":[13,37,44,52,55,60,73,81,97,110,126],"commercial":[14,116],"world.":[15],"The":[16,90],"architecture":[18],"leads":[19],"itself":[20],"to":[21,34,50,108],"a":[22,132],"wide":[23],"range":[24],"of":[25,39,46,54,85,88,96,112],"parallelization":[26],"techniques.":[27],"Multiple":[28],"backend":[29],"servers":[30],"can":[31,67],"be":[32],"used":[33,107],"both":[35],"partition":[36],"corpus":[38],"data,":[41],"thus":[42],"rate":[45],"queries":[47],"serviced,":[48],"and":[49,83,105],"increase":[51],"size":[53],"data":[57],"while":[58],"preserving":[59],"service":[61],"rate.":[62,75],"Alternatively,":[63],"multiple":[64],"engines":[66],"operate":[68],"parallel,":[70],"further":[71],"query":[74],"In":[76],"this":[77],"paper,":[78],"we":[79],"analyze":[80],"performance":[82,133],"scalability":[84],"various":[86],"configurations":[87,91,128],"Nutch.":[89],"were":[92,106],"implemented":[93],"as":[94],"part":[95],"Commercial":[98],"Scale":[99],"Out":[100],"project":[101],"at":[102],"IBM":[103],"Research,":[104],"investigate":[109],"applicability":[111],"scale-out":[113],"architectures":[114],"environments.":[117],"We":[118],"conclude":[119],"highly":[123],"scalable,":[124],"with":[125],"different":[127],"behaving":[129],"differently":[130],"from":[131],"perspective.":[134]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
