{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:10:10Z","timestamp":1756487410770,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,14]]},"DOI":"10.1145\/3713082.3730374","type":"proceedings-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:53:51Z","timestamp":1749203631000},"page":"80-87","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Real Life Is Uncertain. Consensus Should Be Too!"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0423-1071","authenticated-orcid":false,"given":"Reginald","family":"Frank","sequence":"first","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8258-627X","authenticated-orcid":false,"given":"Octavio","family":"Lomeli","sequence":"additional","affiliation":[{"name":"UC Berkeley Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2175-2611","authenticated-orcid":false,"given":"Neil","family":"Giridharan","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1449-1447","authenticated-orcid":false,"given":"Soujanya","family":"Ponnapalli","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3489-2468","authenticated-orcid":false,"given":"Marcos K.","family":"Aguilera","sequence":"additional","affiliation":[{"name":"Broadcom Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3567-801X","authenticated-orcid":false,"given":"Natacha","family":"Crooks","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Data Protection in Amazon S3. https:\/\/docs.aws.amazon.com\/AmazonS3\/latest\/userguide\/DataDurability.html."},{"key":"e_1_3_2_1_2_1","unstructured":"Production-Grade Container Orchestration --- kubernetes.io. https:\/\/kubernetes.io\/. [Accessed 16-01-2025]."},{"key":"e_1_3_2_1_3_1","unstructured":"Reducing the carbon footprint of data centers --- buffalo.edu. https:\/\/www.buffalo.edu\/news\/news-releases.host.html\/content\/shared\/mgt\/news\/reducing-carbon-footprint-data-centers.detail.html. [Accessed 13-01-2025]."},{"key":"e_1_3_2_1_4_1","unstructured":"Spot Instance interruptions - Amazon Elastic Compute Cloud --- docs.amazonaws.cn. https:\/\/docs.amazonaws.cn\/en_us\/AWSEC2\/latest\/UserGuide\/spot-interruptions.html. [Accessed 16-01-2025]."},{"key":"e_1_3_2_1_5_1","unstructured":"https:\/\/community.intel.com\/t5\/Blogs\/Products-and-Solutions\/Security\/Intel-Google-TDX-Security-Review\/post\/1471177."},{"volume-title":"https:\/\/github.com\/ethereum\/","year":"2019","key":"e_1_3_2_1_6_1","unstructured":"Ethereum. https:\/\/github.com\/ethereum\/, 2019."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39989-6_5"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/VTS.2007.22"},{"key":"e_1_3_2_1_9_1","unstructured":"Hussam Amrouch. Techniques for aging soft errors and temperature to increase the reliability of embedded on-chip systems. PhD thesis Karlsruhe Karlsruher Institut f\u00fcr Technologie (KIT) Diss. 2015 2015."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IRPS.2015.7112711"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2015.2443781"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSID49098.2020.00050"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3662158.3662810"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01761-2"},{"key":"e_1_3_2_1_15_1","unstructured":"Mathieu Baudet Avery Ching Andrey Chursin George Danezis Fran\u00e7ois Garillot Zekun Li Dahlia Malkhi Oded Naor Dmitri Perelman and Alberto Sonnino. State machine replication in the libra blockchain. The Libra Assn. Tech. Rep 2019."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/800221.806707"},{"key":"e_1_3_2_1_17_1","unstructured":"brittanyrowe. General Availability of Spot Priority Mix for Azure Virtual Machine Scale Sets Flexible Orchestration Mode --- tech-community.microsoft.com. https:\/\/techcommunity.microsoft.com\/discussions\/compute\/announcing-general-availability-of-spot-priority-mix-for-azure-virtual-machine-s\/3765160 2023. [Accessed 16-01-2025]."