{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:55:38Z","timestamp":1773017738292,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2317698"],"award-info":[{"award-number":["CNS-2317698"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2317751"],"award-info":[{"award-number":["CNS-2317751"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2318937"],"award-info":[{"award-number":["CCF-2318937"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3731569.3764858","type":"proceedings-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T12:43:24Z","timestamp":1759322604000},"page":"305-321","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimistic Recovery for High-Availability Software via Partial Process State Preservation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8938-447X","authenticated-orcid":false,"given":"Yuzhuo","family":"Jing","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4893-9461","authenticated-orcid":false,"given":"Yuqi","family":"Mai","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0258-6952","authenticated-orcid":false,"given":"Angting","family":"Cai","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7370-9816","authenticated-orcid":false,"given":"Yi","family":"Chen","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4990-2606","authenticated-orcid":false,"given":"Wanning","family":"He","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9918-8047","authenticated-orcid":false,"given":"Xiaoyang","family":"Qian","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5951-4183","authenticated-orcid":false,"given":"Peter M.","family":"Chen","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6315-0848","authenticated-orcid":false,"given":"Peng","family":"Huang","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[BUG] Deadlock with streams on redis 7.2. https:\/\/github.com\/redis\/redis\/issues\/12290."},{"key":"e_1_3_2_1_2_1","unstructured":"ClangIR: A new high-level IR for clang. https:\/\/llvm.github.io\/clangir\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Multi-Level Intermediate Representation. https:\/\/mlir.llvm.org."},{"key":"e_1_3_2_1_4_1","unstructured":"Multiple GCP products impacted in us-west2 region \/ us-west2-a zone. https:\/\/status.cloud.google.com\/incidents\/RAGcW4N9jHRkrAjnX2v7."},{"key":"e_1_3_2_1_5_1","unstructured":"Redis persistence. https:\/\/redis.io\/docs\/management\/persistence\/."},{"key":"e_1_3_2_1_6_1","unstructured":"Sap hana fast restart option. https:\/\/help.sap.com\/docs\/SAP_HANA_PLATFORM\/6b94445c94ae495c83a19646e7c3fd56\/ce158d28135147f099b761f8b1ee43fc.html."},{"key":"e_1_3_2_1_7_1","unstructured":"Summary of the amazon s3 service disruption in the northern virginia (us-east-1) region. https:\/\/aws.amazon.com\/message\/41926\/."},{"key":"e_1_3_2_1_8_1","volume-title":"https:\/\/criu.org\/Main_Page","year":"2012","unstructured":"Checkpoint\/restore in userspace. https:\/\/criu.org\/Main_Page, 2012."},{"issue":"12","key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.14778\/3352063.3352131","article-title":"Constant time recovery in azure sql database","volume":"12","author":"Antonopoulos Panagiotis","year":"2019","unstructured":"Panagiotis Antonopoulos, Peter Byrne, Wayne Chen, Cristian Diaconu, Raghavendra Thallam Kodandaramaih, Hanuma Kodavalla, Prashanth Purnananda, Adrian-Leonard Radu, Chaitanya Sreenivas Ravella, and Girish Mittur Venkataramanappa. Constant time recovery in azure sql database. Proceedings of the VLDB Endowment, 12(12):2143\u20132154, August 2019.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"e_1_3_2_1_10_1","volume-title":"The Java Programming Language","author":"Arnold Ken","year":"2005","unstructured":"Ken Arnold, James Gosling, and David Holmes. The Java Programming Language. Addison Wesley Professional, 2005."},{"key":"e_1_3_2_1_11_1","volume-title":"USENIX","author":"Baker Mary","year":"1992","unstructured":"Mary Baker and Mark Sullivan. The recovery box: Using fast recovery to provide high availability in the UNIX environment. In USENIX Summer 1992 Technical Conference, San Antonio, TX, USA, June 1992. USENIX Association."