{"id":"https://openalex.org/W3023512926","doi":"https://doi.org/10.1145/3358960.3375793","title":"Optimizing Interrupt Handling Performance for Memory Failures in Large Scale Data Centers","display_name":"Optimizing Interrupt Handling Performance for Memory Failures in Large Scale Data Centers","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3023512926","doi":"https://doi.org/10.1145/3358960.3375793","mag":"3023512926"},"language":"en","primary_location":{"id":"doi:10.1145/3358960.3375793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358960.3375793","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358960.3375793","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 ACM/SPEC International Conference on Performance Engineering","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/10.1145/3358960.3375793","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018336899","display_name":"Harish Dattatraya Dixit","orcid":"https://orcid.org/0009-0001-1163-5568"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish Dattatraya Dixit","raw_affiliation_strings":["Facebook, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038729392","display_name":"Fan Lin","orcid":"https://orcid.org/0000-0003-2530-859X"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan (Fred) Lin","raw_affiliation_strings":["Facebook, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088522728","display_name":"Bill Holland","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Holland","raw_affiliation_strings":["Facebook, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053817867","display_name":"Matt Beadon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Beadon","raw_affiliation_strings":["Facebook, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967694","display_name":"Zhengyu Yang","orcid":"https://orcid.org/0000-0002-9822-5843"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyu Yang","raw_affiliation_strings":["Facebook, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103061483","display_name":"Sriram Sankar","orcid":"https://orcid.org/0009-0008-4581-8371"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Sankar","raw_affiliation_strings":["Facebook, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9977999925613403,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9927999973297119,"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":0.9886999726295471,"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/interrupt","display_name":"Interrupt","score":0.8604259490966797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7551552057266235},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44776612520217896},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43372660875320435},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.404929518699646},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4006483554840088},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35190725326538086},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10647851228713989}],"concepts":[{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.8604259490966797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551552057266235},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44776612520217896},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43372660875320435},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.404929518699646},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4006483554840088},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35190725326538086},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10647851228713989},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3358960.3375793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358960.3375793","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358960.3375793","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 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3358960.3375793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358960.3375793","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358960.3375793","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 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023512926.pdf","grobid_xml":"https://content.openalex.org/works/W3023512926.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W16130180","https://openalex.org/W1968811450","https://openalex.org/W1977467261","https://openalex.org/W1980073965","https://openalex.org/W2001276096","https://openalex.org/W2017147164","https://openalex.org/W2096865422","https://openalex.org/W2141992894","https://openalex.org/W2156182786","https://openalex.org/W2342204193","https://openalex.org/W2510192911"],"related_works":["https://openalex.org/W4288898221","https://openalex.org/W2505144121","https://openalex.org/W2359206530","https://openalex.org/W2349471271","https://openalex.org/W2382264333","https://openalex.org/W315297852","https://openalex.org/W2543878428","https://openalex.org/W2081917376","https://openalex.org/W4237731087","https://openalex.org/W2359065861"],"abstract_inverted_index":{"Intermittent":[0],"hardware":[1,38,49,71],"failures":[2],"are":[3,11,29,134],"generally":[4],"non-catastrophic":[5],"and":[6,98],"typical":[7],"large-scale":[8,79],"service":[9],"infrastructures":[10],"designed":[12],"to":[13,40,116,123],"tolerate":[14],"them":[15],"while":[16,154],"still":[17],"serving":[18],"user":[19],"traffic.":[20],"However,":[21],"intermittent":[22,70],"errors":[23,72],"cause":[24],"performance":[25,60,107],"aberrations":[26],"if":[27],"they":[28],"not":[30,135],"handled":[31],"appropriately.":[32],"System":[33,94],"error":[34,121,125,131,148],"reporting":[35],"mechanisms":[36],"send":[37],"interrupts":[39,89,149],"the":[41,48,53,59,62,106],"Central":[42],"Processing":[43],"Unit":[44],"(CPU)":[45],"for":[46,146],"handling":[47,88,147],"errors.":[50],"This":[51],"disrupts":[52],"CPU's":[54],"normal":[55],"operation,":[56],"which":[57],"impacts":[58],"of":[61,87,108,137],"server.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"describe":[68],"common":[69],"observed":[73],"on":[74],"server":[75,91],"systems":[76,92],"in":[77,90,111,158],"a":[78,143],"data":[80,161],"center":[81,162],"environment.":[82],"We":[83,104,140],"discuss":[84],"two":[85],"methodologies":[86],"-":[93],"Management":[95],"Interrupt":[96,102],"(SMI)":[97],"Corrected":[99],"Machine":[100],"Check":[101],"(CMCI).":[103],"characterize":[105],"these":[109],"methods":[110,133],"live":[112],"environments":[113],"as":[114],"compared":[115],"prior":[117],"studies":[118],"that":[119,130,150],"used":[120],"injection":[122,132],"simulate":[124],"behavior.":[126,139],"Our":[127],"experience":[128],"shows":[129],"reflective":[136],"production":[138],"also":[141],"present":[142],"hybrid":[144],"approach":[145],"achieves":[151],"better":[152],"performance,":[153],"preserving":[155],"monitoring":[156],"granularity,":[157],"large":[159],"scale":[160],"environments.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
