{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:51:18Z","timestamp":1780505478363,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,5,7]],"date-time":"2017-05-07T00:00:00Z","timestamp":1494115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,5,7]]},"DOI":"10.1145\/3102980.3102983","type":"proceedings-article","created":{"date-parts":[[2017,7,20]],"date-time":"2017-07-20T17:51:38Z","timestamp":1500573098000},"page":"12-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Thinking about Availability in Large Service Infrastructures"],"prefix":"10.1145","author":[{"given":"Jeffrey C.","family":"Mogul","sequence":"first","affiliation":[{"name":"Google Inc., Mountain View, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebecca","family":"Isaacs","sequence":"additional","affiliation":[{"name":"Google Inc., Mountain View, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brent","family":"Welch","sequence":"additional","affiliation":[{"name":"Google Inc., Mountain View, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,5,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.33"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1095810.1095817"},{"key":"e_1_3_2_1_3_1","volume-title":"September","year":"2015","unstructured":"Amazon. Summary of the Amazon DynamoDB Service Disruption and Related Impacts in the US-East Region. https:\/\/aws.amazon.com\/message\/5467D2\/ , September 2015 . Last accessed on Jan 12, 2017. Amazon. Summary of the Amazon DynamoDB Service Disruption and Related Impacts in the US-East Region. https:\/\/aws.amazon.com\/message\/5467D2\/, September 2015. Last accessed on Jan 12, 2017."},{"key":"e_1_3_2_1_4_1","first-page":"223","volume-title":"Proceedings of the Conference on Innovative Data system Research (CIDR)","author":"Baker Jason","year":"2011","unstructured":"Jason Baker , Chris Bond , James C. Corbett , JJ Furman , Andrey Khorlin , James Larson , Jean-Michel Leon , Yawei Li , Alexander Lloyd , and Vadim Yushprakh . Megastore : Providing Scalable, Highly Available Storage for Interactive Services . In Proceedings of the Conference on Innovative Data system Research (CIDR) , pages 223 -- 234 , 2011 . Jason Baker, Chris Bond, James C. Corbett, JJ Furman, Andrey Khorlin, James Larson, Jean-Michel Leon, Yawei Li, Alexander Lloyd, and Vadim Yushprakh. Megastore: Providing Scalable, Highly Available Storage for Interactive Services. In Proceedings of the Conference on Innovative Data system Research (CIDR), pages 223--234, 2011."},{"key":"e_1_3_2_1_5_1","volume-title":"Site Reliability Engineering","author":"Beyer Betsy","year":"2016","unstructured":"Betsy Beyer , Chris Jones , Jennifer Petoff , and Niall Richard Murphy , editors. Site Reliability Engineering . O'Reilly Media, Inc. , 2016 . Betsy Beyer, Chris Jones, Jennifer Petoff, and Niall Richard Murphy, editors. Site Reliability Engineering. O'Reilly Media, Inc., 2016."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1556154.1556172"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.37"},{"key":"e_1_3_2_1_8_1","first-page":"335","volume-title":"Proc. OSDI","author":"Burrows Mike","year":"2006","unstructured":"Mike Burrows . The Chubby lock service for loosely-coupled distributed systems . In Proc. OSDI , pages 335 -- 350 , 2006 . Mike Burrows. The Chubby lock service for loosely-coupled distributed systems. In Proc. OSDI, pages 335--350, 2006."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043571"},{"key":"e_1_3_2_1_10_1","volume-title":"Technique for Cheap Recovery. In Proc. OSDI","author":"Candea George","year":"2004","unstructured":"George Candea , Shinichi Kawamoto , Yuichi Fujiki , Greg Friedman , and Armando Fox . Microreboot --- A Technique for Cheap Recovery. In Proc. OSDI , 2004 . George Candea, Shinichi Kawamoto, Yuichi Fujiki, Greg Friedman, and Armando Fox. Microreboot --- A Technique for Cheap Recovery. In Proc. OSDI, 2004."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/571637.571640"},{"key":"e_1_3_2_1_12_1","unstructured":"HealthCare.gov Progress and Performance Report. Centers for Medicare & Medicaid Services https:\/\/www.cms.gov\/newsroom\/mediareleasedatabase\/press-releases\/2013-press-releases-items\/2013-12-01.html.  