No description available.

No description available.

Quality-of-service (QoS) requirements for the timely delivery of real-time multimedia raise new challenges for the networking world. A key component of QoS is QoS routing which allows the selection of network routes with sufficient resources for requested QoS parameters. Several techniques have been proposed in the literature to compute QoS routes, most of which require dynamic update of link-state information across the Internet. Given the growing size of the Internet, it is becoming increasingly difficult to gather up-to-date state information in a dynamic environment. We propose a new technique to compute QoS routes on the Internet in a fast and efficient manner without any need for dynamic updates. Our method, known as Selective Flooding, checks the state of the links on a set of pre-computed routes from the source to the destination in parallel and based on this information computes the best route and then reserves resources. We implemented Selective Flooding on a QoS routing simulator and evaluated the performance of Selective Flooding compared to source routing for a variety of network parameters. We find Selective Flooding consistently outperforms source routing in terms of call-blocking rate and outperforms source routing in terms of network overhead for some network conditions. The contributions of this thesis include the design of a new QoS routing algorithm, Selective Flooding, extensive evaluation of Selective Flooding under a variety of network conditions and a working simulation model for future research.

With the emergence of computer networks as one of the primary modes of communication, and with their adoption for an increasingly wide range of applications, there is a growing need to understand and characterize the traffic they carry. The rise of large scale network attacks adds urgency to this need. However, the large size, high speed and increasing complexity of these networks imply that tracking and characterizing the traffic they carry is an increasingly difficult problem. Dealing with higher level aggregates, such as flows instead of packets, does not solve the problem because these aggregates tend to be quite numerous and exhibit dynamics of their own. In this thesis, we investigate a novel approach to deal with the immense amounts of data associated with problems in network measurement and monitoring. Building upon the paradigm of Data Streaming, which processes a large stream of data using a small working memory to answer a class of queries, we develop an architecture for Network Data Streaming that can accommodate additional constraints imposed in the context of network monitoring. Using this architecture, we design algorithms for monitoring properties of network traffic that have traditionally been considered too difficult to monitor at high speed network links and routers. Our first algorithm provides the ability to accurately estimate the size of individual flows. A second algorithm to estimate the distribution of flow sizes enables network operators to monitor anomalies in the traffic. Incorporating the use of packet sampling, we can extend the latter algorithm to estimate the flow size distribution of arbitrary subpopulations. Finally, we apply the tools of Network Data Streaming to the operation of packet sampling itself. Using the ability to efficiently estimate flow-statistics such as approximate per-flow size, we design a family of mechanisms where the sampling decision is guided by this knowledge. The individual solutions developed in this thesis share a common architectural theme, supporting the monitoring of highly dynamic populations. Integrating this with the traditional sampling based framework for network monitoring will enable a broad range of applications for accurate and comprehensive monitoring of network traffic.

In this thesis, we propose a new protocol named Layered TCP with RTT Compensation (LTCP-RC, for short). LTCP-RC is a simple modification to the congestion window response of the high-speed protocol, Layered TCP (LTCP). In networks characterized by large link delays and high RTTs, LTCP-RC makes the LTCP protocol more scalable. Ack-clocked schemes, similar to TCP, suffer performance problems like long convergence time and throughput degradation, when RTT experienced by the flow increases. Also, when flows with different RTTs compete, the problem of unfairness among competing flows becomes worse in the case of high-speed protocols. LTCP-RC uses an RTT Compensation technique in order to solve these problems. This thesis presents a general framework to decide the function for RTT Compensation factor and two particular design choices are analyzed in detail. The first algorithm uses a fixed function based on the minimum RTT observed by the flow. The second algorithm uses an adaptive scheme which regulates itself according to the dynamic network conditions. Evaluation of the performance of these schemes is done using analysis and ns-2 simulations. LTCP-RC exhibits significant performance improvement in terms of reduced convergence time, low drop rates, increased utilization in presence of links with channel errors and good fairness properties between the flows,. The scheme is simple to understand, easy to implement on the TCP/IP stack and does not require any additional support from the network resources. The choice of parameters can be influenced to tune the RTT unfairness of the scheme, which is not possible in TCP or other high-speed protocols. The flexible nature of the analysis framework has laid the ground work for the development of new schemes, which can improve the performance of the window based protocols in high delay and heterogeneous networks.

