Résumé confidentiel / Résumé confidentiel

Made available in DSpace on 2014-06-11T19:22:31Z (GMT). No. of bitstreams: 0 Previous issue date: 2011-05-27Bitstream added on 2014-06-13T20:29:02Z : No. of bitstreams: 1 spozito_ds_me_ilha.pdf: 2230007 bytes, checksum: 9240ceb37ed45878d0a4e158290fedf5 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Com a globalização e a evolução tecnológica, a capilaridade das instituições, sejam elas públicas ou privadas, é realidade irreversível. O uso de computadores cada vez mais velozes e com elevada capacidade de armazenamento possibilitou a centralização das informações. Nesse contexto, surge a necessidade de interligar os sistemas computacionais com o objetivo de trocar informações, independentemente da região geográfica. A Internet, utilizando tecnologias de redes de dados, com arquitetura projetada para suportar em nível mundial a comunicação entre computadores, passa a ser a principal ferramenta utilizada na interligação de locais geograficamente distribuídos. Com a tecnologia e infraestrutura disponível para efetivar a comunicação, surge também a necessidade de garantir que os sistemas estejam ativos o maior tempo possível, atendendo a desempenho compatível às atividades desenvolvidas, pois as instituições passam a depender da interação entre os sistemas computacionais, independente do ponto do planeta em que estejam. Este trabalho propõe modelar, desenvolver e realizar ensaios de uma ferramenta que auxilie no monitoramento de pontos interligados por redes de comunicação dados sobre protocolo TCP/IP distribuídos geograficamente. O modelo consiste em monitorar um ou mais pontos, visualizados sobre um mapa com o traçado do perímetro político geográfico da área atendida. Em suma, propõe-se utilizar as ferramentas básicas de teste de conectividade nas redes de comunicação de dados, associadas aos conceitos de georreferenciamento e geoprocessamento / The globalization and technological evolution, allowed the grow of institutions public or private over the entire world with highest capillarity. The development of computers becoming faster and with large storage capacity allowed the centralization of information. In this context the necessity of linking computer systems with the aim to exchange information regardless of geography became a reality. The technics and technologies used in Internet, envolving data communications, with architecture designed to support global communication between computers, becomes the main tool used in the interconnection of thousand geographically distributed sites. With the technology and infrastructure available for an effective communication, also arises the need to ensure that systems are active as long as possible, with a minimum of performance to the services, because the activities in the institutions are dependent upon interaction between computer systems, regardless of the point on the planet they are. This study proposes to model, develop and test a tool to assist in the monitoring of points connected by data communication networks over TCP / IP distributed geographically. The proposed format is to monitor one or more points, displayed on one or more maps with the route of political geographic boundaries of the area served. In short, it is proposed to use the basic tools to test network connectivity in data communications, combined with the concepts of GIS and georeferencing

Esta dissertação descreve os métodos, medidas e análises feitas para otimizar a rede de comunicação de dados do Instituto de Física de São Carlos. As tecnologias e protocolos utilizados na rede são apresentados. Especial atenção é dada a análise do desempenho de VLANs utilizando inicialmente o protocolo LANE no núcleo ATM da rede. Neste caso a rede é composta de switches ATM e ATM-Ethernet. Medidas comparativas foram realizadas com a utilização da tecnologia Fast Ethernet no backbone, que possui uma capacidade de transmissão relativamente próxima da ATM de 155Mbps. Melhores resultados obtidos com a implementação de sub-redes maiores, reduzindo em um numero menor de sub-redes, são discutidos e apresentados. Análises estatísticas baseadas apenas no tempo de resposta da rede são apresentados para avaliar o desempenho das alterações efetuadas nas configurações da rede. Mesmo que o tráfego tenha aumentado muito durante esses anos e que vários serviços tenha sido agregados a esta rede, foi possível adequar o desempenho as novas necessidades beneficiando-se da evolução tecnológica que os equipamentos de rede de dados trouxeram ao IFSC. / This work describes the methods, measures and analyses performed aiming to optimize the data communication network from the Physics Institute of Sao Carlos as well as the technologies and protocols used in the network recently. Special care is given to the analysis of the VLANs performance using, initially, the LANE protocol over ATM which has its core based on pure ATM and ATM-Ethernet switches. Comparative measures had been carried out using a backbone working on a Fast Ethernet technology, which seems to have a very close transmission rate from the ATM 155Mbps. This work also discusses best results acquired with the implementation of larger networks reducing the number of subnetworks, statistical analyses based on time delay of the network in order to evaluate the performance of the changes made on its configuration. Even though the traffic from the Institute has been increased over these years and several services have been added to the network, it was completely possible to adapt the performance to the needs, using the benefits of the technological evolution which the network equipments had brought to the Institute.

