@inproceedings{mukherjee2019reliable,
author = {Mukherjee, Suvam and Raj, Nitin John and , Krishnan Govindraj and Deligiannis, Pantazis and Ravichandran, Chandramouleswaran and Lal, Akash and Rastogi, Aseem and Krishnaswamy, Raja},
title = {Reliable State Machines: A Framework for Programming Reliable Cloud Services},
booktitle = {ECOOP 2019},
year = {2019},
month = {July},
abstract = {Building reliable applications for the cloud is challenging because of unpredictable failures during a program's execution. This paper presents a programming framework called Reliable State Machines (RSMs), that offers fault-tolerance by construction. Using our framework, a programmer can built an application as several (possibly distributed) RSMs that communicate with each other via messages, much in the style of actor-based programming. Each RSM is additionally fault-tolerant by design and offers the illusion of being ``always-alive''. An RSM is guaranteed to process each input request exactly once, as one would expect in a failure-free environment. The RSM runtime automatically takes care of persisting state and rehydrating it on a failover. We present the core syntax and semantics of RSMs, along with a formal proof of failure-transparency.

We provide an implementation of the RSM framework and runtime on the .NET platform for deploying services to Microsoft Azure. We carried out an extensive performance evaluation on micro-benchmarks to show that one can build high-throughput applications with RSMs. We also present a case study where we rewrote a significant part of a production cloud service using RSMs. The resulting service has simpler code and exhibits production-grade performance.},
url = {http://approjects.co.za/?big=en-us/research/publication/reliable-state-machines-a-framework-for-programming-reliable-cloud-services/},
}