Sharding Distributed Replication Systems to Improve Scalability and Throughput

Most existing Byzantine fault-tolerant (BFT) algorithms are very slow and are not designed for large sets of participants trying to reach a consensus. Hence, distributed replication systems that use consensus mechanisms to process clients’ requests have major limitations and problems in scalability, throughput, and performance. Such problems are mainly due to the time and message complexity of the consensus algorithms used in such systems. Such limited scalability and low throughput can be significantly improved by using sharding approach as a technique for partitioning a state into multiple shards, each of which is handled by a subset of the network in parallel. Use of sharding for replication systems is inspired by sharding in databases. Sharding has already been implemented in several blockchain-based replication systems, and although it has shown remarkable potential to improve performance and scalability, current sharding techniques have several significant scalability and security issues. In this chapter, we detail the main challenges in the sharding approach and also explain how the sharding approach can enhance the scalability and throughput of distributed replication systems. We also review the most notable sharding protocols designed for distributed replication systems.