Choreographies for Automatic Recovery

TL;DR

This paper introduces a choreographic model for reversible computations that extends existing models with minimal modifications, ensuring causal consistency without complex instrumentation.

Contribution

It presents a reversible computation model based on global graphs and finite-state machines, requiring only minor decorations for reversibility.

Findings

Model guarantees causal consistency in reversible computations

Reversible semantics are a conservative extension of existing models

Minimal modifications needed for reversibility in choreographies

Abstract

We propose a choreographic model of reversible computations based on a conservative extension of global graphs and communicating finite-state machines. The main advantage of our approach is that does not require to instrument models in order to control reversibility but for a minor decoration of branches. We show that our models are conservative extensions of existing ones and that the reversible semantics guarantees causal consistency.