Virtualization Working Group

From Grid5000
Jump to: navigation, search

Bringing up research and development activities in the context of Grid and Cloud Computing around virtualization technology

Please join the Grid'5000 virtualization mailing list (CFP, important publications, events, ...)

Contents

Overview

The aim of the Virtualization Working Group consists in listing/promoting and pooling the different research and development activities done in the context of the Grid'5000 framework and more generally by the French community around virtualization. The WG is interested by both the use of VM capabilities to deal with scientific and technical challenges and the improvement on the VM technology itself.

Academic Teams Involved (alphabetical order)

  • ASCOLA project (Ecole des Mines de Nantes, INRIA Rennes Bretagne Atlantique)
  • IRIT (Toulouse)
  • MYRIADS project (INRIA Rennes Bretagne Atlantique)
  • RESO project (LIP, INRIA Rhones Alpes)
  • RUNTIME project (LaBRI, INRIA Bordeaux - Sud-Ouest)

Research activities conducted by the Grid'5000 community

Research Project

Green Open Cloud

The Green Open Cloud project supported by the RESO team explores the analysis and design of energy aware Clouds infrastructures.


HIPcal

HIPcal (ANR-06-CIS6-005) studies a new paradigm (grid substrate) based on confined virtual cluster concept for resource control in grids.

OSCAR-V

OSCAR-V aims at providing tools for the creation, the deployment and the management of virtual machines and HostOSes within a cluster.

Software

Entropy

Entropy is a virtual machine manager for clusters. It acts as an infinite control loop, which performs a globally optimized placement according to cluster resource usage and scheduler objectives.

HIPerNet

HIPerNet software is developed, by the RESO team, in the context of the HIPcal project (ANR-06-CIS6-005). HIPCAL studies a new paradigm (grid substrate) based on confined virtual cluster concept for resource control in grids. In particular, we propose to study and implement new approaches for bandwidth sharing and end to end network quality of service guarantees. The global infrastructure (computers, disks, networks) partitioned in virtual infrastructures (aggregation of virtual machines coupled with virtual channels) is dynamically composed. These virtual clusters are multiplexed in time and space, isolated and protected. The goal of this project is to explore an approach in a break with current services-oriented principles developed in grids to jointly enhance the application portability, the communications performance control and their security. The project aims at providing a grid substrate based on end to end bandwidth reservation, control overlay, network and system virtualization, cryptographic identification principles.

JASMINe VMM

JASMINe VMM aims at offering a unified Java-friendly API and object model to manage virtualized servers and their associated hypervisor.

  • Status: in progress
  • Contact:
  • Homepage: JASMINe VMM
  • Availability: Refer to the JASMINe website

VIDA

VIDA (VIrtual Deployment Architecture) is an ongoing project which aims at creating a SOA based infrastructure for the deployment and management of virtual clusters (VCs).

  • Status: in progress
  • Contact:
  • Homepage: JASMINe VIDA
  • Availability: Refer to the VIDA website

VMdeploy

VMdeploy is a shell script that deploys VMware virtual machines on grid nodes, allowing the users to run their scripts into the virtual machines. VMdeploy has the capability to reserve nodes either as soon as possible (interactive) or when resources are idle (besteffort).

OSCAR-V

Virtualization support for OSCAR. OSCAR-V provides a set of tools and package that allow users to deploy virtualized cluster, i.e., virtual machine within a physical cluster.

SVMSched

SVMSched (Smart Virtual Machine Scheduler) is a tool enabling and easing the set-up of on-demand SaaS and PaaS cloud infrastructures on top of OpenNebula. Providing an high-level abstraction of virtual machines, along with a high-capability of dynamicity and customization introduced in the provisioning of virtual machines it enables powerful and flexible resource management capabilities to schedule service execution.

Snooze

Snooze is a scalable, highly available, and energy-efficient virtual machine (VM) management system. Particularly, it allows users to build compute infrastructures from virtualized resources and manage a large number of VMs. For scalability and high availability, Snooze is based on a self-configuring and healing hierarchical architecture. For energy efficiency, Snooze provides a holistic energy management approach via integrated VM resource (i.e. CPU, memory, network) utilization monitoring, server underload/overload mitigation, VM consolidation, and power management. It can be used either to manage production data centers or serve as a research testbed to experiment with advanced VM management algorithms (e.g. VM consolidation).