},{"key":"e_1_3_2_1_12_1","first-page":"31","volume-title":"32nd European Conference on Object-Oriented Programming (ECOOP 2018), volume 109 of Leibniz International Proceedings in Informatics (LIPIcs)","author":"Bell Jonathan","year":"2018","unstructured":"Jonathan Bell and Lu\u00eds Pina. CROCHET: Checkpoint and rollback via lightweight heap traversal on stock JVMs. In Todd Millstein, editor, 32nd European Conference on Object-Oriented Programming (ECOOP 2018), volume 109 of Leibniz International Proceedings in Informatics (LIPIcs), pages 17:1\u201317:31, Dagstuhl, Germany, 2018. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik."},{"key":"e_1_3_2_1_13_1","unstructured":"Phil Bernstein Sergey Bykov Alan Geller Gabriel Kliot and Jorgen Thelin. Orleans: Distributed virtual actors for programmability and scalability. Technical Report MSR-TR-2014-41 March 2014."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC '08","author":"Bowers K. J.","year":"2008","unstructured":"K. J. Bowers, B. J. Albright, B. Bergen, L. Yin, K. J. Barker, and D. J. Kerbyson. 0.374 pflop\/s trillion-particle kinetic modeling of laser plasma interaction on roadrunner. In Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC '08, Austin, TX, USA, 2008. IEEE Press."},{"key":"e_1_3_2_1_15_1","volume-title":"9th Workshop on Hot Topics in Operating Systems (HotOS IX)","author":"Candea George","year":"2003","unstructured":"George Candea and Armando Fox. Crash-only software. In 9th Workshop on Hot Topics in Operating Systems (HotOS IX), Lihue, HI, USA, May 2003. USENIX Association."},{"key":"e_1_3_2_1_16_1","first-page":"3","volume-title":"Proceedings of the 6th Conference on Symposium on Opearting Systems Design & Implementation, OSDI '04","author":"Candea George","year":"2004","unstructured":"George Candea, Shinichi Kawamoto, Yuichi Fujiki, Greg Friedman, and Armando Fox. Microreboot\u2014a technique for cheap recovery. In Proceedings of the 6th Conference on Symposium on Opearting Systems Design & Implementation, OSDI '04, pages 3\u20133, San Francisco, CA, USA, 2004. USENIX Association."},{"key":"e_1_3_2_1_17_1","first-page":"281","volume-title":"Proceedings of the 29th International Conference on Software Engineering, ICSE '07","author":"Chen Haibo","year":"2007","unstructured":"Haibo Chen, Jie Yu, Rong Chen, Binyu Zang, and Pen-Chung Yew. POLUS: A powerful live updating system. In Proceedings of the 29th International Conference on Software Engineering, ICSE '07, page 271\u2013281, Minneapolis, MN, USA, 2007. IEEE Computer Society."},{"key":"e_1_3_2_1_18_1","first-page":"37","volume-title":"Proceedings of the 25th Symposium on Operating Systems Principles, SOSP '15","author":"Chen Haogang","year":"2015","unstructured":"Haogang Chen, Daniel Ziegler, Tej Chajed, Adam Chlipala, M. Frans Kaashoek, and Nickolai Zeldovich. Using crash hoare logic for certifying the FSCQ file system. In Proceedings of the 25th Symposium on Operating Systems Principles, SOSP '15, page 18\u201337, Monterey, CA, USA, 2015. Association for Computing Machinery."},{"key":"e_1_3_2_1_19_1","first-page":"83","volume-title":"Proceedings of the Seventh International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS VII","author":"Chen Peter M.","year":"1996","unstructured":"Peter M. Chen, Wee Teck Ng, Subhachandra Chandra, Christopher Aycock, Gurushankar Rajamani, and David Lowell. The Rio file cache: surviving operating system crashes. In Proceedings of the Seventh International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS VII, page 74\u201383, Cambridge, MA, USA, 1996. Association for Computing Machinery."},{"key":"e_1_3_2_1_20_1","first-page":"794","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen and Carlos Guestrin. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16, page 785\u2013794, San Francisco, CA, USA, 2016. Association for Computing Machinery."},{"key":"e_1_3_2_1_21_1","first-page":"243","volume-title":"Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, SOSP '13","author":"Chidambaram Vijay","year":"2013","unstructured":"Vijay Chidambaram, Thanumalayan Sankaranarayana Pillai, Andrea C. Arpaci-Dusseau, and Remzi H. Arpaci-Dusseau. Optimistic crash consistency. In Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, SOSP '13, page 228\u2013243, Farminton, PA, USA, 2013. Association for Computing Machinery."