{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:13:21Z","timestamp":1769850801792,"version":"3.49.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319920399","type":"print"},{"value":"9783319920405","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-319-92040-5_10","type":"book-chapter","created":{"date-parts":[[2018,5,28]],"date-time":"2018-05-28T07:55:05Z","timestamp":1527494105000},"page":"184-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Machine Learning Based Parallel I\/O Predictive Modeling: A Case Study on Lustre File Systems"],"prefix":"10.1007","author":[{"given":"Sandeep","family":"Madireddy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prasanna","family":"Balaprakash","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Carns","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Latham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Ross","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shane","family":"Snyder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan M.","family":"Wild","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,29]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Barker, K.J., Davis, K., Kerbyson, D.J.: Performance modeling in action: performance prediction of a Cray XT4 system during upgrade. In: International Symposium on Parallel & Distributed Processing, pp. 1\u20138. IEEE (2009)","DOI":"10.1109\/IPDPS.2009.5161098"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Behzad, B., Byna, S., Wild, S.M., Prabhat, M., Snir, M.: Improving parallel I\/O autotuning with performance modeling. In: 23rd International Symposium on High-Performance Parallel and Distributed Computing, pp. 253\u2013256. ACM (2014)","DOI":"10.1145\/2600212.2600708"},{"key":"10_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/978-3-319-67630-2_15","volume-title":"High Performance Computing","author":"E Betke","year":"2017","unstructured":"Betke, E., Kunkel, J.: Real-time I\/O-monitoring of HPC applications with SIOX, elasticsearch, Grafana and FUSE. In: Kunkel, J.M., Yokota, R., Taufer, M., Shalf, J. (eds.) ISC High Performance 2017. LNCS, vol. 10524, pp. 174\u2013186. Springer, Cham (2017). \nhttps:\/\/doi.org\/10.1007\/978-3-319-67630-2_15"},{"key":"10_CR4","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)"},{"key":"10_CR5","unstructured":"Cao, Z., Tarasov, V., Raman, H.P., Hildebrand, D., Zadok, E.: On the performance variation in modern storage stacks. In: FAST, pp. 329\u2013344 (2017)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794. ACM (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"10_CR7","unstructured":"DOE-ASCR: storage systems and input\/output to support extreme scale science. In: DOE Workshops on Storage Systems and Input\/Output (2014)"},{"issue":"3","key":"10_CR8","doi-asserted-by":"publisher","first-page":"15:1","DOI":"10.1145\/2987371","volume":"3","author":"M Dorier","year":"2016","unstructured":"Dorier, M., Antoniu, G., Cappello, F., Snir, M., Sisneros, R., Yildiz, O., Ibrahim, S., Peterka, T., Orf, L.: Damaris: addressing performance variability in data management for post-petascale simulations. ACM Trans. Parallel Comput. 3(3), 15:1\u201315:43 (2016)","journal-title":"ACM Trans. Parallel Comput."},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Dorier, M., Antoniu, G., Ross, R., Kimpe, D., Ibrahim, S.: CALCioM: mitigating I\/O interference in HPC systems through cross-application coordination. In: 28th International Parallel and Distributed Processing Symposium, pp. 155\u2013164. IEEE (2014)","DOI":"10.1109\/IPDPS.2014.27"},{"key":"10_CR10","unstructured":"Feroz, F., Hobson, M., Cameron, E., Pettitt, A.: Importance nested sampling and the MultiNest algorithm. arXiv preprint \narXiv:1306.2144\n\n (2013)"},{"key":"10_CR11","volume-title":"Bayesian Data Analysis","author":"A Gelman","year":"2014","unstructured":"Gelman, A., Carlin, J.B., Stern, H.S., Dunson, D.B., Vehtari, A., Rubin, D.B.: Bayesian Data Analysis, 2nd edn. CRC Press, Boca Raton (2014)","edition":"2"},{"issue":"1","key":"10_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3\u201342 (2006)","journal-title":"Mach. Learn."},{"key":"10_CR13","unstructured":"Geurts, P., Louppe, G.: Learning to rank with extremely randomized trees. In: JMLR: Workshop and Conference Proceedings, vol. 14, pp. 49\u201361 (2011)"},{"key":"10_CR14","unstructured":"Gulati, A., Merchant, A., Varman, P.J.: mClock: handling throughput variability for hypervisor IO scheduling. In: 9th USENIX Conference on Operating Systems Design and Implementation, pp. 437\u2013450. USENIX Association (2010)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Habib, S., Morozov, V., Finkel, H., Pope, A., Heitmann, K., Kumaran, K., Peterka, T., Insley, J., Daniel, D., Fasel, P., et al.: The universe at extreme scale: multi-petaflop sky simulation on the BG\/Q. In: International Conference on High Performance Computing, Networking, Storage and Analysis, p. 4. IEEE (2012)","DOI":"10.1109\/SC.2012.106"},{"key":"10_CR16","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1016\/j.procs.2017.05.026","volume":"108","author":"EC Inacio","year":"2017","unstructured":"Inacio, E.C., Barbetta, P.A., Dantas, M.A.: A statistical analysis of the performance variability of read\/write operations on parallel file systems. Procedia Comput. Sci. 108, 2393\u20132397 (2017)","journal-title":"Procedia Comput. Sci."