Action transverse sur la virtualisation
VIRTUALISATION & DEHARDWARIZATION
June 19-23, 2017
Le Croisic, France
Organized in the frameowork of the action transverse virtualisation du GdR RSD
Within the framework of the ``Groupe de Recherche Réseaux et Systèmes Distribués (RSD)'' supported by CNRS, we are pleased to announce that the 2017 RESCOM summer school edition will be held in Le Croisic, France, from June 19 to June 23, 2017. The RESCOM school is a key event of the French scientific landscape that gathers academics as well as industrials experts during one week to present and discuss about the latest challenges in Information and Communications (ICT) technologies.
Building on previous successful and highly attended editions of the Cloud Days organized by the transversal action ``Virtualization and Clouds'' of the RSD GDR, the 2017 RESCOM edition aims at further bridging the gap between the communication networks and distributed systems experts of the RSD GDR. Although the use of virtualization technologies has been leading to exciting developments for almost ten years now, current solutions for operating virtual infrastructures still need to provide a tighter integration between network, computation and storage resources at a geographically wider area network scope. This integration is mandatory to build the next generation of internet backbones (SDN, NFV...) and to cope with the new requirements of IoT and mobile computing applications that cannot be satisfied by current cloud computing offers.
To favor this cloud/network technology convergence, along the lines of the GDR Cloud Days of gathering together people with a diverse set of backgrounds,
we built the 2017 program in order to define common bases and highlight current challenges addressed by the network and distributed system communities.
We will discuss in particular how virtualization technologies are used in various contexts (mobile, infrastructure, data-centers, edge networks) and present major challenges in the research agenda. The program shows a balanced mix of general lectures and practical sessions with the goal of giving to attendees an large overview while being able to discover and deal with technical aspects.
Domaine Port aux Rocs, Le Croisic.
By train: Le Croisic is accessible by TGV train from Paris-Montparnasse station (via Nantes) or even from Paris CDG train station.
By plane: from Nantes Atlantique Airport, take the shuttle to Nantes train station and from there, a train to Le Croisic.
|June 19. 14:00-15:30||Adrien Lebre (L2SN, Inria): Ubiquitous Computing: from Mainframe to Clouds|
|June 19. 16:30-18:00||Giuseppe Bianchi (U. Rome II): Software Defined Networking: evolution, opportunities and challenges|
As defined in Wikipedia, Software Defined Networking (SDN) is about “decoupling the system that makes decisions about where trafficis sent (the control plane) from the underlying systems that forward traffic tothe selected destination (the data plane)”. In this introductive talk, we will overview the motivation that has lead, less than a decade ago, to the emergenceof SDN as well as the reasons and the pragmatic compromises (most notably inthe OpenFlow Design choices) which have made it viable. The talk will then discuss recent evolution, deployment perspectives, relation with emerging network function virtualization technologies, as well as current limitations and open research issues, with specific focus to the programmability challenges of the data plane.
|June 19. 18:00-19:15||Poster session|
|June 19. 21:00-23:15||Lab 1 and Lab 2 training|
|June 20. 09:00-10:30||Guillaume Pierre (Irisa): From Data Centers to Fog Computing: The Evaporating Cloud|
Cloud computing data centers are composed of very powerful computing nodes connected by reliable backbone networks. However, these resources are concentrated in a small number of a data centers. The latency between an end user and the closest available cloud data center comes in the range of 20-150 ms. A number of latency-sensitive applications (e.g., augmented reality) require extremely low end-to-end latencies and therefore cannot make use of traditional cloud platforms. Fog computing therefore aims to complement traditional cloud infrastructures with additional resources located extremely close to the user, within a couple of network hops. This requires one to distribute machines in a very large number of geographical locations so computation capacity is always available in immediate proximity of any end user. In this presentation I will discuss the application scenarios where fog computing is or isn't useful, and the architectural challenges one needs to face when designing the next-generation fog computing architectures.
|June 20. 11:00-12:30||Giuseppe Bianchi (U. Rome II): Data Plane programmability: the next step in Software Defined Networking|
|Software-Defined Networking (SDN) emerged as an attempt to introduce network innovations faster and to radically simplify and automate the management of large networks. Most of the traditional SDN work promoted theneat separation of the “smart” network control and management plane from the“dumb” packet forwarding plane. However, we believe that this rigid, physical, separation is by no means a conceptual principle, but it is just the consequence of the inability to emerge, so far, with pragmatic device-level programming interfaces more expressive than OpenFlow, i.e., which permit to program and deploy inside the switch more complex and dynamic per-flow “behavioral rules” rather than static forwarding rules. In the talk, we discuss pragmatic and viable ways to formally describe stateful per flow processing while retaining platform independence and portability across different network devices and nodes.
