{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:05:51Z","timestamp":1754154351909,"version":"3.41.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1109\/hpcc64274.2024.00065","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T18:33:48Z","timestamp":1753295628000},"page":"432-441","source":"Crossref","is-referenced-by-count":0,"title":["Examining SSD-correlated Failures within Racks in Production Data Centers"],"prefix":"10.1109","author":[{"given":"Gang","family":"Xian","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusong","family":"Tan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Yu","sequence":"additional","affiliation":[{"name":"China Aerodynamics Research and Development Center,State Key Laboratory of Aerodynamics,Mianyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxiang","family":"Yang","sequence":"additional","affiliation":[{"name":"China Aerodynamics Research and Development Center,State Key Laboratory of Aerodynamics,Mianyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1288783.1288785"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1837915.1837917"},{"article-title":"Availability in globally distributed storage systems","volume-title":"9th USENIX Symposium on Operating Systems Design and Implementation (OSDI 10)","author":"Ford","key":"ref3"},{"key":"ref4","first-page":"151","article-title":"Correlated crash vulnerabilities","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Alagappan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3149349"},{"key":"ref6","first-page":"225","article-title":"Subtleties in tolerating correlated failures in wide-area storage systems","volume":"6","author":"Nath","year":"2006","journal-title":"NSDI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IMW52921.2022.9779284"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356172"},{"key":"ref9","first-page":"961","article-title":"Lessons and actions: What we learned from 10k ssd-related storage system failures","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Xu"},{"key":"ref10","first-page":"417","article-title":"An in-depth study of correlated failures in production ssd-based data centers","volume-title":"19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Han"},{"key":"ref11","first-page":"137","article-title":"A study of ssd reliability in large scale enterprise storage deployments","volume-title":"18th USENIX Conference on File and Storage Technologies (FAST 20)","author":"Maneas"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3543146.3543169"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421300"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2928275.2928278"},{"key":"ref15","article-title":"Dataset of ssd failures in alibaba"},{"key":"ref16","first-page":"15","article-title":"Erasure coding in windows azure storage","volume-title":"2012 USENIX Annual Technical Conference (USENIX ATC 12)","author":"Huang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1323293.1294281"},{"key":"ref18","first-page":"383","article-title":"f4: Facebook\u2019s warm blob storage system","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Muralidhar"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2921551"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.14778\/2535573.2488339"},{"article-title":"Mean time to meaningless: Mttdl, markov models, and storage system reliability","volume-title":"2nd Workshop on Hot Topics in Storage and File Systems (HotStorage 10)","author":"Greenan","key":"ref21"},{"key":"ref22","article-title":"Learning the k in k-means","volume":"16","author":"Hamerly","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.12792\/iciae2015.012"},{"key":"ref24","first-page":"67","article-title":"Flash reliability in production: The expected and the unexpected","volume-title":"14th USENIX Conference on File and Storage Technologies (FAST 16)","author":"Schroeder"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2796314.2745848"},{"key":"ref26","first-page":"165","article-title":"Operational characteristics of ssds in enterprise storage systems: A large-scale field study","volume-title":"20th USENIX Conference on File and Storage Technologies (FAST 22)","author":"Maneas"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356185"},{"key":"ref28","first-page":"1005","article-title":"Nvme ssd failures in the field: the fail-stop and the fail-slow","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Lu"},{"key":"ref29","first-page":"151","article-title":"Making disk failure predictions smarter!","volume-title":"18th USENIX Conference on File and Storage Technologies (FAST 20)","author":"Lu"},{"key":"ref30","first-page":"17","article-title":"Failure trends in a large disk drive population","volume-title":"5th USENIX Conference on File and Storage Technologies","author":"Pinheiro"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3224432"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056062"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2013.2241204"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/PHM.2011.5939558"}],"event":{"name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","start":{"date-parts":[[2024,12,13]]},"location":"Wuhan, China","end":{"date-parts":[[2024,12,15]]}},"container-title":["2024 IEEE International Conference on High Performance Computing and Communications (HPCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11083115\/11083125\/11083279.pdf?arnumber=11083279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T04:49:46Z","timestamp":1753332586000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11083279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/hpcc64274.2024.00065","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]}}}