Luca Muscariello

Evaluating the number of active flows in a scheduler realizing fair statistical bandwidth sharing

Despite its well-known advantages, per-flow fair queueing has not been deployed in the Internet mainly because of the common belief that such scheduling is not scalable. The objective of the present paper is to demonstrate using trace simulations and analytical evaluations that this belief is misguided. We show that although the number of flows in progress increases with link speed, the number that needs scheduling at any moment is largely independent of this rate. The number of such active flows is a random process typically measured in hundreds even though there may be tens of thousands of flows in progress. The simulations are performed using traces from commercial and research networks with quite different traffic characteristics. Analysis is based on models for balanced fair statistical bandwidth sharing and applies properties of queue busy periods to explain the observed behaviour.

Markov models of internet traffic and a new hierarchical MMPP model

The first part of this paper gives a short tutorial survey of Internet traffic modeling, focusing on recent advances in Markov models showing pseudo-LRD (Long Range Dependence) characteristics that match those measured on the Internet. The interest in Markov models of Internet traffic, in spite of the impossibility to achieve true LRD or Self-Similarity, lies in the possibility of exploiting powerful analytical techniques to predict the network performance, which is the ultimate goal when adopting models to either study existing networks or design new ones. Then, the paper describes a new MMPP (Markov Modulated Poisson Process) traffic model that accurately approximates the LRD characteristics of Internet traffic traces over the relevant time scales. The heart of the model is based on the notion of sessions and flows, trying to mimic the real hierarchical generation of packets in the Internet. The proposed model is simple and intuitive: its parameters have a physical meaning, and the model can be tuned with only a few input parameters. Results prove that the queuing behavior of the traffic generated by the MMPP model is coherent with the one produced by real traces collected at our institution edge router under several different traffic loads. Due to its characteristics, the proposed MMPP traffic model can be used as a simple and manageable tool for IP network dimensioning, design and planning: the paper provides examples of its application in both simulative and theoretical analysis.

Passive analysis of TCP anomalies

In this paper, we focus on passive measurements of TCP traffic. We propose a heuristic technique to classify TCP anomalies, i.e., segments that have a sequence number different from the expected one, such as out-of-sequence and duplicate segments. Since TCP is a closed-loop protocol that infers network conditions from packet losses and reacts accordingly, the possibility of carefully distinguishing the causes of anomalies in TCP traffic is very appealing and may be instrumental to understand TCP behavior in real environments. We apply the proposed heuristic to traffic traces collected at both network edges and backbone links. By comparing results obtained from traces collected over several years, we observe some phenomena such as the impact of the introduction of TCP SACK which reduces the unnecessary retransmissions, the large percentage of network reordering, etc. By further studying the statistical properties of TCP anomalies, we find that, while their aggregate exhibits long-range dependence, anomalies suffered by individual long-lived flows are on the contrary uncorrelated. Interestingly, no dependence on the actual link load is observed.

An MMPP-based hierarchical model of Internet traffic

In this paper, we propose a MMPP (Markov modulated Poisson process) traffic model that accurately approximates the LRU (long range dependence) characteristics of Internet traffic traces. Using the notion of sessions and flows, the proposed MMPP model mimics the real hierarchical behavior of the packet generation process by Internet users. Thanks to its hierarchical structure, the proposed model is both simple and intuitive: it allows the generation of traffic with the desired characteristics by easily setting a few input parameters which have a clear physical meaning. Results prove that the queuing behavior of the traffic generated by the MMPP model is coherent with the one produced by the real traces collected at our institution edge router under different networking scenarios and loads. Due to its characteristics, the proposed MMPP traffic model can be used as a simple and manageable tool for IP network performance analysis, as well as for network planning and dimensioning.

Architecture of a network-aware P2P-TV application: the NAPA-WINE approach

Peer to Peer streaming (P2P-TV) applications have recently emerged as cheap and efficient solutions to provide real time streaming services over the Internet. For the sake of simplicity, typical P2P-TV systems are designed and optimized following a pure layered approach, thus ignoring the effect of design choices on the underlying transport network. This simple approach, however, may constitute a threat for the network providers, due to the congestion that P2P-TV traffic can potentially generate. In this article, we present and discuss the architecture of an innovative, network cooperative P2PTV application that is being designed and developed within the STREP Project NAPA WINE1 Our application is explicitly targeted to favor cooperation between the application and the transport network layer.

