{"id":"https://openalex.org/W3186477959","doi":"https://doi.org/10.1145/3468791.3468820","title":"On Lowering Merge Costs of an LSM Tree","display_name":"On Lowering Merge Costs of an LSM Tree","publication_year":2021,"publication_date":"2021-07-06","ids":{"openalex":"https://openalex.org/W3186477959","doi":"https://doi.org/10.1145/3468791.3468820","mag":"3186477959"},"language":"en","primary_location":{"id":"doi:10.1145/3468791.3468820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468791.3468820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"33rd International Conference on Scientific and Statistical Database Management","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/A5038763232","display_name":"Dai Hai Ton That","orcid":"https://orcid.org/0000-0002-3935-2471"},"institutions":[{"id":"https://openalex.org/I82495205","display_name":"University of Alabama in Huntsville","ror":"https://ror.org/02zsxwr40","country_code":"US","type":"education","lineage":["https://openalex.org/I82495205"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dai Hai Ton That","raw_affiliation_strings":["University of Alabama in Huntsville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama in Huntsville","institution_ids":["https://openalex.org/I82495205"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018833411","display_name":"Mohammadsaleh Gharehdaghi","orcid":null},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammadsaleh Gharehdaghi","raw_affiliation_strings":["DePaul University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DePaul University","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007690835","display_name":"Alexander Rasin","orcid":"https://orcid.org/0000-0001-7282-5763"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rasin","raw_affiliation_strings":["DePaul University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DePaul University","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071436717","display_name":"Tanu Malik","orcid":"https://orcid.org/0009-0007-9656-727X"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanu Malik","raw_affiliation_strings":["DePaul University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DePaul University","institution_ids":["https://openalex.org/I118353179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1603,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52033046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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/merge","display_name":"Merge (version control)","score":0.8491429090499878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7454379796981812},{"id":"https://openalex.org/keywords/merge-algorithm","display_name":"Merge algorithm","score":0.7039361596107483},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.6394568681716919},{"id":"https://openalex.org/keywords/merge-sort","display_name":"Merge sort","score":0.6160618662834167},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.5133265852928162},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4520927369594574},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4414590001106262},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.338372141122818},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.22302356362342834},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20590057969093323},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17994800209999084}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.8491429090499878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454379796981812},{"id":"https://openalex.org/C140086265","wikidata":"https://www.wikidata.org/wiki/Q11341754","display_name":"Merge algorithm","level":4,"score":0.7039361596107483},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.6394568681716919},{"id":"https://openalex.org/C35555965","wikidata":"https://www.wikidata.org/wiki/Q189057","display_name":"Merge sort","level":4,"score":0.6160618662834167},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.5133265852928162},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4520927369594574},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4414590001106262},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.338372141122818},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.22302356362342834},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20590057969093323},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17994800209999084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3468791.3468820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468791.3468820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"33rd International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2002128741","https://openalex.org/W2006296837","https://openalex.org/W2068739275","https://openalex.org/W2087946700","https://openalex.org/W2605800201","https://openalex.org/W2622447669","https://openalex.org/W2889258430","https://openalex.org/W2895533467","https://openalex.org/W3138367763","https://openalex.org/W4255405898"],"related_works":["https://openalex.org/W2977813765","https://openalex.org/W1989067202","https://openalex.org/W1997715509","https://openalex.org/W1822668896","https://openalex.org/W2074050947","https://openalex.org/W2165167056","https://openalex.org/W2102143009","https://openalex.org/W1852882392","https://openalex.org/W3038595913","https://openalex.org/W2356015003"],"abstract_inverted_index":{"In":[0,57],"column":[1,11,17,37,80],"stores,":[2],"which":[3,49],"ingest":[4,27],"large":[5],"amounts":[6],"of":[7,95,100,120],"data":[8,28,76],"into":[9],"multiple":[10],"groups,":[12],"query":[13],"performance":[14],"deteriorates.":[15],"Commercial":[16],"stores":[18,38,139],"use":[19],"log-structured":[20],"merge":[21],"(LSM)":[22],"tree":[23,31,46,135],"on":[24],"projections":[25],"to":[26,66,109,115],"rapidly.":[29],"LSM":[30,45,134],"improves":[32],"ingestion":[33],"performance,":[34],"but":[35],"for":[36],"the":[39,68,93,124],"sort-merge":[40,126],"maintenance":[41],"phase":[42],"in":[43,79,97],"an":[44],"is":[47,77],"I/O-intensive,":[48],"slows":[50],"concurrent":[51],"queries":[52],"and":[53,70,91,103,136,142],"reduces":[54],"overall":[55],"throughput.":[56],"this":[58],"paper,":[59],"we":[60],"present":[61],"a":[62,85,117],"simple":[63],"heuristic":[64,87],"approach":[65,132],"reduce":[67],"sorting":[69],"merging":[71],"cost":[72],"that":[73],"arise":[74],"when":[75],"ingested":[78],"stores.":[81],"We":[82,128],"demonstrate":[83],"how":[84],"Min-Max":[86,131],"can":[88],"construct":[89],"buckets":[90,105,112],"identify":[92],"level":[94,119],"sortedness":[96],"each":[98],"range":[99],"data.":[101],"Filled":[102],"relatively-sorted":[104],"are":[106,113],"written":[107],"out":[108],"disk;":[110],"unfilled":[111],"retained":[114],"achieve":[116],"better":[118],"sortedness,":[121],"thus":[122],"avoiding":[123],"expensive":[125],"phase.":[127],"compare":[129],"our":[130],"with":[133],"production":[137],"columnar":[138],"using":[140],"real":[141],"synthetic":[143],"datasets.":[144]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
