Distributed transaction processing over the TCP/IP network suffers from the weak transaction scalability problem, i.e., its performance drops significantly when the number of involved data nodes per transaction increases. Although quite a few of works over the high-performance RDMA-capable network are proposed, they mainly focus on accelerating distributed transaction processing, rather than solving the weak transaction scalability problem. In this paper, we propose RCBench, an RDMA-enabled transaction framework, which serves as a unified evaluation tool for assessing the transaction scalability of various concurrency control algorithms. The usability and advancement of RCBench primarily come from the proposed concurrency control primitives , which facilitate the convenient implementation of RDMA-enabled concurrency control algorithms. Various optimization principles are proposed to ensure that concurrency control algorithms in RCBench can fully benefit from the advantages offered by RDMA-capable networks. We conduct extensive experiments to evaluate the scalability of mainstream concurrency control algorithms. The results show that by exploiting the capabilities of RDMA, concurrency control algorithms in RCBench can obtain 42X performance improvement, and transaction scalability can be achieved in RCBench.

TCP/IP网络上的分布式事务处理存在事务可扩展性弱的问题，即当每个事务涉及的数据节点数量增加时，其性能显着下降。尽管在高性能RDMA网络上提出了相当多的工作，但它们主要集中在加速分布式事务处理，而不是解决事务可扩展性弱的问题。在本文中，我们提出了RCBench，一个支持 RDMA 的事务框架，它作为评估各种并发控制算法的事务可扩展性的统一评估工具。 RCBench的可用性和先进性主要来自于提出的并发控制原语，它有助于方便地实现支持RDMA的并发控制算法。提出了各种优化原则，以确保 RCBench 中的并发控制算法能够充分受益于支持 RDMA 的网络提供的优势。我们进行了大量的实验来评估主流并发控制算法的可扩展性。结果表明，通过利用 RDMA 的功能，RCBench 中的并发控制算法可以获得 42 倍的性能提升，并且可以在 RCBench 中实现事务可扩展性。