{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:04:04Z","timestamp":1778537044904,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF","award":["CCF-1816615, CCF-2029049, CNF-1956007"],"award-info":[{"award-number":["CCF-1816615, CCF-2029049, CNF-1956007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1145\/3458336.3465299","type":"proceedings-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T02:03:56Z","timestamp":1622772236000},"page":"228-235","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Fail-slow fault tolerance needs programming support"],"prefix":"10.1145","author":[{"given":"Andrew","family":"Yoo","sequence":"first","affiliation":[{"name":"University of Illinois"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanli","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Minnesota"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ritesh","family":"Sinha","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Mu","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyin","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Illinois"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,6,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Manage Chained Replication. https:\/\/docs.mongodb.com\/manual\/tutorial\/manage-chained-replication\/.  Manage Chained Replication. https:\/\/docs.mongodb.com\/manual\/tutorial\/manage-chained-replication\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'02) (June","author":"Adya A.","year":"2002","unstructured":"Adya , A. , Howell , J. , Theimer , M. , Bolosky , W. J. , and Douceur , J. R . Cooperative Task Management without Manual Stack Management . In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'02) (June 2002 ). Adya, A., Howell, J., Theimer, M., Bolosky, W. J., and Douceur, J. R. Cooperative Task Management without Manual Stack Management. In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'02) (June 2002)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/945445.945454"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTOS.2001.990058"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18)","author":"Arzani B.","year":"2018","unstructured":"Arzani , B. , Ciraci , S. , Chamon , L. , Zhu , Y. , Liu , H. H. , Padhye , J. , Loo , B. T. , and Outhred , G . 007: Democratically Finding the Cause of Packet Drops . In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18) ( Apr. 2018 ). Arzani, B., Ciraci, S., Chamon, L., Zhu, Y., Liu, H. H., Padhye, J., Loo, B. T., and Outhred, G. 007: Democratically Finding the Cause of Packet Drops. In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18) (Apr. 2018)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 6th USENIX Conference on Operating Systems Design and Implementation (OSDI'04)","author":"Barham P.","year":"2004","unstructured":"Barham , P. , Donnelly , A. , Isaacs , R. , and Mortier , R . Using Magpie for request extraction and workload modelling . In Proceedings of the 6th USENIX Conference on Operating Systems Design and Implementation (OSDI'04) ( Dec. 2004 ). Barham, P., Donnelly, A., Isaacs, R., and Mortier, R. Using Magpie for request extraction and workload modelling. In Proceedings of the 6th USENIX Conference on Operating Systems Design and Implementation (OSDI'04) (Dec. 2004)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'20) (July","author":"Boucher S.","year":"2020","unstructured":"Boucher , S. , Kalia , A. , Andersen , D. G. , and Kaminsky , M . Lightweight Preemptible Functions . In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'20) (July 2020 ). Boucher, S., Kalia, A., Andersen, D. G., and Kaminsky, M. Lightweight Preemptible Functions. In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'20) (July 2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 7th USENIX Conference on Operating Systems Design and Implementation (OSDI'06)","author":"Burrows M.","year":"2006","unstructured":"Burrows , M. The Chubby lock service for loosely-coupled distributed systems . In Proceedings of the 7th USENIX Conference on Operating Systems Design and Implementation (OSDI'06) ( Nov. 2006 ). Burrows, M. The Chubby lock service for loosely-coupled distributed systems. In Proceedings of the 7th USENIX Conference on Operating Systems Design and Implementation (OSDI'06) (Nov. 2006)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281100.1281103"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807152"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 10th USENIX Conference on Operating Systems Design and Implementation (OSDI'12)","author":"Corbett J. C.","year":"2012","unstructured":"Corbett , J. C. , Dean , J. , Epstein , M. , Fikes , A. , Frost , C. , Furman , J. J. , Ghemawat , S. , Gubarev , A. , Heiser , C. , Hochschild , P. , Hsieh , W. , Kanthak , S. , Kogan , E. , Li , H. , Lloyd , A. , Melnik , S. , Mwaura , D. , Nagle , D. , Quinlan , S. , Rao , R. , Rolig , L. , Saito , Y. , Szymaniak , M. , Taylor , C. , Wang , R. , and Woodford , D . Spanner: Google's Globally-Distributed Database . In