Gabriele Mencagli
Skip Abstract Section
Abstract
Adaptiveness in distributed parallel applications is a key feature to provide satisfactory performance results in the face of unexpected events such as workload variations and time-varying user requirements. The adaptation process is based on the ability to change specific characteristics of parallel components (e.g., their parallelism degree) and to guarantee that such modifications of the application configuration are effective and durable. Reconfigurations often incur a cost on the execution (a performance overhead and/or an economic cost). For this reason advanced adaptation strategies have become of paramount importance. Effective strategies must achieve properties like control optimality (making decisions that optimize the global application QoS), reconfiguration stability expressed in terms of the average time between consecutive reconfigurations of the same component, and optimizing the reconfiguration amplitude (number of allocated/deallocated resources). To control such parameters, in this article we propose a method based on a Cooperative Model-based Predictive Control approach in which application controllers cooperate to make optimal reconfigurations and taking account of the durability and amplitude of their control decisions. The effectiveness and the feasibility of the methodology is demonstrated through experiments performed in a simulation environment and by comparing it with other existing techniques.
- Abdelwahed, S., Kandasamy, N., and Neema, S. 2004. Online control for self-management in computing systems. In Proceedings of the 10th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS’04). 368--375. Google Scholar
Digital Library
- Abdelwahed, S., Bai, J., Su, R., and Kandasamy, N. 2009. On the application of predictive control techniques for adaptive performance management of computing systems. IEEE Trans. Netw. Serv. Manage. 6, 4, 212--225. Google ScholarDigital Library
- Aldinucci, M., Danelutto, M., and Vanneschi, M. 2006. Autonomic qos in assist grid-aware components. In Proceedings of the 14th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP’06). IEEE, 221--230. Google ScholarDigital Library
- Aldinucci, M., Campa, S., Danelutto, M., and Vanneschi, M. 2008. Behavioural skeletons in gcm: Autonomic management of grid components. In Proceedings of the Euromicro International Conference on Parallel, Distributed and Network-Based Processing. 54--63. Google ScholarDigital Library
- Aldinucci, M., Danelutto, M., and Kilpatrick, P. 2009. Towards hierarchical management of autonomic components: A case study. In Proceedings of the 17th Euromicro International Conference on Parallel, Distributed and Network-Based Processing. 3--10. Google ScholarDigital Library
- Arshad, N., Heimbigner, D., and Wolf, A. L. 2007. Deployment and dynamic reconfiguration planning for distributed software systems. Softw. Quality Control 15, 3, 265--281. Google ScholarDigital Library
- Balsamo, S. 2011. Queueing networks with blocking: Analysis, solution algorithms and properties. In Network Performance Engineering. Springer, 233--257. Google ScholarDigital Library
- Bertolli, C., Mencagli, G., and Vanneschi, M. 2011. Consistent reconfiguration protocols for adaptive high-performance applications. In Proceedings of the 7th International Wireless Communications and Mobile Computing Conference. 2121--2126.Google Scholar
- Cole, M. 2004. Bringing skeletons out of the closet: A pragmatic manifesto for skeletal parallel programming. Parallel Comput. 30, 3, 389--406. Google ScholarDigital Library
- Coppola, M., Danelutto, M., Tonellotto, N., Vanneschi, M., and Zoccolo, C. 2007. Execution support of high performance heterogeneous component-based applications on the grid. In Proceedings of the CoreGRID, UNICORE Summit, Petascale Computational Biology and Bioinformatics Conference on Parallel Processing (Euro-Par’06). Springer, 171--185. Google ScholarDigital Library
- Costa, R., Brasileiro, F., Lemos, G., and Sousa, D. 2013. Analyzing the impact of elasticity on the profit of cloud computing providers. Future Generation Computer Syst. 29, 7. Google ScholarDigital Library
- Garcia, C. E., Prett, D. M., and Morari, M. 1989. Model predictive control: Theory and practice a survey. Automatica 25, 335--348. Google ScholarDigital Library
- Gelper, S., Fried, R., and Croux, C. 2010. Robust forecasting with exponential and Holt-Winters smoothing. J. Forecasting 29, 3, 285--300.Google Scholar
- Ghanbari, H., Simmons, B., Litoiu, M., and Iszlai, G. 2011. Exploring alternative approaches to implement an elasticity policy. In Proceedings of the IEEE International Conference on Cloud Computing. 716--723. Google ScholarDigital Library
- Gomes, A. T. A., Batista, T. V., Joolia, A., and Coulson, G. 2007. Architecting dynamic reconfiguration in dependable systems. In Architecting Dependable Systems IV, Springer, 237--261. Google ScholarDigital Library
