Abstract — In this paper, we present the design, implementation, and evaluation of the iPlane, a scalable service providing accurate predictions of Internet path performance for emerging overlay services. Unlike the more common black box latency prediction techniques in use today, the iPlane builds an explanatory model of the Internet. We predict end-to-end performance by composing measured performance of segments of known Internet paths. This method allows us to accurately and efficiently predict latency, bandwidth, capacity and loss rates between arbitrary Internet hosts. We demonstrate the feasibility and utility of the iPlane service by applying it to several representative overlay services in use today: content distribution, swarming peer-to-peer filesharing, and voice-over-IP. In each case, we observe that using iPlane’s predictions leads to a significant improvement in end user performance. 1

Recent measurement based studies reveal that most of the Internet connections are short in terms of the amount of traffic they carry (mice), while a small fraction of the connections are carrying a large portion of the traffic (elephants). A careful study of the TCP protocol shows that without help from an Active Queue Management (AQM) policy, short connections tend to lose to long connections in their competition for bandwidth. This is because short connections do not gain detailed knowledge of the network state, and therefore they are doomed to be less competitive due to the conservative nature of the TCP congestion control algorithm.

The limitations of BGP routing in the Internet are often blamed for poor end-to-end performance and prolonged connectivity interruptions. Recent work advocates using overlays to effectively bypass BGP’s path selection in order to improve performance and fault tolerance. In this paper, we explore the possibility that BGP route control, when coupled with ISP multihoming, can provide competitive end-to-end performance and reliability. Using extensive measurements of paths between nodes in a large content distribution network, we compare the relative benefits of overlay routing and multihoming route control in terms of round-trip latency, throughput of 1MB TCP transfers, and path availability. We observe that the performance from route control employed in conjunction with multihoming to three ISPs (3-multihoming), is within 5-15 % of that from overlay routing employed in conjunction 3-multihoming, in terms of both end-to-end RTT and throughput. We also show that while multihoming cannot offer the nearly perfect resilience of overlays, it can eliminate almost all failures experienced by a singly-homed end-network. Our results demonstrate that, by leveraging the capability of multihoming route control, it is not necessary to circumvent BGP routing to extract good wide-area performance and availability from the existing routing system.

Improving the performance of data transfers in the Internet (such as Web transfers) requires a detailed understanding of when and how delays are introduced. Unfortunately, the complexity of data transfers like those using HTTP is great enough that identifying the precise causes of delays is difficult. In this paper we describe a method for pinpointing where delays are introduced into applications like HTTP by using critical path analysis. By constructing and pro ling the critical path, it is possible to determine what fraction of total transfer latency is due to packet propagation, network variation (e.g., queuing at routers or route uctuation), packet losses, and delays at the server and at the client. We have implemented our technique in a tool called tcpeval that automates critical path analysis for Web transactions. We show that our analysis method is robust enough to analyze traces taken for two different TCP implementations (Linux and FreeBSD). To demonstrate the utility of our approach, we present the results of critical path analysis for a set of Web transactions taken over 14 days under a variety of server and network conditions. The results show that critical path analysis can shed considerable light on the causes of delays in Web transfers, and can expose subtleties in the behavior of the entire end-to-end system.

Most of the traffic in today's Internet is controlled by the Transmission Control Protocol (TCP). Hence, the performance of TCP has a significant impact on the performance of the overall Internet. TCP is a complex protocol with many user-configurable parameters and a range of different implementations. In addition, research continues to produce new developments in congestion control mechanisms and TCP options, and it is useful to trace the deployment of these new mechanisms in the Internet. As a final concern, the stability and fairness of the current Internet relies on the voluntary use of congestion control mechanisms by end hosts. Therefore it is important to test TCP implementations for conformant end-toend congestion control. Since web traffic forms the majority of the TCP traffic, TCP implementations in today's web servers are of particular interest. We have developed a tool called TCP Behavior Inference Tool (TBIT) to characterize the TCP behavior of a remote web server. In this paper, we describe TBIT, and present results about the TCP behaviors of major web servers, obtained using this tool. We also describe the use of TBIT to detect bugs and non-compliance in TCP implementations deployed in public web servers.

