{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T06:00:42Z","timestamp":1761976842210,"version":"build-2065373602"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642452925"},{"type":"electronic","value":"9783642452932"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-45293-2_28","type":"book-chapter","created":{"date-parts":[[2013,11,25]],"date-time":"2013-11-25T13:47:06Z","timestamp":1385387226000},"page":"367-380","source":"Crossref","is-referenced-by-count":2,"title":["Research on Optimum Checkpoint Interval for Hybrid Fault Tolerance"],"prefix":"10.1007","author":[{"given":"Lei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Felix, S., Maren, L., Miroslaw, M.: A Survey of Online Failure Prediction Methods. ACM Computing Surveys 42, Article No. 10 (2010)","DOI":"10.1145\/1670679.1670680"},{"key":"28_CR2","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1177\/1094342009106189","volume":"23","author":"F. Cappello","year":"2009","unstructured":"Cappello, F.: fault tolerance in petascale\/exascale systems: current knowledge, challenges and research opportunities. The International Journal of High Performance Computing Applications\u00a023, 212\u2013226 (2009)","journal-title":"The International Journal of High Performance Computing Applications"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Varela, M.R., Ferreira, K.B., Riesen, R.: Fault-Tolerance for Exascale Systems. In: 2010 IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS), pp. 1\u20134 (2010)","DOI":"10.1109\/CLUSTERWKSP.2010.5613081"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Leonardo, F., Dolores, R., Emilio, L.: What Is Missing in Current Checkpoint Interval Models? In: 2011 International Conference on Distributed Computing Systems, pp. 322\u2013332 (2011)","DOI":"10.1109\/ICDCS.2011.12"},{"key":"28_CR5","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1145\/361147.361115","volume":"17","author":"J.W. Young","year":"1974","unstructured":"Young, J.W.: A first order approximation to the optimum checkpoint interval. Commun. ACM\u00a017, 530\u2013531 (1974)","journal-title":"Commun. ACM"},{"issue":"3","key":"28_CR6","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1177\/1094342004046045","volume":"18","author":"W. Gropp","year":"2004","unstructured":"Gropp, W., Lusk, E.: Fault Tolerance in Message Passing Interface Programs. International Journal of High Performance Computing Applications\u00a018(3), 363\u2013372 (2004)","journal-title":"International Journal of High Performance Computing Applications"},{"key":"28_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/3-540-44864-0_1","volume-title":"Computational Science - ICCS 2003","author":"J. Daly","year":"2003","unstructured":"Daly, J.: A model for predicting the optimum checkpoint interval for restart dumps. In: Sloot, P.M.A., Abramson, D., Bogdanov, A.V., Gorbachev, Y.E., Dongarra, J., Zomaya, A.Y. (eds.) ICCS 2003, Part IV. LNCS, vol.\u00a02660, pp. 3\u201312. Springer, Heidelberg (2003)"},{"key":"28_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"J. Daly","year":"2006","unstructured":"Daly, J.: A higher order estimate of the optimum checkpoint interval for restart dumps. Future Generation Computer Systems\u00a022, 303\u2013312 (2006)","journal-title":"Future Generation Computer Systems"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Avritzer, A., Bondi, A., Grottke, M., Trivedi, K.S., et al.: Performance assurance via software rejuvenation: Monitoring, statistics and algorithms. In: Proc. International Conference on Dependable Systems and Networks, pp. 435\u2013444 (2006)","DOI":"10.1109\/DSN.2006.58"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Gujrati, P., Li, Y., Lan, Z., Thakur, R., et al.: A meta-learning failure predictor for BlueGene\/L systems. In: The 2007 International Conference on Parallel Processing, p. 40 (2007)","DOI":"10.1109\/ICPP.2007.9"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Gu, X., Papadimitriou, S., Yu, P.S., Chang, S.P.: Toward predictive failure management for distributed stream processing systems. In: The 28th International Conference on Distributed Computing Systems, pp. 825\u2013832 (2008)","DOI":"10.1109\/ICDCS.2008.34"},{"key":"28_CR12","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1016\/j.jpdc.2011.10.009","volume":"72","author":"C. Wang","year":"2012","unstructured":"Wang, C., Mueller, F., Engelmann, C., Scott, S.L.: Proactive process-level live migration and back migration in HPC environments. Journal of Parallel and Distributed Computing\u00a072, 254\u2013267 (2012)","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Jangjaimon, I., Tzeng, N.-F.: Adaptive Incremental Checkpointing via Delta Compression for Networked Multicore Systems. In: The 27th IEEE International Symposium on Parallel & Distributed Processing (IPDPS 2013), pp. 7\u201318 (2013)","DOI":"10.1109\/IPDPS.2013.33"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Moody, A., Bronevetsky, G., Mohror, K., de Supinski, B.R.: Design, Modeling, and Evaluation of a Scalable Multi-level Checkpointing System. In: The 2010 International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2010), pp. 1\u201311 (2010)","DOI":"10.1109\/SC.2010.18"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-45293-2_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T23:03:32Z","timestamp":1746054212000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-45293-2_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642452925","9783642452932"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-45293-2_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}