{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:51:33Z","timestamp":1774590693157,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319499550","type":"print"},{"value":"9783319499567","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-49956-7_24","type":"book-chapter","created":{"date-parts":[[2016,11,18]],"date-time":"2016-11-18T09:01:20Z","timestamp":1479459680000},"page":"305-318","source":"Crossref","is-referenced-by-count":8,"title":["System Monitoring-Based Holistic Resource Utilization Analysis for Every User of a Large HPC Center"],"prefix":"10.1007","author":[{"given":"Dmitry","family":"Nikitenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantin","family":"Stefanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Zhumatiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vadim","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Teplov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Shvets","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,19]]},"reference":[{"key":"24_CR1","unstructured":"Voevodin, V., Stefanov, K.: Supercomputers at exascale: bigdata and extreme computing of the total monitoring. In: BDEC Workshop, Barcelona, 29-30 January (2015)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Stefanov, K., Voevodin, 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)","DOI":"10.1109\/CLUSTER.2015.83"},{"key":"24_CR3","unstructured":"Zenoss. http:\/\/www.zenoss.org"},{"key":"24_CR4","unstructured":"Zabbix. http:\/\/www.zabbix.com"},{"key":"24_CR5","unstructured":"Cacti\u00ae. http:\/\/www.cacti.net"},{"issue":"7","key":"24_CR6","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":"24_CR7","unstructured":"The OpenNMS project. http:\/\/www.opennms.org"},{"key":"24_CR8","unstructured":"Nagios - the industry standard in IT infrastructure monitoring. http:\/\/www.nagios.org"},{"key":"24_CR9","unstructured":"Collectd \u2013 The system statistics collection daemon. https:\/\/collectd.org"},{"key":"24_CR10","unstructured":"Nikitenko, D.: Complex approach to performance analysis of supercomputer systems based on system monitoring data. In: Numerical Methods and Programming vol. 15, pp. 85\u201397 (2014)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Gunter, D., Tierney, B., Jackson, K., Lee, J., Stoufer, M.: Dynamic monitoring of high-performance distributed applications. In: Proceedings 11th IEEE International Symposium on High Performance Distributed Computing, pp. 163\u2013170 (2002)","DOI":"10.1109\/HPDC.2002.1029915"},{"issue":"1","key":"24_CR12","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":"24_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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. (eds.) ICCS 2009, Part II. LNCS, vol. 5545, pp. 686\u2013695. Springer, Heidelberg (2009)"},{"issue":"6","key":"24_CR14","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":"24_CR15","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":"24_CR16","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":"24_CR17","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":"24_CR18","doi-asserted-by":"crossref","unstructured":"Ries, B., et al.: The paragon performance monitoring environment. In: Supercomputing 1993, Proceedings, pp. 850\u2013859 (1993)","DOI":"10.1145\/169627.169851"},{"key":"24_CR19","unstructured":"Joint RF-EU HOPSA Project. http:\/\/www.vi-hps.org\/projects\/hopsa\/overview"},{"key":"24_CR20","unstructured":"Open Trace Format (OTF2). https:\/\/silc.zih.tu-dresden.de\/otf2-current\/html"},{"key":"24_CR21","unstructured":"Mohr, B., Hagersten, E., Gim\u00e9nez, J., Kn\u00fcpfer, A., Nikitenko, D., Nilsson, M., Servat, H., Shah, A., Voevodin, V., Winkler, F., Wolf, F., Zhukov, I.: The HOPSA workflow and tools. In: Proceedings of the 6th International Parallel Tools Workshop, Stuttgart, September 2012"},{"key":"24_CR22","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. LNCS, vol. 9573, pp. 12\u201322. Springer, Heidelberg (2016). doi: 10.1007\/978-3-319-32149-3_2"},{"key":"24_CR23","unstructured":"Adinets, A., Bryzgalov, P., Nikitenko, D., Stefanov, K., Voevodin, V., Zhumatiy, S.: Job digest: an approach to dynamic analysis of job characteristics on supercomputers. In: Numerical Methods and Programming: Advanced Computing, vol. 13. Sect. 2, pp. 160\u2013166 (2012)"},{"key":"24_CR24","unstructured":"Nikitenko, D., Voevodin, V., Zhumatiy, S., Stefanov, K., Teplov, A., Shvets, P., Voevodin, V.: Supercomputer application integral characteristics analysis for the whole queued job collection of large-scale HPC systems. In: Parallel Computational Technologies (PCT 2016): Proceedings of the International Scientific Conference. Chelyabinsk, Publishing of the South Ural State University, pp. 20\u201330 (2016)"},{"key":"24_CR25","unstructured":"Nikitenko, D., Voevodin, V., Zhumatiy, S.: Octoshell: large supercomputer complex administration system. In: proceedings of Russian Supercomputing Days International Conference, Moscow, Russia, 28-29 September 2015, Proceedings, CEUR Workshop Proceedings, vol. 1482, pp. 69\u201383 (2015)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Nikitenko, D., et al.: Resolving frontier problems of mastering large-scale supercomputer complexes. In: Proceedings of the ACM International Conference on Computing Frontiers (CF 2016), pp. 349\u2013352. ACM, New York (2016)","DOI":"10.1145\/2903150.2903481"},{"key":"24_CR27","unstructured":"Slurm Workload Manager. http:\/\/slurm.schedmd.com"},{"key":"24_CR28","unstructured":"Cleo cluster batch system. http:\/\/sourceforge.net\/projects\/cleo-bs"},{"key":"24_CR29","unstructured":"Clustrx. http:\/\/t-platforms.ru\/products\/software\/clustrxproductfamily\/clustrxwatch.html"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Voevodin, V., Voevodin, V., Shaikhislamov, D., Nikitenko, D.: Data mining method for anomaly detection in the supercomputer task flow. In: proceedings of Numerical Computations: Theory and Algorithms, The 2nd International Conference and Summer School, 20-24 June 2016, Pizzo calabro, Italy (2016)","DOI":"10.1063\/1.4965379"},{"key":"24_CR31","unstructured":"Description of random forest algorithm and its realization. http:\/\/scikit-learn.org\/stable\/modules\/ensemble.html#random-forests"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49956-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:50:11Z","timestamp":1718905811000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-49956-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319499550","9783319499567"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49956-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}