Reliability and fault-tolerance by choreographic design

Abstract

Distributed programs are hard to get right because they are required to be open, scalable, long-running, and tolerant to faults. In particular, the recent approaches to distributed software based on (micro-)services where different services are developed independently by disparate teams exacerbate the

problem. In fact, services are meant to be composed together and run in open context where unpredictable behaviours can emerge. This makes it necessary to adopt suitable strategies for monitoring

the execution and incorporate recovery and adaptation mechanisms so to make distributed programs more flexible and robust. The typical approach that is currently adopted is to embed such mechanisms in the program logic, which makes it hard to extract, compare and debug. We propose an approach that employs formal abstractions for specifying failure recovery and adaptation strategies. Although implementation agnostic, these abstractions would be amenable to algorithmic synthesis of code, monitoring and tests. We consider message-passing programs (a la Erlang, Go, or MPI) that are gaining momentum both in academia and industry. Our research agenda consists of (1) the definition of formal behavioural models encompassing failures, (2) the specification of the relevant properties of adaptation and recovery strategy, (3) the automatic generation of monitoring, recovery, and adaptation logic in target languages of interest.