We posit that the unprecedented ability to locally deploy, in each network switch, third-party programmed platform-agnostic control functions, not only questions the rigid control/data plane separation that so far has driven SDN efforts, but rather might even pave the road towards the viable return of some “active networking” ideas in the SDN arena.
|June 20. 14:00-16:00||Lab 1: From virtual machines to OpenStack leveraging container technologies|
|June 20. 16:30-19:00||Lab 2: SDN forwarding and switching.|
|June 20. 21:00-23:15||Lab 1 and Lab 2 follow-up|
|June 21. 09:00-10:30||Fabien Hermenier (i3S): TBA|
|June 21. 11:00-12:30||Vania Conan (Thales): NFV Orchestration|
NFV orchestration is key in the emergence of virtualized networks: it comes as a complement to the Software Defined Network paradigm and represents the next step towards automating network management. In a virtualized network setting the network functions (routing, name resolution, firewalling, network acceleration, …) are provided as software packages, Virtual Network Functions (VNFs). This changes dramatically how network management must be addressed, as it must adopt the standard practice of software development and operations. This also opens new opportunities to achieve in practice the long standing goal of automating network management. In this talk we review the main challenges of NFV orchestration, VNF chaining and illustrate the benefits that this approach can bring to network management. The talk draws on example work done in the lab on on-line and off-line VNF placement and chaining using game theoretic approaches. It concludes with future perspectives to further improve network elasticity with adaptive NFV orchestration.
|June 21. 21:00-23:15||Lab 1 and Lab 2 follow-up|
|June 22. 09:00-10:30||Jérémie Leguay (Huawei): Online and Global Network Optimization with SDN|
|The computation power of SDN controllers fosters the development of a new generation of control plane that uses compute-intensive operations to automate and optimize the network configuration across layers. From now on, cutting-edge optimization and machine learning algorithms can be used to control networks in real-time. This formidable opportunity transforms the way routing systems should be conceived and designed.
This talk analyzes the ongoing transformation of network architectures and surveys various emerging SDN technologies (protocols, software architectures) under the light of their potential for real-time network optimization. It then reviews algorithm challenges for the next generation of routing platforms (e.g., admission control, routing optimization, configuration updates, monitoring). In particular, it shows that the main challenge is the resolution of combinatorial problems at large-scale and in an online fashion. As an illustration, it goes through a number of recent algorithmic contributions to solve both offline and online problems at scale using tools from optimization and control theory. Finally, it reviews promising directions on robust routing and distributed computing under investigations.
|June 22. 11:00-12:30||Shadi Ibrahim (Inria): Big Data Processing in the Cloud: Hadoop and Beyond|
Data volumes are ever growing, for a large application spectrum going from traditional database applications, scientific simulations to emerging applications including Web 2.0 and online social networks. To cope with this added weight of Big Data, we have recently witnessed a paradigm shift in the way data is processed through the MapReduce model. First promoted by Google, MapReduce has become, due to the popularity of its open-source implementation Hadoop, the de facto programming paradigm for Big Data processing in large-scale data-centers and clouds.
The goal of this talk is to serve as a first step towards exploring the Hadoop platform and also to provide a short introduction into working with big data in Hadoop. An overview on Big Data including definitions, the source of Big Data, and the main challenges introduced by Big Data, will be presented. We will then present the MapReduce programming model as an important programming model for Big Data processing in the Cloud. Hadoop ecosystem and some of major Hadoop features will then be discussed. Finally, we will discuss several approaches and methods used to optimise the performance of Hadoop in the Cloud. Finally, we will discuss the limitations of Hadoop and introduce new Big Data systems including Spark.
