Hyperledger Fabric（HLF）是一個廣受採用的許可式區塊鏈平台，Hyperledger Fabric（HLF）是一個廣受採用的許可式區塊鏈平台，其模組化的執行—排序—驗證（Execute-Order-Validate）架構提供了良好的靈活性，但其預設的基於 Raft 的排序服務每次決策需要多次網路往返（RTT），在高負載下容易成為系統效能瓶頸。本論文提出 seqFabric，透過批次層級的排序設計將序列器共識（sequencer-based consensus）整合至 HLF，實現單次往返排序，比 Raft 減少一次往返。基於雜湊值的酬載分離機制進一步提升了高負載情境下的效能表現。實驗結果顯示，雜湊版本相較於 Raft 基準，吞吐量最高提升 330.8%，平均延遲降低 3.22×，並在接近飽和點時，P95 尾部延遲約為完整酬載版本的三分之一。

Hyperledger Fabric (HLF) is an open-source permissioned blockchain platform that achieves flexibility through a modular Execute-Order-Validate architecture, but its default Raft-based ordering service requires multiple round trips per decision, becoming a bottleneck under high load. We present seqFabric, which integrates sequencer-based consensus into HLF via a batch-level ordering design, achieving single-RTT ordering, one fewer round trip than Raft. Hash-based payload separation further improves performance under heavy load. Experiments show that this hash-based variant achieves up to 330.8% higher throughput and 3.22× lower mean latency than Raft, while suppressing P95 tail latency to about one-third of the full-payload baseline near its saturation point.

[1] E. Androulaki, A. Barger, V. Bortnikov, et al., “Hyperledger fabric: A distributed operating system for permissioned blockchains,” in Proceedings of the thirteenth EuroSys conference, 2018, pp. 1–15 (cit. p. 1).
[2] E. Androulaki, M. Brandenburger, M. B. Rosenbaum, A. De Caro, et al., “Fabric-x: Scaling hyperledger fabric for asset exchange,” in Companion of the International Conference on Management of Data, ser. SIGMOD Companion ’26, India: Association for Computing Machinery, 2026, pp. 162–174 (cit. pp. 1, 5).
[3] Atomix, Nopaxos-replica: NOPaxos replica for Go, https : / / pkg . go . dev /github.com/atomix/nopaxos-replica (cit. p. 27).
[4] A. Barger, Y. Manevich, H. Meir, and Y. Tock, “A byzantine fault tolerant consensus library for hyperledger fabric,” in IEEE International Conference on Blockchain and Cryptocurrency (ICBC), IEEE, 2021 (cit. p. 5).
[5] I. Choi, E. Michael, Y. Li, D. R. Ports, and J. Li, “Hydra:{serialization-free} network ordering for strongly consistent distributed applications,” in 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), 2023, pp. 293–320 (cit. pp. 2, 5, 9, 10, 13, 15, 16, 23, 36).
[6] A. Demers, D. Greene, C. Hauser, et al., “Epidemic algorithms for replicated database maintenance,” in Proceedings of the sixth annual ACM Symposium on Principles of distributed computing, 1987, pp. 1–12 (cit. pp. 8, 19).
[7] C. Gorenflo, S. Lee, L. Golab, and S. Keshav, “Fastfabric: Scaling hyperledger fabric to 20 000 transactions per second,” International Journal of Network Management, vol. 30, no. 5, e2099, 2020 (cit. pp. 1, 5, 18).
[8] gRPC Authors, gRPC: A high-performance, open-source universal RPC framework, https://grpc.io, 2015 (cit. p. 29).
[9] M. Haseeb, J. Geng, D. Duclos-Cavalcanti, et al., “Network support for scalable and high performance cloud exchanges,” in Proceedings of the ACM SIGCOMM 2025 Conference, 2025, pp. 1110–1131 (cit. p. 4).
[10] M. Haseeb, J. Geng, A. Panda, et al., “Probabilistic fair ordering of events,” arXiv preprint arXiv:2602.09148, 2026 (cit. p. 4).