},{"issue":"1","key":"e_1_3_2_1_22_1","article-title":"A survey of software aging and rejuvenation studies","volume":"10","author":"Cotroneo Domenico","year":"2014","unstructured":"Domenico Cotroneo, Roberto Natella, Roberto Pietrantuono, and Stefano Russo. A survey of software aging and rejuvenation studies. ACM Journal of Emerging Technologies in Computing Systems, 10(1), January 2014.","journal-title":"ACM Journal of Emerging Technologies in Computing Systems"},{"key":"e_1_3_2_1_23_1","first-page":"14","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Duplyakin Dmitry","year":"2019","unstructured":"Dmitry Duplyakin, Robert Ricci, Aleksander Maricq, Gary Wong, Jonathon Duerig, Eric Eide, Leigh Stoller, Mike Hibler, David Johnson, Kirk Webb, Aditya Akella, Kuangching Wang, Glenn Ricart, Larry Landweber, Chip Elliott, Michael Zink, Emmanuel Cecchet, Snigdhaswin Kar, and Prabodh Mishra. The design and operation of CloudLab. In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 1\u201314, Renton, WA, USA, July 2019. USENIX Association."},{"issue":"3","key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1145\/568522.568525","article-title":"A survey of rollback-recovery protocols in message-passing systems","volume":"34","author":"Elnozahy E. N.","year":"2002","unstructured":"E. N. (Mootaz) Elnozahy, Lorenzo Alvisi, Yi-Min Wang, and David B. Johnson. A survey of rollback-recovery protocols in message-passing systems. ACM Computing Surveys, 34(3):375\u2013408, September 2002.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_2_1_25_1","first-page":"74","volume-title":"Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation, OSDI '10","author":"Ford Daniel","year":"2010","unstructured":"Daniel Ford, Fran\u00e7ois Labelle, Florentina I. Popovici, Murray Stokely, Van-Anh Truong, Luiz Barroso, Carrie Grimes, and Sean Quinlan. Availability in globally distributed storage systems. In Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation, OSDI '10, page 61\u201374, Vancouver, BC, Canada, 2010. USENIX Association."},{"key":"e_1_3_2_1_26_1","volume-title":"2006 USENIX Annual Technical Conference, USENIX ATC '06","author":"Geels Dennis","year":"2006","unstructured":"Dennis Geels, Gautam Altekar, Scott Shenker, and Ion Stoica. Replay debugging for distributed applications. In 2006 USENIX Annual Technical Conference, USENIX ATC '06, Boston, MA, USA, May 2006. USENIX Association."},{"key":"e_1_3_2_1_27_1","first-page":"292","volume-title":"Proceedings of the Eighteenth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '13","author":"Giuffrida Cristiano","year":"2013","unstructured":"Cristiano Giuffrida, Anton Kuijsten, and Andrew S. Tanenbaum. Safe and automatic live update for operating systems. In Proceedings of the Eighteenth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '13, page 279\u2013292, Houston, TX, USA, 2013. Association for Computing Machinery."},{"key":"e_1_3_2_1_28_1","first-page":"549","volume-title":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, SIGMOD '14","author":"Goel Aakash","year":"2014","unstructured":"Aakash Goel, Bhuwan Chopra, Ciprian Gerea, Dhruv M\u00e1t\u00e1ni, Josh Metzler, Fahim Ul Haq, and Janet Wiener. Fast database restarts at Facebook. In Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, SIGMOD '14, page 541\u2013549, Snowbird, UT, USA, 2014. Association for Computing Machinery."},{"key":"e_1_3_2_1_29_1","first-page":"12","volume-title":"Proceedings of the Fifth Symposium on Reliability in Distributed Software and Database Systems, (SRDS 1986","author":"Gray Jim","year":"1986","unstructured":"Jim Gray. Why do computers stop and what can be done about it? In Proceedings of the Fifth Symposium on Reliability in Distributed Software and Database Systems, (SRDS 1986), pages 3\u201312, Los Angeles, CA, USA, January 1986. IEEE Computer Society."