{"id":"https://openalex.org/W4404400627","doi":"https://doi.org/10.1145/3694715.3695951","title":"Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value Stores","display_name":"Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value Stores","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404400627","doi":"https://doi.org/10.1145/3694715.3695951"},"language":"en","primary_location":{"id":"doi:10.1145/3694715.3695951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3694715.3695951","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3694715.3695951","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3694715.3695951","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112034098","display_name":"Zhisheng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhisheng Hu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0003-1498-7053","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034442315","display_name":"Pengfei Zuo","orcid":"https://orcid.org/0000-0001-9982-5130"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Zuo","raw_affiliation_strings":["Huawei Cloud, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9982-5130","affiliations":[{"raw_affiliation_string":"Huawei Cloud, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029999092","display_name":"Yizou Chen","orcid":"https://orcid.org/0009-0003-8226-6856"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yizou Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0003-8226-6856","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Wang","orcid":"https://orcid.org/0009-0003-2162-5675"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0003-2162-5675","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104075638","display_name":"Junliang Hu","orcid":"https://orcid.org/0000-0001-6253-4233"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junliang Hu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6253-4233","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102930563","display_name":"Ming-Chang Yang","orcid":"https://orcid.org/0000-0002-4029-757X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ming-Chang Yang","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK), Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4029-757X","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK), Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9994999766349792,"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":0.9994000196456909,"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/key","display_name":"Key (lock)","score":0.6669653058052063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6370786428451538},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6092535853385925},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5897131562232971},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.34943366050720215},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.24965959787368774},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17327767610549927},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08045527338981628}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6669653058052063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370786428451538},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6092535853385925},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5897131562232971},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.34943366050720215},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.24965959787368774},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17327767610549927},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08045527338981628},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3694715.3695951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3694715.3695951","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3694715.3695951","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3694715.3695951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3694715.3695951","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3694715.3695951","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404400627.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1977329921","https://openalex.org/W1985229168","https://openalex.org/W2074881976","https://openalex.org/W2090204040","https://openalex.org/W2101939036","https://openalex.org/W2137291643","https://openalex.org/W2148575324","https://openalex.org/W2270495481","https://openalex.org/W2593880849","https://openalex.org/W2606496125","https://openalex.org/W2740433577","https://openalex.org/W2751343396","https://openalex.org/W2762796393","https://openalex.org/W2912606234","https://openalex.org/W2999097477","https://openalex.org/W3190496320","https://openalex.org/W3194881980","https://openalex.org/W3207452942","https://openalex.org/W4205983429","https://openalex.org/W4226379841","https://openalex.org/W4255681033","https://openalex.org/W4281715971","https://openalex.org/W4316660797","https://openalex.org/W4318541517","https://openalex.org/W4320067488","https://openalex.org/W4323841535","https://openalex.org/W4327930439","https://openalex.org/W4372263679","https://openalex.org/W4381327067","https://openalex.org/W4388692132","https://openalex.org/W6686169942","https://openalex.org/W7071880036"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Disaggregated":[0],"memory":[1,48,211],"(DM)":[2],"has":[3],"garnered":[4],"increasing":[5],"attention":[6],"due":[7],"to":[8,39,115,147,156,162,174,187,199,204],"high":[9,47],"resource":[10],"utilization.":[11],"Fault":[12],"tolerance":[13],"is":[14],"critical":[15],"for":[16,75,101,107],"key-value":[17],"(KV)":[18],"stores":[19,31],"on":[20,32,37,64,83,167,221],"DM":[21,33,65,116],"since":[22],"machine":[23],"failures":[24],"are":[25,34],"common":[26],"in":[27],"datacenters.":[28],"Existing":[29],"KV":[30,79,91,108,177,219],"generally":[35],"based":[36],"replication":[38],"achieve":[40],"fault":[41],"tolerance,":[42],"which":[43],"however":[44],"suffer":[45],"from":[46],"space":[49,129,171,212],"and":[50,66,70,78,104,123,131,182,209],"performance":[51,121,149],"overheads.":[52],"In":[53],"this":[54,112],"paper,":[55],"we":[56,86],"investigate":[57],"the":[58,76,102,153,216],"efficiency":[59],"of":[60,126,134],"different":[61],"fault-tolerant":[62,97],"mechanisms":[63],"reveal":[67],"that":[68,93,194],"checkpointing":[69,100,145],"erasure":[71,105,135],"coding":[72,106],"work":[73],"best":[74],"index":[77,103,165],"pairs":[80,178],"respectively.":[81],"Based":[82],"these":[84,139],"observations,":[85],"present":[87],"Aceso,":[88],"a":[89,95,143,159,169,183],"DM-based":[90],"store":[92,220],"employs":[94],"hybrid":[96,113],"mechanism,":[98],"combining":[99],"pairs.":[109],"However,":[110],"applying":[111],"mechanism":[114,173],"introduces":[117],"multiple":[118],"challenges,":[119,140],"i.e.,":[120],"interference":[122,150],"data":[124],"loss":[125],"checkpointing,":[127],"slow":[128],"reclamation":[130,172],"failure":[132],"recovery":[133,185],"coding.":[136],"To":[137],"address":[138],"Aceso":[141,195],"leverages":[142],"differential":[144],"scheme":[146,186],"reduce":[148],"incurred":[151],"by":[152],"bandwidth":[154],"consumption":[155],"transmit":[157],"checkpoints,":[158],"versioning":[160],"approach":[161],"recover":[163],"lost":[164],"updates":[166],"failures,":[168],"delta-based":[170],"reclaim":[175],"obsolete":[176],"with":[179,215],"negligible":[180],"overhead,":[181],"tiered":[184],"minimize":[188],"user":[189],"disruption.":[190],"Our":[191],"experiments":[192],"show":[193],"simultaneously":[196],"achieves":[197],"up":[198,203],"2.7\u00d7":[200],"throughput":[201],"improvement,":[202],"54%":[205],"tail":[206],"latency":[207],"reduction,":[208],"44%":[210],"savings":[213],"compared":[214],"state-of-the-art":[217],"replication-based":[218],"DM.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
