Grid'5000 user report for Carlos Barrios

Jump to: navigation, search

User information

Carlos Barrios (users, user, grenoble, ml-users, digitalis user)
More user information in the user management interface.

Experiments

  • High Bandwidth Data Transfer Analisys and Modeling in Grids (Networking) [achieved]
    Description: In the High Performance Computing research, the modeling of systems performance allows to known the behavior a system according to the users requeriments. Also, a model gives a specification for the construction, maintenance, scalability or replication of a high performance computing infrastructure. In this work, it presents a model of high bandwidth data transfer since the analisys of experimental data. This experimentation has been made in the clusters of Grid5000.
    Results: A experimental model of the Grid5000 characteristics of the high bandwidth transfer of the great size messages intra-clusters and inter-cluster communication.
  • NFSp: A Non-Intrusive Parallel NFS Server (Networking) [achieved]
    Description: NFSp stands for Parallel NFS. The main idea of this project is to use several nodes as I/O backend for one server, which is seen by clients like a regular NFS. This means that NFSp is a plug-in replacement for any currently used server, at the same time, thanks to the I/O nodes used for actual I/O operations it provides very good performance. This project was the subject of Pierre Lombard's PhD thesis in 2001. The implementation which accompanied the dissertation supported NFS version 2 and was available as standalone application or a patch for the Linux 2.4 kernel. The first implementation has brought several concepts to apply to a NFS server such as data striping, I/O servers redundancy, .... . Yet, the main drawback this version had was there was only one meta-data server: since it acted as a central point through which every request had to go, it was indeed a scalability limitation (especially for write performances). In 2003, Rafael Avila started his PhD on a new distributed version, called distributed NFSp. The dNFSp project takes the NFSp concept to the next level. It's main goal is to provide better performance to applications exploring both read and write operations, since the last one is not tackled by the original model. The basis for the proposed system is a distributed metadata management model, which allows for better scalability and reduces the computational cost on the original NFSp metaserver, and also a relaxed mechanism for maintaining metadata coherence based on LRC (Lazy Release Consistency), which enables the distribution of the service without incurring in costly data synchronisation operations.
    Results: One of the first NFS parallel model.
    More information here
  • MEG PROJECT (Application) [in progress]
    Description: The project aims to make the study about the scalability opportunities between the electromagnetic applications and your execution in grid platforms.
    Results:
    More information here
  • Grid Computing Security (Other) [in progress]
    Description:
    Results:
  • Grid Computing Virtualization on Non High Available Platforms (Middleware) [in progress]
    Description: The objective of this project is to build and deploy enormous environments through virtualization of machines using Xen paravirtualizacion
    Results:
  • (Networking) []
    Description:
    Results:
  • (Other) [planned]
    Description: Account was involved in the High Performance Interaction for Scientific Computing project. This project aims to exploit large scale architectures with visualization and simulation applications for scientific needs.
    Results:
  • Griduis-2: A High Available high performance computing infrastructure based on G5K (Middleware) [in progress]
    Description:
    Results:
    More information here

Publications

Collaborations

    Success stories and benefits from Grid'5000

    • Success stories
    • We arrive to contribute with a realistic performance evaluation technique to treat massive and parallel data transfer on high bandwidth networks into Grid computing environments. This realistic performance evaluation technique is addressed to observe in real time the data transfer behaviors during the execution of Grid computing applications.

    last update: 2011-06-22 11:20:00

    Personal tools
    Namespaces

    Variants
    Views
    Actions
    Public Portal
    Users Portal
    Admin portal
    Wiki special pages
    Toolbox