HealthCare.gov Progress and Performance Report. Centers for Medicare & Medicaid Services https:\/\/www.cms.gov\/newsroom\/mediareleasedatabase\/press-releases\/2013-press-releases-items\/2013-12-01.html."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2002.1029005"},{"key":"e_1_3_2_1_14_1","volume-title":"Mike Dahlin. Making Byzantine Fault Tolerant Systems Tolerate Byzantine Faults. In Proc. NSDI. USENIX","author":"Clement Allen","year":"2009","unstructured":"Allen Clement , Edmund Wong , Lorenzo Alvisi , and Mike Dahlin. Making Byzantine Fault Tolerant Systems Tolerate Byzantine Faults. In Proc. NSDI. USENIX , 2009 . Allen Clement, Edmund Wong, Lorenzo Alvisi, and Mike Dahlin. Making Byzantine Fault Tolerant Systems Tolerate Byzantine Faults. In Proc. NSDI. USENIX, 2009."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806781"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491245"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294281"},{"key":"e_1_3_2_1_19_1","volume-title":"Ford. Icebergs in the Clouds: the Other Risks of Cloud Computing. In Proc. HotCloud","author":"Bryan","year":"2012","unstructured":"Bryan Ford. Icebergs in the Clouds: the Other Risks of Cloud Computing. In Proc. HotCloud , 2012 . Bryan Ford. Icebergs in the Clouds: the Other Risks of Cloud Computing. In Proc. HotCloud, 2012."},{"key":"e_1_3_2_1_20_1","volume-title":"August","author":"Glick Adam","year":"2016","unstructured":"Adam Glick , Jason Roth , Ralph Squillace , and Simon Rolfe . Disaster recovery and high availability for applications built on Microsoft Azure. https:\/\/docs.microsoft.com\/en-us\/azure\/resiliency\/resiliency-disaster-recovery-high-availability-azure-applications , August 2016 . Last accessed on Jan 12, 2017. Adam Glick, Jason Roth, Ralph Squillace, and Simon Rolfe. Disaster recovery and high availability for applications built on Microsoft Azure. https:\/\/docs.microsoft.com\/en-us\/azure\/resiliency\/resiliency-disaster-recovery-high-availability-azure-applications, August 2016. Last accessed on Jan 12, 2017."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934891"},{"key":"e_1_3_2_1_22_1","volume-title":"January","author":"Graham-Cumming John","year":"2017","unstructured":"John Graham-Cumming . How and why the leap second affected Cloudflare DNS. https:\/\/blog.cloudflare.com\/how-and-why-the-leap-second-affected-cloudflare-dns\/ , January 2017 . John Graham-Cumming. How and why the leap second affected Cloudflare DNS. https:\/\/blog.cloudflare.com\/how-and-why-the-leap-second-affected-cloudflare-dns\/, January 2017."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3102980.3103005"},{"key":"e_1_3_2_1_24_1","volume-title":"Benjamin Reed. ZooKeeper: Wait-free Coordination for Internet-scale Systems. In Proc. USENIX ATC","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 Proc. USENIX ATC , 2010 . Patrick Hunt, Mahadev Konar, Flavio P. Junqueira, and Benjamin Reed. ZooKeeper: Wait-free Coordination for Internet-scale Systems. In Proc. USENIX ATC, 2010."},{"key":"e_1_3_2_1_25_1","volume-title":"The Art of Computer Systems Performance Analysis","author":"Jain Raj","year":"1991","unstructured":"Raj Jain . The Art of Computer Systems Performance Analysis , chapter 3. John Wiley , 1991 . Raj Jain. The Art of Computer Systems Performance Analysis, chapter 3. John Wiley, 1991."},{"key":"e_1_3_2_1_26_1","first-page":"59","volume-title":"John Wilkes. Designing for Disasters. In Proc. FAST","author":"Keeton Kimberley","year":"2004","unstructured":"Kimberley Keeton , Cipriano Santos , Dirk Beyer , Jeffrey Chase , and John Wilkes. Designing for Disasters. In Proc. FAST , pages 59 -- 62 , 2004 . Kimberley Keeton, Cipriano Santos, Dirk Beyer, Jeffrey Chase, and John Wilkes. Designing for Disasters. In Proc. FAST, pages 59--62, 2004."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/146941.146942"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294267"},{"key":"e_1_3_2_1_29_1","volume-title":"Hierarchical Bandwidth Allocation for WAN Distributed Computing. In Proc. SIGCOMM '15","author":"Kumar Alok","year":"2015","unstructured":"Alok Kumar , Sushant Jain , Uday Naik , Anand Raghuraman , Nikhil Kasinadhuni , Enrique Cauich Zermeno , C. Stephen Gunn , Jing Ai , Bj\u00f6rn Carlin , Mihai Amarandei-Stavila , Mathieu Robin , Aspi Siganporia , Stephen Stuart , and Amin Vahdat . BwE : Flexible , Hierarchical Bandwidth Allocation for WAN Distributed Computing. In Proc. SIGCOMM '15 , 2015 . Alok Kumar, Sushant Jain, Uday Naik, Anand Raghuraman, Nikhil Kasinadhuni, Enrique Cauich Zermeno, C. Stephen Gunn, Jing Ai, Bj\u00f6rn Carlin, Mihai Amarandei-Stavila, Mathieu Robin, Aspi Siganporia, Stephen Stuart, and Amin Vahdat. BwE: Flexible, Hierarchical Bandwidth Allocation for WAN Distributed Computing. In Proc. SIGCOMM '15, 2015."