{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:30:41Z","timestamp":1774593041513,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319712543","type":"print"},{"value":"9783319712550","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","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":[[2017]]},"DOI":"10.1007\/978-3-319-71255-0_42","type":"book-chapter","created":{"date-parts":[[2017,11,14]],"date-time":"2017-11-14T14:51:04Z","timestamp":1510671064000},"page":"516-529","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["JobDigest \u2013 Detailed System Monitoring-Based Supercomputer Application Behavior Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2864-7995","authenticated-orcid":false,"given":"Dmitry","family":"Nikitenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2820-7196","authenticated-orcid":false,"given":"Alexander","family":"Antonov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9431-9490","authenticated-orcid":false,"given":"Pavel","family":"Shvets","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3474-8696","authenticated-orcid":false,"given":"Sergey","family":"Sobolev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0930-2713","authenticated-orcid":false,"given":"Konstantin","family":"Stefanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1897-1828","authenticated-orcid":false,"given":"Vadim","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6036-5106","authenticated-orcid":false,"given":"Vladimir","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5770-3071","authenticated-orcid":false,"given":"Sergey","family":"Zhumatiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,11,15]]},"reference":[{"key":"42_CR1","unstructured":"Zenoss. http:\/\/www.zenoss.org . Last accessed 10 May 2017"},{"key":"42_CR2","unstructured":"Zabbix. http:\/\/www.zabbix.com . Last accessed 10 May 2017"},{"key":"42_CR3","unstructured":"Cacti\u00ae. http:\/\/www.cacti.net . Last accessed 10 May 2017"},{"issue":"7","key":"42_CR4","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1016\/j.parco.2004.04.001","volume":"30","author":"ML Massie","year":"2004","unstructured":"Massie, M.L., et al.: The ganglia distributed monitoring system: design, implementation, and experience. Parallel Comput. 30(7), 817\u2013840 (2004)","journal-title":"Parallel Comput."},{"key":"42_CR5","unstructured":"The OpenNMS project. http:\/\/www.opennms.org . Last accessed 10 May 2017"},{"key":"42_CR6","unstructured":"Nagios - the industry standard in IT infrastructure monitoring. http:\/\/www.nagios.org . Last accessed 10 May 2017"},{"key":"42_CR7","unstructured":"Collectd \u2013 The system statistics collection daemon. https:\/\/collectd.org . Last accessed 10 May 2017"},{"key":"42_CR8","doi-asserted-by":"publisher","unstructured":"Stefanov, K.S., Voevodin, Vl.V.: Distributed modular monitoring (DiMMon) approach to supercomputer monitoring. In: Proceedings of the 2015 IEEE International Conference on Cluster Computing, pp. 502\u2013503. IEEE (2015). https:\/\/doi.org\/10.1109\/CLUSTER.2015.83","DOI":"10.1109\/CLUSTER.2015.83"},{"key":"42_CR9","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1016\/j.procs.2015.11.071","volume":"66","author":"KS Stefanov","year":"2015","unstructured":"Stefanov, K.S., Voevodin, Vl.V., Zhumatiy, S.A., Voevodin, Vad.V.: Dynamically reconfigurable distributed modular monitoring system for supercomputers (DiMMon). Procedia Comput. Sci. 66, 625\u2013634 (2015). Elsevier B.V. https:\/\/doi.org\/10.1016\/j.procs.2015.11.071","journal-title":"Procedia Comput. Sci."},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Gunter, D., Tierney, B., Jackson, K., Lee, J., Stoufer, M.: Dynamic monitoring of high-performance distributed applications. In: Proceedings of the 11th IEEE International Symposium on High Performance Distributed Computing, pp. 163\u2013170 (2002)","DOI":"10.1109\/HPDC.2002.1029915"},{"issue":"1","key":"42_CR11","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1015789220266","volume":"23","author":"J Mellor-Crummey","year":"2002","unstructured":"Mellor-Crummey, J., Fowler, R.J., Marin, G., Tallent, N.: HPCVIEW: a tool for top-down analysis of node performance. J. Supercomput. 23(1), 81\u2013104 (2002)","journal-title":"J. Supercomput."},{"key":"42_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1007\/978-3-642-01973-9_77","volume-title":"Computational Science \u2013 ICCS 2009","author":"H Jagode","year":"2009","unstructured":"Jagode, H., Dongarra, J., Alam, S., Vetter, J., Spear, W., Malony, A.D.: A holistic approach for performance measurement and analysis for petascale applications. