{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:28:00Z","timestamp":1743049680799,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319321486"},{"type":"electronic","value":"9783319321493"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","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":[[2016]]},"DOI":"10.1007\/978-3-319-32149-3_2","type":"book-chapter","created":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T02:24:42Z","timestamp":1459477482000},"page":"12-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["An Approach for Ensuring Reliable Functioning of a Supercomputer Based on a Formal Model"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Antonov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitry","family":"Nikitenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Shvets","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Sobolev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantin","family":"Stefanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vadim","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Zhumatiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,2]]},"reference":[{"issue":"2","key":"2_CR1","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1177\/1094342014522573","volume":"28","author":"M Snir","year":"2014","unstructured":"Snir, M., Wisniewski, R.W., Abraham, J.A., Adve, S.V., Bagchi, S., Balaji, P., Belak, J., Bose, P., Cappello, F., Carlson, B., Chien, A.A., Coteus, P., Debardeleben, N.A., Diniz, P., Engelmann, C., Erez, M., Fazzari, S., Geist, A., Gupta, R., Johnson, F., Krishnamoorthy, S., Leyffer, S., Liberty, D., Mitra, S., Munson, T.S., Schreiber, R., Stearley, J., Hensbergen, E.V.: Addressing failures in exascale computing. Int. J. High Perform. Comput. Appl. 28(2), 129\u2013173 (2014)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"1","key":"2_CR2","first-page":"5","volume":"1","author":"F Cappello","year":"2014","unstructured":"Cappello, F., Geist, F., Gropp, W., Kale, S., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput. Front. Innovations 1(1), 5\u201328 (2014)","journal-title":"Supercomput. Front. Innovations"},{"key":"2_CR3","unstructured":"HP, BTO Software (part of HP Software Division). http:\/\/www8.hp.com\/us\/en\/software\/enterprise-software.html"},{"key":"2_CR4","unstructured":"Ford, E., Elkin, B., Denham, S., Khoo, B., Bohnsack, M., Turcksin, C., Ferreira, L.: Building a Linux HPC Cluster with xCAT. An IBM Redbooks Publication. http:\/\/www.redbooks.ibm.com\/abstracts\/sg246623.html?Open"},{"key":"2_CR5","unstructured":"Nagios monitoring system description. http:\/\/www.nagios.org\/"},{"key":"2_CR6","unstructured":"Zabbix system. http:\/\/www.zabbix.com\/"},{"issue":"7","key":"2_CR7","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1016\/j.parco.2004.04.001","volume":"30","author":"ML Massie","year":"2004","unstructured":"Massie, M.L., Chun, B.N., Culler, D.E.: The ganglia distributed monitoring system: design, implementation, and experience. Parallel Comput. 30(7), 817\u2013840 (2004)","journal-title":"Parallel Comput."},{"key":"2_CR8","unstructured":"Zenoss - Open Source Network Monitoring and Systems Management. http:\/\/www.zenoss.org\/"},{"key":"2_CR9","unstructured":"Clustrx SAFE (AESS) software. http:\/\/www.t-platforms.com\/products\/hpc\/software\/clustrxproductfamily\/clustrx-safe.html"},{"issue":"3","key":"2_CR10","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1007\/s11704-014-3503-1","volume":"8","author":"K Lu","year":"2014","unstructured":"Lu, K., Wang, X., Li, G., et al.: Iaso: an autonomous fault-tolerant management system for supercomputers. Front. Comput. Sci. 8(3), 378\u2013390 (2014)","journal-title":"Front. Comput. Sci."},{"key":"2_CR11","unstructured":"Antonov, A.S., Vad, V., Voevodin Vl, V., Voevodin, S.A. Zhumatiy, D.A. Nikitenko, S.I. Sobolev, K.S. Stefanov, P.A. Shvets: Securing of reliable, efficient autonomous functioning of supercomputers: basic principles and system prototype. Vestnik UGATU (Scientific Journal of Ufa State Aviation Technical University) 18(2(63)), 227\u2013236 (2014)"},{"key":"2_CR12","unstructured":"Octotron core repository. https:\/\/github.com\/srcc-msu\/octotron_core"},{"key":"2_CR13","unstructured":"Octotron framework: modeling and monitoring of complex computer systems. https:\/\/github.com\/srcc-msu\/octotron"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-32149-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T01:06:01Z","timestamp":1607994361000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-32149-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319321486","9783319321493"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-32149-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"2 April 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}