Simon Oechsner

Characterization of BitTorrent swarms and their distribution in the Internet

The optimization of overlay traffic resulting from applications such as BitTorrent is a challenge addressed by several recent research initiatives. However, the assessment of such optimization techniques and their performance in the real Internet remains difficult. Despite a considerable set of works measuring real-life BitTorrent swarms, several characteristics of those swarms relevant for the optimization of overlay traffic have not yet been investigated. In this work, we address this lack of realistic swarm statistics by presenting our measurement results. In particular, we provide a statistical characterization of the swarm sizes, the distribution of peers over autonomous systems (ASs), the fraction of peers in the largest AS, and the size of the shared files. To this end, we consider different types of shared content and identify particular characteristics of regional swarms. The selection of the presented data is inspired by ongoing discussions in the IETF working group on application layer traffic optimization (ALTO). Our study is intended to provide input for the design and the assessment of ALTO solutions for BitTorrent, but the applicability of the results is not limited to that purpose.

Pushing the performance of Biased Neighbor Selection through Biased Unchoking

Locality promotion in P2P content distribution networks is currently a major research topic. One of the goals of all discussed approaches is to reduce the interdomain traffic that causes high costs for ISPs. However, the focus of the work in this field is generally on the type of locality information that is provided to the overlay and on the entities that exchange this information. An aspect that is mostly neglected is how this information is used by the peers. In this paper, we consider the predominant approach of Biased Neighbor Selection and compare it with Biased Unchoking, which is an alternative locality aware peer selection strategy that we propose in this paper. We show that both mechanisms complement each other for the BitTorrent file sharing application and achieve the best performance when combined.

Interaction patterns between P2P content distribution systems and ISPs

Peer-to-peer (P2P) content distribution systems are a major source of traffic in the Internet, but the application layer protocols they use are mostly unaware of the underlying network in accordance with the layered structure of the Internets protocol stack. Nevertheless, the need for improved network efficiency and the business interests of Internet service providers (ISPs) are both strong drivers toward a cross-layer approach in peer-to-peer protocol design, calling for P2P systems that would in some way interact with the ISPs. Recent research shows that the interaction, which can rely on information provided by both parties, can be mutually beneficial. In this article we first give an overview of the kinds of information that could potentially be exchanged between the P2P systems and the ISPs, and discuss their usefulness and the ease of obtaining and exchanging them. We also present a classification of the possible approaches for interaction based on the level of involvement of the ISPs and the P2P systems, and we discuss the potential strengths and the weaknesses of these approaches.

Can P2P-Users Benefit from Locality-Awareness?

Locality-awareness is considered as a promising approach to increase the efficiency of content distribution by peer-to-peer (P2P) networks, e.g., BitTorrent. It is intended to reduce the inter-domain traffic which is costly for Internet service providers (ISPs) and simultaneously increase the performance from the viewpoint of the P2P users, i.e, shorten download times. This win-win situation should be achieved by a preferred exchange of information between peers which are located closely to each other in the underlying network topology. A set of studies shows that these approaches can lead to a win-win situation under certain conditions, and to a win-no lose situation in most cases. However, the scenarios used assume mostly homogeneous peer distributions and that all peers have the same access speed. This is not the case in practice according to several measurement studies. Therefore, we extend previous work in this paper by studying scenarios with real-life, skewed peer distributions and heterogeneous access bandwidths of peers. We show that even a win-no lose situation is difficult to achieve under those conditions and that the actual impact for a specific peer depends heavily on the used locality-aware peer selection and the concrete scenario. Therefore, we conclude that current proposals need to be refined so that users of P2P networks can be sure that they also benefit from their use. Otherwise, a broad acceptance of the concept of locality-awareness in the user community of P2P networks will not take place.

The Impact of Caching on BitTorrent-Like Peer-to-Peer Systems

Peer-to-peer file-sharing systems are responsible for a significant share of the traffic between Internet service providers (ISPs) in the Internet. In order to decrease their peer-to-peer related transit traffic costs, many ISPs have deployed caches for peer-to-peer traffic in recent years. We consider how the different types of peer-to-peer caches - caches already available on the market and caches expected to become available in the future - can possibly affect the amount of inter-ISP traffic. We develop a fluid model that captures the effects of the caches on the system dynamics of peer-to-peer networks, and show that caches can have adverse effects on the system dynamics depending on the system parameters. We combine the fluid model with a simple model of inter-ISP traffic and show that the impact of caches cannot be accurately assessed without considering the effects of the caches on the system dynamics. We identify scenarios when caching actually leads to increased transit traffic. Our analytical results are supported by extensive simulations and experiments with real BitTorrent clients.