Proceedings of the 10th USENIX Conference on Operating Systems Design and Implementation (OSDI'12) ( Oct. 2012 ). Corbett, J. C., Dean, J., Epstein, M., Fikes, A., Frost, C., Furman, J. J., Ghemawat, S., Gubarev, A., Heiser, C., Hochschild, P., Hsieh, W., Kanthak, S., Kogan, E., Li, H., Lloyd, A., Melnik, S., Mwaura, D., Nagle, D., Quinlan, S., Rao, R., Rolig, L., Saito, Y., Szymaniak, M., Taylor, C., Wang, R., and Woodford, D. Spanner: Google's Globally-Distributed Database. In Proceedings of the 10th USENIX Conference on Operating Systems Design and Implementation (OSDI'12) (Oct. 2012)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 10th Workshop on Hot Topics in Operating Systems (HotOS'05)","author":"Cunningham R.","year":"2005","unstructured":"Cunningham , R. , and Kohler , E . Making Events Less Slippery With eel . In Proceedings of the 10th Workshop on Hot Topics in Operating Systems (HotOS'05) ( June 2005 ). Cunningham, R., and Kohler, E. Making Events Less Slippery With eel. In Proceedings of the 10th Workshop on Hot Topics in Operating Systems (HotOS'05) (June 2005)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2815400.2815409"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133373.1133410"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523627"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3189759.3189761"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2815400.2815428"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 46th International Conference on Very Large Data Bases (VLDB'20)","author":"Huang D.","year":"2020","unstructured":"Huang , D. , Liu , Q. , Cui , Q. , Fang , Z. , Ma , X. , Xu , F. , Shen , L. , Tang , L. , Zhou , Y. , Huang , M. , Wei , W. , Liu , C. , Zhang , J. , Li , J. , Wu , X. , Song , L. , Sun , R. , Yu , S. , Zhao , L. , Cameron , N. , Pei , L. , and Tang , X . TiDB: A Raft-based HTAP Database . In Proceedings of the 46th International Conference on Very Large Data Bases (VLDB'20) ( Sept. 2020 ). Huang, D., Liu, Q., Cui, Q., Fang, Z., Ma, X., Xu, F., Shen, L., Tang, L., Zhou, Y., Huang, M., Wei, W., Liu, C., Zhang, J., Li, J., Wu, X., Song, L., Sun, R., Yu, S., Zhao, L., Cameron, N., Pei, L., and Tang, X. TiDB: A Raft-based HTAP Database. In Proceedings of the 46th International Conference on Very Large Data Bases (VLDB'20) (Sept. 2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291170"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3102980.3103005"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 2010 USENIX Conference on USENIX Annual Technical Conference (USENIX ATC'10) (June","author":"Hunt P.","year":"2010","unstructured":"Hunt , P. , Konar , M. , Junqueira , F. P. , and Reed , B . ZooKeeper: Wait-free Coordination for Internet-scale Systems . In Proceedings of the 2010 USENIX Conference on USENIX Annual Technical Conference (USENIX ATC'10) (June 2010 ). Hunt, P., Konar, M., Junqueira, F. P., and Reed, B. ZooKeeper: Wait-free Coordination for Internet-scale Systems. In Proceedings of the 2010 USENIX Conference on USENIX Annual Technical Conference (USENIX ATC'10) (June 2010)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1243418.1243426"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00069"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'07) (June","author":"Krohn M.","year":"2007","unstructured":"Krohn , M. , Kohler , E. , and Kaashoek , M. F . Events Can Make Sense . In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'07) (June 2007 ). Krohn, M., Kohler, E., and Kaashoek, M. F. Events Can Make Sense. In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'07) (June 2007)."},{"key":"e_1_3_2_1_25_1","volume-title":"Paxos Made Simple. ACM SIGACT News (Distributed Computing Column) 32, 4 (Dec","author":"Lamport L.","year":"2001","unstructured":"Lamport , L. Paxos Made Simple. ACM SIGACT News (Distributed Computing Column) 32, 4 (Dec . 2001 ), 51--58. Lamport, L. Paxos Made Simple. ACM SIGACT News (Distributed Computing Column) 32, 4 (Dec. 2001), 51--58."},{"key":"e_1_3_2_1_26_1","volume-title":"Microsoft Research","author":"Lamport L.","year":"2005","unstructured":"Lamport , L. Fast Paxos . Tech. Rep. MSR-TR-2005-112 , Microsoft Research , 2005 . Lamport, L. Fast Paxos. Tech. Rep. MSR-TR-2005-112, Microsoft Research, 2005."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190552"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI'20)","author":"Lou C.","year":"2020","unstructured":"Lou , C. , Huang , P. , and Smith , S . Understanding, Detecting and Localizing Partial Failures in Large System Software . In Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI'20) ( Feb. 2020 ). Lou, C., Huang, P., and Smith, S. Understanding, Detecting and Localizing Partial Failures in Large System Software. In Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI'20) (Feb. 2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2815400.2815415"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2517350"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation (OSDI'20)","author":"Ngo K.","year":"2020","unstructured":"Ngo , K. , Sen , S. , and Lloyd , W . Tolerating Slowdowns in Replicated State Machines using Copilots . In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation (OSDI'20) ( Nov. 2020 ). Ngo, K., Sen, S., and Lloyd, W. Tolerating Slowdowns in Replicated State Machines using Copilots. