Grid'5000 user report for Alexandra Carpen Amarie

Jump to: navigation, search

User information

Alexandra Carpen Amarie (users, user, grenoble, ml-users user)
More user information in the user management interface.


  • Detecting malicious clients in the BlobSeer data-sharing service (Middleware) [achieved]
    Description: BlobSeer is a data-sharing system that addresses the problem of efficiently storing massive data in large-scale distributed environments. The goal of the experiment is to evaluate a malicious clients detection component we designed on top of BlobSeer. The tests focus on two different directions. First, we want to evaluate the reliability and the performance of the detection module for the illegal user actions, by measuring the delay between the users’ operations and the moment when they are detected as being malicious. Second, we determined the impact on the performance of BlobSeer operations when its components are equipped with an introspective system that constantly collects monitoring data from it.
    Results: The results show that the Security Management framework we proposed meets the requirements of a data storage system in a large-scale deployment: it was able to deal with a large number of simultaneous attacks and to restore and preserve the performance of the target system. Additionally, we showed that the introspection layer we developed for BlobSeer is able to generate all the relevant data needed by the security framework, while remaining non-intrusive.


  • MapReduce Applications in the Cloud: A Cost Evaluation of Computation and Storage [2012] (international)
    EntryType: inproceedings
    Isbn: 978-3-642-32343-0
    Booktitle: Data Management in Cloud, Grid and P2P Systems
    Volume: 7450
    Series: Lecture Notes in Computer Science
    Editor: Hameurlain, Abdelkader and Hussain, FarookhKhadeer and Morvan, Franck and Tjoa, AMin
    Publisher: Springer Berlin Heidelberg
    Author: Moise, Diana and Carpen-Amarie, Alexandra
    Pages: 37-48
    Abstract: MapReduce is a powerful paradigm that enables rapid implementation of a wide range of distributed data-intensive applications. The Hadoop project, its main open source implementation, has recently been widely adopted by the Cloud computing community. This paper aims to evaluate the cost of moving MapReduce applications to the Cloud, in order to find a proper trade-off between cost and performance for this class of applications. We provide a cost evaluation for running MapReduce applications in the Cloud, by looking into two aspects: the overhead implied by the execution of MapReduce jobs in the Cloud, compared to an execution on a Grid, and the actual costs of renting the corresponding Cloud resources. For our evaluation, we compared the runtime of 3 MapReduce applications executed with the Hadoop framework, in two environments: 1)on clusters belonging to the Grid'5000 experimental grid testbed and 2)in a Nimbus Cloud deployed on top of Grid'5000 nodes.
  • Bringing Introspection into BlobSeer: Towards a Self-Adaptive Distributed Data Management System [2011] (international)
    EntryType: article
    Author: Carpen-Amarie, Alexandra and Costan, Alexandru and Antoniu, Gabriel and Boug\'e Luc and Cai, Jing
    Publisher: University of Zielona G{\'o}ra Press, Poland
    Journal: International Journal of Applied Mathematics & Computer Science
    Audience: internationale
    Note: To appear in 2011
    Volume: 21
    Number: 2
  • Managing Data Access on Clouds: A Generic Framework for Enforcing Security Policies [2011] (international)
    EntryType: inproceedings
    Author: Basescu, Cristina and Carpen-Amarie, Alexandra and Leordeanu, Catalin and Costan, Alexandru and Antoniu, Gabriel
    Booktitle: The 25th International Conference on Advanced Information Networking and Applications (AINA-2011)
    Address: Singapore
  • Towards a Self-Adaptive Data Management System for Cloud Environments [2011] (international)
    EntryType: inproceedings
    Hal_id: inria-00575511
    Author: Carpen-Amarie, Alexandra
    Booktitle: 25th IEEE International Symposium on Parallel & Distributed Processing: Workshops and Phd Forum (IPDPS '11)
    Address: Anchorage Etats-Unis
    Audience: internationale
  • Bringing Introspection Into the BlobSeer Data-Management System Using the MonALISA Distributed Monitoring Framework [2009] (international)
    EntryType: inproceedings
    Author: Carpen-Amarie, Alexandra and Cai, Jing and Costan, Alexandru and Antoniu, Gabriel and Boug{\'e}, Luc
    Keywords: Distributed system; storage management; large-scale system; monitoring; introspection
    Language: English
    Booktitle: International Workshop on Autonomic Distributed Systems
    Address: Krakow, Poland
    Audience: international


    Success stories and benefits from Grid'5000

    last update: 2012-09-11 18:11:13