{"id":"https://openalex.org/W2885687832","doi":"https://doi.org/10.1145/3225058.3225102","title":"Index Shard Replication Strategies for Improving Resource Utilization in Large Scale Search Engines","display_name":"Index Shard Replication Strategies for Improving Resource Utilization in Large Scale Search Engines","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2885687832","doi":"https://doi.org/10.1145/3225058.3225102","mag":"2885687832"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","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/A5026498734","display_name":"Yusen Li","orcid":"https://orcid.org/0000-0001-6623-350X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yusen Li","raw_affiliation_strings":["Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015527156","display_name":"Xueyan Tang","orcid":"https://orcid.org/0000-0002-7404-7595"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xueyan Tang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036580072","display_name":"Wentong Cai","orcid":"https://orcid.org/0000-0002-0183-3835"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wentong Cai","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086493023","display_name":"Jiancong Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancong Tong","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390120","display_name":"Xiaoguang Liu","orcid":"https://orcid.org/0000-0002-9010-3278"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Liu","raw_affiliation_strings":["Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367418","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-8910-8979"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040819820","display_name":"Gao Chuansong","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuansong Gao","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003903373","display_name":"Xuan Cao","orcid":"https://orcid.org/0009-0005-5728-6075"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Cao","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012657677","display_name":"Guanhui Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanhui Geng","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101784124","display_name":"Minghui Li","orcid":"https://orcid.org/0000-0002-7969-7271"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5026498734"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.1845,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54573886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9959999918937683,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9923999905586243,"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/replication","display_name":"Replication (statistics)","score":0.8173278570175171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7670631408691406},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6936168670654297},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5451145172119141},{"id":"https://openalex.org/keywords/bin-packing-problem","display_name":"Bin packing problem","score":0.5441974997520447},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5430828928947449},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5155575275421143},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4751018285751343},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.42202234268188477},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35843440890312195},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3278990387916565},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1838591992855072},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15500500798225403},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13253197073936462},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1146554946899414},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11089250445365906},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07771891355514526},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07553562521934509}],"concepts":[{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.8173278570175171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670631408691406},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6936168670654297},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5451145172119141},{"id":"https://openalex.org/C87219788","wikidata":"https://www.wikidata.org/wiki/Q814581","display_name":"Bin packing problem","level":3,"score":0.5441974997520447},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5430828928947449},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5155575275421143},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4751018285751343},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.42202234268188477},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35843440890312195},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3278990387916565},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1838591992855072},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15500500798225403},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13253197073936462},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1146554946899414},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11089250445365906},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07771891355514526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07553562521934509},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3666388733","display_name":null,"funder_award_id":"16JCYBJC41900,17JCYBJC15300","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"},{"id":"https://openalex.org/G442361742","display_name":null,"funder_award_id":"MOE2013-T2-2-067","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G8775057229","display_name":null,"funder_award_id":"61373018,61602266,11550110491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W7698046","https://openalex.org/W1975709346","https://openalex.org/W1982012874","https://openalex.org/W1987341903","https://openalex.org/W1994242182","https://openalex.org/W2028083097","https://openalex.org/W2032866865","https://openalex.org/W2039678943","https://openalex.org/W2063435439","https://openalex.org/W2072156548","https://openalex.org/W2076471773","https://openalex.org/W2082973176","https://openalex.org/W2090913810","https://openalex.org/W2098395496","https://openalex.org/W2106956947","https://openalex.org/W2118651798","https://openalex.org/W2133569115","https://openalex.org/W2138662031","https://openalex.org/W2142994777","https://openalex.org/W2152437528","https://openalex.org/W2154045882","https://openalex.org/W2167514501","https://openalex.org/W2341458219","https://openalex.org/W2347137561","https://openalex.org/W2400508655","https://openalex.org/W2412124276","https://openalex.org/W2470835488","https://openalex.org/W2612391007","https://openalex.org/W3098002645","https://openalex.org/W3213634139","https://openalex.org/W4214835284","https://openalex.org/W4255845876"],"related_works":["https://openalex.org/W2797538013","https://openalex.org/W2026961896","https://openalex.org/W173368591","https://openalex.org/W2034272113","https://openalex.org/W2138242427","https://openalex.org/W2104955674","https://openalex.org/W4288260564","https://openalex.org/W2068892231","https://openalex.org/W2096053066","https://openalex.org/W2001915926"],"abstract_inverted_index":{"With":[0],"the":[1,5,23,27,55,66,76,82,86,97,103,115,136,139,149,156,159,178,181],"rapid":[2],"growth":[3],"of":[4,19,26,69,84,89,102,138,151,180],"Web":[6,28],"scale,":[7],"large":[8],"scale":[9],"search":[10,92,131],"engines":[11],"have":[12,61],"to":[13,21,113,177],"set":[14],"up":[15],"a":[16,62,100],"huge":[17],"number":[18],"machines":[20,90],"place":[22],"index":[24,31,38,56,77,182],"files":[25,32],"contents.":[29],"The":[30,118,133],"are":[33,41,121],"normally":[34],"divided":[35],"into":[36],"smaller":[37],"shards":[39],"which":[40],"often":[42],"replicated":[43],"so":[44],"that":[45,54,162,170],"queries":[46],"can":[47],"be":[48],"processed":[49],"in":[50,91,186],"parallel.":[51],"We":[52,95,168],"observe":[53],"shard":[57,78,183],"replication":[58,79,184],"strategy":[59,164,185],"could":[60],"significant":[63],"impact":[64,150],"on":[65,155],"resource":[67,87],"utilization":[68,88],"machines.":[70],"In":[71],"this":[72,171],"paper,":[73],"we":[74],"investigate":[75],"problem":[80,98],"with":[81],"goal":[83],"improving":[85],"engine":[93],"datacenters.":[94],"formulate":[96],"as":[99],"variant":[101],"Multi-Dimensional":[104],"Vector":[105],"Bin":[106],"Packing":[107],"Problem":[108],"and":[109,158],"propose":[110],"several":[111],"strategies":[112,120],"approximate":[114],"optimal":[116],"solution.":[117],"proposed":[119,140],"evaluated":[122],"by":[123],"extensive":[124],"experiments":[125],"using":[126],"data":[127],"from":[128],"real":[129],"commercial":[130],"engines.":[132],"results":[134],"demonstrate":[135],"effectiveness":[137],"strategies.":[141],"Our":[142],"work":[143],"also":[144],"yields":[145],"many":[146],"insights":[147],"about":[148],"different":[152],"input":[153],"properties":[154],"performance":[157],"key":[160],"factors":[161],"each":[163],"is":[165],"sensitive":[166],"to.":[167],"believe":[169],"paper":[172],"will":[173],"provide":[174],"valuable":[175],"guidance":[176],"choice":[179],"practice.":[187]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