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009, Part II. LNCS, vol. 5545, pp. 686\u2013695. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-01973-9_77"},{"issue":"6","key":"42_CR13","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/cpe.1553","volume":"22","author":"L Adhianto","year":"2010","unstructured":"Adhianto, L., Banerjee, S., Fagan, M., Krentel, M., Marin, G., Mellor-Crummey, J., Tallent, N.R.: HPCTOOLKIT: tools for performance analysis of optimized parallel programs. Concurrency Comput. Pract. Exp. 22(6), 685\u2013701 (2010)","journal-title":"Concurrency Comput. Pract. Exp."},{"key":"42_CR14","unstructured":"Eisenhauer, G., Kraemer, E., Schwan, K., Stasko, J., Vetter, J., Mallavarupu, N.: Falcon: on-line monitoring and steering of large-scale parallel programs. In: Proceedings of the Fifth Symposium on the Frontiers of Massively Parallel Computation, pp. 422\u2013429 (1995)"},{"key":"42_CR15","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.1016\/j.procs.2012.04.215","volume":"9","author":"M Kluge","year":"2012","unstructured":"Kluge, M., Hackenberg, D., Nagel, W.E.: Collecting distributed performance data with dataheap: generating and exploiting a holistic system view. Procedia Comput. Sci. 9, 1969\u20131978 (2012)","journal-title":"Procedia Comput. Sci."},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Mooney, R., Schmidt, K.P., Studham, R.S.: NWPerf: a system wide performance monitoring tool for large Linux clusters. In: 2004 IEEE International Conference on Cluster Computing (IEEE Cat. No.04EX935), pp. 379\u2013389 (2004)","DOI":"10.1109\/CLUSTR.2004.1392637"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Ries, B., et al.: The paragon performance monitoring environment. In: Proceedings of Supercomputing 1993, pp. 850\u2013859 (1993)","DOI":"10.1145\/169627.169851"},{"key":"42_CR18","first-page":"85","volume":"15","author":"DA Nikitenko","year":"2014","unstructured":"Nikitenko, D.A.: Complex approach to performance analysis of supercomputer systems based on system monitoring data. Numer. Meth. Programm. New Comput. Technol. 15, 85\u201397 (2014)","journal-title":"Numer. Meth. Programm. New Comput. Technol."},{"issue":"2","key":"42_CR19","first-page":"104","volume":"14","author":"AS Antonov","year":"2013","unstructured":"Antonov, A.S., Zhumatiy, S.A., Nikitenko, D.A., Stefanov, K.S., Teplov, A.M., Shvets, P.A.: Analysis of dynamic characteristics of job stream on supercomputer system. Numer. Meth. Program. New Comput. Technol. 14(2), 104\u2013108 (2013)","journal-title":"Numer. Meth. Program. New Comput. Technol."},{"key":"42_CR20","first-page":"160","volume":"13","author":"DA Nikitenko","year":"2012","unstructured":"Nikitenko, D.A., Adinets, A.V., Bryzgalov, P.A., Stefanov, K.S., Voevodin, Vad.V., Zhumatiy, S.A.: Job Digest - approach to analysis of application dynamic characteristics on supercomputer systems. Numer. Meth. Program. New Comput. Technol. 13, 160\u2013166 (2012)","journal-title":"Numer. Meth. Program. New Comput. Technol."},{"key":"42_CR21","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-3-319-32243-8_2","volume-title":"High Performance Computer Applications","author":"V Voevodin","year":"2016","unstructured":"Voevodin, V., Voevodin, V.: Efficiency of exascale supercomputer centers and supercomputing education. In: Gitler, I., Klapp, J. (eds.) ISUM 2015. CCIS, vol. 595, pp. 14\u201323. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-32243-8_2"},{"issue":"2","key":"42_CR22","doi-asserted-by":"publisher","first-page":"72","DOI":"10.14529\/jsfi160205","volume":"3","author":"DA Nikitenko","year":"2016","unstructured":"Nikitenko, D.A., Zhumatiy, S.A., Shvets, P.A.: Making large-scale systems observable \u2014 another inescapable step towards exascale. Supercomput. Front. Innovations 3(2), 72\u201379 (2016). https:\/\/doi.org\/10.14529\/jsfi160205","journal-title":"Supercomput. Front. Innovations"},{"key":"42_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/978-3-319-32149-3_2","volume-title":"Parallel Processing and Applied Mathematics","author":"A Antonov","year":"2016","unstructured":"Antonov, A., Nikitenko, D., Shvets, P., Sobolev, S., Stefanov, K., Voevodin, V., Voevodin, V., Zhumatiy, S.: An approach for ensuring reliable functioning of a supercomputer based on a formal model. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K., Kitowski, J., Wiatr, K. (eds.) PPAM 2015, Part I. LNCS, vol. 9573, pp. 12\u201322. