Abstract
Modern network services make increasing use of virtualized compute and network resources. This is enabled by the growing availability of softwarized network functions, which take on major roles in the total traffic flow (such as caching, routing or as firewall). To ensure reliable operation of its services, the service provider needs a good understanding of the performance of the deployed softwarized network functions. Ideally, the service performance should be predictable, given a certain input workload and a set of allocated (virtualized) resources (such as vCPUs and bandwidth). This helps to estimate more accurately how much resources are needed to operate the service within its performance specifications. To predict its performance, the network function should be profiled in the whole range of possible input workloads and resource configurations. However, this input can span a large space of multiple parameters and many combinations to test, resulting in an expensive and overextended measurement period. To mitigate this, we present a profiling framework and a sampling heuristic to help select both workload and resource configurations to test. Additionally, we compare several machine-learning based methods for the best prediction accuracy, in combination with the sampling heuristic. As a result, we obtain a reduced dataset which can still model the performance of the network functions with adequate accuracy, while requiring less profiling time. Compared to uniform sampling, our tests show that the heuristic achieves the same modeling accuracy with up to five times less samples.
Similar content being viewed by others
References
5G-PPP Software Network Working Group. Cloud-native and verticals’ services. Technical report, 5G-PPP Software Network Working Group, 2019. https://5g-ppp.eu/wp-content/uploads/2019/09/5GPPP-Software-Network-WG-White-Paper-2019_FINAL.pdf. Accessed 01 Oct 2019
Mimidis-Kentis, Angelos, Soler, Jose, Veitch, Paul, Broadbent, Adam, Mobilio, Marco, Riganelli, Oliviero, Van Rossem, Steven, Tavernier, Wouter, Sayadi, Bessem: The next generation platform as a service: composition and deployment of platforms and services. Futur Internet 11(5), 119 (2019)
Van Rossem, S., Sayadi, B., Roullet, L., Mimidis, A., Paolino, M., Veitch, P., Berde, B., Labrador, I., Ramos, A., Tavernier, W., et al.: A vision for the next generation platform-as-a-service. In: 2018 IEEE 5G World Forum (5GWF), pp. 14–19. IEEE, New York (2018)
Van Rossem, S., Tavernier, W., Colle, D., Pickavet, M., Demeester, P.: Profile-based resource allocation for virtualized network functions. IEEE Trans. Netw. Serv. Manag. 16, 1374–88 (2019)
Wood, T., Cherkasova, L., Ozonat, K., Shenoy, P.: Profiling and modeling resource usage of virtualized applications. In: ACM/IFIP/USENIX international conference on distributed systems platforms and open distributed processing, pp. 366–387. Springer, Berlin (2008)
Sciancalepore, Vincenzo, Yousaf, Faqir Zarrar, Costa-Perez, Xavier: z-torch: an automated nfv orchestration and monitoring solution. IEEE Trans. Netw. Serv. Manag. 15(4), 1292–1306 (2018)
Cao, L., Sharma, P., Fahmy, S., Saxena, V.: Nfv-vital: a framework for characterizing the performance of virtual network functions. In: 2015 IEEE conference on network function virtualization and software defined network (NFV-SDN), pp. 93–99. IEEE, New York (2015)
Gokan Khan, M., Bastani, S., Taheri, J., Kassler, A., Deng, S.: Nfv-inspector: a systematic approach to profile and analyze virtual network functions. In: 2018 IEEE 7th international conference on cloud networking (CloudNet), pp. 1–7 (2018)
Peuster, M., Karl, H.: Profile your chains, not functions: Automated network service profiling in develops environments. In: Network function virtualization and software defined networks (NFV-SDN). IEEE, New York (2017)
Van Rossem, S., Tavernier, W., Peuster, M., Colle, D., Pickavet, M., Demeester, P.: Monitoring and debugging using an sdk for nfv-powered telecom applications. In: IEEE NFV-SDN2016, the IEEE conference on network function virtualization and software defined networks
Rosa, Raphael Vicente, Bertoldo, Claudio, Rothenberg, Christian Esteve: Take your vnf to the gym: a testing framework for automated nfv performance benchmarking. IEEE Commun. Mag. 55(9), 110–117 (2017)
Nam, J., Seo, J., Shin, S.: Probius: automated approach for vnf and service chain analysis in software-defined nfv. In: Proceedings of the symposium on SDN research. pp. 14. ACM, New York (2018)
Iglesias, J. O., Aroca, J. A., Hilt, V., Lugones, D.: Orca: an orchestration automata for configuring vnfs. In: Proceedings of the 18th ACM/IFIP/USENIX middleware conference, pp. 81–94 (2017)
Duplyakin, D., Brown, J., Ricci, R.: Active learning in performance analysis. In: 2016 IEEE international conference on cluster computing (CLUSTER), pp. 182–191 (2016)
