Performance modeling and analysis of a Hyperledger-based system using GSPN

Abstract

As a highly scalable permissioned blockchain platform, Hyperledger Fabric supports a wide range of industry use cases ranging from governance to finance. In this paper, we propose a model to analyze the performance of a Hyperledgerbased system by using Generalised Stochastic Petri Nets (GSPN). This model decomposes a transaction flow into multiple phases and provides a simulation-based approach to obtain the system latency and throughput with a specific arrival rate. Based on this model, we analyze the impact of different configurations of ordering service on system performance to find out the bottleneck. Moreover, a mathematical configuration selection approach is proposed to determine the best configuration which can maximize the system throughput. Finally, extensive experiments are performed on a running system to validate the proposed model and approaches.

Performance Evaluation of Blockchain Systems: A Systematic Survey

“…8. They can be also refined into five phases, namely HTTP, endorsement, ordering, validation & committing, and response [111]. HLF's modular design makes it possible to separately build a model for each phase and then cascade them to analyze the performance from the net/system level.…”

“…HLF's modular design makes it possible to separately build a model for each phase and then cascade them to analyze the performance from the net/system level. There have been two studies on HLF performance analysis using GSPN [111] and SRN [112], respectively. Both follow these general steps: 1) clarify transaction process steps and the business logic behind them; 2) create the associated transition diagrams of Petri nets according to the corresponding rules under reasonable assumptions; 3) translate to Markov chains for analytical solutions or directly leverage mathematical tools for numerical simulation solutions.…”

Adding semantics to measurements: Ontology-guided, systematic performance analysis

“…Performance optimization: [45,14,21,27] 3. Formal consensus modelling: [42,43,22,54,52] Category 1 receives most of the attention, which is identifying the performance characteristics of HLF. The evaluations employ empirical sensitivity analyses to measure the change in key performance indicators (such as throughput and end-toend latency) when applying different network scales, configurations, and workloads.…”

Porting a benchmark with a classic workload to blockchain: TPC-C on Hyperledger Fabric

“…The proposed improvements target either the steps of the consensus process or the architecture itself. • Formal models of the consensus process [13,23,24,30,31].…”