},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Isaila, F., Balaprakash, P., Wild, S.M., Kimpe, D., Latham, R., Ross, R., Hovland, P.: Collective I\/O tuning using analytical and machine learning models. In: International Conference on Cluster Computing, pp. 128\u2013137. IEEE (2015)","DOI":"10.1109\/CLUSTER.2015.29"},{"issue":"2","key":"10_CR18","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1023\/A:1007665907178","volume":"37","author":"MI Jordan","year":"1999","unstructured":"Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K.: An introduction to variational methods for graphical models. Mach. Learn. 37(2), 183\u2013233 (1999)","journal-title":"Mach. Learn."},{"key":"10_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-319-20119-1_19","volume-title":"High Performance Computing","author":"J Kunkel","year":"2015","unstructured":"Kunkel, J., Zimmer, M., Betke, E.: Predicting performance of non-contiguous I\/O with machine learning. In: Kunkel, J.M., Ludwig, T. (eds.) ISC High Performance 2015. LNCS, vol. 9137, pp. 257\u2013273. Springer, Cham (2015). \nhttps:\/\/doi.org\/10.1007\/978-3-319-20119-1_19"},{"key":"10_CR20","unstructured":"Kuo, C.S., Nomura, A., Matsuoka, S., Shah, A., Wolf, F., Zhukov, I.: Environment matters: how competition for I\/O among applications degrades their performance. IPSJ SIG Technical report 2013-HPC-142(11), 1\u20137 (2013)"},{"issue":"1","key":"10_CR21","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1145\/166962.166994","volume":"21","author":"Edward K. Lee","year":"1993","unstructured":"Lee, E.K., Katz, R.H.: An analytic performance model of disk arrays. In: ACM SIGMETRICS Performance Evaluation Review, vol. 21, pp. 98\u2013109. ACM (1993)","journal-title":"ACM SIGMETRICS Performance Evaluation Review"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Lockwood, G.K., Snyder, S., Yoo, W., Harms, K., Nault, Z., Byna, S., Carns, P., Wright, N.J.: UMAMI: a recipe for generating meaningful metrics through holistic I\/O performance analysis. In: 2nd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems (PDSW-DISCS 2017) (2017)","DOI":"10.1145\/3149393.3149395"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Lofstead, J., Zheng, F., Liu, Q., Klasky, S., Oldfield, R., Kordenbrock, T., Schwan, K., Wolf, M.: Managing variability in the IO performance of petascale storage systems. In: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312. IEEE (2010)","DOI":"10.1109\/SC.2010.32"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Madireddy, S., Balaprakash, P., Carns, P., Latham, R., Ross, R., Snyder, S., Wild, S.M.: Analysis and correlation of application I\/O performance and system-wide I\/O activity. In: International Conference on Networking, Architecture, and Storage, pp. 1\u201310. IEEE (2017)","DOI":"10.1109\/NAS.2017.8026844"},{"key":"10_CR25","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18, 50\u201360 (1947)","journal-title":"Ann. Math. Stat."},{"issue":"40","key":"10_CR26","first-page":"1","volume":"18","author":"AGDG Matthews van der","year":"2017","unstructured":"van der Matthews, A.G.D.G., Wilk, M., Nickson, T., Fujii, K., Boukouvalas, A., Le\u00f3n-Villagr\u00e1, P., Ghahramani, Z., Hensman, J.: GPflow: a gaussian process library using TensorFlow. J. Mach. Learn. Res. 18(40), 1\u20136 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR27","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Snyder, S., Carns, P., Harms, K., Ross, R., Lockwood, G.K., Wright, N.J.: Modular HPC I\/O characterization with Darshan. In: Workshop on Extreme-Scale Programming Tools (2016)","DOI":"10.1109\/ESPT.2016.006"},{"issue":"5","key":"10_CR29","doi-asserted-by":"publisher","first-page":"2069","DOI":"10.1007\/s11227-016-1904-7","volume":"73","author":"SW Son","year":"2017","unstructured":"Son, S.W., Sehrish, S., Liao, W., Oldfield, R., Choudhary, A.: Reducing I\/O variability using dynamic I\/O path characterization in petascale storage systems. J. Supercomput. 73(5), 2069\u20132097 (2017)","journal-title":"J. Supercomput."},{"key":"10_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1494-6","volume-title":"Interpolation of Spatial Data: Some Theory for Kriging","author":"ML Stein","year":"2012","unstructured":"Stein, M.L.: Interpolation of Spatial Data: Some Theory for Kriging. Springer, New York (2012). \nhttps:\/\/doi.org\/10.1007\/978-1-4612-1494-6"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Xie, B., Huang, Y., Chase, J.S., Choi, J.Y., Klasky, S., Lofstead, J., Oral, S.: Predicting output performance of a petascale supercomputer. In: 26th International Symposium on High-Performance Parallel and Distributed Computing, pp. 181\u2013192. ACM, New York (2017)","DOI":"10.1145\/3078597.3078614"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Yildiz, O., Dorier, M., Ibrahim, S., Ross, R., Antoniu, G.: On the root causes of cross-application I\/O interference in HPC storage systems. In: International Parallel and Distributed Processing Symposium, pp. 750\u2013759. IEEE (2016)","DOI":"10.1109\/IPDPS.2016.50"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92040-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,5,28]],"date-time":"2018-05-28T07:58:55Z","timestamp":1527494335000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92040-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319920399","9783319920405"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92040-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}