Benzene: Scaling Blockchain with Cooperation-Based Sharding

Zhongteng Cai, Junyuan Liang, Wuhui Chen*, Zicong Hong, Hong Ning Dai, Jianting Zhang, Zibin Zheng

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Sharding has been considered as a prominent approach to enhance the limited performance of blockchain. However, most sharding systems leverage a non-cooperative design, which lowers the fault tolerance resilience due to the decreased mining power as the consensus execution is limited to each separated shard. To this end, we present Benzene, a novel sharding system that enhances the performance by cooperation-based sharding while defending the per-shard security. First, we establish a double-chain architecture for function decoupling. This architecture separates transaction-recording functions from consensus-execution functions, thereby enabling the cross-shard cooperation during consensus execution while preserving the concurrency nature of sharding. Second, we design a cross-shard block verification mechanism leveraging Trusted Execution Environment (TEE), via which miners can verify blocks from other shards during the cooperation process with the minimized overheads. Finally, we design a voting-based consensus protocol for cross-shard cooperation. Transactions in each shard are confirmed by all shards that simultaneously cast votes, consequently achieving an enhanced fault tolerance and lowering the confirmation latency. We implement Benzene and conduct both prototype experiments and large-scale simulations to evaluate the performance of Benzene. Results show that Benzene achieves superior performance than existing sharding/non-sharding blockchain protocols. In particular, Benzene achieves a linearly-improved throughput with the increased number of shards (e.g., 32,370 transactions per second with 50 shards) and maintains a lower confirmation latency than Bitcoin (with more than 50 shards). Meanwhile, Benzene maintains a fixed fault tolerance at 1/3 even with the increased number of shards.

Original languageEnglish
Pages (from-to)639-654
Number of pages16
JournalIEEE Transactions on Parallel and Distributed Systems
Volume34
Issue number2
Early online date13 Dec 2022
DOIs
Publication statusE-pub ahead of print - 13 Dec 2022

Scopus Subject Areas

  • Signal Processing
  • Hardware and Architecture
  • Computational Theory and Mathematics

User-Defined Keywords

  • Blockchain
  • sharding
  • scalability
  • function decoupling
  • consensus algorithm

Cite this