{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:19:51Z","timestamp":1742912391438,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540854500"},{"type":"electronic","value":"9783540854517"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-85451-7_7","type":"book-chapter","created":{"date-parts":[[2008,8,19]],"date-time":"2008-08-19T13:15:29Z","timestamp":1219151729000},"page":"58-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Providing Non-stop Service for Message-Passing Based Parallel Applications with RADIC"],"prefix":"10.1007","author":[{"given":"Guna","family":"Santos","sequence":"first","affiliation":[]},{"given":"Angelo","family":"Duarte","sequence":"additional","affiliation":[]},{"given":"Dolores","family":"Rexachs","sequence":"additional","affiliation":[]},{"given":"Emilio","family":"Luque","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"7_CR1","unstructured":"Schroeder, B., Gibson, G.A.: Understanding failures in petascale computers. Journal of Physics: Conference Series\u00a078, 012022 (11 p.) (2007)"},{"key":"7_CR2","unstructured":"Duarte, A., Rexachs, D., Luque, E.: Increasing the cluster availability using RADIC. In: IEEE International Conference on Cluster Computing, 2006, pp. 1\u20138 (2006)"},{"issue":"3","key":"7_CR3","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"E.N.M. Elnozahy","year":"2002","unstructured":"Elnozahy, E.N.M., Alvisi, L., Wang, Y.M., Johnson, D.B.: A survey of rollback-recovery protocols in message-passing systems. ACM Computing Surveys\u00a034(3), 375\u2013408 (2002)","journal-title":"ACM Computing Surveys"},{"key":"7_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48158-3_2","volume-title":"Using MPI: Portable Parallel Programming with the Message-Passing Interface","author":"W. Gropp","year":"1999","unstructured":"Gropp, W., Lusk, E., Skjellum, A.: Using MPI: Portable Parallel Programming with the Message-Passing Interface. MIT Press, Cambridge (1999); LCCN: QA76.642 G76 1999"},{"key":"7_CR5","first-page":"142","volume-title":"Fault Tolerance in Distributed Systems","author":"P. Jalote","year":"1994","unstructured":"Jalote, P.: Reliable, Atomic and Causal Broadcast. In: Fault Tolerance in Distributed Systems, vol.\u00a01, p. 142. P T R Prentice Hall, USA (1994)"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/11846802_26","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"A. Duarte","year":"2006","unstructured":"Duarte, A., Rexachs, D., Luque, E.: An intelligent management of fault tolerance in cluster using radicmpi. In: Mohr, B., Tr\u00e4ff, J.L., Worringen, J., Dongarra, J. (eds.) PVM\/MPI 2006. LNCS, vol.\u00a04192, pp. 150\u2013157. Springer, Heidelberg (2006)"},{"issue":"3","key":"7_CR7","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1177\/1094342006067469","volume":"20","author":"A. Bouteiller","year":"2006","unstructured":"Bouteiller, A., Herault, T., Krawezik, G., Lemarinier, P., Cappello, F.: Mpich-v project: A multiprotocol automatic fault-tolerant mpi. International Journal of High Performance Computing Applications\u00a020(3), 319 (2006)","journal-title":"International Journal of High Performance Computing Applications"},{"key":"7_CR8","unstructured":"Li, Y., Lan, Z.: Exploit failure prediction for adaptive fault-tolerance in cluster computing. In: Proceedings of the Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID 2006), May 16-19, 2006, vol.\u00a01, pp. 531\u2013538 (2006)"},{"issue":"12","key":"7_CR9","first-page":"2553","volume":"86","author":"M. Kondo","year":"2003","unstructured":"Kondo, M., Hayashida, T., Imai, M., Nakamura, H., Nanya, T., Hori, A.: Evaluation of checkpointing mechanism on score cluster system. IEICE Transactions on Information and Systems\u00a086(12), 2553\u20132562 (2003)","journal-title":"IEICE Transactions on Information and Systems"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2008 \u2013 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-85451-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T13:23:59Z","timestamp":1589894639000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-85451-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540854500","9783540854517"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-85451-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}