Laurent Mathy

A survey of proposals for an alternative group communication service

As expectations for the Internet to support multimedia applications grow, new services need to be deployed. One of them is the group communication service for one-to-many or many-to-many data delivery. After more than a decade of important research and development efforts, the deployment of multicast routing in the Internet is far behind expectations. Therefore, a first motivation for an alternative group communication service is to bypass the lack of native IP multicast routing. Although less efficient and scalable than native multicast routing, such alternative services are generally suitable for the purpose. A second possible motivation is to go beyond the limitations of classic multicast routing for very specific working environments. We identify, classify, and discuss some of these alternative approaches.

Network virtualization architecture: proposal and initial prototype

The tussle between reliability and functionality of the Internet is firmly biased on the side of reliability. New enabling technologies fail to achieve traction across the majority of ISPs. We believe that the greatest challenge is not in finding solutions and improvements to the Internets many problems, but in how to actually deploy those solutions and re-balance the tussle between reliability and functionality. Network virtualization provides a promising approach to enable the coexistence of innovation and reliability. We describe a network virtualization architecture as a technology for enabling Internet innovation. This architecture is motivated from both business and technical perspectives and comprises four main players. In order to gain insight about its viability, we also evaluate some of its components based on experimental results from a prototype implementation.

Towards high performance virtual routers on commodity hardware

Modern commodity hardware architectures, with their multiple multi-core CPUs and high-speed system interconnects, exhibit tremendous power. In this paper, we study performance limitations when building both software routers and software virtual routers on such systems. We show that the fundamental performance bottleneck is currently the memory system, and that through careful mapping of tasks to CPU cores, we can achieve forwarding rates of 7 million minimum-sized packets per second on mid-range server-class systems, thus demonstrating the viability of software routers. We also find that current virtualisation systems, when used to provide forwarding engine virtualisation, yield aggregate performance equivalent to that of a single software router, a tenfold improvement on current virtual router platform performance. Finally, we identify principles for the construction of high-performance software router systems on commodity hardware, including full router virtualisation support.

An Overlay Tree Building Control Protocol

TBCP is a generic Tree Building Control Protocol designed to build overlay spanning trees among participants of a multicast session, without any specific help from the network routers. TBCP therefore falls into the general category of protocols and mechanisms often referred to as Application-Level Multicasting. TBCP is an efficient, distributed protocol that operates with partial knowledge of the group membership and restricted network topology information. One of the major strategies in TBCP is to reduce convergence time by building as good a tree as possible early on, given the restricted membership/topology information available at the different nodes of the tree. We analyse our TBCP protocol by means of simulations, which shows its suitability for purpose.

Adaptive virtual network provisioning

In the future, virtual networks will be allocated, maintained and managed much like clouds offering flexibility, extensibility and elasticity with resources acquired for a limited time and even on a lease basis. Adaptive provisioning is required to maintain virtual network topologies, comply with established contracts, expand initial allocations on demand, release resources no longer useful, optimize resource utilization and respond to anomalies, faults and evolving demands. In this paper, we elaborate on adaptive virtual resource provisioning to maintain virtual networks, allocated initially on demand, in response to a virtual network creation request. We propose a distributed fault-tolerant embedding algorithm, which relies on substrate node agents to cope with failures and severe performance degradation. This algorithm coupled with dynamic resource binding is integrated and evaluated within a medium-scale experimental infrastructure.

GRIDKIT: Pluggable Overlay Networks for Grid Computing

A ‘second generation’ approach to the provision of Grid middleware is now emerging which is built on service-oriented architecture and web services standards and technologies. However, advanced Grid applications have significant demands that are not addressed by present-day web services platforms. As one prime example, current platforms do not support the rich diversity of communication ‘interaction types’ that are demanded by advanced applications (e.g. publish-subscribe, media streaming, peer-to-peer interaction). In the paper we describe the Gridkit middleware which augments the basic service-oriented architecture to address this particular deficiency. We particularly focus on the communications infrastructure support required to support multiple interaction types in a unified, principled and extensible manner—which we present in terms of the novel concept of pluggable overlay networks.

Evaluating Xen for Router Virtualization

In this paper, we evaluate the performance of a software IP router forwarding plane inside the Xen virtual machine monitor environment with a view to identifying (some) design issues in Virtual Routers. To this end, we evaluate and compare the forwarding performance of two identical Linux software router configurations, run either above the Xen hypervisor or within vanilla Linux. Even with minimal sized packets, we show that the Xen DomO privileged domain offers near native forwarding performance at the condition that the sollicitation to unpriviledged domains stay minimal, whereas Xen unprivileged domains offer very poor performance in every cases. This shows that an important design principle for virtual router platforms must be to handle all forwarding, for all virtual routers, onto the same forwarding engine, in order to avoid much detrimental per-packet context switching.

Securing internet coordinate embedding systems

This paper addresses the issue of the security of Internet Coordinate Systems,by proposing a general method for malicious behavior detection during coordinate computations. We first show that the dynamics of a node, in a coordinate system without abnormal or malicious behavior, can be modeled by a Linear State Space model and tracked by a Kalman filter. Then we show, that the obtained model can be generalized in the sense that the parameters of a filtercalibrated at a node can be used effectively to model and predict the dynamic behavior at another node, as long as the two nodes are not too far apart in the network. This leads to the proposal of a Surveyor infrastructure: Surveyor nodes are trusted, honest nodes that use each other exclusively to position themselves in the coordinate space, and are therefore immune to malicious behavior in the system.During their own coordinate embedding, other nodes can thenuse the filter parameters of a nearby Surveyor as a representation of normal, clean system behavior to detect and filter out abnormal or malicious activity. A combination of simulations and PlanetLab experiments are used to demonstrate the validity, generality, and effectiveness of the proposed approach for two representative coordinate embedding systems, namely Vivaldi and NPS.

From content distribution networks to content networks - issues and challenges

Due to the technical developments in electronics the amount of digital content is continuously increasing. In order to make digital content respectively multimedia content available to potentially large and geographically distributed consumer populations, Content Distribution Networks (CDNs) are used. The main task of current CDNs is the efficient delivery and increased availability of content to the consumer. This area has been subject to research for several years. Modern CDN solutions aim to additionally automate the CDN management. Furthermore, modern applications do not just perform retrieval or access operations on content, but also create content, modify content, actively place content at appropriate locations of the infrastructure, etc. If these operations are also supported by the distribution infrastructure, we call the infrastructure Content Networks (CN) instead of CDN. In order to solve the major challenges of future CNs, researchers from different communities have to collaborate, based on a common terminology. It is the aim of this paper, to contribute to such a terminology, to summarize the state-of-the-art, and to highlight and discuss some grand challenges for CNs that we have identified. Our conception of these challenges is supported by the answers to a questionnaire we received from many leading European research groups in the field.

Fast Userspace Packet Processing

In recent years, we have witnessed the emergence of high speed packet I/O frameworks, bringing unprecedented network performance to userspace. Using the Click modular router, we rst review and quantitatively compare several such packet I/O frameworks, showing their superiority to kernel-based forwarding. We then reconsider the issue of software packet processing, in the context of modern commodity hardware with hardware multi-queues, multi-core processors and non-uniform memory access. Through a combination of existing techniques and improvements of our own, we derive modern general principles for the design of software packet processors. Our implementation of a fast packet processor framework, integrating a faster Click with both Netmap and DPDK, ex-hibits up-to about 2.3x speed-up compared to other software implementations, when used as an IP router.