},{"key":"e_1_3_2_1_30_1","first-page":"16","volume-title":"Proceedings of the Seventh ACM Symposium on Cloud Computing, SoCC '16","author":"Gunawi Haryadi S.","year":"2016","unstructured":"Haryadi S. Gunawi, Mingzhe Hao, Riza O. Suminto, Agung Laksono, Anang D. Satria, Jeffry Adityatama, and Kurnia J. Eliazar. Why does the cloud stop computing? Lessons from hundreds of service outages. In Proceedings of the Seventh ACM Symposium on Cloud Computing, SoCC '16, page 1\u201316, Santa Clara, CA, USA, 2016. Association for Computing Machinery."},{"key":"e_1_3_2_1_31_1","first-page":"892","volume-title":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD '20","author":"Haubenschild Michael","year":"2020","unstructured":"Michael Haubenschild, Caetano Sauer, Thomas Neumann, and Viktor Leis. Rethinking logging, checkpoints, and recovery for highperformance storage engines. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD '20, page 877\u2013892, Portland, OR, USA, 2020. Association for Computing Machinery."},{"key":"e_1_3_2_1_32_1","first-page":"557","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Hauer Tam\u00e1s","year":"2020","unstructured":"Tam\u00e1s Hauer, Philipp Hoffmann, John Lunney, Dan Ardelean, and Amer Diwan. Meaningful availability. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), pages 545\u2013557, Santa Clara, CA, USA, February 2020. USENIX Association."},{"key":"e_1_3_2_1_33_1","first-page":"23","volume-title":"Proceedings of the ACM SIGPLAN 2001 Conference on Programming Language Design and Implementation, PLDI '01","author":"Hicks Michael","year":"2001","unstructured":"Michael Hicks, Jonathan T. Moore, and Scott Nettles. Dynamic software updating. In Proceedings of the ACM SIGPLAN 2001 Conference on Programming Language Design and Implementation, PLDI '01, page 13\u201323, Snowbird, UT, USA, 2001. Association for Computing Machinery."},{"key":"e_1_3_2_1_34_1","first-page":"482","volume-title":"Proceedings of the Twelfth European Conference on Computer Systems, EuroSys '17","author":"Ching-Hsiang Hsu Terry","year":"2017","unstructured":"Terry Ching-Hsiang Hsu, Helge Br\u00fcgner, Indrajit Roy, Kimberly Keeton, and Patrick Eugster. NVthreads: Practical persistence for multithreaded applications. In Proceedings of the Twelfth European Conference on Computer Systems, EuroSys '17, page 468\u2013482, Belgrade, Serbia, 2017. Association for Computing Machinery."},{"key":"e_1_3_2_1_35_1","first-page":"90","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Huang Lexiang","year":"2022","unstructured":"Lexiang Huang, Matthew Magnusson, Abishek Bangalore Muralikrishna, Salman Estyak, Rebecca Isaacs, Abutalib Aghayev, Timothy Zhu, and Aleksey Charapko. Metastable failures in the wild. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pages 73\u201390, Carlsbad, CA, USA, July 2022. USENIX Association."},{"key":"e_1_3_2_1_36_1","first-page":"648","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI '22","author":"Jing Yuzhuo","year":"2022","unstructured":"Yuzhuo Jing and Peng Huang. Operating system support for safe and efficient auxiliary execution. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI '22, pages 633\u2013648, Carlsbad, CA, USA, July 2022. USENIX Association."},{"key":"e_1_3_2_1_37_1","volume-title":"2005 USENIX Annual Technical Conference, USENIX ATC '05","author":"King Samuel T.","year":"2005","unstructured":"Samuel T. King, George W. Dunlap, and Peter M. Chen. Debugging operating systems with time-traveling virtual machines. In 2005 USENIX Annual Technical Conference, USENIX ATC '05, Anaheim, CA, USA, April 2005. USENIX Association."},{"key":"e_1_3_2_1_38_1","first-page":"381","volume-title":"Proceedings of the Twenty-Fifth International Symposium on Fault-Tolerant Computing, FTCS '95","author":"Kolettis Nick","year":"1995","unstructured":"Nick Kolettis and N. Dudley Fulton. Software rejuvenation: Analysis, module and applications. In Proceedings of the Twenty-Fifth International Symposium on Fault-Tolerant Computing, FTCS '95, page 381, Pasadena, CA, USA, 1995. IEEE Computer Society."},{"key":"e_1_3_2_1_39_1","volume-title":"2007 USENIX Annual Technical Conference on Proceedings of the USENIX Annual Technical Conference, ATC '07","author":"Laadan Oren","year":"2007","unstructured":"Oren Laadan and Jason Nieh. Transparent checkpoint-restart of multiple processes on commodity operating systems. In 2007 USENIX Annual Technical Conference on Proceedings of the USENIX Annual Technical Conference, ATC '07, Santa Clara, CA, USA, 2007. USENIX Association."