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation (OSDI'20) (Nov. 2020)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 2014 USENIX Annual Technical Conference (USENIX ATC'14) (June","author":"Ongaro D.","year":"2014","unstructured":"Ongaro , D. , and Ousterhout , J . In Search of an Understandable Consensus Algorithm . In Proceedings of the 2014 USENIX Annual Technical Conference (USENIX ATC'14) (June 2014 ). Ongaro, D., and Ousterhout, J. In Search of an Understandable Consensus Algorithm. In Proceedings of the 2014 USENIX Annual Technical Conference (USENIX ATC'14) (June 2014)."},{"key":"e_1_3_2_1_33_1","volume-title":"Presentation at the 1996 USENIX Annual Technical Conference (Sept.","author":"Ousterhout J.","year":"1995","unstructured":"Ousterhout , J. Why threads are a bad idea (for most purposes) . In Presentation at the 1996 USENIX Annual Technical Conference (Sept. 1995 ). Ousterhout, J. Why threads are a bad idea (for most purposes). In Presentation at the 1996 USENIX Annual Technical Conference (Sept. 1995)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'19) (July","author":"Panda B.","year":"2019","unstructured":"Panda , B. , Srinivasan , D. , Ke , H. , Gupta , K. , Khot , V. , and Gunawi , H. S . IASO: A Fail-Slow Detection and Mitigation Framework for Distributed Storage Services . In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'19) (July 2019 ). Panda, B., Srinivasan, D., Ke, H., Gupta, K., Khot, V., and Gunawi, H. S. IASO: A Fail-Slow Detection and Mitigation Framework for Distributed Storage Services. In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC'19) (July 2019)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352125"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI'19)","author":"Tan C.","year":"2019","unstructured":"Tan , C. , Jin , Z. , Guo , C. , Zhang , T. , Wu , H. , Deng , K. , Bi , D. , and Xiang , D . NetBouncer: Active Device and Link Failure Localization in Data Center Networks . In Proceedings of the 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI'19) ( Feb. 2019 ). Tan, C., Jin, Z., Guo, C., Zhang, T., Wu, H., Deng, K., Bi, D., and Xiang, D. NetBouncer: Active Device and Link Failure Localization in Data Center Networks. In Proceedings of the 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI'19) (Feb. 2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 6th USENIX Conference on Operating Systems Design and Implementation (OSDI'04)","author":"van Renesse R.","year":"2004","unstructured":"van Renesse , R. , and Schneider , F. B . Chain Replication for Supporting High Throughput and Availability . In Proceedings of the 6th USENIX Conference on Operating Systems Design and Implementation (OSDI'04) ( Dec. 2004 ). van Renesse, R., and Schneider, F. B. Chain Replication for Supporting High Throughput and Availability. In Proceedings of the 6th USENIX Conference on Operating Systems Design and Implementation (OSDI'04) (Dec. 2004)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2737958"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522727"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2815400.2815404"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18)","author":"Zhang Q.","year":"2018","unstructured":"Zhang , Q. , Yu , G. , Guo , C. , Dang , Y. , Swanson , N. , Yang , X. , Yao , R. , , Chintalapati , M. , Krishnamurthy , A. , and Anderson , T . Deep-view: Virtual Disk Failure Diagnosis and Pattern Detection for Azure . In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18) ( Apr. 2018 ). Zhang, Q., Yu, G., Guo, C., Dang, Y., Swanson, N., Yang, X., Yao, R., , Chintalapati, M., Krishnamurthy, A., and Anderson, T. Deep-view: Virtual Disk Failure Diagnosis and Pattern Detection for Azure. In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18) (Apr. 2018)."}],"event":{"name":"HotOS '21: Workshop on Hot Topics in Operating Systems","location":"Ann Arbor Michigan","acronym":"HotOS '21","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Workshop on Hot Topics in Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458336.3465299","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3458336.3465299","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3458336.3465299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:19Z","timestamp":1750195699000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458336.3465299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":41,"alternative-id":["10.1145\/3458336.3465299","10.1145\/3458336"],"URL":"https:\/\/doi.org\/10.1145\/3458336.3465299","relation":{},"subject":[],"published":{"date-parts":[[2021,6]]},"assertion":[{"value":"2021-06-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}