},{"key":"e_1_3_2_1_18_1","volume-title":"Practical byzantine fault tolerance and proactive recovery. ACM Transactions on Computer Systems (TOCS), 20(4):398--461","author":"Castro Miguel","year":"2002","unstructured":"Miguel Castro and Barbara Liskov. Practical byzantine fault tolerance and proactive recovery. ACM Transactions on Computer Systems (TOCS), 20(4):398--461, 2002."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2019.00020"},{"key":"e_1_3_2_1_20_1","first-page":"37","volume-title":"2013 USENIX Annual Technical Conference (USENIX ATC 13)","author":"Cidon Asaf","year":"2013","unstructured":"Asaf Cidon, Stephen Rumble, Ryan Stutsman, Sachin Katti, John Ousterhout, and Mendel Rosenblum. Copysets: Reducing the frequency of data loss in cloud storage. In 2013 USENIX Annual Technical Conference (USENIX ATC 13), pages 37--48, 2013."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629602"},{"key":"e_1_3_2_1_22_1","volume-title":"Zekun Li, Dahlia Malkhi, Alberto Sonnino, and Alexander Spiegelman. Be aware of your leaders","author":"Cohen Shir","year":"2021","unstructured":"Shir Cohen, Rati Gelashvili, Lefteris Kokoris Kogias, Zekun Li, Dahlia Malkhi, Alberto Sonnino, and Alexander Spiegelman. Be aware of your leaders, 2021."},{"key":"e_1_3_2_1_23_1","volume-title":"Sanjay Ghemawat, Andrey Gubarev, Christopher Heiser, Peter Hochschild, et al. Spanner: Google's globally distributed database. ACM Transactions on Computer Systems (TOCS), 31(3):1--22","author":"Corbett James C","year":"2013","unstructured":"James C Corbett, Jeffrey Dean, Michael Epstein, Andrew Fikes, Christopher Frost, Jeffrey John Furman, Sanjay Ghemawat, Andrey Gubarev, Christopher Heiser, Peter Hochschild, et al. Spanner: Google's globally distributed database. ACM Transactions on Computer Systems (TOCS), 31(3):1--22, 2013."},{"key":"e_1_3_2_1_24_1","unstructured":"CrowdStrike. Technical Details: Falcon Update for Windows Hosts | CrowdStrike --- crowdstrike.com. https:\/\/www.crowdstrike.com\/blog\/falcon-update-for-windows-hosts-technical-details\/. [Accessed 10-09-2024]."},{"key":"e_1_3_2_1_25_1","volume-title":"Silent data corruptions at scale. arXiv preprint arXiv:2102.11245","author":"Dixit Harish Dattatraya","year":"2021","unstructured":"Harish Dattatraya Dixit, Sneha Pendharkar, Matt Beadon, Chris Mason, Tejasvi Chakravarthy, Bharath Muthiah, and Sriram Sankar. Silent data corruptions at scale. arXiv preprint arXiv:2102.11245, 2021."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/96559.96565"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833787"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.92"},{"key":"e_1_3_2_1_29_1","volume-title":"Security vulnerabilities of sgx and countermeasures: A survey. ACM Computing Surveys (CSUR), 54(6):1--36","author":"Fei Shufan","year":"2021","unstructured":"Shufan Fei, Zheng Yan, Wenxiu Ding, and Haomeng Xie. Security vulnerabilities of sgx and countermeasures: A survey. ACM Computing Surveys (CSUR), 54(6):1--36, 2021."},{"key":"e_1_3_2_1_30_1","volume-title":"9th USENIX Symposium 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 9th USENIX Symposium on Operating Systems Design and Implementation (OSDI 10), 2010."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00090"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17653-2_23"},{"key":"e_1_3_2_1_33_1","unstructured":"Peter Ga\u017ei Aggelos Kiayias and Dionysis Zindros. Proof-of-stake sidechains. Cryptology ePrint Archive Report 2018\/1239 2018. https:\/\/eprint.iacr.org\/2018\/1239."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132757"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132757"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695942"},{"key":"e_1_3_2_1_37_1","volume-title":"2nd Workshop on Hot Topics in Storage and File Systems (HotStorage 10)","author":"Greenan Kevin M","year":"2010","unstructured":"Kevin M Greenan, James S Plank, and Jay J Wylie. Mean time to meaningless:{MTTDL}, markov models, and storage system reliability. In 2nd Workshop on Hot Topics in Storage and File Systems (HotStorage 10), 2010."