{"id":"https://openalex.org/W7116344541","doi":"https://doi.org/10.1145/3754598.3754617","title":"Origami: Efficient ML-Driven Metadata Load Balancing for Distributed File Systems","display_name":"Origami: Efficient ML-Driven Metadata Load Balancing for Distributed File Systems","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116344541","doi":"https://doi.org/10.1145/3754598.3754617"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754617","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754617","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754617","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075038966","display_name":"Y. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiduo Wang","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8787-0134","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210139765","https://openalex.org/I4210144487","https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063959536","display_name":"Wenda Tang","orcid":"https://orcid.org/0000-0003-2590-5669"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenda Tang","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6684-4642","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210139765","https://openalex.org/I4210144487","https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120918568","display_name":"Linghang Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghang Meng","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-7384-8529","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210139765","https://openalex.org/I4210144487","https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120939197","display_name":"Liang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2527-5049","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210139765","https://openalex.org/I4210144487","https://openalex.org/I4210136246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600528","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-3472-1717"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210139765","display_name":"Beijing Computing Center","ror":"https://ror.org/047r47y76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210139765"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3472-1717","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210139765","https://openalex.org/I4210144487","https://openalex.org/I4210136246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075038966"],"corresponding_institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4210139765","https://openalex.org/I4210144487"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62317713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.8449000120162964,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.8449000120162964,"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":0.07209999859333038,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.056299999356269836,"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/metadata","display_name":"Metadata","score":0.9380000233650208},{"id":"https://openalex.org/keywords/namespace","display_name":"Namespace","score":0.8398000001907349},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.6431999802589417},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.47690001130104065},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47519999742507935},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.42289999127388},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.4106999933719635},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.399399995803833}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9380000233650208},{"id":"https://openalex.org/C2778383056","wikidata":"https://www.wikidata.org/wiki/Q873636","display_name":"Namespace","level":2,"score":0.8398000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235999941825867},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6431999802589417},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5569000244140625},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47690001130104065},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.42289999127388},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.4106999933719635},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.399399995803833},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C2779370713","wikidata":"https://www.wikidata.org/wiki/Q357554","display_name":"Load management","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.2863999903202057},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C146152329","wikidata":"https://www.wikidata.org/wiki/Q1932543","display_name":"Data migration","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754617","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754617","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754617","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754617","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7564435601234436,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1972234887","https://openalex.org/W1988909795","https://openalex.org/W2025669595","https://openalex.org/W2027758281","https://openalex.org/W2034796080","https://openalex.org/W2035970724","https://openalex.org/W2106168995","https://openalex.org/W2600652590","https://openalex.org/W2612261081","https://openalex.org/W2749286555","https://openalex.org/W2758353308","https://openalex.org/W2764131694","https://openalex.org/W2768070465","https://openalex.org/W2802643674","https://openalex.org/W2948155983","https://openalex.org/W2950445386","https://openalex.org/W3145031041","https://openalex.org/W3205377733","https://openalex.org/W3210665448","https://openalex.org/W4238584892","https://openalex.org/W4283379365","https://openalex.org/W4320067949","https://openalex.org/W4366668503","https://openalex.org/W4372258399","https://openalex.org/W4388041443","https://openalex.org/W4390097799","https://openalex.org/W4401568101"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"distributed":[1],"file":[2],"systems":[3],"(DFSs)":[4],"rely":[5],"on":[6,40,116,141,177],"metadata":[7,31,45,59,97,101,109,132,232],"server":[8],"clusters":[9],"to":[10,46,63,91,146,168,183,203,226],"manage":[11],"large-scale":[12],"files":[13],"and":[14,22,33,42,105,134,185,200,218,241],"achieve":[15],"scalability.":[16],"However,":[17],"the":[18,65,129,136,148,165,195],"hierarchical":[19],"namespace":[20,219],"structure":[21],"dynamic":[23],"user":[24,142],"workloads":[25],"pose":[26],"severe":[27],"challenges":[28],"for":[29,153],"efficient":[30],"partitioning":[32],"load":[34,102,110,216],"balancing.":[35],"Existing":[36],"approaches":[37,81],"primarily":[38],"focus":[39],"identifying":[41],"redistributing":[43],"hot":[44],"address":[47],"imbalances.":[48],"While":[49],"these":[50],"load-balancing":[51],"strategies":[52,104],"offer":[53],"potential":[54],"benefits,":[55],"they":[56,87],"often":[57],"reduce":[58],"locality,":[60],"ultimately":[61],"failing":[62],"improve":[64],"end-to-end":[66,118,243],"job":[67,119,154],"completion":[68,120,155],"time\u2014a":[69],"key":[70],"metric":[71],"prioritized":[72],"by":[73,234,245],"users.":[74],"Although":[75],"recent":[76],"research":[77],"reveals":[78],"that":[79,224],"learning-based":[80,108],"are":[82,160],"effective":[83,94],"in":[84,95],"predicting":[85,190,194],"hotspots,":[86],"have":[88],"been":[89],"shown":[90],"be":[92],"less":[93],"improving":[96],"performance.":[98],"We":[99],"revisit":[100],"balancing":[103,217],"propose":[106,164],"a":[107,212],"balance":[111],"framework":[112],"Origami,":[113],"which":[114,178],"focuses":[115],"minimizing":[117],"time":[121,156],"rather":[122],"than":[123],"equalizing":[124],"loads.":[125],"Origami":[126,163,210,229],"first":[127],"decomposes":[128],"overhead":[130],"of":[131,138,150,189,197],"operations":[133],"assesses":[135],"impact":[137],"migration":[139,151,171,191,198,208],"decisions":[140,152,199],"requests,":[143],"allowing":[144],"us":[145],"compute":[147],"benefits":[149,196],"when":[157],"future":[158],"requests":[159],"known.":[161],"Subsequently,":[162],"Meta-OPT":[166,202],"algorithm":[167],"determine":[169],"near-optimal":[170],"decisions.":[172],"Finally,":[173],"we":[174,179],"implemented":[175],"OrigamiFS,":[176],"collected":[180],"statistical":[181],"data":[182],"train":[184],"validate":[186],"ML-models":[187],"capable":[188],"benefits.":[192],"By":[193],"employing":[201],"quickly":[204],"explore":[205],"nearly":[206],"optimal":[207],"decisions,":[209],"makes":[211],"better":[213],"trade-off":[214],"between":[215],"locality.":[220],"Our":[221],"evaluation":[222],"shows":[223],"compared":[225],"state-of-the-art":[227],"methods,":[228],"increases":[230],"aggregated":[231],"throughput":[233,244],"1.12-2.51":[235],"\u00d7":[236],"across":[237],"three":[238],"real-world":[239],"workloads,":[240],"enhances":[242],"1.11-2.02":[246],"\u00d7.":[247]},"counts_by_year":[],"updated_date":"2025-12-21T02:06:08.432651","created_date":"2025-12-21T00:00:00"}