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-32149-3_2"},{"key":"42_CR24","doi-asserted-by":"publisher","unstructured":"Nikitenko, D.A., Voevodin, Vl.V., Zhumatiy, S.A.: Resolving frontier problems of mastering large-scale supercomputer complexes. In: ACM International Conference on Computing Frontiers (CF 2016), Como, Italy, pp. 349\u2013352. ACM, New York, 16\u201318 May 2016. https:\/\/doi.org\/10.1145\/2903150.2903481","DOI":"10.1145\/2903150.2903481"},{"key":"42_CR25","unstructured":"Nikitenko, D.A., Voevodin, Vl.V., Zhumatiy, S.A.: Octoshell: large supercomputer complex administration system. In: Russian Supercomputing Days International Conference, Moscow, Russia. CEUR Workshop Proceedings, vol. 1482, pp. 69\u201383, 28\u201329 September 2015"},{"key":"42_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/978-3-319-49956-7_24","volume-title":"Algorithms and Architectures for Parallel Processing","author":"D Nikitenko","year":"2016","unstructured":"Nikitenko, D., Stefanov, K., Zhumatiy, S., Voevodin, V., Teplov, A., Shvets, P.: System monitoring-based holistic resource utilization analysis for every user of a large HPC center. In: Carretero, J., et al. (eds.) ICA3PP 2016. LNCS, vol. 10049, pp. 305\u2013318. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49956-7_24"},{"key":"42_CR27","unstructured":"Slurm Workload Manager. http:\/\/slurm.schedmd.com . Last accessed 10 May 2017"},{"key":"42_CR28","unstructured":"Clustrx. http:\/\/www.hpcc.unical.it\/hpc2010\/ctrbs\/tkachev.pdf . Last accessed 10 May 2017"},{"key":"42_CR29","unstructured":"JobDigest components. https:\/\/github.com\/srcc-msu\/job_statistics . Last accessed 10 May 2017"},{"key":"42_CR30","unstructured":"Mohr, B., Hagersten, E., Gim\u00e9nez, J., Kn\u00fcpfer, A., Nikitenko, D., Nilsson, M., Servat, H., Shah, A., Voevodin, Vl., Winkler, F., Wolf, F., Zhukov, I.: The HOPSA workflow and tools. In: Proceedings of the 6th International Parallel Tools Workshop, Stuttgart (2012)"},{"key":"42_CR31","first-page":"36","volume":"7","author":"Vl.V. Voevodin","year":"2012","unstructured":"Voevodin, Vl.V., Zhumatiy, S.A., Sobolev, S.I., Antonov, A.S., Bryzgalov, P.A., Nikitenko, D.A., Stefanov, K.S., Voevodin, Vad.V.: Practice of \u201cLomonosov\u201d Supercomputer. Open Systems J. 7, 36\u201339 (2012). Open Systems Publ., Moscow","journal-title":"Open Systems J."},{"key":"42_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-3-319-49956-7_23","volume-title":"Algorithms and Architectures for Parallel Processing","author":"A Antonov","year":"2016","unstructured":"Antonov, A., Teplov, A.: Generalized approach to scalability analysis of parallel applications. In: Carretero, J., et al. (eds.) ICA3PP 2016. LNCS, vol. 10049, pp. 291\u2013304. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49956-7_23"},{"key":"42_CR33","unstructured":"Nikitenko, D.A., Voevodin, Vl.V., Voevodin, Vad.V., Zhumatiy, S.A., Stefanov, K.S., Teplov, A.M., Shvets, P.A.: Supercomputer application integral characteristics analysis for the whole queued job collection of large-scale HPC systems. In: 10th Annual International Scientific Conference on Parallel Computing Technologies, PCT 2016. CEUR Workshop Proceedings, vol. 1576, Arkhangelsk, Russian Federation, pp. 20\u201330, 29\u201331 March 2016"},{"key":"42_CR34","doi-asserted-by":"publisher","unstructured":"Voevodin, Vl.V., Voevodin, Vad.V., Shaikhislamov, D.I., Nikitenko, D.A.: Data mining method for anomaly detection in the supercomputer task flow: numerical computations: theory and algorithms. In: The 2nd International Conference and Summer School, Pizzo calabro, Italy. AIP Conference Proceedings, vol. 1776, pp. 090015-1\u2013090015-4, 20\u201324 June 2016. https:\/\/doi.org\/10.1063\/1.4965379","DOI":"10.1063\/1.4965379"},{"issue":"2","key":"42_CR35","first-page":"48","volume":"14","author":"DYu Andreev","year":"2013","unstructured":"Andreev, D.Yu., Antonov, A.S., Voevodin, Vad.V., Zhumatiy, S.A., Nikitenko, D.A., Stefanov, K.S., Shvets, P.A.: A system for the automated finding of inefficiencies and errors in parallel programs. Numer. Meth. Program. New Comput. Technol. 14(2), 48\u201353 (2013)","journal-title":"Numer. Meth. Program. New Comput. Technol."}],"container-title":["Communications in Computer and Information Science","Supercomputing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-71255-0_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T16:50:29Z","timestamp":1719593429000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-71255-0_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319712543","9783319712550"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-71255-0_42","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}