Web browsing has been one of the most popular activities on the internet. The increasing importance of the Web in everyday life calls for device-independent access to existing web sites. Although, there is full Web access available on mobile phones the user experience is often poor when compared to the Web user experience on Personal Computer (PC). Therfore, it is important for the Internet service provider to find the indications of user dissatisfaction from the network. While using the mobile Web, user can normally abort the transfer by pressing the stop or reset buttons in the browsers, leaving the page being downloaded by following a bookmark or can close the connection. Such events can be observed through the TCP reset (RST) flag from traffic on network level. In this thesis we have investigated the possible causes of TCP RST flags mobile Web session is interrupted. We further analyze up to what extent we can rely on TCP RST flags for being an indication of user dissatisfaction in mobile web browsing. Therefore, an experiment testbed is developed to capture the TCP packet traces during controlled active tests. Results are gathered using mobile devices with four popular mobile operating systems (OS). The trace files captured are analyzed using perl script to dicern the flow and focusing on the TCP RST flag during the flow. Further, TSTAT tool is used to validate our trace files. / 0760-882089

Várias características da Internet mudaram drasticamente desde que o TCP foi criado, como o maior compartilhamento de recursos devido à maior quantidade de usuários, maior largura de banda disponível, a existência de muitas conexões que podem percorrer longas distâncias e a ubiquidade das redes sem fio. Confrontado com essas novas características, o TCP apresenta diversas limitações. Dentre elas estão a subutilização da rede quando a largura de banda é da ordem de centenas de Gbps, o favorecimento de conexões que possuem pouco atraso (poucas dezenas de milisegundos), a incapacidade de distinção de causas de perdas de pacote e a demora para estabelecimento de conexões seguras (até 3 RTTs). Nesse contexto, com o objetivo de tornar o transporte de dados na Internet mais rápido e eficiente, a Google desenvolveu o protocolo QUIC. O QUIC propõe diversos avanços em relação aos protocolos existentes, como um novo mecanismo para estabelecimento de conexão e controle de congestionamento otimizado. Resultados apresentados pela Google mostraram claro ganho de desempenho em relação ao TCP, justificando o trabalho de tornar o QUIC um padrão IETF da Internet. Porém, esses resultados são impossíveis de serem verificados porque nos relatórios divulgados não há informação suficiente para que os cenários de teste sejam reproduzidos e porque é implausível possuir a mesma infraestrutura para os testes que a Google tem. Neste trabalho, avaliamos o desempenho do protocolo QUIC em diversos cenários de rede, comparando-o com o desempenho de várias implementações do TCP, principalmente o CUBIC. Diferente do realizado na literatura, todos os cenários utilizados são bem descritos, permitindo a reprodutibilidade dos experimentos. Além disso, para a realização dos experimentos foi criado um novo módulo que implementa o QUIC no simulador de redes NS-3. Este módulo está disponível como software livre, permitindo que outros pesquisadores usem o módulo para replicar e verificar nossos experimentos e para criarem novos experimentos de forma reprodutível. Ademais, eles também podem usar o módulo como uma ferramenta para avaliar, de maneira rápida, o comportamento de novas técnicas dentro do protocolo. / Many characteristics of the Internet have drastically changed since TCP was created such as the increase on resource sharing due to a larger number of Internet users, the growth of available bandwidth, the existence of many connections that may travel long distances and the ubiquity of wireless networks. When faced with those new characteristics, TCP showed severe limitations. Among them are network underutilization in high bandwidth environments of hundreds of Gbps, favoring of connections with small delays (few tens of milliseconds), incapacity of distinguishing packet loss causes and high delays for establishing secure connections (up to 3 RTTs). In this context, with the goal of making Internet data transport faster and more efficient, Google has developed the QUIC protocol. QUIC proposes many advances compared to existing protocols, such as a new mechanism for establishing connections and an optimized congestion control algorithm. Google has reported results indicating that QUIC performs better than TCP, justifying the work on making QUIC an IETF Internet standard. However, those results cannot be verified because on the published reports there is not enough information to reproduce the test scenarios and it is implausible to have the same test infrastructure Google has. In this work, we evaluate QUICs performance in a number of network scenarios, comparing it with the performance of different TCP flavours, specially TCP CUBIC. Unlike other works in the literature, all scenarios are well described, enabling experiment replicability. Furthermore, to run experiments we created a new module that implements QUIC on the network simulator NS-3. The module is available as free software, allowing other researchers to use it to reproduce and verify our experiments and to create new ones in a replicable way. Additionally, they can use the module as a tool to quickly assess the behaviour of new techniques in the protocol.