},{"key":"e_1_3_2_1_40_1","first-page":"2004","volume-title":"Proceedings of the International Symposium on Code Generation and Optimization: Feedback-directed and Runtime Optimization, CGO '04","author":"Lattner Chris","unstructured":"Chris Lattner and Vikram Adve. Llvm: A compilation framework for lifelong program analysis & transformation. In Proceedings of the International Symposium on Code Generation and Optimization: Feedback-directed and Runtime Optimization, CGO '04, pages 75\u2013, Washington, DC, USA, 2004. IEEE Computer Society."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation, OSDI '20","author":"Levy Sebastien","year":"2020","unstructured":"Sebastien Levy, Randolph Yao, Youjiang Wu, Yingnong Dang, Peng Huang, Zheng Mu, Pu Zhao, Tarun Ramani, Naga Govindaraju, Xukun Li, Qingwei Lin, Gil Lapid Shafriri, and Murali Chintalapati. Predictive and adaptive failure mitigation to avert production cloud vm interruptions. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation, OSDI '20, Virtual, 2020. USENIX Association."},{"key":"e_1_3_2_1_42_1","first-page":"64","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI '16","author":"Litton James","year":"2016","unstructured":"James Litton, Anjo Vahldiek-Oberwagner, Eslam Elnikety, Deepak Garg, Bobby Bhattacharjee, and Peter Druschel. Light-Weight contexts: An OS abstraction for safety and performance. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI '16, pages 49\u201364, Savannah, GA, November 2016. USENIX Association."},{"key":"e_1_3_2_1_43_1","first-page":"125","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI '22","author":"Lou Chang","year":"2022","unstructured":"Chang Lou, Cong Chen, Peng Huang, Yingnong Dang, Si Qin, Xinsheng Yang, Xukun Li, Qingwei Lin, and Murali Chintalapati. RESIN: A holistic service for dealing with memory leaks in production cloud infrastructure. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI '22, pages 109\u2013125, Carlsbad, CA, USA, July 2022. USENIX Association."},{"key":"e_1_3_2_1_44_1","first-page":"125","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation, OSDI '22","author":"Lou Chang","year":"2022","unstructured":"Chang Lou, Cong Chen, Peng Huang, Yingnong Dang, Si Qin, Xinsheng Yang, Xukun Li, Qingwei Lin, and Murali Chintalapati. RESIN: A holistic service for dealing with memory leaks in production cloud infrastructure. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI '22, pages 109\u2013125, Carlsbad, CA, USA, July 2022. USENIX Association."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 4th Conference on Symposium on Operating System Design & Implementation -","volume":"4","author":"Lowell David E.","year":"2000","unstructured":"David E. Lowell, Subhachandra Chandra, and Peter M. Chen. Exploring failure transparency and the limits of generic recovery. In Proceedings of the 4th Conference on Symposium on Operating System Design & Implementation - Volume 4, OSDI '00, San Diego, CA, USA, 2000. USENIX Association."},{"key":"e_1_3_2_1_46_1","first-page":"4","volume-title":"Proceedings of the 9th USENIX Conference on Hot Topics in Storage and File Systems, HotStorage'17","author":"Marathe Virendra J.","year":"2017","unstructured":"Virendra J. Marathe, Margo Seltzer, Steve Byan, and Tim Harris. Persistent Memcached: Bringing legacy code to byte-addressable persistent memory. In Proceedings of the 9th USENIX Conference on Hot Topics in Storage and File Systems, HotStorage'17, pages 4\u20134, Santa Clara, CA, USA, 2017. USENIX Association."},{"key":"e_1_3_2_1_47_1","first-page":"17","volume-title":"Proceedings of the 16th Workshop on Hot Topics in Operating Systems, HotOS '17","author":"Mogul Jeffrey C.","year":"2017","unstructured":"Jeffrey C. Mogul, Rebecca Isaacs, and Brent Welch. Thinking about availability in large service infrastructures. In Proceedings of the 16th Workshop on Hot Topics in Operating Systems, HotOS '17, page 12\u201317, Whistler, BC, Canada, 2017. Association for Computing Machinery."