{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T20:35:31Z","timestamp":1780346131294,"version":"3.54.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"China 973 Program","award":["2011CB302602"],"award-info":[{"award-number":["2011CB302602"]}]},{"name":"China 863 Program","award":["2015AA01A202"],"award-info":[{"award-number":["2015AA01A202"]}]},{"DOI":"10.13039\/501100000266","name":"UK EPSRC WRG Platform Project","doi-asserted-by":"publisher","award":["EP\/F0577644\/1"],"award-info":[{"award-number":["EP\/F0577644\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HGJ Program","award":["2013ZX01039-002-001-001"],"award-info":[{"award-number":["2013ZX01039-002-001-001"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC Program","doi-asserted-by":"publisher","award":["61202424"],"award-info":[{"award-number":["61202424"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC Program","doi-asserted-by":"publisher","award":["91118008"],"award-info":[{"award-number":["91118008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC Program","doi-asserted-by":"publisher","award":["61170294"],"award-info":[{"award-number":["61170294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2017,11,1]]},"DOI":"10.1109\/tsc.2016.2544313","type":"journal-article","created":{"date-parts":[[2016,3,21]],"date-time":"2016-03-21T18:55:56Z","timestamp":1458586556000},"page":"969-983","source":"Crossref","is-referenced-by-count":19,"title":["Reliable Computing Service in Massive-Scale Systems through Rapid Low-Cost Failover"],"prefix":"10.1109","volume":"10","author":[{"given":"Renyu","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Garraghan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SOSE.2014.45"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2172\/984082"},{"key":"ref33","article-title":"Torque resource manager","author":"staples","year":"0","journal-title":"Proc ACM\/IEEE Conf Supercomput"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1987.232562"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2014.2304500"},{"key":"ref30","first-page":"335","article-title":"The chubby lock service for loosely-coupled distributed systems","author":"burrows","year":"0","journal-title":"Proc of the 7th Symp on Operating systems design and implementation"},{"key":"ref37","article-title":"Large-scale cluster management at google with borg","author":"verma","year":"0","journal-title":"Proc 10th Eur Conf Comput Syst"},{"key":"ref36","first-page":"1","article-title":"Hotrestore: A fast restore system for virtual machine cluster","author":"cui","year":"0","journal-title":"Proc USENIX Large Install Syst Admin Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2002.1009167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WISE.2003.1254461"},{"key":"ref10","article-title":"The evolution of the recovery block concept","author":"randell","year":"1995","journal-title":"Software Fault Tolerannce"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2014.7097869"},{"key":"ref11","author":"jalote","year":"1994","journal-title":"Fault Tolerance in Distributed Systems"},{"key":"ref12","first-page":"757","article-title":"Fast transparent failover for reliable web service","author":"aghdaie","year":"0","journal-title":"Proc Int Conf Parallel Distrib Comput Syst"},{"key":"ref13","first-page":"285","article-title":"Apollo: Scalable and coordinated scheduling for cloud-scale computing","author":"boutin","year":"0","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"},{"key":"ref14","year":"0"},{"key":"ref15","year":"0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2004.2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HASE.2014.24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.24"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0951-8320(94)00073-W"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2011.5958247"},{"key":"ref3","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","author":"hindman","year":"2011","journal-title":"Proc 8th USENIX Conf Netw Syst Des Implementation"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01741-4","author":"barroso","year":"2013","journal-title":"The Datacenter as a Computer An Introduction to the Design of Warehouse-Scale Machines"},{"key":"ref29","first-page":"11","article-title":"Zookeeper: Wait-free coordination for internet-scale systems","author":"hunt","year":"0","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SOSE.2016.73"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2010.47"},{"key":"ref2","article-title":"Cisco Global Cloud Index: Forecast and Methodology, 2014-2019","year":"2015"},{"key":"ref9","year":"2008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13119-6_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522716"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SERVICES.2011.108"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2013.40"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISORC.2015.39"},{"key":"ref22","first-page":"1","article-title":"Improving MapReduce fault tolerance in the cloud","author":"zheng","year":"0","journal-title":"Proc IEEE Int Symp Parallel Distrib Process Workshops PhD Forum"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref21","first-page":"252","article-title":"D2ps: A dependable data provisioning service in multi-tenants cloud environments","author":"yang","year":"0","journal-title":"Proc 7th IEEE Int Symp High Assurance Syst Eng"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.112"},{"key":"ref24","year":"2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21236\/ADA555881"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2010.01.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2014.2314661"},{"key":"ref26","author":"lyu","year":"1996","journal-title":"Handbook of Software Reliability Engineering"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1773394.1773400"},{"key":"ref25","article-title":"The methodology of n-version programming","author":"avizienis","year":"0","journal-title":"Software Fault Tolerance"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4629386\/8169176\/07437494.pdf?arnumber=7437494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T08:54:49Z","timestamp":1692262489000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7437494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,1]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2016.2544313","relation":{},"ISSN":["1939-1374"],"issn-type":[{"value":"1939-1374","type":"print"}],"subject":[],"published":{"date-parts":[[2017,11,1]]}}}