Roland Bless

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.

Early binding updates for mobile IPv6

The long latency associated with mobile IPv6 home-address and care-of-address tests can significantly impact delay-sensitive applications. This paper presents an optimization of mobile IPv6 correspondent registrations that evades the latency of both address tests. An optimized correspondent registration eliminates 50%, or more, of the additional delay that a standard correspondent registration adds to the network stacks overall latency. The optimization is realized as an optional, and fully backward-compatible, extension to mobile IPv6.

The Underlay Abstraction in the Spontaneous Virtual Networks (SpoVNet) Architecture

Overlay-based services are a popular approach for providing functions like multicast, quality of service or security in the Internet without requiring infrastructure support. This paper presents the Underlay Abstraction Layer in the Spontaneous Virtual Networks (SpoVNet) architecture that enables easy and flexible creation of such services. Also building on an overlay approach, the Underlay Abstraction provides generic functionality to cope with mobility, multi-homing, and heterogeneity. It manages node mobility by separating node identifiers from network locators and it provides persistent connections by transparently switching locators. Multi-homing is supported by choosing the most appropriate pair of network locators for each connection. In order to cope with network and protocol heterogeneity, it uses dedicated overlay nodes, e.g., for relaying between IPv4 and IPv6 hosts. Since the functionality provided by the Underlay Abstraction can be used by several overlay-based services in parallel, redundant functionality is removed from services and applications.

Quality-of-service signaling for next-generation IP-based mobile networks

We present a novel end-to-end QoS architecture that enables seamless services over heterogeneous wireless access networks. We discuss the main architectural approaches and design issues of mobility-aware QoS signaling in IP networks. Then we introduce a QoS signaling architecture that integrates resource management with mobility management. It is based on a domain resource manager concept and nicely supports various handover types in an integrated approach. In particular, we support anticipated handover with pre-reservation of resources over the old network before the mobile node is attached to the new access point.

Evaluation of differentiated services using an implementation under Linux

Current efforts to provide distinct levels of quality-of-service in the Internet are concentrated on the differentiated services (DS) approach. In order to investigate the gain for users of those differentiated services, early experiences with implementations with respect to real applications are needed. Simulation models are often not sufficient if a judgement of the behavior under realistic traffic scenarios is desired. Because implementing new functionality into dedicated router hardware is difficult and time-consuming, we focused on a software implementation for standard PC hardware. In this paper we present an implementation of differentiated services functions for a PC-based router running under the Linux operating system. Two per-hop forwarding behaviors for assured service and premium service were realized. Components for traffic conditioning such as traffic meter, token bucket, leaky bucket and traffic shaper were implemented as well as an efficient traffic classificator and queueing disciplines. We describe the design and implementation issues of these components, which were validated in detail by measurements. Evaluation of these measurements shows that the proposed forwarding behaviors work well for boundary and interior routers. But, it also becomes apparent that standard applications using short-lived TCP connections cannot always exploit the requested service completely whereas rate-controlled sending applications are able to take full advantage of it. Furthermore, it is planned to release the implementation to the public for research purposes.

Integration of the FreeBSD TCP/IP-stack into the discrete event simulator OMNet++

The discrete event simulator OMNeT++, that is programmed in C++, shows a steady growing popularity. Due to its well-structured nature, it is easy to understand and easy to use. A shortcoming of it, however, is the limited number of available simulation models. Especially, for network simulations a validated TCP implementation was missing. In order to avoid a re-implementation of a full-featured TCP, including all potential implementation errors and costly validation tests, we integrated a TCP/IP stack of a real operating system into OMNeT++. In this paper we show that such a port is feasible with reasonable effort and we describe difficulties of the integration process as well as the applied solutions. We also present some evaluation results that outline memory and CPU usage.

Dynamic Aggregation of Reservations for Internet Services

Global availability of on-demand services with an associated guaranteed quality-of-service (QoS) is still missing in the Internet today. The Differentiated Services architecture achieves scalability in the data plane by treating all flows with a specific type of service as one aggregate. In order to provide guaranteed end-to-end reservations, the control plane (e.g., performing admission control and management of resource reservations) has to be scalable as well. The DARIS architecture provides this essential linkage between scalability in the packet forwarding path and scalability of QoS management in the Internet. It comprises a novel concept of dynamic and hierarchical aggregation, which acts on the network level of autonomous systems (ASes). This relieves management entities in intermediate ASes of processing load by reducing their managed reservation states as well as the number of signaling messages that have to be processed significantly. Moreover, novel and special support for aggregation by a dedicated signaling protocol mechanism is provided.

Network Virtualization from a Signaling Perspective

The use of network virtualization promises additional flexibility and opens up many opportunities for deploying future network architectures. But the increased flexibility creates additional costs with respect to management and control as well as new issues that need to be addressed. In this paper, we describe a framework that allows for dynamic setup of virtual networks and we point out required mechanisms, interfaces, and protocols. Additionally, we take into account runtime aspects by examining control interfaces and signaling protocols necessary for the management of virtual networks and the attachment of end users.

Group communication in differentiated services networks

The Differentiated Services (DiffServ) approach will also bring benefits for multicast applications which need quality of service support. For instance, a highly reliable multicast service can be provided based on the proposed expedited forwarding behavior. Such a service may also be used advantageously in a global computing cluster infrastructure, e.g., for distribution of synchronization messages. However, DiffServ multicast services have not been addressed in a very detailed manner yet. This paper illustrates some of the problems which will arise when IP Multicast is used in DiffServ networks without taking special precautions into account for providing it. Those problems mainly lead to situations in which other service users are affected adversely. In order to retain the benefits of the DiffServ approach, a quite simple and scalable solution for those problems is needed, not resulting in additional complexity or costs in a DiffServ domain. The proposed architecture in this paper requires only an additional entry for the DiffServ Codepoint in multicast routing tables and some support by management mechanisms. The discussion of the related problems and presentation of the solution is illustrated and confirmed by some measurements performed with a Linux implementation of DiffServ, and an adapted Linux multicast router.

Fast scoped rerouting for BGP

This paper presents an approach to improve inter-domain connectivity in the Internet. This novel concept deploys inter-domain routing functions on two different time scales. The innovative fast scoped rerouting approach operates on a fine granular time scale while regular BGP is used on a coarse granular time scale. The overall concept intends to provide fast recovery from failures and to reduce the amount of globally visible BGP update messages. It also provides an alternative path in case of failure. Thus, this novel approach improves the Internets ability to derive a coherent view of its topology.