},{"key":"e_1_3_2_1_48_1","first-page":"148","volume-title":"Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '17","author":"Nalli Sanketh","year":"2017","unstructured":"Sanketh Nalli, Swapnil Haria, Mark D. Hill, Michael M. Swift, Haris Volos, and Kimberly Keeton. An analysis of persistent memory use with WHISPER. In Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '17, pages 135\u2013148, Xi'an, China, 2017. ACM."},{"key":"e_1_3_2_1_49_1","first-page":"410","volume-title":"Proceedings of the Seventeenth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS XVII","author":"Narayanan Dushyanth","year":"2012","unstructured":"Dushyanth Narayanan and Orion Hodson. Whole-system persistence. In Proceedings of the Seventeenth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS XVII, page 401\u2013410, London, England, UK, 2012. Association for Computing Machinery."},{"issue":"1","key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/TSE.2011.124","article-title":"On fault representativeness of software fault injection","volume":"39","author":"Natella Roberto","year":"2013","unstructured":"Roberto Natella, Domenico Cotroneo, Joao A. Duraes, and Henrique S. Madeira. On fault representativeness of software fault injection. IEEE Transactions on Software Engineering, 39(1):80\u201396, January 2013.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_1_51_1","first-page":"83","volume-title":"Proceedings of the 27th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI '06","author":"Neamtiu Iulian","year":"2006","unstructured":"Iulian Neamtiu, Michael Hicks, Gareth Stoyle, and Manuel Oriol. Practical dynamic software updating for c. In Proceedings of the 27th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI '06, page 72\u201383, Ottawa, Ontario, Canada, 2006. Association for Computing Machinery."},{"key":"e_1_3_2_1_52_1","volume-title":"5th Symposium on Operating Systems Design and Implementation, OSDI '02","author":"Osman Steven","year":"2002","unstructured":"Steven Osman, Dinesh Subhraveti, Gong Su, and Jason Nieh. The design and implementation of Zap: A system for migrating computing environments. In 5th Symposium on Operating Systems Design and Implementation, OSDI '02, Boston, MA, USA, December 2002. USENIX Association."},{"key":"e_1_3_2_1_53_1","first-page":"61","volume-title":"Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference, USENIX ATC '19","author":"Panda Biswaranjan","year":"2019","unstructured":"Biswaranjan Panda, Deepthi Srinivasan, Huan Ke, Karan Gupta, Vinayak Khot, and Haryadi S. Gunawi. IASO: A fail-slow detection and mitigation framework for distributed storage services. In Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference, USENIX ATC '19, page 47\u201361, Renton, WA, USA, 2019. USENIX Association."},{"key":"e_1_3_2_1_54_1","unstructured":"David Patterson Aaron Brown Pete Broadwell George Candea Mike Chen James Cutler Patricia Enriquez Armando Fox Emre Kiciman Matthew Merzbacher David Oppenheimer Naveen Sastry William Tetzlaff Jonathan Traupman and Noah Treuhaft. Recovery oriented computing (ROC): Motivation definition techniques and case studies. Technical Report UCB\/CSD-02-1175 March 2002."},{"key":"e_1_3_2_1_55_1","volume-title":"USENIX 1995 Technical Conference, USENIX ATC '95","author":"Plank James S.","year":"1995","unstructured":"James S. Plank, Micah Beck, Gerry Kingsley, and Kai Li. Libckpt: Transparent checkpointing under UNIX. In USENIX 1995 Technical Conference, USENIX ATC '95, New Orleans, LA, USA, January 1995. USENIX Association."},{"key":"e_1_3_2_1_56_1","first-page":"248","volume-title":"Proceedings of the Twentieth ACM Symposium on Operating Systems Principles, SOSP '05","author":"Qin Feng","year":"2005","unstructured":"Feng Qin, Joseph Tucek, Jagadeesan Sundaresan, and Yuanyuan Zhou. Rx: Treating bugs as allergies\u2014a safe method to survive software failures. In Proceedings of the Twentieth ACM Symposium on Operating Systems Principles, SOSP '05, page 235\u2013248, Brighton, UK, 2005. Association for Computing Machinery."