Mitigating unfairness in locality-aware peer-to-peer networks

Locality awareness is considered as a promising approach to increase the efficiency of content distribution by peer-to-peer (P2P) networks, e.g., BitTorrent. It is intended to reduce the inter-domain traffic, which is costly for Internet service providers (ISPs), and to simultaneously increase the performance from the viewpoint of P2P users, i.e., to shorten download times. This win-win situation should be achieved by a preferred exchange of information between peers which are located close to each other in the underlying network topology. A set of studies shows that these approaches can lead to a win-win situation under certain conditions, and to a win-no lose situation in most cases. However, the scenarios used mostly assume homogeneous peer distributions. This is not the case in practice according to recent measurement studies. Therefore, we extend previous work in this paper by studying scenarios with real-life, skewed peer distributions. We show that even a win-no lose situation is difficult to achieve under those conditions and that the actual impact for a specific peer heavily depends on the used locality-aware peer selection and the specific scenario. This contradicts the principle of economic traffic management (ETM), which aims for a solution where all involved players benefit and consequently have an incentive to adopt locality awareness. Therefore, we propose and evaluate refinements of current proposals, allowing all users of P2P networks to be sure that their application performance is not reduced. This mitigates the unfairness introduced by current proposals which is a key requirement for a broad acceptance of the concept of locality awareness in the user community of P2P networks.

Experience-based admission control (EBAC)

Classical admission control approaches take either descriptor or measurement based information about the traffic into account without relating them to each other. We propose a experience-based AC (EBAC) which uses an empirical percentile of the effective reservation utilization to determine a suitable overbooking factor. In this paper, we show the impact of different measurement time scale resolutions and different quantiles on the performance of the system. We propose aging mechanisms for statistic collection to make the system adaptive to traffic mixes that change over time. We illustrate their effectiveness by simulation results.

Caching for BitTorrent-like P2P systems: a simple fluid model and its implications

Peer-to-peer file-sharing systems are responsible for a significant share of the traffic between Internet service providers (ISPs) in the Internet. In order to decrease their peer-to-peer-related transit traffic costs, many ISPs have deployed caches for peer-to-peer traffic in recent years. We consider how the different types of peer-to-peer caches—caches already available on the market and caches expected to become available in the future—can possibly affect the amount of inter-ISP traffic. We develop a fluid model that captures the effects of the caches on the system dynamics of peer-to-peer networks and show that caches can have adverse effects on the system dynamics depending on the system parameters. We combine the fluid model with a simple model of inter-ISP traffic and show that the impact of caches cannot be accurately assessed without considering the effects of the caches on the system dynamics. We identify scenarios when caching actually leads to increased transit traffic. Motivated by our findings, we propose a proximity-aware peer-selection mechanism that avoids the increase of the transit traffic and improves the cache efficiency. We support the analytical results by extensive simulations and experiments with real BitTorrent clients.

A Framework of Economic Traffic Management Employing Self-Organization Overlay Mechanisms

Applications based on overlays have become very popular, due to the separation they provide and the improvement of perceived QoS by the end-user. Recent studies show that overlays have a significant impact on the traffic management and the expenditures of the underlying network operators. In this paper, we define a framework for Economic Traffic Management (ETM) mechanisms that optimize the traffic impact of overlay applications on ISP and telecommunication operator networks based on the interaction of network operators, overlay providers and users. We first provide a definition and an overview of Self-Organization Mechanisms (SOMs) and ETM for overlays. We then describe a basic framework for the interaction of components of SOMs and ETM, in terms of information and metrics provided, decisions made etc. Finally, we describe in detail how SOMs can be used to support ETM and we illustrate our approach and its implications by means of a specific example.

A QoE-Aware P2P Streaming System Using Scalable Video Coding

P2P streaming has attracted much attention recently with promises for higher revenues and better load distribution. Still, the majority of P2P video streaming systems today employ the one-size-fits-all concept where the same video bit-rate is offered to all users. Here the promising H.264/Scalable Video Coding (SVC) standard is seen as a necessity in not only supporting heterogeneous resources, but also in reducing the impact of P2P dynamics on the perceived Quality-of-Experience (QoE). In this demonstration we present our streaming application that uses SVC to adapt to different user requirements and resources. The application employs a novel QoE- aware layer selection algorithm that maximizes flexibility through SVC while taking impact on QoE into consideration.