PhD related to virtualization concerns in distributed computing since 2008

Name Topic Team Contact Homepage
Fabienne Anhalt Network virtualization and Virtual Routers RESO fabienne.anhalt@ens-lyon.fr http://perso.ens-lyon.fr/fabienne.anhalt
François Diakhaté Efficient Shared Memory Message Passing for Inter-VM Communications. RUNTIME fdiakh@gmail.com
Eugen Feller Autonomic and Energy-Efficient Management of Large-Scale Virtualized Data Centers MYRIADS eugen.feller@inria.fr http://www.irisa.fr/myriads/members/efeller
Jérôme Gallard Ddeploying and managing virtual machines in Grids. PARIS Jerome.Gallard@inria.fr http://www.irisa.fr/paris/web/component/option,com_uhp/task,view/Itemid,110/id,63/
Fabien Hermenier Dynamic Management of Virtual Machines in clusters ASCOLA fabien.hermenier@emn.fr http://www.emn.fr/x-info/fhermeni/
Guilherme Koslovski Virtual Resources and Interconnection Networks Description Language RESO guilherme.koslovski@ens-lyon.fr http://perso.ens-lyon.fr/guilherme.koslovski
Hien Nguyen Van SLA-aware virtual resource management for service hosting platforms. ORANGE LABS hien.nguyenvan@orange-ftgroup.com
Anne-Cécile Orgerie Energy awareness in Clouds infrastructures. RESO Anne-Cécile Orgerie http://perso.ens-lyon.fr/annececile.orgerie
Jonathan Pastor Design and Development of a fully distributed IaaS system. ASCOLA Jonathan Pastor http://www.emn.fr/z-info/ascola/doku.php?id=internet:members:jpastor:overview


Rémy Pottier DSL for VM Management ASCOLA remy.pottier@mines-nantes.fr http://www.emn.fr/z-info/ascola/doku.php?id=internet:members:rpottier:overview


Flavien Quesnel Toward Cooperative Management of Large-scale Virtualized Infrastructures: the Case of Scheduling. ASCOLA Flavien Quesnel http://www.emn.fr/z-info/fquesnel/
Alain Tchana Migration of virtual machines in distributed architectures (focus on MPI applications) IRIT tchana@irit.fr
Rodrigue Chakode Computing On-demand: Scheduling within virtual infrastructures, Dynamic resource allocation, Dynamic and automatic reconfigurability of computing environments, etc. INRIA Mescal Team Rodrigue.Chakode@imag.f http://mescal.imag.fr/membres/rodrigue.chakode/

Other Research Project / Software

Nimbus

Nimbus is an open source toolkit that allows you to turn your cluster into an Infrastructure-as-a-Service (IaaS) cloud.

OpenNebula

OpenNebula is a Virtual Infrastructure Manager that orchestrates storage, network and virtualization technologies to enable the dynamic placement of multi-tier services (groups of interconnected virtual machines) on distributed infrastructures.

VirtualLinux

VirtuaLinux is a Linux meta-distribution that allows the creation, deployment and administration of virtualized clusters with no single point of failure. VirtuaLinux architecture supports disk-less configurations and provides an efficient, iSCSI based abstraction of the SAN. Clusters running VirtuaLinux exhibit no master node to boost resilience and flexibity.

Grivon

The GriVon project (i.e., AIST cloud computing research) aims to develop a novel management framework for distributed computing resources among multiple datacenters. It covers cluster virtualization, datacenter migration, and Green IT initiatives.

Resources

Useful Links

Slides

Main events

Conferences

  • ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments (VEE)
  • ACM SIGMOD/SIGOPS International Conference on Cloud Computing (SOCC)

Worshops

  • Workshop on Virtualization Technologies in Distributed Computing (VTDC)
  • ACM Workshop on System-level Virtualization for High Performance Computing (HPCVirt) -- HPCVirt 2007, HPCVirt 2008, HPCVirt 2009
  • Workshop on Virtualization in High-Performance Cloud Computing (VHPC)

Bibtex Archive

Please join the virtualization working group on citeulike http://www.citeulike.org/groupfunc/11707/home

The first objective of this citeulike group consists in : listing all important (or less important) papers around virtualization technologies. Each engineer/researcher (interns / phd student, post-doc, permanent, ...) can add new references and thus improve the list. The second objective is to maintain a bibtex file as complete and as clean as possible (editor, year, page, ....) for the community. Such a file will be really useful to write papers in the principal conferences/journals.


For each new entry, please give the different informations :

- Title: only the first letter should be uppercase
- Authors: the list should be as complete as possible
- Booktitle
- Editors
- Pages number
- Year
- Location

The bibkey should rely on the following scheme : firstauthorname:confXX where XX stands for the year (ex : martin:ccgrid09)

Please try to find the best tags from the available ones and add report or workshop or conference as th main tag

Personal tools
Namespaces

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