Abstract
The holy-grail of large complex storage systems in enterprises today is for these systems to be self-governing. We propose a self-tuning scheme for large storage filers, on which very little work has been done in the past. Our system uses the performance counters generated by a filer to assess its health in real-time and modify the workload and/or tune the system parameters for optimizing the operational metrics. We use a Pruned Random Forest based solution to predict overload in real-time — the model is run on every snapshot of counter values. Large number of trees in a random forest model has an immediate adverse effect on the time to take a decision. A large random forest is therefore not viable in a real-time scenario. Our solution uses a pruned random forest that performs as well as the original forest. A saliency analysis is carried out to identify components of the system that require tuning in case an overload situation is predicted. This allows us to initiate some ‘action’ on the bottleneck components. The ‘action’ we have explored in our experiments is ‘throttling’ the bottleneck component to prevent overload situations.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Almuallim, H., Dietterich, T.G.: Learning boolean concepts in the presence of many irrelevant features. Artif. Intell. 69(1–2), 279–305 (1994)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Contributions, M.K.: caret: Classification and Regression Training, r package version 5.15-044 (2012)
Dheenadayalan, K., Muralidhara, V.N., Datla, P., Srinivasaraghavan, G., Shah, M.: Premonition of storage response class using skyline ranked ensemble method. In: 2014 21st International Conference on High Performance Computing (HiPC), pp. 1–10, December 2014
Dheenadayalan, K., Srinivasaraghavan, G., Muralidhara, V.N.: Pruning a random forest by learning a learning algorithm. MLDM 2016. LNCS (LNAI), vol. 9729, pp. 516–529. Springer, Cham (2016). doi:10.1007/978-3-319-41920-6_41
Fawagreh, K., Gaber, M.M., Elyan, E.: On extreme pruning of random forest ensembles for real-time predictive applications. CoRR abs/1503.04996 (2015)
Ganapathi, A.S.: Predicting and Optimizing System Utilization and Performance via Statistical Machine Learning. Ph.D. thesis, EECS Department, University of California, Berkeley, December 2009
Ganger, G.R., Strunk, J.D., Klosterman, A.J.: Self-*storage: Brick-based storage with automated administration. Technical report, Carnegie Mellon University, School of Computer Science, Technical report (2003)
Ghemawat, S., Gobioff, H., Leung, S.T.: The google file system. In: Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles, pp. 29–43. ACM (2003)
Hall, M.A.: Correlation-based feature selection for discrete and numeric class machine learning. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 359–366. Morgan Kaufmann Publishers Inc. (2000)
Hamerly, G., Elkan, C.: Bayesian approaches to failure prediction for disk drives, pp. 202–209. Morgan Kaufmann Publishers Inc. (2001)
Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artif. Intell. 97(1–2), 273–324 (1997)
Lee, E.K.: Performance Modeling and Analysis of Disk Arrays. Ph.D. thesis, EECS Department, University of California, Berkeley, August 1993
Liaw, A., Wiener, M.: Classification and regression by randomforest. R News 2(3), 18–22 (2002)
Martinez-Munoz, G., Hernandez-Lobato, D., Suarez, A.: An analysis of ensemble pruning techniques based on ordered aggregation. IEEE Trans. Patt. Anal. Mach. Intell. 31(2), 245–259 (2009)
Murray, J.F., Hughes, G.F., Kreutz-Delgado, K.: Machine learning methods for predicting failures in hard drives: a multiple-instance application. J. Mach. Learn. Res. 6, 783–816 (2005)
NetApp Inc.: Managing workload performance by using storage qos. https://library.netapp.com/ecmdocs/ECMP1196798/html/GUID-660A6C00-6D7E-4EE5-B97E-9D33C0B706B5.html
Opitz, D.W.: Feature selection for ensembles. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence, pp. 379–384. American Association for Artificial Intelligence (1999)
Pollack, K.T., Uttamchandani, S.M.: Genesis: a scalable self-evolving performance management framework for storage systems. In: 26th IEEE International Conference on Distributed Computing Systems, p. 33 (2006)
Powers, D.M.W.: Evaluation: from precision, recall and f-measure to roc., informedness, markedness & correlation. J. Mach. Learn. Technol. 2(1), 37–63 (2011)
Schwing, A.G., Zach, C., Zheng, Y., Pollefeys, M.: Adaptive random forest - how many “experts” to ask before making a decision? In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1377–1384. IEEE Computer Society (2011)
Tamon, C., Xiang, J.: On the boosting pruning problem. In: López de Mántaras, R., Plaza, E. (eds.) ECML 2000. LNCS (LNAI), vol. 1810, pp. 404–412. Springer, Heidelberg (2000). doi:10.1007/3-540-45164-1_41
Tang, H., Gulbeden, A., Zhou, J., Strathearn, W., Yang, T., Chu, L.: A self-organizing storage cluster for parallel data-intensive applications. In: Proceedings of the 2004 ACM/IEEE Conference on Supercomputing, p. 52. IEEE Computer Society (2004)
Tsoumakas, G., Partalas, I., Vlahavas, I.: An ensemble pruning primer. In: Okun, O., Valentini, G. (eds.) Applications of Supervised and Unsupervised Ensemble Methods. SCI, vol. 245, pp. 1–13. Springer, Heidelberg (2009). doi:10.1007/978-3-642-03999-7_1
Zhu, Y., Jiang, H., Wang, J., Xian, F.: Hba: distributed metadata management for large cluster based storage systems. IEEE Trans. Parallel Distrib. Syst. 19(6), 750–763 (2008)
Acknowledgments
This research work was partially funded by NetApp Inc. The views and conclusions contained herein are those of the authors only.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Dheenadayalan, K., Srinivasaraghavan, G., Muralidhara, V.N. (2017). Self-tuning Filers — Overload Prediction and Preventive Tuning Using Pruned Random Forest. In: Kim, J., Shim, K., Cao, L., Lee, JG., Lin, X., Moon, YS. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2017. Lecture Notes in Computer Science(), vol 10235. Springer, Cham. https://doi.org/10.1007/978-3-319-57529-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-319-57529-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57528-5
Online ISBN: 978-3-319-57529-2
eBook Packages: Computer ScienceComputer Science (R0)