Sixth International Conference on Simulation Tools and Techniques

Research Article

A Framework for High Performance Simulation of Transactional Data Grid Platforms

  • @INPROCEEDINGS{10.4108/icst.simutools.2013.251737,
        author={Pierangelo Di Sanzo and Francesco Antonacci and Bruno Ciciani and Roberto Palmieri and Alessandro Pellegrini and Sebastiano Peluso and Francesco Quaglia and Diego Rughetti and Roberto Vitali},
        title={A Framework for High Performance Simulation of Transactional Data Grid Platforms},
        proceedings={Sixth International Conference on Simulation Tools and Techniques},
        publisher={ICST},
        proceedings_a={SIMUTOOLS},
        year={2013},
        month={7},
        keywords={transactional data platforms parallel discrete event simulation},
        doi={10.4108/icst.simutools.2013.251737}
    }
    
  • Pierangelo Di Sanzo
    Francesco Antonacci
    Bruno Ciciani
    Roberto Palmieri
    Alessandro Pellegrini
    Sebastiano Peluso
    Francesco Quaglia
    Diego Rughetti
    Roberto Vitali
    Year: 2013
    A Framework for High Performance Simulation of Transactional Data Grid Platforms
    SIMUTOOLS
    ACM
    DOI: 10.4108/icst.simutools.2013.251737
Pierangelo Di Sanzo1, Francesco Antonacci1, Bruno Ciciani1, Roberto Palmieri1, Alessandro Pellegrini1,*, Sebastiano Peluso1, Francesco Quaglia1, Diego Rughetti1, Roberto Vitali1
  • 1: Sapienza, University of Rome
*Contact email: pellegrini@dis.uniroma1.it

Abstract

One reason for the success of in-memory (transactional) data grids lies on their ability to fit elasticity requirements imposed by the cloud oriented pay-as-you-go cost model. In fact, by relying on in-memory data maintenance, these platforms can be dynamically resized by simply setting up (or shutting down) instances of so called data cache servers. However, defining the well suited amount of cache servers to be deployed, and the degree of in-memory replication of slices of data, in order to optimize reliability/availability and performance tradeoffs, is far from being a trivial task. To cope with this issue, in this article we present a framework for high performance simulation of in-memory data grid systems, which can be employed as a support for timely what-if analysis and exploration of the effects of reconfiguration strategies. The framework consists of a discrete event simulation library modeling differentiated data grid components in a modular fashion, which allows easy (re)-modeling of different data grid architectures (e.g. characterized by different concurrency control schemes). Also, the library has been designed to be layered on top of the open source {\sf ROOT-Sim} parallel simulation engine, natively offering facilities for optimized resource usage in the context of model execution on top of multi-core and cluster based architectures.