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527408"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465297"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626304"},{"key":"e_1_3_2_1_41_1","volume-title":"Flexible paxos: Quorum intersection revisited. arXiv preprint arXiv:1608.06696","author":"Howard Heidi","year":"2016","unstructured":"Heidi Howard, Dahlia Malkhi, and Alexander Spiegelman. Flexible paxos: Quorum intersection revisited. arXiv preprint arXiv:1608.06696, 2016."},{"key":"e_1_3_2_1_42_1","volume-title":"2010 USENIX Annual Technical Conference (USENIX ATC 10)","author":"Hunt Patrick","year":"2010","unstructured":"Patrick Hunt, Mahadev Konar, Flavio P Junqueira, and Benjamin Reed. ZooKeeper: Wait-free coordination for internet-scale systems. In 2010 USENIX Annual Technical Conference (USENIX ATC 10), 2010."},{"key":"e_1_3_2_1_43_1","unstructured":"ju shim. Use Azure Spot Virtual Machines - Azure Virtual Machines --- learn.microsoft.com. https:\/\/learn.microsoft.com\/en-us\/azure\/virtual-machines\/spot-vms#eviction-policy. [Accessed 16-01-2025]."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2011.5958223"},{"key":"e_1_3_2_1_45_1","unstructured":"Saurabh Kadekodi. DISK-ADAPTIVE REDUNDANCY: tailoring data redundancy to disk-reliability heterogeneity in cluster storage systems. PhD thesis PhD thesis Carnegie Mellon University 2020."},{"key":"e_1_3_2_1_46_1","first-page":"345","volume-title":"17th USENIX Conference on File and Storage Technologies (FAST 19)","author":"Kadekodi Saurabh","year":"2019","unstructured":"Saurabh Kadekodi, K. V. Rashmi, and Gregory R. Ganger. Cluster storage systems gotta have HeART: improving storage efficiency by exploiting disk-reliability heterogeneity. In 17th USENIX Conference on File and Storage Technologies (FAST 19), pages 345--358, Boston, MA, February 2019. USENIX Association."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04355-0_47"},{"key":"e_1_3_2_1_48_1","volume-title":"Backblaze Drive Stats for Q1 2024 --- backblaze.com. https:\/\/www.backblaze.com\/blog\/backblaze-drive-stats-for-q1-2024\/","author":"Klein Andy","year":"2024","unstructured":"Andy Klein. Backblaze Drive Stats for Q1 2024 --- backblaze.com. https:\/\/www.backblaze.com\/blog\/backblaze-drive-stats-for-q1-2024\/, 2024. [Accessed 14-09-2024]."},{"key":"e_1_3_2_1_49_1","volume-title":"Revisiting reliability in large-scale machine learning research clusters. arXiv preprint arXiv:2410.21680","author":"Kokolis Apostolos","year":"2024","unstructured":"Apostolos Kokolis, Michael Kuchnik, John Hoffman, Adithya Kumar, Parth Malani, Faye Ma, Zachary DeVito, Shubho Sengupta, Kalyan Saladi, and Carole-Jean Wu. Revisiting reliability in large-scale machine learning research clusters. arXiv preprint arXiv:2410.21680, 2024."},{"key":"e_1_3_2_1_50_1","first-page":"51","volume-title":"December 2001)","author":"Lamport Leslie","year":"2001","unstructured":"Leslie Lamport. Paxos made simple. ACM SIGACT News (Distributed Computing Column) 32, 4 (Whole Number 121, December 2001), pages 51--58, 2001."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519270.3538425"},{"key":"e_1_3_2_1_52_1","volume-title":"4th USENIX Symposium on Networked Systems Design & Implementation (NSDI 07)","author":"Li Jinyuan","year":"2007","unstructured":"Jinyuan Li and David Mazi\u00e8res. Beyond One-Third faulty replicas in byzantine fault tolerant systems. In 4th USENIX Symposium on Networked Systems Design & Implementation (NSDI 07), Cambridge, MA, April 2007. USENIX Association."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833768"},{"key":"e_1_3_2_1_54_1","first-page":"717","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Li Mengyuan","year":"2021","unstructured":"Mengyuan Li, Yinqian Zhang, Huibo Wang, Kang Li, and Yueqiang Cheng. {CIPHERLEAKS}: Breaking constant-time cryptography on {AMD}{SEV} via the ciphertext side channel. In 30th USENIX Security Symposium (USENIX Security 21), pages 717--732, 2021."},{"key":"e_1_3_2_1_55_1","volume-title":"Technology preview for secure value recovery","author":"Lund Joshua","year":"2019","unstructured":"Joshua Lund. Technology preview for secure value recovery, 2019."