With the ever increasing deployment and usage of gigabit networks, traditional network anomaly detection based intrusion detection systems have not scaled accordingly. Most, if not all, systems deployed assume the availability of complete and clean data for the purpose of intrusion detection. We contend that this assumption is not valid. Factors like noise in the audit data, mobility of the nodes, and the large amount of data generated by the network make it difficult to build a normal traffic profile of the network for the purpose of anomaly detection. From this perspective, the leitmotif of the research effort described in this dissertation is the design of a novel intrusion detection system that has the capability to detect intrusions with high accuracy even when complete audit data is not available. In this dissertation, we take a holistic approach to anomaly detection to address the threats posed by network based denial-of-service attacks by proposing improvements in every step of the intrusion detection process. At the data collection phase, we have implemented an adaptive sampling scheme that intelligently samples incoming network data to reduce the volume of traffic sampled, while maintaining the intrinsic characteristics of the network traffic. A Bloom filters based fast flow aggregation scheme is employed at the data pre-processing stage to further reduce the response time of the anomaly detection scheme. Lastly, this dissertation also proposes an expectation-maximization algorithm based anomaly detection scheme that uses the sampled audit data to detect intrusions in the incoming network traffic. / Ph. D.

Reliable and efficient data transfer on the Internet is an important issue. Since late 70's the protocol responsible for that has been the de facto standard TCP, which has proven to be successful through out the years, its self-managed congestion control algorithms have retained the stability of the Internet for decades. However, the variety of existing new technologies such as high-speed networks (e.g. fibre optics) with high-speed long-delay set-up (e.g. cross-Atlantic links) and wireless technologies have posed lots of challenges to TCP congestion control algorithms. The congestion control research community proposed solutions to most of these challenges. This dissertation adds to the existing work by: firstly tackling the highspeed long-delay problem of TCP, we propose enhancements to one of the existing TCP variants (part of Linux kernel stack). We then propose our own variant: TCP-Gentle. Secondly, tackling the challenge of differentiating the wireless loss from congestive loss in a passive way and we propose a novel loss differentiation algorithm which quantifies the noise in packet inter arrival times and use this information together with the span (ratio of maximum to minimum packet inter arrival times) to adapt the multiplicative decrease factor according to a predefined logical formula. Finally, extending the well-known drift model of TCP to account for wireless loss and some hypothetical cases (e.g. variable multiplicative decrease), we have undertaken stability analysis for the new version of the model.

La tendance en HPC est à l'accroissement du nombre de coeurs par noeud de calcul pour une quantité totale de mémoire par noeud constante. A large échelle, l'un des principaux défis pour les applications parallèles est de garder une faible consommation mémoire. Cette thèse présente une couche de communication multi-threadée sur Infiniband, laquelle fournie de bonnes performances et une faible consommation mémoire. Nous ciblons les applications scientifiques parallélisées grâce à la bibliothèque MPI ou bien combinées avec un modèle de programmation en mémoire partagée. En partant du constat que le nombre de connexions réseau et de buffers de communication est critique pour la mise à l'échelle des bibliothèques MPI, la première contribution propose trois approches afin de contrôler leur utilisation. Nous présentons une topologie virtuelle extensible et entièrement connectée pour réseaux rapides orientés connexion. Dans un contexte agrégeant plusieurs cartes permettant d'ajuster dynamiquement la configuration des buffers réseau utilisant la technologie RDMA. La seconde contribution propose une optimisation qui renforce le potentiel d'asynchronisme des applications MPI, laquelle montre une accélération de deux des communications. La troisième contribution évalue les performances de plusieurs bibliothèques MPI exécutant une application de modélisation sismique en contexte hybride. Les expériences sur des noeuds de calcul jusqu'à 128 coeurs montrent une économie de 17 % sur la mémoire. De plus, notre couche de communication multi-threadée réduit le temps d'exécution dans le cas où plusieurs threads OpenMP participent simultanément aux communications MPI. / A recent trend in high performance computing shows a rising number of cores per compute node, while the total amount of memory per compute node remains constant. To scale parallel applications on such large machines, one of the major challenges is to keep a low memory consumption. This thesis develops a multi-threaded communication layer over Infiniband which provides both good performance of communications and a low memory consumption. We target scientific applications parallelized using the MPI standard in pure mode or combined with a shared memory programming model. Starting with the observation that network endpoints and communication buffers are critical for the scalability of MPI runtimes, the first contribution proposes three approaches to control their usage. We introduce a scalable and fully-connected virtual topology for connection-oriented high-speed networks. In the context of multirail configurations, we then detail a runtime technique which reduces the number of network connections. We finally present a protocol for dynamically resizing network buffers over the RDMA technology. The second contribution proposes a runtime optimization to enforce the overlap potential of MPI communications, showing a 2x improvement factor on communications. The third contribution evaluates the performance of several MPI runtimes running a seismic modeling application in a hybrid context. On large compute nodes up to 128 cores, the introduction of OpenMP in the MPI application saves up to 17 % of memory. Moreover, we show a performance improvement with our multi-threaded communication layer where the OpenMP threads concurrently participate to the MPI communications

