Improving Cloud Simulation using the Monte-Carlo Method

Luke Bertot (1) , Stéphane Genaud (1) , Julien Gossa (1)

1 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie

In the cloud computing model, cloud providers invoice clients for resource consumption. Hence, tools helping the client to budget the cost of running his application are of pre-eminent importance. However, the opaque and multi-tenant nature of clouds make task runtimes variable and hard to predict, and hamper the creation of reliable simulation tools. In this paper, we propose an improved simulation framework that takes into account this variability using the Monte-Carlo method. We consider the execution of batch jobs on an actual platform, scheduled using typical heuristics based on the user estimates of task runtimes. We model the observed variability through simple random variables to use as inputs to the Monte-Carlo simulation. Based on this stochastic process, predictions are expressed as interval-based makespan and cost. We show that, our method can capture over 90% of the empirical observations of makespan while keeping the capture interval size below 5% of the average makespan.

Domaines: Calcul parallèle, distribué et partagé [cs.DC]; Modélisation et simulation

Luke Bertot, Stéphane Genaud, Julien Gossa. Improving Cloud Simulation using the Monte-Carlo Method. Euro-Par 2018: Parallel Processing, 11014, pp.404-416, 2018. ⟨hal-02161784⟩