A Middleware Approach to Synchronize Transaction Data to Blockchain

Blockchain is a kind of distributed accounting system with the characteristics of decentralization, openness, transparency, non-tampering and de-trust. Recently, blockchain-based applications appear in various fields such as IoT, supply-chain, etc. A practical requirement of applying the Blockchain technology to the conventional supply-chain system is the trans-action synchronization between databases and the blockchain systems. This paper proposes a middleware that supports non-intrusive, efficient, fault-tolerant transaction data synchronization. The middleware is designed under three principles. The first is to divide the process of transaction synchronization into several independent phases. The second is to convert the representation of database transaction into an optimal form for blockchain, and transactions are packed and written into blockchain in a batch mode. The third is to guarantee the consistency between database and blockchain through failure recovery mechanism. Utilities like pipeline processing and transaction mapping built on this middleware achieve significant performance improvement. The peak TPS of Hyperledger Fabric reaches above 16000, which is more than 32 times of the direct submission method.