Building a cooperative P2P-TV application over a wise network: the approach of the European FP-7 strep NAPA-WINE

Introduction TV services over the Internet can be provided by either exploiting IP multicast functionalities or relying on a pure peer-to-peer (P2P) approach. The first technique will only work on a network infrastructure controlled by a single broadband operator due to limitations of IP multicast facilities. The main goal of the project is the study of a future system suitable for HQTV live streaming over the Internet based on P2P technology, or a P2P-HQTV system. The major focus is on overcoming todays pure layered approach through a cooperative paradigm in which the application and network layers cooperate to optimize the quality of service offered to end users.

Web user-session inference by means of clustering techniques

This paper focuses on the definition and identification of ldquoWeb user-sessionsrdquo, aggregations of several TCP connections generated by the same source host. The identification of a user-session is non trivial. Traditional approaches rely on threshold based mechanisms. However, these techniques are very sensitive to the value chosen for the threshold, which may be difficult to set correctly. By applying clustering techniques, we define a novel methodology to identify Web user-sessions without requiring an a priori definition of threshold values. We define a clustering based approach, we discuss pros and cons of this approach, and we apply it to real traffic traces. The proposed methodology is applied to artificially generated traces to evaluate its benefits against traditional threshold based approaches. We also analyze the characteristics of user-sessions extracted by the clustering methodology from real traces and study their statistical properties. Web user-sessions tend to be Poisson, but correlation may arise during periods of network/hosts anomalous behavior.

Minimizing the overhead in implementing flow-aware networking

An enhanced flow-aware Internet is arguably a more effective means of ensuring adequate performance than implementing the complex standardized QoS architectures. This flow-aware network would provide flow-level performance guarantees for real time and data applications by implementing per-flow fair queueing and by limiting the impact of overload through flow level admission control. The paper discusses the feasibility of the implied router mechanisms and proposes original solutions that minimize the necessary overhead with respect to the current best effort network. Preferred solutions significantly reduce requirements for flow state by employing directly addressed bitmaps to record flow status, as necessary for scheduling and admission control, respectively.

Passive Identification and Analysis of TCP Anomalies

In this paper we focus on passive measurements of TCP traffic, main component of nowadays traffic. We propose a heuristic technique for the classification of the anomalies that may occur during the lifetime of a TCP flow, such as out-of-sequence and duplicate segments. Since TCP is a closed-loop protocol that infers network conditions by means of losses and reacts accordingly, the possibility of carefully distinguishing the causes of anomalies in TCP traffic is very appealing, since it may be instrumental to the deep understanding of TCP behavior in real environments and to protocol engineering as well. We apply the proposed heuristic to traffic traces collected at both networks edges and backbone links. By studying the statistical properties of TCP anomalies, we find that their aggregate exhibits Long Range Dependence phenomena, but that anomalies suffered by individual long-lived flows are on the contrary uncorrelated. Interestingly, no dependence to the actual link load is observed.

On the properties of TCP flow arrival process

We study the TCP flow arrival process, starting from the aggregated measurement at the TCP flow level taken from our campus network. In particular, we analyze the statistical properties of the TCP flow arrival process. We define the different traffic aggregates by splitting the original trace, such that i) each of them is constituted by all the TCP flows belonging to the same traffic relation, i.e., with the same source/destination IP addresses and ii) each traffic aggregate has, bytewise, the same amount of traffic. To induce a divisions of TCP-elephants and TCP-mice into different traffic aggregates, the used algorithm packs the largest traffic relations in the first traffic aggregates, so that subsequently generated aggregates are constituted by an increasing number of smaller traffic relations. The long range dependency (LRD) characteristics are presented, showing the possible causes of the LRD of TCP flow arrival process in i) the heavy tailed distribution of the number of flows in a traffic aggregate, and ii) the presence of TCP-elephants within them.