L'accès à Internet par satellite permet de connecter des régions isolées de la terre ou des utilisateurs en mouvement, pour lesquels une solution terrestre peut s’avérer couteuse voire impossible. L’utilisation de constellations de satellite en orbite basse permet de transmettre avec des délais similaires à ceux des transmissions terrestres, permettant l’utilisation des protocoles de transport classiques comme TCP. L’utilisation d’un tel environnement engendre cependant des contraintes spécifiques à ce type de réseau, comme des délais de transmission variables et un important taux d’erreur, principalement lors de la traversée de l’atmosphère. Pour compenser ces forts taux de pertes, des mécanismes de fiabilisation doivent être introduit au niveau des couche basse. Ces mécanismes ont toutefois un impact négatif sur les performances des protocoles de transport, notamment TCP, limitant grandement le débit. Le but de cette thèse est de comprendre dans un premier temps les interactions entre les mécanismes de fiabilisation et les protocoles de transport, pour ensuite proposer des solutions permettant d’améliorer la qualité des transmissions. / LEO satellite constellations allow to connect isolated or mobile users to the Internet, when terrestrial solutions are too expensive or impossible to deploy. Using such constellations allow to connect these areas with transmission delays close to terrestrial delays, and then to use the classic transport protocols such as TCP. However, this environment brings new impairments such as variable delays and important error rate between the satellite and the ground receiver. To counteract this high error rate, reliability schemes are introduced on the link between the satellite and the ground user. However, these schemes have a negative impact on the transport protocol (TCP), mitigating the throughput, and which has not been deeply studied yet. In this thesis, we first understand the impact of the reliability schemes on the transport layer, and then propose solutions to improve the efficiency of the transmissions.

This document describes a design procedure of interface between VGA camera and GSM/GPRS modem for displaying JPEG pictures captured by camera on website. Interface is realized by eight-bit micricontroller ATMEL with application written in C language. For picture transfer to server a TCP/IP stack is implemented into modem. The document is divided into two main parts. The first part describes architecture of the system, used components (camera, modem, microcontroller) and electronic circuit design. The second part of the document is focused on the software for the system. Firstly operating system of modem is desribed, OpenAT development environment for modem application design and WIPsoft library, which is used to implement TCP/IP stack. Next is described application for microcontroller which controlls camera and modem. Last part of this document describes server application and web interface.

The main task of this thesis was to explore the requirements of different telecommunications services on the network parameter, that are packet delay, packet loss, throughput, jitter. Make to test network service with WAN network emulator and load simulators. Next focus was to explore TCP congestion avoidance algorithms and focus on their throughput. The purpose of the first chapter is to introduce Quality of Service (QoS) for VoIP, video conversation, streaming audio, streaming video and data. The second chapter are to explore various types of delay, that are created from the sender through network device, transmission media to the recipient. The third chapter is to introduce NetDisturb application. It is application, that can emulate real properties of the data network and incoming traffic affect example packet delay, packet loss, bandwidth limit and so on. The key objectives of the fourth and fifth part is TCP protocol and TCP congestion avoidance algorithms. Hier are to introduce TCP protocol basic properties, congestion avoidance mechanisms and analysis of TCP congestion avoidance algorithms. In the practical part are created two laboratory exercises. First laboratory exercise is designed on the implementation QoS for various types of traffic. Second laboratory exercise is focused on the analysis TCP congestion avoidance algorithms and their throughput.