[11] C. V. Helliar, L. Crawford, L. Rocca, C. Teodori, and M. Veneziani, “Permissionless and permissioned blockchain diffusion,” International Journal of Information Management, vol. 54, p. 102 136, 2020 (cit. p. 7).
[12] Z. István, A. Sorniotti, and M. Vukolić, “Streamchain: Do blockchains need blocks?”In Proceedings of the 2nd workshop on scalable and resilient infrastructures for distributed ledgers, 2018, pp. 1–6 (cit. pp. 1, 5).
[13] B.-J. Ji and T.-W. Kuo, “Better clients, less conflicts: Hyperledger fabric conflict avoidance,” in 2024 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), IEEE, 2024, pp. 368–376 (cit. p. 6).
[14] M. Kogias and E. Bugnion, “Hovercraft: Achieving scalability and fault-tolerance for microsecond-scale datacenter services,” in Proceedings of the Fifteenth European Conference on Computer Systems, 2020, pp. 1–17 (cit. p. 8).
[15] L. Kuhring, Z. István, A. Sorniotti, and M. Vukolić, “Streamchain: Building a low latency permissioned blockchain for enterprise use-cases,” in 2021 IEEE International Conference on Blockchain (Blockchain), IEEE, 2021, pp. 130–139 (cit. p. 5).
[16] H.-T. Kung and J. T. Robinson, “On optimistic methods for concurrency control,”ACM Transactions on Database Systems (TODS), vol. 6, no. 2, pp. 213–226, 1981(cit. p. 6).
[17] J. Li, E. Michael, N. K. Sharma, A. Szekeres, and D. R. Ports, “Just say {no} to paxos overhead: Replacing consensus with network ordering,” in 12th USENIX Symposiumon Operating Systems Design and Implementation (OSDI 16), 2016, pp. 467–483 (cit. pp. 2, 9, 10, 13, 15, 16, 23).
[18] Y. Manevich, H. Meir, K. Elkhiyaoui, Y. Tock, and M. Buzaglo, “Arma: Byzantine fault tolerant consensus with horizontal scalability,” arXiv preprint arXiv:2405.16575, 2024 (cit. pp. 1, 5).
[19] B. M. Oki and B. H. Liskov, “Viewstamped replication: A new primary copy method to support highly-available distributed systems,” in Proceedings of the seventh annual ACM Symposium on Principles of distributed computing, 1988, pp. 8–17 (cit.p. 2).
[20] D. Ongaro and J. Ousterhout, “In search of an understandable consensus algorithm,”in 2014 USENIX annual technical conference (USENIX ATC 14), 2014, pp. 305–319 (cit. pp. 1, 8).
[21] Z. Peng, Y. Zhang, Q. Xu, et al., “Neuchain: A fast permissioned blockchain system with deterministic ordering,” Proceedings of the VLDB Endowment, vol. 15, no. 11, pp. 2585–2598, 2022 (cit. pp. 1, 5).
[22] J. Qi, X. Chen, Y. Jiang, et al., “Bidl: A high-throughput, low-latency permissioned blockchain framework for datacenter networks,” in Proceedings of the ACM SIGOPS 28th symposium on operating systems principles, 2021, pp. 18–34 (cit. pp. 1, 4).
[23] F. B. Schneider, “Implementing fault-tolerant services using the state machine approach: A tutorial,” Acm Computing Surveys (CSUR), vol. 22, no. 4, pp. 299–319, 1990 (cit. p. 1).
[24] A. Sharma, F. M. Schuhknecht, D. Agrawal, and J. Dittrich, “Blurring the lines between blockchains and database systems: The case of hyperledger fabric,” in Proceedings of the 2019 International Conference on Management of Data, 2019, pp. 105–122 (cit. pp. 1, 6).
[25] UWSysLab, NOPaxos reference implementation, https://github.com/UWSysLab/NOPaxos, 2016 (cit. p. 27).