- Hellerstein, J. L., Diao, Y., Parekh, S., and Tilbury, D. M. 2004. Feedback Control of Computing Systems. John Wiley & Sons. Google ScholarDigital Library
- Horvath, T., Abdelzaher, T., Skadron, K., and Liu, X. 2007. Dynamic voltage scaling in multitier web servers with end-to-end delay control. IEEE Trans. Comput. 56, 4, 444--458. Google ScholarDigital Library
- Kandasamy, N., Abdelwahed, S., and Khandekar, M. 2006. A hierarchical optimization framework for autonomic performance management of distributed computing systems. In Proceedings of the 26th IEEE International Conference on Distributed Computing Systems (ICDCS’06). 9. Google ScholarDigital Library
- Kephart, J. and Walsh, W. 2004. An artificial intelligence perspective on autonomic computing policies. In Proceedings of the 5th IEEE International Workshop on Policies for Distributed Systems and Networks (POLICY’04). 3--12. Google ScholarDigital Library
- Khan, A., Yan, X., Tao, S., and Anerousis, N. 2012. Workload characterization and prediction in the cloud: A multiple time series approach. In Proceedings of the IEEE Network Operations and Management Symposium. 1287--1294.Google Scholar
- Khargharia, B., Hariri, S., and Yousif, M. S. 2008. Autonomic power and performance management for computing systems. Cluster Comput. 11, 2, 167--181. Google ScholarDigital Library
- Kusic, D. and Kandasamy, N. 2007. Risk-aware limited lookahead control for dynamic resource provisioning in enterprise computing systems. Cluster Comput. 10, 4, 395--408. Google ScholarDigital Library
- Kusic, D., Kandasamy, N., and Jiang, G. 2011. Combined power and performance management of virtualized computing environments serving session-based workloads. IEEE Trans. Netw. Serv. Manage. 8, 3, 245--258.Google ScholarCross Ref
- Lee, H., Bouhchouch, A., Dallery, Y., and Frein, Y. 1998. Performance evaluation of open queueing networks with arbitrary configuration and finite buffers. Ann. Operations Research 79, 181--206.Google ScholarCross Ref
- Lee, H.-S. and Pollock, S. M. 1991. Approximation analysis of open acyclic exponential queueing networks with blocking. Oper. Res. 38, 6, 1123--1134. Google ScholarDigital Library
- Lisani, J.-L., Rudin, L., Monasse, P., Morel, J. M., and Yu, P. 2005. Meaningful automatic video demultiplexing with unknown number of cameras, contrast changes, and motion. In Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS’05). 604--608.Google Scholar
- Liu, H. and Parashar, M. 2006. Accord: A programming framework for autonomic applications. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 36, 3, 341--352. Google ScholarDigital Library
- Lobel, I. and Ozdaglar, A. 2011. Distributed subgradient methods for convex optimization over random networks. IEEE Trans. Autom. Control 56, 6, 1291--1306.Google ScholarCross Ref
- Loesing, S., Hentschel, M., Kraska, T., and Kossmann, D. 2012. Stormy: An elastic and highly available streaming service in the cloud. In Proceedings of the Joint EDBT/ICDT Workshops (EDBT-ICDT’12). ACM, New York, 55--60. Google ScholarDigital Library
- Loureiro, E., Nixon, P., and Dobson, S. 2012. Decentralized and optimal control of shared resource pools. ACM Trans. Auton. Adapt. Syst. 7, 1, 14:1--14:31. Google ScholarDigital Library
- Maggio, M., Hoffmann, H., Papadopoulos, A. V., Panerati, J., Santambrogio, M. D., Agarwal, A., and Leva, A. 2012. Comparison of decision-making strategies for self-optimization in autonomic computing systems. ACM Trans. Auton. Adapt. Syst. 7, 4, 36:1--36:32. Google ScholarDigital Library
- Meiländer, D., Ploss, A., Glinka, F., and Gorlatch, S. 2012. A dynamic resource management system for real-time online applications on clouds. In Proceedings of the International Conference on Parallel Processing (Euro-Par’11). Springer, 149--158. Google ScholarDigital Library
- Mencagli, G. 2012. A control-theoretic methodology for controlling adaptive structured parallel computations. Ph.D. thesis, Department of Computer Science, University of Pisa, Italy.Google Scholar
- Mencagli, G. and Vanneschi, M. 2011. Qos-control of structured parallel computations: A predictive control approach. In Proceedings of the IEEE 3rd International Conference on Cloud Computing Technology and Science (CLOUDCOM’11). IEEE, 296--303. Google ScholarDigital Library
- Mencagli, G. and Vanneschi, M. 2013. Analysis of control-theoretic predictive strategies for the adaptation of distributed parallel computations. In Proceedings of the 1st ACM Workshop on Optimization Techniques for Resources Management in Clouds (ORMaCloud’13). ACM, New York, 33--40. Google ScholarDigital Library
- Mencagli, G., Vanneschi, M., and Vespa, E. 2013a. Control-theoretic adaptation strategies for autonomic reconfigurable parallel applications on cloud environments. In Proceedings of the International Conference on High Performance Computing and Simulation. 11--18.Google Scholar