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/258533.258650"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/259380.259458"},{"key":"e_1_3_2_1_58_1","first-page":"1","article-title":"The stellar consensus protocol: A federated model for internet-level consensus","volume":"32","author":"Mazieres David","year":"2015","unstructured":"David Mazieres. The stellar consensus protocol: A federated model for internet-level consensus. Stellar Development Foundation, 32:1--45, 2015.","journal-title":"Stellar Development Foundation"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2796314.2745848"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1994.365692"},{"key":"e_1_3_2_1_61_1","first-page":"2022","article-title":"The raft consensus algorithm","volume":"190","author":"Ongaro Diego","year":"2015","unstructured":"Diego Ongaro and John Ousterhout. The raft consensus algorithm. Lecture Notes CS, 190:2022, 2015.","journal-title":"Lecture Notes CS"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483582"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/50202.50214"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/1267903.1267905"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/AsianHOST47458.2019.9006701"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613156"},{"key":"e_1_3_2_1_67_1","first-page":"467","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Shamis Alex","year":"2022","unstructured":"Alex Shamis, Peter Pietzuch, Burcu Canakci, Miguel Castro, Cedric Fournet, Edward Ashton, Amaury Chamayou, Sylvan Clebsch, Antoine Delignat-Lavaud, Matthew Kerner, Julien Maffre, Olga Vrousgou, Christoph M. Wintersteiger, Manuel Costa, and Mark Russinovich. IA-CCF: Individual accountability for permissioned ledgers. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22), pages 467--491, Renton, WA, April 2022. USENIX Association."},{"key":"e_1_3_2_1_68_1","first-page":"36","article-title":"Solving ai tasks with chatgpt and its friends in hugging face","author":"Shen Yongliang","year":"2024","unstructured":"Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484566"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2010.02.002"},{"key":"e_1_3_2_1_71_1","volume-title":"Shoal: Improving dag-bft latency and robustness","author":"Spiegelman Alexander","year":"2023","unstructured":"Alexander Spiegelman, Balaji Arun, Rati Gelashvili, and Zekun Li. Shoal: Improving dag-bft latency and robustness, 2023."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3386134"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2008.28"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2013.08.016"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00041"},{"key":"e_1_3_2_1_76_1","first-page":"961","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Xu Erci","year":"2019","unstructured":"Erci Xu, Mai Zheng, Feng Qin, Yikang Xu, and Jiesheng Wu. Lessons and actions: What we learned from 10k {SSD-Related} storage system failures. In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 961--976, 2019."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524229"}],"event":{"name":"HOTOS '25: Workshop on Hot Topics in Operating Systems","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Banff AB Canada","acronym":"HOTOS '25"},"container-title":["Proceedings of the Workshop on Hot Topics in Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3713082.3730374","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3713082.3730374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T16:48:34Z","timestamp":1756486114000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3713082.3730374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,14]]},"references-count":77,"alternative-id":["10.1145\/3713082.3730374","10.1145\/3713082"],"URL":"https:\/\/doi.org\/10.1145\/3713082.3730374","relation":{},"subject":[],"published":{"date-parts":[[2025,5,14]]},"assertion":[{"value":"2025-06-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}