Thiagarajan, J. J., Jain, N., Anirudh, R., Gimenez, A., Sridhar, R., Marathe, A., Wang, T., Emani, M., Bhatele, A., Gamblin, T.: Bootstrapping parameter space exploration for fast tuning. In: Proceedings of the 2018 international conference on supercomputing, pp. 385–395 (2018)
Crombecq, Karel, Gorissen, Dirk, Deschrijver, Dirk, Dhaene, Tom: A novel hybrid sequential design strategy for global surrogate modeling of computer experiments. SIAM J. Sci. Comput. 33(4), 1948–1974 (2011)
Giannakopoulos, I., Tsoumakos, D., Papailiou, N., Koziris Panic, N.: modeling application performance over virtualized resources. In: 2015 IEEE International Conference on cloud engineering (IC2E), pp. 213–218. IEEE, New York (2015)
Peuster, M., Karl, H.: Understand your chains and keep your deadlines: introducing time-constrained profiling for nfv. In: 2018 14th international conference on network and service management (CNSM), pp. 240–246 (2018)
Giannakopoulos, I., Tsoumakos, D., Koziris, N.: A decision tree based approach towards adaptive modeling of big data applications. In: 2017 IEEE international conference on Big Data (Big Data), pp. 163–172. IEEE, New York (2017)
Dunn, K.: Process improvement using data (2019). https://learnche.org/pid/. Accessed 01 Oct 2019
ETSI. Network functions virtualisation (nfv): architectural framework (2014) https://www.etsi.org/deliver/etsi_gs/NFV/001_099/002/01.02.01_60/gs_NFV002v010201p.pdf. Accessed 05 Feb 2020
Kulkarni, S. G., Zhang, W., Hwang, J., Rajagopalan, S., Ramakrishnan, K. K., Wood, T., Arumaithurai, M., Fu, X.: Nfvnice: dynamic backpressure and scheduling for nfv service chains. In: Proceedings of the conference of the ACM special interest group on data communication, pp. 71–84 (2017)
Parmar, H., Thornburgh, M.: Adobe's Real Time Messaging Protocol (RTMP) Specification. Adobe Developer Connection, (2012). https://www.adobe.com/devnet/rtmp.html
Pantos, R., May, W.: Http live streaming, rfc 8216. Technical report (2017). https://tools.ietf.org/html/rfc8216. Accessed 01 Oct 2019
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, 2825–2830 (2011)
Smola, Alex J, Schölkopf, Bernhard: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004)
Williams, C.K.I., Rasmussen, C.E.: Gaussian Processes for Machine Learning, vol. 2. MIT press, Cambridge (2006)
Pfitscher, R.J., Jacobs, A.S., Zembruzki, L., dos Santos, R.L., Scheid, E.J., Franco, M.F., Schaeffer-Filho, A., Granville, L.Z.: Guiltiness: a practical approach for quantifying virtual network functions performance. Comput. Netw. 161, 14–31 (2019)
Khalid, J., Rozner, E., Felter, W., Xu, C., Rajamani, K., Ferreira, A., Akella, A.: Iron: isolating network-based \(\{\)CPU\(\}\) in container environments. In 15th \(\{\)USENIX\(\}\) Symposium on Networked Systems Design and Implementation (\(\{\)NSDI\(\}\) 18), pp. 313–328 (2018)
Uta, A., Custura, A., Duplyakin, D., Jimenez, I., Rellermeyer, J., Maltzahn, C., Ricci, R., Iosup, A.: Is big data performance reproducible in modern cloud networks? In: 17th USENIX symposium on networked systems design and implementation (NSDI 20), pp. 513–527, Santa Clara, CA, February 2020. USENIX Association
Xiong, P., Pu, C., Zhu, X., Griffith, R.: vperfguard: an automated model-driven framework for application performance diagnosis in consolidated cloud environments. In: Proceedings of the 4th ACM/SPEC international conference on performance engineering, pp. 271–282 (2013)
Gan, Y., Zhang, Y., Hu, K., Cheng, D., He, Y., Pancholi, M., Delimitrou, C.: Seer: leveraging big data to navigate the complexity of performance debugging in cloud microservices. In: Proceedings of the twenty-fourth international conference on architectural support for programming languages and operating systems, pp. 19–33 (2019)
Grohmann, J., Nicholson, P. K., Iglesias, J. O., Kounev, S., Lugones, D.: Monitorless: predicting performance degradation in cloud applications with machine learning. In: Proceedings of the 20th international middleware conference, pp. 149–162 (2019)
Acknowledgements
This work has been performed in the framework of the NGPaaS and 5GTANGO project, funded by the European Commission under the Horizon 2020 and 5G-PPP Phase2 programmes, resp. under Grant Agreement No. 761557 and 761493 (http://ngpaas.eu) (https://www.5gtango.eu). This work is partly funded by UGent BOF/GOA project “Autonomic Networked Multimedia Systems”
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Van Rossem, S., Tavernier, W., Colle, D. et al. Optimized Sampling Strategies to Model the Performance of Virtualized Network Functions. J Netw Syst Manage 28, 1482–1521 (2020). https://doi.org/10.1007/s10922-020-09547-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10922-020-09547-8