Avaliação de Desempenho de Migração ao Vivo de Contêineres com Redes de Petri Estocásticas
Abstract
Currently, most data centers around the world use microservices and containers. Containers typically run on a single controlling host, accessing a single kernel. The more systems are distributed the greater the probability of failure. An alternative to mitigate the problem of unavailability and loss of performance is to migrate containers between hosts. There are utilities like Checkpoint Restoration In Userspace (CRIU) that can be used specifically to perform the migration of containers, however it is not easy to choose a specific migration policy considering the architectural particularities and the software that is running in a distributed way in the containers. This paper proposes a Stochastic Petri Net (SPN) model to model migration policies for containers (and also VMs), evaluating the mean migration time of such elements. The model also allows calculating the probability of each policy completing the migration process in a given period of time. This is the first work with these characteristics in the context of migration of virtualizable elements.
References
Conforti, L., Virdis, A., Puliafito, C., and Mingozzi, E. (2021). Extending the quic protocol to support live container migration at the edge. In 2021 IEEE 22nd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), pages 61–70. IEEE.
German, R. (2000). Performance analysis of communication systems with non-Markovian stochastic Petri nets. John Wiley & Sons, Inc.
Jain, R. (1990). The art of computer systems performance analysis: techniques for experimental design, measurement, simulation, and modeling. john wiley & sons.
Junior, P. S., Miorandi, D., and Pierre, G. (2020). Stateful container migration in geo-distributed environments. In 2020 IEEE International Conference on Cloud Computing Technology and Science (CloudCom), pages 49–56. IEEE.
Maciel, P., Matos, R., Silva, B., Figueiredo, J., Oliveira, D., Fé, I., Maciel, R., and Dantas, J. (2017). Mercury: Performance and dependability evaluation of systems with exponential, expolynomial, and general distributions. In 2017 IEEE 22nd Pacific Rim international symposium on dependable computing (PRDC), pages 50–57. IEEE.
Maheshwari, S., Choudhury, S., Seskar, I., and Raychaudhuri, D. (2018). Traffic-aware dynamic container migration for real-time support in mobile edge clouds. In 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), pages 1–6. IEEE.
Marsan, M. A., Balbo, G., Conte, G., Donatelli, S., and Franceschinis, G. (1998). Modelling with generalized stochastic petri nets. ACM SIGMETRICS performance evaluation review, 26(2):2.
Nelson, R. (2013). Probability, stochastic processes, and queueing theory: the mathematics of computer performance modeling. Springer Science & Business Media.
Pickartz, S., Eiling, N., Lankes, S., Razik, L., and Monti, A. (2016). Migrating linux containers using criu. In High Performance Computing: ISC High Performance 2016 International Workshops, ExaComm, E-MuCoCoS, HPC-IODC, IXPUG, IWOPH, Pˆ 3MA, VHPC, WOPSSS, Frankfurt, Germany, June 19–23, 2016, Revised Selected Papers 31, pages 674–684. Springer.
Puliafito, C., Vallati, C., Mingozzi, E., Merlino, G., Longo, F., and Puliafito, A. (2019). Container migration in the fog: A performance evaluation. Sensors, 19(7):1488.
Qiu, Y., Lung, C.-H., Ajila, S., and Srivastava, P. (2019). Experimental evaluation of lxc container migration for cloudlets using multipath tcp. Computer Networks, 164:106900.
Ramanathan, S., Kondepu, K., Razo, M., Tacca, M., Valcarenghi, L., and Fumagalli, A. (2021). Live migration of virtual machine and container based mobile core network components: A comprehensive study. IEEE Access, 9:105082–105100.
