{"id":"https://openalex.org/W4309561483","doi":"https://doi.org/10.1145/3568425","title":"End-to-end I/O Monitoring on Leading Supercomputers","display_name":"End-to-end I/O Monitoring on Leading Supercomputers","publication_year":2022,"publication_date":"2022-11-19","ids":{"openalex":"https://openalex.org/W4309561483","doi":"https://doi.org/10.1145/3568425"},"language":"en","primary_location":{"id":"doi:10.1145/3568425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3568425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3568425","source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3568425","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100778640","display_name":"Bin Yang","orcid":"https://orcid.org/0000-0002-3783-2228"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Yang","raw_affiliation_strings":["Shandong University, National Supercomputing Center in Wuxi, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-3783-2228","affiliations":[{"raw_affiliation_string":"Shandong University, National Supercomputing Center in Wuxi, Jinan, China","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Tsinghua, Beijing, University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9740-6581","affiliations":[{"raw_affiliation_string":"Tsinghua, Beijing, University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425849","display_name":"Tianyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-3491-5909","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682518","display_name":"Shichao Liu","orcid":"https://orcid.org/0000-0003-4714-3749"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Liu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-4714-3749","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083800790","display_name":"Xiaosong Ma","orcid":"https://orcid.org/0000-0003-1261-2496"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Xiaosong Ma","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0003-1261-2496","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758692","display_name":"Xiyang Wang","orcid":"https://orcid.org/0000-0001-7567-5211"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyang Wang","raw_affiliation_strings":["National Supercomputing Center in Wuxi, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7567-5211","affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620772","display_name":"Weiguo Liu","orcid":"https://orcid.org/0000-0001-8834-0453"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Liu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8834-0453","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4048,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8922736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":"1","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9912999868392944,"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/T11478","display_name":"Caching and Content Delivery","score":0.9866999983787537,"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/supercomputer","display_name":"Supercomputer","score":0.8444198966026306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802951455116272},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5726438760757446},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4770975708961487},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.46639129519462585},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4619605243206024},{"id":"https://openalex.org/keywords/beacon","display_name":"Beacon","score":0.4323311448097229},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3971734941005707},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.35385414958000183}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8444198966026306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802951455116272},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5726438760757446},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4770975708961487},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.46639129519462585},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4619605243206024},{"id":"https://openalex.org/C102168758","wikidata":"https://www.wikidata.org/wiki/Q7321258","display_name":"Beacon","level":2,"score":0.4323311448097229},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3971734941005707},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.35385414958000183}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3568425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3568425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3568425","source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3568425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3568425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3568425","source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1726774817","display_name":null,"funder_award_id":"2017YFA0604500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3583593893","display_name":null,"funder_award_id":"41776010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7321677127","display_name":null,"funder_award_id":"2017YFA0604500","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309561483.pdf","grobid_xml":"https://content.openalex.org/works/W4309561483.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1970466368","https://openalex.org/W1989299066","https://openalex.org/W1999897898","https://openalex.org/W2038924755","https://openalex.org/W2051928657","https://openalex.org/W2057710325","https://openalex.org/W2081765326","https://openalex.org/W2106930560","https://openalex.org/W2152984210","https://openalex.org/W2157692945","https://openalex.org/W2166598697","https://openalex.org/W2182232625","https://openalex.org/W2185036183","https://openalex.org/W2187152421","https://openalex.org/W2293392140","https://openalex.org/W2333683487","https://openalex.org/W2475126267","https://openalex.org/W2487095677","https://openalex.org/W2526048219","https://openalex.org/W2748963574","https://openalex.org/W2749286555","https://openalex.org/W2767497803","https://openalex.org/W2767725805","https://openalex.org/W2889082215","https://openalex.org/W2895690683","https://openalex.org/W2902659137","https://openalex.org/W2905331484","https://openalex.org/W2985168981","https://openalex.org/W2990714382","https://openalex.org/W3022923721","https://openalex.org/W3174251760","https://openalex.org/W3210652973","https://openalex.org/W4220986471","https://openalex.org/W4232611972","https://openalex.org/W4246788062","https://openalex.org/W4254786406","https://openalex.org/W4301352251","https://openalex.org/W4301973706"],"related_works":["https://openalex.org/W2106845956","https://openalex.org/W3158435160","https://openalex.org/W1643556013","https://openalex.org/W2790129070","https://openalex.org/W2277502495","https://openalex.org/W2130422012","https://openalex.org/W3188540151","https://openalex.org/W2112938119","https://openalex.org/W2132294172","https://openalex.org/W2941957272"],"abstract_inverted_index":{"This":[0],"paper":[1],"offers":[2],"a":[3],"solution":[4],"to":[5,157,177],"overcome":[6],"the":[7,27,33,37,49,135],"complexities":[8],"of":[9,134,185],"production":[10,81],"system":[11,25,121],"I/O":[12,20,44,78,102,124,152],"performance":[13,103,125],"monitoring.":[14],"We":[15],"present":[16],"Beacon,":[17],"an":[18],"end-to-end":[19],"resource":[21,128],"monitoring":[22,187],"and":[23,42,56,65,69,76,106,127,183],"diagnosis":[24,79],"for":[26,88,101],"40960-node":[28],"Sunway":[29],"TaihuLight":[30,87],"supercomputer,":[31],"currently":[32,145],"fourth-ranked":[34],"supercomputer":[35],"in":[36,151],"world.":[38],"Beacon":[39,181],"simultaneously":[40],"collects":[41],"correlates":[43],"tracing/profiling":[45],"data":[46,188],"from":[47],"all":[48],"compute":[50],"nodes,":[51,53,55],"forwarding":[52],"storage":[54],"metadata":[57],"servers.":[58],"With":[59,83],"mechanisms":[60],"such":[61],"as":[62],"aggressive":[63],"online":[64],"offline":[66],"trace":[67],"compression":[68],"distributed":[70],"caching/storage,":[71],"it":[72,156,176],"delivers":[73],"scalable,":[74],"low-overhead,":[75],"sustainable":[77],"under":[80],"use.":[82],"Beacon\u2019s":[84,95,149,172],"deployment":[85],"on":[86,166],"more":[89],"than":[90],"three":[91],"years,":[92],"we":[93,154,170],"demonstrate":[94,171],"effectiveness":[96],"with":[97,142],"real-world":[98],"use":[99],"cases":[100],"issue":[104],"identification":[105],"diagnosis.":[107],"It":[108],"has":[109],"already":[110,139],"successfully":[111],"helped":[112],"center":[113],"administrators":[114],"identify":[115],"obscure":[116],"design":[117],"or":[118,130],"configuration":[119],"flaws,":[120],"anomaly":[122],"occurrences,":[123],"interference,":[126],"under-":[129],"over-provisioning":[131],"problems.":[132],"Several":[133],"exposed":[136],"problems":[137],"have":[138],"been":[140],"fixed,":[141],"others":[143],"being":[144],"addressed.":[146],"Encouraged":[147],"by":[148,174],"success":[150],"monitoring,":[153],"extend":[155],"monitor":[158],"interconnection":[159],"networks,":[160],"which":[161],"is":[162],"another":[163],"contention":[164],"point":[165],"supercomputers.":[167,179],"In":[168],"addition,":[169],"generality":[173],"extending":[175],"other":[178],"Both":[180],"codes":[182],"part":[184],"collected":[186],"are":[189],"released.":[190],"1":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
