CESSNA: Resilient Edge-Computing

ABSTRACT

The introduction of computational resources at the network edge has moved us from a Client-Server model to a Client-Edge-Server model. By offloading computation from clients and/or servers, this approach can reduce response latency, backbone bandwidth, and computational requirements on clients. While this is an attractive paradigm for many applications, particularly 5G mobile networks and IoT devices, it raises the question of how one can design such a client-edge-server system to tolerate edge failures and client mobility. The key challenge is to ensure correctness when the edge processing is stateful (so the processing depends on state it has previously seen from the client and/or server). In this paper we propose an initial design for meeting this challenge called Client-Edge-Server for Stateful Network Applications (CESSNA).

References

1. G. Ananthanarayanan, P. Bahl, P. Bodík, K. Chintalapudi, M. Philipose, L. Ravindranath, and S. Sinha. Real-time video analytics: The killer app for edge computing. Computer, 50(10):58--67, 2017.
2. T. C. Bressoud and F. B. Schneider. Hypervisor-based fault-tolerance. In SOSP, 1995.
3. J. Corbet. Checkpoint/restart in userspace. LWN https://lwn.net/Articles/572125/,2013.
4. V. Cozzolino, A. Y. Ding, and J. Ott. FADES: Fine-grained edge offloading with unikernels. In HotConNet, pages 36--41, 2017.
5. B. Cully, G. Lefebvre, D. T. Meyer, M. Feeley, N. C. Hutchinson, and A. Warfield. Remus: High availability via asynchronous virtual machine replication. In NSDI, 2008.
6. Docker checkpoint and restore. https://github.com/docker/cli/blob/master/experimental/checkpoint-restore.md, 2018.
7. Y. Dong, W. Ye, Y. Jiang, I. Pratt, S. Ma, J. Li, and H. Guan. COLO: coarse-grained lock-stepping virtual machines for non-stop service. In SOCC, 2013.
8. G. W. Dunlap, D. G. Lucchetti, M. A. Fetterman, and P. M. Chen. Execution replay of multiprocessor virtual machines. In VEE, 2008.
9. E. N. Elnozahy, L. Alvisi, Y. Wang, and D. B. Johnson. A survey of rollback-recovery protocols in message-passing systems. ACM Comput. Surv., 34(3), 2002.
10. B. I. Ismail, E. M. Goortani, M. B. A. Karim, W. M. Tat, S. Setapa, J. Y. Luke, and O. H. Hoe. Evaluation of docker as edge computing platform. In 2015 IEEE Conference on Open Systems (ICOS), Aug 2015.
11. OpenFog Consortium Architecture Working Group. OpenFog Reference Architecture for Fog Computing, Feb. 2017. https://www.openfogconsortium.org/ra/.
12. J. Sherry, P. X. Gao, S. Basu, A. Panda, A. Krishnamurthy, C. Maciocco, M. Manesh, J. Martins, S. Ratnasamy, L. Rizzo, and S. Shenker. Rollback-recovery for middle-boxes. In Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, SIGCOMM 2015, London, United Kingdom, August 17-21, 2015, 2015.
13. I. Zhang, T. Denniston, Y. Baskakov, and A. Garthwaite. Optimizing vm checkpointing for restore performance in vmware esxi. In USENIX Annual Technical Conference, 2013.

Index Terms

• Networks

  • Network architectures

    • Programming interfaces

  • Network properties

    • Network mobility

    • Network reliability