Orientador: Nelson Luis Saldanha da Fonseca / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-13T20:11:45Z (GMT). No. of bitstreams: 1 Michel_NeilaFernanda_M.pdf: 1961141 bytes, checksum: f4470a332c9b5f764b7bd3b912c27db1 (MD5) Previous issue date: 2008 / Resumo: O protoloco TCP Reno começou a operar em 01 de Janeiro de 1983. Desde sua concepção, houveram expressivos avanços nas tecnologias de transmissão de dados, como a introdução de enlaces ópticos e de satélites, 'que permitem altas taxas de transmissão. O TCP Reno continua sendo o protocolo padrão na Internet. Entretanto existem inúmeras dificuldades na sua operação, que causam baixo desempenho em redes com produto banda-atraso elevado, devido ao mecanismo de atualização do tamanho da janela de congestionamento. Para superar suas deficiências, vários protocolos variantes do TCP Reno têm sido propostos com o objetivo de melhorar a utilização de recursos em redes de alta velocidade, e por esta razão são denominados "Protocolos para Redes de Alta Velocidade" . Para que as proposições de variantes do TCP levem a protocolos que operem eficientemente em redes com alto valor do produto banda-atraso, é necessário que se avalie quais variações da dinâmica do crescimento da janela de transmissão são efetivas. Nesta dissertação avalia-se um conjunto de protocolos variantes do TCP para redes de alta velocidade através de simulações. Diversas propriedades importantes para protocolos do tipo TCP são investigadas / Abstract: The importance of the Reno TCP protocol started operating in January 01 st, 1983. Since this milestone, there were expressive advances on data transmission technologies, such as those of optical fibers and satellite channels which allow high transmission rates on long distances. Reno TCP remains the Internet standard protocol. However, its operation presents several dificulties in networks with high bandwidth-delay product, producing poor performance due its window congestion mechanism. In order to overcome its deficiencies, several variants have been proposed with the aim of enhancing its utilization in high speed networks. These variants are generally called "High Speed Networks Protocols". Transmission chàracteristics, properties and performance evaluation are essencial to the identification of problems and avoidance of poor performance. In this dissertation a set of TCP variants protocols for high speed networks is evaluated. Several important properties of these protocols are investigated / Mestrado / Redes de Computadores / Mestre em Ciência da Computação

Orientadores: Michel Zamboni Rached, Julio Cesar Rodrigues Fernandes de Oliveira / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-23T22:08:51Z (GMT). No. of bitstreams: 1 Silva_EdsonPortoda_M.pdf: 2920023 bytes, checksum: 44d415ca69c358709f1b816f7e603047 (MD5) Previous issue date: 2013 / Resumo: O Resumo poderá ser visualizado no texto completo da tese digital / Abstract: The complete Abstract is available with the full electronic document. / Mestrado / Telecomunicações e Telemática / Mestre em Engenharia Elétrica