Section: Software and Platforms

DRMSim

Participants : David Coudert, Luc Hogie [correspondant] , Aurélien Lancin, Nicolas Nisse, Issam Tahiri.

Around 45,000 lines, developed in Java, collaboration between Coati , LaBRI, and Alcatel-Lucent Bell labs.

DRMSim relies on a discrete-event simulation engine aiming at enabling the large-scale simulations of routing models. DRMSim is developped in the framework of the FP7 EULER project. It proposes a general routing model which accommodates any network configuration. Aside to this, it includes specific models for Generalized Linear Preference (GLP), and k-chordal network topologies, as well as implementations of routing protocols, including a previously defined routing protocol and lightweight versions of BGP (Border Gateway Protocol).

The metric model takes measures along a discrete-event simulation which can be performed in many ways.

Commonly, a simulation campaign consists in iterating over the set of combinations of parameter values, calling the simulation function for every combination. These combinations are most often complex, impeding their description by a set of mathematical functions. Thus DRMSim provides a simulation methodology that describes (programmatically) the way a simulation campaign should be conducted.

DRMSim stores on disk every step of the execution of a simulation campaign. In a simulation campaign, simulation runs are independent (no simulation depends on the result computed by another simulation). Consequently they can be executed in parallel. Because one simulation is most likely to use large amount of memory and to be multi-threaded, parallelizing the simulation campaign on one single computer is a poor parallelization scheme. Instead, we currently work at enabling the remote parallel execution of several simulation runs, with the same distribution framework that is used in the Grph library.

DRMSim relies on the Mascsim abstract discrete-event simulation framework, the Grph library and the Java4Unix integration framework.

In 2013, the work on DRMSim consisted (1) in the implementation of a full support for dynamic networks, including topological modifications and evolving transfer loads in the simulated network. The implementation of the BGP protocol was updated so as to support these dynamic properties. (2) This implementation of BGP was also augmented with a framework enabling its dynamic profiling. (3) Finally DRMSim does no longer relies on the Dipergrafs library. Instead it now uses Grph , which brings better performance, stability and a broader set of graph algorithms.

See also the web page http://drmsim.gforge.inria.fr/ .