Setchain: Improving Blockchain Scalability with Byzantine Distributed Sets and Barriers

TL;DR

Setchain introduces a Byzantine-tolerant, partial-order blockchain data structure that significantly improves scalability by relaxing total order constraints and enabling faster, epoch-based synchronization for smart contract applications.

Contribution

The paper proposes Setchain, a novel distributed data type that allows partial ordering of operations, enhancing blockchain scalability without sacrificing safety under Byzantine conditions.

Findings

Setchain achieves orders of magnitude faster performance than traditional consensus-based ledgers.

It enables efficient epoch-based synchronization for grow-only sets.

Setchain can serve as a scalable sidechain for smart contract solutions.

Abstract

Blockchain technologies are facing a scalability challenge, which must be overcome to guarantee a wider adoption of the technology. This scalability issue is mostly caused by the use of consensus algorithms to guarantee the total order of the chain of blocks (and of the operations within each block). However, total order is often overkilling, since important advanced applications of smart-contracts do not require a total order of all the operations. Hence, if a more relaxed partial order (instead of a total order) is allowed under certain safety conditions, a much higher scalability can be achieved. In this paper, we propose a distributed concurrent data type, called Setchain, that allows implementing this partial order and increases significantly blockchain scalability. A Setchain implements a grow-only set object whose elements are not totally ordered, unlike conventional blockchain operations. When convenient, the Setchain allows forcing a synchronization barrier that assigns permanently an epoch number to a subset of the latest elements added. With the Setchain, operations in the same epoch are not ordered, while operations in different epochs are. We present different Byzantine-tolerant implementations of Setchain, prove their correctness and report on an empirical evaluation of a direct implementation. Our results show that Setchain is orders of magnitude faster than consensus-based ledgers to implement grow-only sets with epoch synchronization. Since the Setchain barriers can be synchronized with block consolidation, Setchain objects can be used as a sidechain to implement many smart contract solutions with much faster operations than on basic blockchains.