},{"key":"e_1_3_2_1_57_1","volume-title":"6th Symposium on Operating Systems Design & Implementation (OSDI 04)","author":"Rinard Martin","year":"2004","unstructured":"Martin Rinard, Cristian Cadar, Daniel Dumitran, Daniel M. Roy, Tudor Leu, and Jr. William S. Beebee. Enhancing server availability and security through Failure-Oblivious computing. In 6th Symposium on Operating Systems Design & Implementation (OSDI 04), San Francisco, CA, USA, December 2004. USENIX Association."},{"key":"e_1_3_2_1_58_1","volume-title":"Lawrence Berkeley National Laboratory","author":"Roman Eric","year":"2002","unstructured":"Eric Roman. A survey of checkpoint\/restart implementations. Technical report, Lawrence Berkeley National Laboratory, Tech, 2002."},{"key":"e_1_3_2_1_59_1","first-page":"666","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation, OSDI '20","author":"Rommel Florian","year":"2020","unstructured":"Florian Rommel, Christian Dietrich, Daniel Friesel, Marcel K\u00f6ppen, Christoph Borchert, Michael M\u00fcller, Olaf Spinczyk, and Daniel Lohmann. From global to local quiescence: Wait-Free code patching of Multi-Threaded processes. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI '20, pages 651\u2013666, Virtual, November 2020. USENIX Association."},{"issue":"2","key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1002\/spe.576","article-title":"High-performance benchmarking with web polygraph. Software","volume":"34","author":"Rousskov Alex","year":"2004","unstructured":"Alex Rousskov and Duane Wessels. High-performance benchmarking with web polygraph. Software: Practice and Experience, 34(2):187\u2013211, February 2004.","journal-title":"Practice and Experience"},{"key":"e_1_3_2_1_61_1","first-page":"129","volume-title":"Proceedings of the Sixteenth European Conference on Computer Systems, EuroSys '21","author":"Russinovich Mark","year":"2021","unstructured":"Mark Russinovich, Naga Govindaraju, Melur Raghuraman, David Hepkin, Jamie Schwartz, and Arun Kishan. Virtual machine preserving host updates for zero day patching in public cloud. In Proceedings of the Sixteenth European Conference on Computer Systems, EuroSys '21, page 114\u2013129, Online Event, UK, 2021. Association for Computing Machinery."},{"key":"e_1_3_2_1_62_1","first-page":"654","volume-title":"2009 IEEE International Conference on Web Services","author":"Shao Lingshuang","unstructured":"Lingshuang Shao, Junfeng Zhao, Tao Xie, Lu Zhang, Bing Xie, and Hong Mei. User-perceived service availability: A metric and an estimation approach. In 2009 IEEE International Conference on Web Services, pages 647\u2013654. IEEE, 2009."},{"key":"e_1_3_2_1_63_1","first-page":"3","volume-title":"Proceedings of the Annual Conference on USENIX Annual Technical Conference, ATEC '04","author":"Srinivasan Sudarshan M.","year":"2004","unstructured":"Sudarshan M. Srinivasan, Srikanth Kandula, Christopher R. Andrews, and Yuanyuan Zhou. Flashback: A lightweight extension for rollback and deterministic replay for software debugging. In Proceedings of the Annual Conference on USENIX Annual Technical Conference, ATEC '04, page 3, Boston, MA, USA, 2004. USENIX Association."},{"issue":"3","key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1145\/3959.3962","article-title":"Optimistic recovery in distributed systems","volume":"3","author":"Strom Rob","year":"1985","unstructured":"Rob Strom and Shaula Yemini. Optimistic recovery in distributed systems. ACM Transactions on Computer Systems, 3(3):204\u2013226, August 1985.","journal-title":"ACM Transactions on Computer Systems"},{"issue":"1","key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/1993744.1993757","article-title":"Record and transplay: Partial checkpointing for replay debugging across heterogeneous systems","volume":"39","author":"Subhraveti Dinesh","year":"2011","unstructured":"Dinesh Subhraveti and Jason Nieh. Record and transplay: Partial checkpointing for replay debugging across heterogeneous systems. ACM SIGMETRICS Performance Evaluation Review, 39(1):109\u2013120, June 2011.","journal-title":"ACM SIGMETRICS Performance Evaluation Review"},{"key":"e_1_3_2_1_66_1","volume-title":"Proceedings of the 6th Workshop on Programming Languages and Operating Systems, PLOS '11","author":"Visan Ana-Maria","year":"2011","unstructured":"Ana-Maria Visan, Kapil Arya, Gene Cooperman, and Tyler Denniston. Urdb: A universal reversible debugger based on decomposing debugging histories. In Proceedings of the 6th Workshop on Programming Languages and Operating Systems, PLOS '11, Cascais, Portugal, 2011. Association for Computing Machinery."