Stream-based State-Machine Replication

TL;DR

This paper introduces stream-based state-machine replication, implementing protocols on top of data-stream frameworks to reduce complexity and overhead, demonstrated through a prototype called Tara based on Heron.

Contribution

The paper presents a novel stream-based approach to state-machine replication, simplifying implementation and management by leveraging existing data-stream processing frameworks.

Findings

Tara tolerates crashes with request handling, checkpointing, and view changes.

Tara's implementation is under 1,500 lines of code.

The approach significantly reduces development and operational overhead.

Abstract

Developing state-machine replication protocols for practical use is a complex and labor-intensive process because of the myriad of essential tasks (e.g., deployment, communication, recovery) that need to be taken into account in an implementation. In this paper, we show how this problem can be addressed with stream-based replication, a novel approach that implements a replication protocol as application on top of a data-stream processing framework. With such framework already handling most essential tasks and furthermore providing means for debugging and monitoring, this technique has the key benefit of significantly minimizing overhead for both programmers as well as system operators. Our first stream-based protocol Tara tolerates crashes and comprises full-fledged mechanisms for request handling, checkpointing, and view changes. Still, Tara's prototype implementation, which is based on Twitter's Heron framework, consists of fewer than 1,500 lines of application-level code.