Browsing by Subject "Performance modeling"

A blockchain is an immutable record of transactions (called ledger ) between a distributed set of mutually untrusting peers. Although blockchain networks provide tremendous benefits, there are concerns about whether their performance would be a hindrance to its adoption. Our research is focused on Hyperledger Fabric (HLF), which is an open-source implementation of a distributed ledger platform for running smart contracts in a modular architecture. This thesis presents our research on performance modeling of Hyperledger Fabric using a Stochastic Petri Nets modeling formalism known as Stochastic Reward Nets (SRN). We capture the key system operations and complex interactions between them. We focus on two different releases of HLF, viz. v0.6 and v1.0+ (V1). HLF v0.6 follows a traditional state-machine replication architecture followed by many other blockchain platforms, whereas HLF V1 follows a novel execute-order-validate architecture. We parameterize and validate our models with data collected from a real-world Fabric network setup. Our models provide a quantitative framework that helps compare different deployment configurations of Fabric and make design trade-off decisions. It also enables us to compute performance for a system with proposed architectural improvements before they are implemented. From our analysis, we recommend design improvements along with the estimates of performance improvement. Overall, our models provide a stepping stone to the Hyperledger Fabric community towards achieving optimal performance of Fabric in the real-world deployments.

Cloud computing appears to be a paradigm shift in service oriented computing. Massively scalable Cloud architectures are spawned by new business and social applications as well as Internet driven economics. Besides being inherently large scale and highly distributed, Cloud systems are almost always virtualized and operate in automated shared environments. The deployed Cloud services are still in their infancy and a variety of research challenges need to be addressed to predict their long-term behavior. Performance and dependability of Cloud services are in general stochastic in nature and they are affected by a large number of factors, e.g., nature of workload and faultload, infrastructure characteristics and management policies. As a result, developing scalable and predictive analytics for Cloud becomes difficult and non-trivial. This dissertation presents the research framework needed to develop high fidelity stochastic models for large scale enterprise systems using Cloud computing as an example. Throughout the dissertation, we show how the developed models are used for: (i) performance and availability analysis, (ii) understanding of power-performance trade-offs, (ii) resiliency quantification, (iv) cost analysis and capacity planning, and (v) risk analysis of Cloud services. In general, the models and approaches presented in this thesis can be useful to a Cloud service provider for planning, forecasting, bottleneck detection, what-if analysis or overall optimization during design, development, testing and operational phases of a Cloud.