},{"key":"e_1_3_2_1_67_1","first-page":"216","volume-title":"Proceedings of the Fourteenth ACM Symposium on Operating Systems Principles, SOSP '93","author":"Wahbe Robert","year":"1993","unstructured":"Robert Wahbe, Steven Lucco, Thomas E. Anderson, and Susan L. Graham. Efficient software-based fault isolation. In Proceedings of the Fourteenth ACM Symposium on Operating Systems Principles, SOSP '93, page 203\u2013216, Asheville, NC, USA, 1993. Association for Computing Machinery."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/FTCS.1995.466999","volume-title":"Proceedings of the Twenty-Fifth International Symposium on Fault-Tolerant Computing, FTCS '95","author":"Wang Yi-Min","year":"1995","unstructured":"Yi-Min Wang, Yennun Huang, Kiem-Phong Vo, Pe-Yu Chung, and C. Kintala. Checkpointing and its applications. In Proceedings of the Twenty-Fifth International Symposium on Fault-Tolerant Computing, FTCS '95, page 22, Pasadena, CA, USA, 1995. IEEE Computer Society."},{"key":"e_1_3_2_1_69_1","first-page":"382","volume-title":"Proceedings of the 2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks, DSN '14","author":"Wei Jiesheng","year":"2014","unstructured":"Jiesheng Wei, Anna Thomas, Guanpeng Li, and Karthik Pattabiraman. Quantifying the accuracy of high-level fault injection techniques for hardware faults. In Proceedings of the 2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks, DSN '14, page 375\u2013382, Atlanta, GA, USA, 2014. IEEE Computer Society."},{"key":"e_1_3_2_1_70_1","first-page":"16","volume-title":"Haibo Chen. TreeSLS: A Whole-system Persistent Microkernel with Tree-structured State Checkpoint on NVM. In Proceedings of the 29th Symposium on Operating Systems Principles, SOSP '23","author":"Wu Fangnuo","year":"2023","unstructured":"Fangnuo Wu, Mingkai Dong, Gequan Mo, and Haibo Chen. TreeSLS: A Whole-system Persistent Microkernel with Tree-structured State Checkpoint on NVM. In Proceedings of the 29th Symposium on Operating Systems Principles, SOSP '23, page 1\u201316, Koblenz, Germany, 2023. Association for Computing Machinery."},{"key":"e_1_3_2_1_71_1","first-page":"2","volume-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, NSDI '12","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, and Ion Stoica. Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, NSDI '12, page 2, San Jose, CA, USA, 2012. USENIX Association."},{"key":"e_1_3_2_1_72_1","first-page":"10","volume-title":"Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, HotCloud'10","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin, Scott Shenker, and Ion Stoica. Spark: cluster computing with working sets. In Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, HotCloud'10, page 10, Boston, MA, USA, 2010. USENIX Association."},{"key":"e_1_3_2_1_73_1","first-page":"477","volume-title":"Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, OSDI '14","author":"Zheng Wenting","year":"2014","unstructured":"Wenting Zheng, Stephen Tu, Eddie Kohler, and Barbara Liskov. Fast databases with fast durability and recovery through multicore parallelism. In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, OSDI '14, page 465\u2013477, Broomfield, CO, USA, 2014. USENIX Association."}],"event":{"name":"SOSP '25: ACM SIGOPS 31st Symposium on Operating Systems Principles","location":"Lotte Hotel World Seoul Republic of Korea","acronym":"SOSP '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","USENIX"]},"container-title":["Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles"],"original-title":[],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T12:51:43Z","timestamp":1759323103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731569.3764858"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":73,"alternative-id":["10.1145\/3731569.3764858","10.1145\/3731569"],"URL":"https:\/\/doi.org\/10.1145\/3731569.3764858","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}