{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T13:55:09Z","timestamp":1781358909706,"version":"3.54.1"},"reference-count":31,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:00:00Z","timestamp":1781308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2026,11,30]]},"abstract":"<jats:p>\n                    Persisting tail latency in storage systems poses critical challenges to cloud computing and real-time applications. While existing software solutions predominantly target transient latency spikes through single-operation prediction, their effectiveness diminishes significantly when confronting persisting performance degradation in modern SSDs. We present\n                    <jats:bold>LatVision<\/jats:bold>\n                    , an operating system (OS) kernel-level monitoring framework that integrates dual-layer prediction and attention mechanisms for cross-storage latency analysis.\n                  <\/jats:p>\n                  <jats:p>Leveraging eBPF to capture I\/O performance metrics at the OS kernel level, LatVision implements a dual-layer detection pipeline: a lightweight classifier initially filters normal operations, while suspicious data failing the Layer-1 screening are routed to Layer-2 prediction model for double check. This hierarchical architecture reduces average computational overhead by 75.3% compared with monolithic prediction models. An attention-enhanced neural network further improves persisting tail latency prediction precision by prioritizing critical temporal patterns.<\/jats:p>\n                  <jats:p>Experimental evaluations across six SSD and HDD configurations demonstrate LatVision\u2019s generalization capability, achieving prediction accuracy exceeding 90% across all test cases. Heuristic algorithm integration with the prediction results enhances operational stability under diverse workload conditions. The framework achieves real-time, lightweight, and high-precision persisting tail latency prediction for low-latency SSDs while maintaining minor latency overhead.<\/jats:p>","DOI":"10.1145\/3800950","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T20:44:12Z","timestamp":1774039452000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LatVision: Attention-Driven Dual-Layer Prediction Model for Persisting Tail Latency in SSDs and HDDs"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9200-7060","authenticated-orcid":false,"given":"Linxiao","family":"Bai","sequence":"first","affiliation":[{"name":"National University of Defense Technology","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7076-4239","authenticated-orcid":false,"given":"Zhijie","family":"Jiang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6042-7489","authenticated-orcid":false,"given":"Yuanliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4493-4265","authenticated-orcid":false,"given":"Haoran","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7761-9914","authenticated-orcid":false,"given":"Xiangbing","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6900-4507","authenticated-orcid":false,"given":"Wang","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9869-8453","authenticated-orcid":false,"given":"Bin","family":"Lin","sequence":"additional","affiliation":[{"name":"Academy of Military Sciences of the Chinese Peoples Liberation Army Graduate School","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,13]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"2010. Non-volatile memory express. Retrieved from https:\/\/www.ibm.com\/topics\/nvme"},{"key":"e_1_3_1_3_2","unstructured":"2017. Extending extended BPF. Retrieved from https:\/\/lwn.net\/Articles\/603983\/"},{"key":"e_1_3_1_4_2","unstructured":"2017. A thorough introduction to eBPF. Retrieved from https:\/\/lwn.net\/Articles\/740157\/"},{"key":"e_1_3_1_5_2","unstructured":"2019. Filebench. Retrieved from https:\/\/github.com\/filebench\/filebench"},{"key":"e_1_3_1_6_2","unstructured":"2019. Solid-state drive. Retrieved from https:\/\/www.ibm.com\/topics\/solid-state-drives"},{"key":"e_1_3_1_7_2","unstructured":"2021. 3D Xpoint: A Breakthrough in Non-Volatile Memory Technology. Retrieved from https:\/\/www.intel.com\/content\/www\/us\/en\/architecture-and-technology\/intel-micron-3d-xpoint-webcast.html"},{"key":"e_1_3_1_8_2","unstructured":"2025. Flexible I\/O Tester. Retrieved from https:\/\/github.com\/axboe\/fio"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.71"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2025.103405"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242086"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2019.000-2"},{"key":"e_1_3_1_14_2","first-page":"173","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Hao Mingzhe","year":"2020","unstructured":"Mingzhe Hao, Levent Toksoz, Nanqinqin Li, Edward Edberg Halim, Henry Hoffmann, and Haryadi S. Gunawi. 2020. LinnOS: Predictability on unpredictable flash storage with a light neural network. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 173\u2013190. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi20\/presentation\/hao"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064187"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770\u2013778. DOI:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_17_2","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60 6 (May 2017) 84\u201390. DOI:10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Huaicheng Li Martin L. Putra Ronald Shi Xing Lin Gregory R. Ganger and Haryadi S. Gunawi. 2021. IODA: A host\/device co-design for strong predictability contract on modern flash storage. In Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles (Virtual Event Germany) (SOSP\u201921). Association for Computing Machinery New York NY USA 263\u2013279. DOI:10.1145\/3477132.3483573","DOI":"10.1145\/3477132.3483573"},{"key":"e_1_3_1_22_2","volume-title":"USENIX Conference on File and Storage Technologies","author":"Lu Ruiming","year":"2023","unstructured":"Ruiming Lu, Erci Xu, Yiming Zhang, Fengyi Zhu, Zhaosheng Zhu, Mengtian Wang, Zongpeng Zhu, Guangtao Xue, Jiwu Shu, Minglu Li, and Jiesheng Wu. 2023. Perseus: A fail-slow detection framework for cloud storage systems. In USENIX Conference on File and Storage Technologies. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:257285445"},{"key":"e_1_3_1_23_2","first-page":"1005","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Lu Ruiming","year":"2022","unstructured":"Ruiming Lu, Erci Xu, Yiming Zhang, Zhaosheng Zhu, Mengtian Wang, Zongpeng Zhu, Guangtao Xue, Minglu Li, and Jiesheng Wu. 2022. NVMe SSD failures in the field: The fail-stop and the fail-slow. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). USENIX Association, Carlsbad, CA, 1005\u20131020. Retrieved fromhttps:\/\/www.usenix.org\/conference\/atc22\/presentation\/lu"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043563"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITC30.2018.00039"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3505139"},{"key":"e_1_3_1_28_2","unstructured":"Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv:1905.11946. Retrieved from https:\/\/arxiv.org\/abs\/1905.11946"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197340"},{"key":"e_1_3_1_30_2","volume-title":"11th USENIX Workshop on Hot Topics in Storage and File Systems, HotStorage 2019, Renton, WA, USA, July 8-9, 2019","author":"Wu Kan","year":"2019","unstructured":"Kan Wu, Andrea C. Arpaci-Dusseau, and Remzi H. Arpaci-Dusseau. 2019. Towards an unwritten contract of intel optane SSD. In 11th USENIX Workshop on Hot Topics in Storage and File Systems, HotStorage 2019, Renton, WA, USA, July 8-9, 2019, Daniel Peek and Gala Yadgar (Eds.). USENIX Association. Retrieved from https:\/\/www.usenix.org\/conference\/hotstorage19\/presentation\/wu-kan"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00025"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2017.14"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3800950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T12:57:15Z","timestamp":1781355435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3800950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,13]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,11,30]]}},"alternative-id":["10.1145\/3800950"],"URL":"https:\/\/doi.org\/10.1145\/3800950","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,13]]},"assertion":[{"value":"2025-05-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}