|June 22. 14:00-16:00||Lab 3: From virtual machines to OpenStack leveraging container technologies|
|June 22. 16:30-18:00||Lab 4: SDN forwarding and switching.|
|June 22. 18:00-19:15||Poster session (award announcement)|
|June 22. 21:00-23:15||Lab 3 and Lab 4 follow-up|
|June 23. 09:00-10:30||Paolo Bellavista (U. Bologna): Edge Computing for IoT Application Scenarios|
|The number of connected devices worldwide continues to grow and is forecast to triple by the end of 2019, from 15 to 50 billion. It starts to be widely recognized that this continuous and exponential growth will inevitably forcetowards a deep transformation of how we organize, manage, and access virtualized distributed resources, which we currently identify with the global location-transparent cloud. This transformation is particularly central for IoT application scenarios, where strict latency and reliability requirements, e.g., for prompt actuation of control loops, are crucial to determine even theoverall stability and behaviour of the system. In this perspective, edge computing (or fog computing, or cloudlets) is expected to play a very relevant role in future IoT infrastructures and in efficient IoT-to-cloud integration in wide-scale deployment environments.
The objectives of this talk will be to introduce the primary advantages and stillopen technical challenges related to edge computing design, implementation, anddeployment in application scenarios with strict latency and reliability requirements, e.g., in Industry 4.0 production plants. In addition to modelsfor related architectures, for hierarchical locality management, for data aggregation and trigger determination at both sensors/actuators and edge nodes,for distributed control functions at both cloud and edge nodes, the course willdiscuss about the state-of-the-art of dynamic distribution of processing functions in the three layers of a node-edge-cloud IoT deployment environment .The illustrated concepts will be accompanied by practical examples (e.g., using distributed geometric monitoring functions that dynamically migrate as Docker-containerized edge computing functions), as well as a fresh overview ofmechanisms/technologies/standardization directions that can be considered towards the vision of an efficient edge computing support for “industrial-grade” IoT applications.
|June 23. 11:00-12:30||Lucas Nussbaum (Loria): Scaling the Experiments|
|There is a wide range of options to experiment on distributed systems
and networking. Simulators running on a laptop or self-made testbeds are
sometimes enough, but our field usually targets large to very large
systems with potentially millions or billions of elements. In such a
case, relying on a laptop or a self-made testbed is impossible. To scale
up our experimental research, we can rely on larger-scale
infrastructures and testbeds.
In a first part, this talk will provide an overview of the landscape of infrastructures and testbeds supporting experimental research in distributed systems and networking.
In a second part, we will focus on SDN/NFV experimentation, and will provide some feedback about the current state of available experimentation tools targeting large scale systems.
Lab 1: From virtual machines to OpenStack leveraging container technologies.
Responsibles: Ronan-Alexandre Cherrueau, Dimitri Pertin, Matthieu Simonin, L2SN.
More details TBA.
Lab 2: SDN forwarding and switching.
Responsible: Kamel Attou, Chi-Dung Phung, Stefano Secci (LIP6), José Sanchez (Orange).
More details TBA.
Lab 3: Cloud orchestration.
Responsible: Fabien Hermenier, i3S.
More details TBA.
Lab 4: SDN routing and NFV chaining.
Damien Saucez, Inria.
More details TBA.
We encourage young researchers to present their work with a poster. Posters may be accompanied by technical demonstrations not requiring Internet access and additional screens. Researchers will present their work during a poster session on Monday, June 19, and Wednesday, June 21. Students will benefit from an exceptional forum composed of young and senior researchers from both communities to exchange ideas and new projects around their work.
We ask to submit the poster proposal for review with a title and an extended abstract of up to two pages to the school committee.
Extended abstracts must be submitted in PDF following the IEEE conference format to https://easychair.org/conferences/?conf=rescom17 before April 30, 11:59PM CET. Accepted poster abstracts will be published in the online programme.
|University / public research institution participant||700 Euro TTC|
|Company participant||850 Euro TTC|
*limited number of places at this rate.
Free registration for CNRS staff.
All prices include accommodation, meals, social event and school access.
A certificate of attendance with the hour volume can be produced on request.
Click here to register: registration platform
LS2N, Inria, Nantes.
Inria, Sophia Antipolis.
Rémy Durand, LS2N, Université de Nantes
Salima Hamma, LS2N, Université de Nantes
Adrien Lebre, LS2N, Inria, Nantes
Rémi Lehn, LS2N, Université de Nantes
Benoît Parrein, LS2N, Université de Nantes
Dimitri Pertin, L2SN, Inria, Nantes.
Want to sponsor? Drop an email to email@example.com
ASSOCIATED RESEARCH PROJECTS