Rethink the Linearizability Constraints of Raft for Distributed Systems

With the deployment of modern hardware such as Flash-based SSDs and the high-speed network in distributed systems, the distributed consensus and consistency module (e.g., Raft) is typically the most time-consuming part. The reason lies in that Raft introduces some very strict constraints to ensure t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering 2023-11, Vol.35 (11), p.1-14
Main Authors: Wang, Yangyang, Wang, Zikai, Chai, Yunpeng, Wang, Xin
Format: Article
Language:English
Subjects:
Algorithms
Computer networks
consensus
Consensus algorithm
Consistency
Distributed databases
distributed system
Hardware
Indexes
linearizability
Raft
Synchronization
Throughput
Voting
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the deployment of modern hardware such as Flash-based SSDs and the high-speed network in distributed systems, the distributed consensus and consistency module (e.g., Raft) is typically the most time-consuming part. The reason lies in that Raft introduces some very strict constraints to ensure the linearizability. Therefore, in this paper, we rethink these constraints in-depth and find that some of them are not necessary, and can be broken to accelerate the performance significantly without breaking the linear consistency for distributed systems. An improved distributed consensus algorithm called BUC-Raft (Breaking Unnecessary Constraints of Raft) is proposed in this paper and implemented in an industry-level distributed system. The experimental results suggest that both the write and the read performance can be accelerated significantly by BUC-Raft.
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2023.3235399