The market penetration of mobile access devices with multiple network interfaces has increased dramatically over the last few years. As a consequence, the quest for a widespread multi-path transport protocol that takes advantage of all available interfaces simultaneously to increase data throughput and improve robustness, has received considerable attention. One prominent protocol introduced by the IETF is Multipath TCP (MPTCP). MPTCP is an extension to the predominant single-path transport protocol, the Transport Control Protocol (TCP) that enables multihomed devices to aggregate available resources transparently to the applications. Combining multiple radio access technologies, like LTE and Wi-Fi, with diverse characteristics in terms of transmission rates and fluctuations opens for novel challenges that may disrupt and even harm the data throughput. Therefore MPTCP must take path heterogeneity into account. For MPTCP to supersede single-path TCP it is required that MPTCP always achieve at least the throughput of the best individual TCP path. This thesis investigates if MPTCP with uncoupled congestion control fulfills this condition, and if so, how much it improves the throughput. By examining the protocol in a deterministic emulated environment defined by the characteristics of LTE, we conclude two key factors impacting the outcome: the download size and the difference in characteristics between the paths. Our experiments show that MPTCP overall fulfills this task, especially during path homogeneity with near aggregated results. But we also show that MPTCP may decrease data throughput with 16% compared to TCP during path heterogeneity. Hence MPTCP does not always fulfill the goal of throughput. We therefore conclude further intelligence is needed for the packet scheduling mechanism to avoid throughput degradation in the initial phase of a transmission.

The surge in the cloud computing is due to its cost effective benefits and the rapid scalability of computing resources, and the crux of this is virtualization.  Virtualization technology enables a single physical machine to be shared by multiple operating systems. This increases the eciency of the hardware, hence decreases the cost of cloud computing. However, as the load in the guest operating system increases, at some point the physical resources cannot support all the applications efficiently. Input and output services, especially network applications, must share the same total bandwidth and this sharing can be negatively affected by virtualization overheads. Network packets may undergo additional processing and have to wait until the virtual machine is scheduled by the underlying hypervisor before reaching the final service application, such as a web server.In a virtualized environment it is not the load (due to the processing of the user data) but the network overhead, that is the major problem. Modern network interface cards have enhanced network virtualization by handling IP packets more intelligently through TCP segmentation offload, interrupt coalescence, and other virtualization specific hardware. Jumbo frames have long been proposed for their advantages in traditional environment. They increase network throughput and decrease CPU utilization.  Jumbo frames can better exploit Gigabit Ethernet and offer great enhancements to the virtualized environment by utilizing the bandwidth more effectively while lowering processor overhead. This thesis shows a network performance improvement of 4.7% in a Xen virtualized environment by using jumbo frames.  Additionally the thesis examines TCP's performance in Xen and compares Xen with the same operations running on a native Linux system. / Den kraftiga ökningen i datormoln är på grund av dess kostnadseffektiva fördelar och den snabba skalbarhet av datorresurser, och kärnan i detta är virtualisering. Virtualiseringsteknik möjliggör att man kan köra era operativsystem på en enda fysisk maskin. Detta ökar effektiviteten av hårdvaran, vilket gör att kostnaden minskar för datormoln. Men eftersom lasten i gästoperativsystemet ökar, gör att de fysiska resurserna inte kan stödja alla program på ett effektivt sätt. In-och utgångstjänster, speciellt nätverksapplikationer, måste dela samma totala bandbredd gör att denna delning kan påverkas negativt av virtualisering. Nätverkspaket kan genomgå ytterligare behandling och måste vänta tills den virtuella maskinen är planerad av den underliggande hypervisor innan den slutliga services applikation, till exempel en webbserver. I en virtuell miljö är det inte belastningen (på grund av behandlingen av användarens data) utan nätverket overhead, som är det största problemet. Moderna nätverkskort har förbättrat nätverk virtualisering genom att hantera IP-paket mer intelligent genom TCP- segmenterings avlastning, avbrotts sammansmältning och genom en annan hårdvara som är specifik för virtualisering. Jumboramar har länge föreslagits för sina fördelar i traditionell miljö. De ökar nätverk genomströmning och minska CPU-användning. Genom att använda Jumbo frames kan Gigabit Ethernet användandet förbättras samt erbjuda stora förbättringar för virtualiserad miljö genom att utnyttja bandbredden mer effektivt samtidigt sänka processor overhead. Det här examensarbetet visar ett nätverk prestandaförbättring på 4,7% i en Xen virtualiserad miljö genom att använda jumbo frames. Dessutom undersöker det TCP prestanda i Xen och jämför Xen med samma funktion som körs på en Linux system.