Regression-based resource provisioning for session slowdown guarantee in multi-tier Internet servers

Autonomous management of a multi-tier Internet service involves two critical and challenging tasks, one understanding its dynamic behaviors when subjected to dynamic workloads and second adaptive management of its resources to achieve performance guarantees. We propose a statistical machine learning based approach to achieve session slowdown guarantees of a multi-tier Internet service. Session slowdown is the relative ratio of a session’s total queueing delay to its total processing time. It is a compelling performance metric of session-based online transactions because it directly measures user-perceived relative performance and it is independent of the session length. However, there is no analytical model for session slowdown on multi-tier servers. We first conduct training to learn the statistical regression models that quantitatively capture an Internet service’s dynamic behaviors as relationships between various service parameters. Then, we propose a dynamic resource provisioning approach that utilizes the learned regression models to efficiently achieve session slowdown guarantee under dynamic workloads. The approach is based on the combination of offline training and online monitoring of the Internet service behavior. Simulations using the industry standard TPC-W benchmark demonstrate the effectiveness and efficiency of the regression based resource provisioning approach for session slowdown oriented performance guarantee of a multi-tier e-commerce application.     

Multiclass P2P networks: Static resource allocation for service differentiation and bandwidth diversity

We propose a multiclass fluid model for BitTorrent-like content-distribution systems. The new model can model heterogeneous peers, in which peers have different access bandwidths. The model can also model BitTorrent-like systems which provide differential service (for example, first class and second class service) to the participating peers. The fluid model leads to a non-linear system of differential equations with special structure. For the service differentiation problem, we prove that the system of differential equations admits a unique stable equilibrium, that we compute in closed-form. We also provide the average download times for both classes. For the bandwidth diversity problem, we show that the system of differential equations has a stable state that may depend on the initial conditions. We compute the average download time of both classes for each reachable steady-state.