Internet performance measurement is commonly perceived as a high-cost control-plane activity and until now it has tended to be implemented on top of the network's forwarding operation. Consequently, measurement mechanisms have often had to trade relevance and accuracy over non-intrusiveness and cost effectiveness. In this paper, we present the software implementation of an in-line measurement mechanism that uses native structures of the Internet Protocol version 6 (IPv6) stack to piggyback measurement information on data-carrying traffic as this is routed between two points in the network. We carefully examine the overhead associated with both the measurement process and the measurement data, and we demonstrate that direct two-point measurement has minimal impact on throughput and on system processing load. The results of this paper show that adequately engineered measurement mechanisms that exploit selective processing do not compromise the network's forwarding efficiency, and can be deployed in an always-on manner to reveal the true performance of network traffic over small timescales.

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.

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.

Steven Deering's multicast communication model offers a powerful and flexible service for group communicating processes. Sending a multidestination datagram with only one local source operation, implicit source discovery for an open group, and logical binding. All theses features without limits on group size and dynamics. This proposition, later called any source multicast (ASM) has not been deployed at large scale on Internet partially because of the unscalability of multicast routing protocols. A new service model but potentially scalable to the whole Internet has been proposed: source specific multicast (SSM). It is less powerful because it needs an explicit source discovery mechanism for receivers. In this paper, we propose and evaluate such a session layer mechanism. This protocol offers the source discovery service missing from source specific multicast routing. We have implemented this protocol, which permits us to evaluate its feasibility and scalability.

IPv6 is intended to be the next network layer protocol of the Internet and it is designed to overcome the limitations of the current IPv4 protocol. However, the lack of resources in routers is still the issue in the deployment of state storing protocols in the IPv6 network. In particular, multicast protocols have taken the resources up to their limits for maintaining multicast tree information. The aim of this paper is to study the possible benefit of distributing the multicast tree states on the IPv6 topology in order to optimize the IPv6 network resource usage. To be able to carry out this study, we first had to map the topology of the current IPv6 network. We have used our network cartographer software in order to build an accurate map of the IPv6 network. We then studied the distribution of multicast states by using a simple repartition function. We have found that the use of this function can heavily decrease the number of states stored by the most loaded nodes at the cost of a small overall increase of the total number of states on the topology.