A Dual Digraph Approach for Leaderless Atomic Broadcast (Extended Version)

TL;DR

This paper introduces AllConcur+, an improved leaderless atomic broadcast algorithm that optimizes performance by using a redundancy-free overlay network during failure-free periods and switches to a resilient network when failures occur, enhancing efficiency and robustness.

Contribution

AllConcur+ extends existing leaderless atomic broadcast algorithms by enabling minimal work during failure-free intervals and automatic recovery during failures, reducing redundancy and improving performance.

Findings

AllConcur+ matches non-failure throughput of AllGather.

It outperforms AllConcur, LCR, and Libpaxos in throughput and latency.

Performance remains robust under occasional failures.

Abstract

Many distributed systems work on a common shared state; in such systems, distributed agreement is necessary for consistency. With an increasing number of servers, these systems become more susceptible to single-server failures, increasing the relevance of fault-tolerance. Atomic broadcast enables fault-tolerant distributed agreement, yet it is costly to solve. Most practical algorithms entail linear work per broadcast message. AllConcur -- a leaderless approach -- reduces the work, by connecting the servers via a sparse resilient overlay network; yet, this resiliency entails redundancy, limiting the reduction of work. In this paper, we propose AllConcur+, an atomic broadcast algorithm that lifts this limitation: During intervals with no failures, it achieves minimal work by using a redundancy-free overlay network. When failures do occur, it automatically recovers by switching to a resilient overlay network. In our performance evaluation of non-failure scenarios, AllConcur+ achieves comparable throughput to AllGather -- a non-fault-tolerant distributed agreement algorithm -- and outperforms AllConcur, LCR and Libpaxos both in terms of throughput and latency. Furthermore, our evaluation of failure scenarios shows that AllConcur+'s expected performance is robust with regard to occasional failures. Thus, for realistic use cases, leveraging redundancy-free distributed agreement during intervals with no failures improves performance significantly.