Most of the traffic in today's Internet is controlled by the Transmission Control Protocol (TCP). Hence, the performance of TCP has a significant impact on the performance of the overall Internet. Since web traffic forms the majority of the TCP traffic, TCP implementations in today's web servers are of particular interest. However, TCP is a complex protocol with many user-configurable parameters and a range of different implementations. In addition, research continues to produce new developments in congestion control mechanisms and TCP options, and it is useful to trace the deployment of these new mechanisms in the Internet. As a final concern, the stability and fairness of the current Internet relies on the voluntary use of congestion control mechanisms by end hosts. Therefore it is important to test TCP implementations for conformant end-to-end congestion control. We have developed a tool called TCP Behavior Identification Tool (TBIT) to characterize the TCP behavior of a remote web ...

We survey recent advances in theories and models for Internet Quality of Service (QoS). We start with the theory of network calculus, which lays the foundation for support of deterministic performance guarantees in networks, and illustrate its applications to integrated services, differentiated services, and streaming media playback delays. We also present mechanisms and architecture for scalable support of guaranteed services in the Internet, based on the concept of a stateless core. Methods for scalable control operations are also briefly discussed. We then turn our attention to statistical performance guarantees, and describe several new probabilistic results that can be used for a statistical dimensioning of differentiated services. Lastly, we review recent proposals and results in supporting performance guarantees in a best effort context. These include models for elastic throughput guarantees based on TCP performance modeling, techniques for some quality of service differentiation without access control, and methods that allow an application to control the performance it receives, in the absence of network support.

Predicting the throughput of large TCP transfers is important for a broad class of applications. This paper focuses on the design, empirical evaluation, and analysis of TCP throughput predictors. We first classify TCP throughput prediction techniques into two categories: Formula-Based (FB) and History-Based (HB). Within each class, we develop representative prediction algorithms, which we then evaluate empirically over the RON testbed. FB prediction relies on mathematical models that express the TCP throughput as a function of the characteristics of the underlying network path. It does not rely on previous TCP transfers in the given path, and it can be performed with non-intrusive network measurements. We show, however, that the FB method is accurate only if the TCP transfer is window-limited to the point that it does not saturate the underlying path, and explain the main causes of the prediction errors. HB techniques predict the throughput of TCP flows from a time series of previous TCP throughput measurements on the same path, when such a history is available. We show that even simple HB predictors, such as Moving Average and Holt-Winters, using a history of few and sporadic samples, can be quite accurate. On the negative side, HB predictors are highly path-dependent. We explain the cause of such path dependencies based on two key factors: the load on the path and the degree of statistical multiplexing.

We propose a recursive, analytical model to predict the TCP performance in terms of completion time for short-lived flows. Based on the knowledge of the average dropping probability, the average roundtrip time and the flow length, the model provides very good results when compared to simulation.

While almost all of the existing models for TCP performance focus on the steady-state throughput of infinite flows, most TCP connections in today's Internet are very short and spend most of their time in the slow start phase, making steady-state models inappropriate. This paper focuses on two of the most important shortcomings of current models. Firstly, we present models for the latency of TCP Reno with independent losses for which currently no models exist. Secondly, we investigate the effects of network and protocol factors on TCP performance and quantify and isolate their contribution to TCP latency using an empirical model. Our analytic model gives a more accurate estimation of TCP latencies in Internet measurements than those predicted by [3], which extends the steady state analysis of [14] to model finite flows with correlated losses. The main features of our work are the modeling of timeouts and slow start phases which occur anywhere during the transfer and a more accurate model for the evolution of the cwnd in the slow start phase. The proposed model can also estimate the steady-state throughput of long flows. We also introduce empirical models for TCP Reno which allow a better "feel" of TCP latency and the nature of its dependence on loss probabilities and window limitation along with a sensitivity analysis of the effects of delayed acknowledgments (ACKs), window limitation and packet size on TCP latency.