Work

RL-Paxos: Relieving the Leader's Burden with Efficient Task Offloading in Distributed Consensus

Year: 2026

Type: conference-paper

Abstract: Existing state machine replication protocols are typically leader-based, with the leader responsible for all operations, leading to a scalability bottleneck. Despite extensive research efforts to address this issue, alleviating the leader's workload remains a significant challenge. In this paper, we provide an indepth analysis of the leader bottleneck and introduce RL-Paxos, which retains only the core function of ordering (e.g., establishing a global order and performing commutativity checks) for the leader, while offloading other tasks to the followers. We integrate RL-Paxos into the classic Paxos protocol and compare it with state-of-the-art protocols. Extensive experimental evaluations demonstrate that RL-Paxos achieves high throughput and low wide-area latency under conditions of high concurrency, multinode deployment, mixed workloads, and read-only scenarios.

Source: IEEE International Conference on Data Engineering (ICDE)

DOI: 10.1109/icde65706.2026.00101

Authors: Chenhao Zhang, Jinquan Wang, Meng Han, Bing Wei, Xiaojian Liao, Limin Xiao, Shanchen Pang

Institutions: China University of Petroleum, East China, Beihang University, Tsinghua University, Hainan University

Language: English

Topic: Distributed systems and fault tolerance

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7202290741

FWCI:

Cites: 23

Cited by:

Related to: 10