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/279227.279229"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2004.17"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0166-5316(92)90002-X"},{"key":"e_1_3_2_1_33_1","volume-title":"The Atlantic","author":"Meyer Robinson","year":"2015","unstructured":"Robinson Meyer . The Secret Startup That Saved the Worst Website in America . The Atlantic , July 2015 . Robinson Meyer. The Secret Startup That Saved the Worst Website in America. The Atlantic, July 2015."},{"key":"e_1_3_2_1_35_1","volume-title":"Case Study: Critical Controls that Could Have Prevented Target Breach","author":"Radichel Teri","year":"2014","unstructured":"Teri Radichel . Case Study: Critical Controls that Could Have Prevented Target Breach . SANS Institute InfoSec Reading Room , August 2014 . Teri Radichel. Case Study: Critical Controls that Could Have Prevented Target Breach. SANS Institute InfoSec Reading Room, August 2014."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1975.9939"},{"key":"e_1_3_2_1_37_1","volume-title":"Case Study: Critical Controls that Sony Should Have Implemented","author":"Sanchez Gabriel","year":"2015","unstructured":"Gabriel Sanchez . Case Study: Critical Controls that Sony Should Have Implemented . SANS Institute InfoSec Reading Room , June 2015 . Gabriel Sanchez. Case Study: Critical Controls that Sony Should Have Implemented. SANS Institute InfoSec Reading Room, June 2015."},{"key":"e_1_3_2_1_38_1","first-page":"1","volume-title":"Proc. HOTOS","author":"Shah Mehul A.","year":"2007","unstructured":"Mehul A. Shah , Mary Baker , Jeffrey C. Mogul , and Ram Swaminathan . Auditing to Keep Online Storage Services Honest . In Proc. HOTOS , pages 11: 1 -- 11 :6, 2007 . Mehul A. Shah, Mary Baker, Jeffrey C. Mogul, and Ram Swaminathan. Auditing to Keep Online Storage Services Honest. In Proc. HOTOS, pages 11:1--11:6, 2007."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787508"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2010.03.005"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934874"},{"key":"e_1_3_2_1_42_1","volume-title":"Threat Modeling","author":"Swiderski Frank","year":"2004","unstructured":"Frank Swiderski and Window Snyder . Threat Modeling . Microsoft Press , Redmond, WA, USA , 2004 . Frank Swiderski and Window Snyder. Threat Modeling. Microsoft Press, Redmond, WA, USA, 2004."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522731"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470455432.ch4"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/945445.945470"},{"key":"e_1_3_2_1_46_1","volume-title":"Proc. OSDI","author":"Yu Haifeng","year":"2000","unstructured":"Haifeng Yu and Amin Vahdat . Design and evaluation of a continuous consistency model for replicated services . In Proc. OSDI , 2000 . Haifeng Yu and Amin Vahdat. Design and evaluation of a continuous consistency model for replicated services. In Proc. OSDI, 2000."}],"event":{"name":"HotOS '17: Workshop on Hot Topics in Operating Systems","location":"Whistler BC Canada","acronym":"HotOS '17","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 16th Workshop on Hot Topics in Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3102980.3102983","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3102980.3102983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:37:06Z","timestamp":1750217826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3102980.3102983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,7]]},"references-count":45,"alternative-id":["10.1145\/3102980.3102983","10.1145\/3102980"],"URL":"https:\/\/doi.org\/10.1145\/3102980.3102983","relation":{},"subject":[],"published":{"date-parts":[[2017,5,7]]},"assertion":[{"value":"2017-05-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}