Round Table 2014-08-20 & 2014-09-01

  • Vincent Kherbache
    • Planning live-migrations to prepare servers for maintenance (VHPC’14) [slides]
  • Oleksandra Kulankhina
    • Verifying the correct composition of distributed components: Formalisation and Tool (FOCLASA’14) [slides]

Round Table 2014-06-26

  • Sara Kaddouri
    • Scalable, Dynamic and Expressive Social Data Streams’ Analytic (Master defense rehearsal) []
  • Galyna Zholtkevych
    • Optimisation of behaviour of component-based distributed systems (Master defense rehearsal) [slides]

Round Table 2014-06-16

  • Matias Ibañez
    • Autonomic management of gcm/proactive components (Internship) [slides]
  • Justine Rochas
    • Active Objects & Co. (PhD first year summary) [slides]

Talk Florian Kammueller Wednesday 23 at 14:00

Florian Kammueller (from Middlesex University) is visiting the Scale team from April 22 to April 25

Subject of the talk: Invalidating Policies using Structural Information
Insider threats are a major threat to many organisations. Even
worse, insider attacks are usually hard to detect, especially if an
attack is based on actions that the attacker has the right to
perform. In this paper we present a step towards detecting the risk
for this kind of attacks by invalidating policies using structural
information of the organisational model. Based on this structural
information and a description of the organisation’s policies, our
approach invalidates the policies and identifies exemplary sequences
of actions that lead to a violation of the policy in question. Based
on these examples, the organisation can identify real attack vectors
that might result in an insider attack. This information can be used
to refine access control system or policies.

Soutenance de thèse de Laurent Pellegrino // PhD defence

Jeudi 3 Avril à 13h30 salle Euler Violet de l’INRIA Sophia Antipolis.

Titre : Un intergiciel gérant des événements pour permettre l’émergence
d’interactions dynamiques et ubiquitaires dans l’Internet des services.

Le jury est composé de :
Ioana MANOLESCU, Inria Saclay – Île-de-France (rapporteur)
Etienne RIVIÈRE, Université de Neuchâtel (rapporteur)
Johan MONTAGNAT, CNRS (examinateur)
Ester PACITTI, Université de Montpellier 2 (examinateur)
Vivien QUÉMA, Grenoble INP (examinateur)
Françoise BAUDE, Université de Nice-Sophia Antipolis (directeur)
Fabrice HUET, Université de Nice-Sophia Antipolis (co-encadrant)

Continue reading

Seminaire Sara Bouchenak le Vendredi 28 mars a 15h30

Titre: Service Level Agreement for Cloud Computing: Towards a Control-Theoretic Approach

Resume: Cloud Computing is a paradigm for enabling remote, on-demand access to a set of configurable computing resources. This model aims to provide hardware and software services to customers, while minimizing human efforts in terms of service installation, configuration and maintenance, for both cloud provider and cloud customer. A cloud may have the form of an Infrastructure as a Service (IaaS), a Platform as a Service (PaaS) or a Software as a Service (SaaS). However, cloud’s ad-hoc management in terms of quality-of-service and service level agreement (SLA) poses significant challenges to the performance, availability, energy consumption and economical costs of the cloud. We believe that a differentiating element between Cloud Computing environments will be the quality-of-service and the service level agreement (SLA) provided by the cloud. In this talk, we will discuss the definition and implementation of a novel cloud model: SLAaaS (SLA aware Service). The SLAaaS model enriches the general paradigm of Cloud Computing, and enables systematic and transparent integration of service levels and SLA to the cloud. SLAaaS is orthogonal to IaaS, PaaS and SaaS clouds and may apply to any of them. Both the cloud provider and cloud customer points of view are taken into account. From cloud provider’s point of view, we present autonomic SLA management to handle performance, availability, energy and cost issues in the cloud. An innovative approach combines control theory techniques with distributed algorithms and language support in order to build autonomic elastic clouds. Novel models, control laws, distributed algorithms and languages will be proposed for automated provisioning, configuration and deployment of cloud services to meet SLA requirements, while tackling scalability and dynamics issues. On the other hand from cloud customer’s point of view, we discuss SLA governance. It allows cloud customers to be part of the loop and to ba automatically notified about the state of the cloud, such as SLA violation and cloud energy consumption. The former provides more transparecy about SLA guaranties, and the latter aims to raise customers’ awareness about cloud’s energy footprint.
Biographie de l’oratrice : Sara Bouchenak is Associate Professor in Computer Science at University of Grenoble I since 2004. She is the Academic Program Chair of the first year of the international Master of Science in Informatics at Grenoble. She is a member of the ERODS research group at LIG laboratory, where she conducts research on highly-available, dependable and manageable distributed computer systems. Prior to that, she was a visiting professor at Universidad Politécnica de Madrid, Spain, in 2009/2010, and an associate researcher at EPFL, Switzerland, in 2003.

Sara Bouchenak is a member of ACM, IEEE, and EuroSys; she was an officer of the French chapter of ACM-SIGOPS. She received her HDR (Habilitation à Diriger les Recherches) from University of Grenoble I in 2010, and her PhD in computer science from Grenoble Institute of Technology in 2001.

Lieu: salle de conf I3S

Seminaire Gaetan Hains le jeudi 6 mars a 11heures

Titre: Les algorithmes parallèles rencontrent les architectures hétérogènes: BSP devient SGL.

Resume: Depuis une trentaine d’année on sait accorder la réplication des processeurs avec le découpage des données
pour accélérer les opérations informatique. Le modèle Bulk­synchronous parallelism (BSP) permet de gérer
l’équilibre entre parallélisme et communications pour que les accélérations soient fiables sur des données et
des machines de taille illimitée.
Mais depuis le début des années 2000 les machines parallèles se compliquent: elles ont une hiérarchie
mémoire multi­niveaux et leurs processeurs ne sont pas hétérogènes. Le mélange entre multi­processeurs,
multi­coeurs et accélérateurs complique la tâche de l’algorithme parallèle.
Nous avons inventé un modèle SGL (scatter­gather language) qui généralise BSP à ces systèmes tout en
simplifiant la programmation.  L’exposé présente ce contexte, le modèle SGL, ses performances et
applications aux algorithmes parallèles les plus importants sur architectures hétérogènes.

Lieu: Salle de conférence I3S

Round Table 2014-02-11

  • Fabien Hermenier
    • Higher SLA Satisfaction in Datacenters with Continuous VM Placement Constraints (HotDep’2013) (slides)
  • Yanwen Chen
    • A Timed-pNets semantic model for distributed systems (slides)

Past Round Tables

Details of previous Round Tables (OASIS team) can be found here.