Portable, Efficient, and Practical Library-Level Choreographic Programming

Abstract

Choreographic programming (CP) is an emerging paradigm for programming distributed applications that run on multiple nodes. In CP, the programmer writes one program, called a choreography, that is then transformed to individual programs for each node via a compilation step called endpoint projection (EPP). While CP languages have existed for over a decade, library-level CP -- in which choreographies are expressed as programs in an existing host language, and choreographic language constructs and EPP are provided entirely by a host-language library -- is in its infancy. Library-level CP has great potential, but existing implementations have portability, efficiency, and practicality drawbacks that hinder its adoption. In this paper, we aim to advance the state of the art of library-level CP with two novel techniques for choreographic library design and implementation: endpoint projection as dependency injection (EPP-as-DI), and choreographic enclaves. EPP-as-DI is a language-agnostic technique for implementing EPP at the library level. Unlike existing library-level approaches, EPP-as-DI asks little from the host language -- support for higher-order functions is all that is required -- making it usable in a wide variety of host languages. Choreographic enclaves are a language feature that lets the programmer define sub-choreographies within a larger choreography. Within an enclave, "knowledge of choice" is propagated only among the enclave's participants, enabling the seamless use of the host language's conditional constructs while addressing the efficiency limitations of existing library-level CP implementations. We implement EPP-as-DI and choreographic enclaves in ChoRus, the first CP library for the Rust programming language. Our case studies and benchmarks demonstrate that the usability and performance of ChoRus compares favorably to traditional distributed programming in Rust.