Explorando Estratégias de Orquestração de Telemetria em Planos de Dados Programáveis
Abstract
As networks and their applications evolve, new monitoring aspects and finer granularity become important for correctly identifying and characterizing situations related to, for example, load imbalance and micro-bursts. Data Plane Telemetry emerges in this context as a promising approach to meet this demand, enabling the insertion of information about the network state directly into production packets traversing the network. This kind of telemetry enables unprecedented monitoring accuracy and precision, but may also lead to degradation of traffic if applied naively. In this paper we propose and evaluate strategies for the orchestration of data plane telemetry that explore the effects of concentrating the monitoring load on a small number of packet flows or of distributing it among a larger number of them. The evaluation results demonstrate that it is possible to obtain good quality in terms of coverage, freshness and consistency while considerably reducing production traffic degradation.
References
Bosshart, P., Gibb, G., Kim, H.-S., Varghese, G., McKeown, N., Izzard, M., Mujica, F., and Horowitz, M. (2013). Forwarding metamorphosis: Fast programmable matchaction processing in hardware for sdn. In Proceedings of the ACM SIGCOMM Conference, SIGCOMM ’13, pages 99–110, New York, NY, USA. ACM.
Cheng, G. and Yu, J. (2017). Adaptive sampling for openow network measurement methods. In Proceedings of the International Conference on Future Internet Technologies, CFI’17, pages 4:1–4:7, New York, NY, USA. ACM.
Chowdhury, S. R., Bari, M. F., Ahmed, R., and Boutaba, R. (2014). Payless: A low cost network monitoring framework for software dened networks. In Proceedings of the IEEE Network Operations and Management Symposium, NOMS’14, pages 1–9.
Cordeiro, W. L. d. C., Marques, J. A., and Gaspary, L. P. (2017). Data plane programmability beyond openow: Opportunities and challenges for network and service operations and management. Journal of Network and Systems Management, 25(4):784–818.
Handigol, N., Heller, B., Jeyakumar, V., Mazieres, D., and McKeown, N. (2014). I know In what your packet did last hop: Using packet histories to troubleshoot networks. Proceedings of the USENIX Conference on Networked Systems Design and Implementation, NSDI’14, pages 71–85, Berkeley, CA, USA. USENIX Association.
Jeyakumar, V., Alizadeh, M., Geng, Y., Kim, C., and Maziéres, D. (2014). Millions of little minions: Using packets for low latency network programming and visibility. SIGCOMM Comput. Commun. Rev., 44(4):3–14.
Kim, C., Sivaraman, A., Katta, N., Bas, A., Dixit, A., and Wobker, L. J. (2015). In Proceedings of the ACM band network telemetry via programmable dataplanes. SIGCOMM Symposium on SDN Research, SOSR’15.
McKeown, N., Anderson, T., Balakrishnan, H., Parulkar, G., Peterson, L., Rexford, J., Shenker, S., and Turner, J. (2008). Openow: Enabling innovation in campus networks. SIGCOMM Comput. Commun. Rev., 38(2):69–74.
Rocha, A., Sampaio, L. N., Vieira, A. B., Wehmuth, K., and Ziviani, A. (2016). Revisitando metrologia de redes: Do passado às novas tendências. In Simpósio Brasileiro de Redes de Computadores e Sistema Distribuídos, SBRC 2016, pages 151–209.
Tangari, G., Tuncer, D., Charalambides, M., and Pavlou, G. (2017). Decentralized monitoring for large-scale software-dened networks. In Proceedings of the IFIP/IEEE Symposium on Integrated Network and Service Management (IM), pages 289–297.
Thomas, J. and Laupkhov, P. (2016). Tracking packets’ paths and latency via int (in-band network telemetry). 3rd P4 Workshop.
Zhang, Q., Liu, V., Zeng, H., and Krishnamurthy, A. (2017). High-resolution measurement of data center microbursts. In Proceedings of the Internet Measurement Conference, IMC ’17, pages 78–85, New York, NY, USA. ACM.
Zhu, Y., Kang, N., Cao, J., Greenberg, A., Lu, G., Mahajan, R., Maltz, D., Yuan, L., Zhang, M., Zhao, B. Y., and Zheng, H. (2015). Packet-level telemetry in large datacenter networks. In Proceedings of the ACM SIGCOMM Conference, SIGCOMM ’15, pages 479–491, New York, NY, USA. ACM.
