[an error occurred while processing this directive]

ZTE Communications ›› 2024, Vol. 22 ›› Issue (2): 19-29.DOI: 10.12142/ZTECOM.202402004

• Special Topic • 上一篇    下一篇

  

  • 收稿日期:2024-03-23 出版日期:2024-06-28 发布日期:2024-06-25

Optimization of High-Concurrency Conflict Issues in Execute-Order-Validate Blockchain

MA Qianli1(), ZHANG Shengli1, WANG Taotao1, YANG Qing1, WANG Jigang2   

  1. 1.Shenzhen University, Shenzhen 518000, China
    2.ZTE Corporation, Shenzhen 518057, China
  • Received:2024-03-23 Online:2024-06-28 Published:2024-06-25
  • About author:MA Qianli (maqianli@foxmail.com) received his BE degree in software engineering from University of Electronic Science and Technology of China in 2020. He is currently working toward his ME degree in electronic information engineering from Shenzhen University, China. His research focuses on blockchain.
    ZHANG Shengli received his BE degree in electronic engineering and ME degree in communication and information engineering from University of Science and Technology of China in 2002 and 2005, respectively, and PhD degree with the Department of Information Engineering, The Chinese University of Hong Kong, China in 2008. After that, he joined Communication Engineering Department, Shenzhen University, China, where he is currently a full professor. He has authored or coauthored more than 20 IEEE top journal papers and ACM top conference papers, including IEEE Journal on Selected Areas in Communications, IEEE Transactions on Wireless Communications, IEEE Transactions on Mobile Computing, IEEE Transactions on Communications, and ACM Mobicom. His research interests include blockchain, physical layer network coding, and wireless networks.
    WANG Taotao received his PhD degree in information engineering from The Chinese University of Hong Kong (CUHK), China in 2015, MS degree in information and signal processing from Beijing University of Posts and Telecommunications, China in 2011, and BS degree in electrical engineering from University of Electronic Science and Technology of China in 2008. He joined the College of Information Engineering, Shenzhen University, China, as a tenure-track assistant professor in 2016 and was promoted as a tenured associate professor in 2021.
    YANG Qing received his BE degree (Hons.) from Huazhong University of Science and Technology, China and PhD degree from The Chinese University of Hong Kong, China. In 2018, he joined as an assistant professor at the College of Electronics and Information Engineering, Shenzhen University, China and the Principal Researcher at the Blockchain Technology Research Center, Shenzhen University.
    WANG Jigang received his PhD degree in computer science from Harbin Engineering University, China in 2007. From May 2007 to June 2009, he held a postdoctoral position in Institute of Computer Science, Tsinghua University. From August 2009, Dr. WANG has been with Cyber Security Product Line, ZTE Corporation as general manager. His recent research interests include operating systems, network and information security, and artificial intelligence.

Abstract:

With the maturation and advancement of blockchain technology, a novel execute-order-validate (EOV) architecture has been proposed, allowing transactions to be executed in parallel during the execution phase. However, parallel execution may lead to multi-version concurrency control (MVCC) conflicts during the validation phase, resulting in transaction invalidation. Based on different causes, we categorize conflicts in the EOV blockchain into two types: within-block conflicts and cross-block conflicts, and propose an optimization solution called FabricMan based on Fabric v2.4. For within-block conflicts, a reordering algorithm is designed to improve the transaction success rate and parallel validation is implemented based on the transaction conflict graph. We also merge transfer transactions to prevent triggering multiple version checks. For cross-block conflicts, a cache-based version validation mechanism is implemented to detect and terminate invalid transactions in advance. Experimental comparisons are conducted between FabricMan and two other systems, Fabric and Fabric++. The results show that FabricMan outperforms the other two systems in terms of throughput, transaction abort rate, algorithm execution time, and other experimental metrics.

Key words: blockchain, MVCC conflict, reordering, parallel validation, transaction merging