- Mencagli, G., Vanneschi, M., and Vespa, E. 2013b. Reconfiguration stability of adaptive distributed parallel applications through a cooperative predictive control approach. In Proceedings of the 19th International Conference on Parallel Processing (Euro-Par’13). Springer, 329--340. Google ScholarDigital Library
- Nedic, A. and Ozdaglar, A. 2009. Distributed subgradient methods for multi-agent optimization. IEEE Trans. Autom. Control 54, 1, 48--61.Google ScholarCross Ref
- Park, S.-M. and Humphrey, M. 2011. Predictable high-performance computing using feedback control and admission control. IEEE Trans. Parallel Distrib. Syst. 22, 3, 396--411. Google ScholarDigital Library
- Quiroz, A., Kim, H., Parashar, M., Gnanasambandam, N., and Sharma, N. 2009. Towards autonomic workload provisioning for enterprise grids and clouds. In Proceedings of the 10th IEEE/ACM International Conference on Grid Computing. 50--57.Google Scholar
- Raghavendra, R., Ranganathan, P., Talwar, V., Wang, Z., and Zhu, X. 2008. No ‘power’ struggles: Coordinated multi-level power management for the data center. SIGOPS Oper. Syst. Rev. 42, 2, 48--59. Google ScholarDigital Library
- Ram, S. S., Nedic, A., and Veeravalli, V. V. 2009. Distributed subgradient projection algorithm for convex optimization. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’09). IEEE, 3653--3656. Google ScholarDigital Library
- Reiff-Marganiec, S. and Turner, K. J. 2004. Feature interaction in policies. Comput. Netw. 45, 569--584. Google ScholarDigital Library
- Tsai, W. T., Song, W., Chen, Y., and Paul, R. 2007. Dynamic system reconfiguration via service composition for dependable computing. In Proceedings of the 12th Monterey Conference on Reliable Systems on Unreliable Networked Platforms. Springer, 203--224. Google ScholarDigital Library
- Valente, F. 2010. Multi-stream speech recognition based on Dempster-Shafer combination rule. Speech Commun. 52, 3, 213--222.Google ScholarCross Ref
- Vanneschi, M. and Veraldi, L. 2007. Dynamicity in distributed applications: Issues, problems and the assist approach. Parallel Comput. 33, 12, 822--845. Google ScholarDigital Library
- Wang, X., Du, Z., Chen, Y., Li, S., Lan, D., Wang, G., and Chen, Y. 2008. An autonomic provisioning framework for outsourcing data center based on virtual appliances. Cluster Comput. 11, 3, 229--245. Google ScholarDigital Library
- Warneke, D. and Kao, O. 2011. Exploiting dynamic resource allocation for efficient parallel data processing in the cloud. IEEE Trans. Parallel Distrib. Syst. 22, 6. Google ScholarDigital Library
- Weigold, T., Aldinucci, M., Danelutto, M., and Getov, V. 2012. Process-driven biometric identification by means of autonomic grid components. Int. J. Auton. Adapt. Commun. Syst. 5, 3, 274--291. Google ScholarDigital Library
- Yuan, Q., Liu, Z., Peng, J., Wu, X., Li, J., Han, F., Li, Q., Zhang, W., Fan, X., and Kong, S. 2011. A leasing instances based billing model for cloud computing. In Proceedings of the 6th International Conference on Advances in Grid and Pervasive Computing (GPC’11). Springer, 33--41. Google ScholarDigital Library
- Zhang, R., Lu, C., Abdelzaher, T. F., and Stankovic, J. A. 2002. Controlware: A middleware architecture for feedback control of software performance. In Proceedings of the 22nd International Conference on Distributed Computing Systems (ICDCS’02). IEEE, 301. Google ScholarDigital Library
Index Terms
- A Cooperative Predictive Control Approach to Improve the Reconfiguration Stability of Adaptive Distributed Parallel Applications
Recommendations
Reconfiguration stability of adaptive distributed parallel applications through a cooperative predictive control approach
Euro-Par'13: Proceedings of the 19th international conference on Parallel ProcessingDistributed parallel applications executed on heterogeneous and dynamic environments need to adapt their configuration (in terms of parallelism degree and parallelism form for each component) in response to unpredictable factors related to the physical ...
Adaptive model predictive control of autonomic distributed parallel computations with variable horizons and switching costs
Autonomic computing is a paradigm for building systems capable of adapting their operation when external changes occur, such as workload variations, load surges and changes in the resource availability. The optimal configuration in terms of the number ...
FPGA-based fine-grain parallel computing (abstract only)
FPGA '11: Proceedings of the 19th ACM/SIGDA international symposium on Field programmable gate arraysFPGAs are increasing in computing power at a significant rate while the non-recurring engineering costs and time-to-market remain significant lower than those for application-specific integrated circuits (ASICs), encouraging FPGAs to be used in areas ...
Comments