This pages contains all the tools and software models developed by the SPANDO project.
Software modules for simulating Amazon EC2 burstable instances.
Software modules and traces for the refactor and deployment heuristic used in the CLOUD 2016 paper.
Implementation of the heuristic used in the Cluster Computing 2016 paper.
It is a collection of MATLAB scripts implementing the functions described in the paper, which is a significantly improved version of SPANDO-Mapper, with new more updated traces.
Implementation of the heuristic used in the ICCAC 2015 paper.
It is a collection of MATLAB scripts implementing the functions described in the paper. The main purpose is to decide which and how many cloud resources to rent in order to run a cloud application, how to map the application components to the rented resources, and what spot price bids to use in order to minimise the total cost while fulfilling some performance requirements. The provided implementation allows the specification of the application model, the resource model, the performance requirements, and the traces of past spot prices (used to drive the prediction). Once all the input has been provided, an allocation matrix with an optimal solution is provided as output.