Muitos sistemas recentes de processamento paralelo e distribuído trabalham com acesso intensivo a dados, combinando facilidades de computação e armazenamento de dados para a construção de sistemas de grande escala, com custos reduzidos. Nesses sistemas, a interligação de um grande número de nós resulta na divisão sucessiva da capacidade de transferência, tornando a movimentação de dados um importante fator de limitação de desempenho. Ao se escalonar as tarefas computacionais em nós próximos dos dados, melhorias significativas no desempenho podem ser obtidas. Entretanto, a informação sobre a localidade dos dados não está facilmente acessível para o programador. Seu uso requer a interação com rotinas internas dos sistemas de arquivos, ou exige a adoção de um modelo de programação específico, normalmente associado a uma plataforma de execução já preparada para escalonar tarefas com aproveitamento da localidade dos dados. Este trabalho desenvolve a proposta de um mecanismo e interface para prover acesso a informações de localidade, além de permitir o controle da distribuição de novos dados. As operações de consulta e controle são realizadas por meio de arquivos e diretórios especiais, adicionados de forma transparente a um sistema de arquivos com blocos de dados distribuídos, apropriado para a execução em ambientes de processamento paralelo. O sistema é denominado parfs e permite obter as informações de localidade com operações de leitura e escrita em arquivos comuns, sem a necessidade do uso de bibliotecas ou modelos de programação específicos. Testes foram realizados para avaliar a proposta. Utilizando o escalonamento seletivo de operações de acesso a dados, baseado na informação de localidade, foram obtidos ganhos significativos de desempenho nessas operações. / Many recent data intensive parallel processing systems are built with cost effective hardware and combine compute and storage facilities. In such systems, interconnecting large numbers of nodes results in bandwidth-bisecting networks, making data movement an important performance limiting factor. By distributing jobs near data, significant performance improvements can be achieved. However, data locality information is not easily available to the programmer. It requires interaction with file system internals, or the adoption of custom programming and run-time frameworks providing embedded locality-aware job scheduling. This document develops a proposal of a mechanism and an interface to provide locality information and new data placement control. The query and control tasks are performed through special file and directories transparently added to a distributed file system, suitable for parallel processing environments. The file system is called parfs and allows the use of locality by read and write operations over regular files, with no need of libraries or specific programming models. Tests were conducted to assess the feasibility of the proposal. Through selective scheduling of data operations, based on locality information, significant performance gains were obtained in such operations.

Esta pesquisa é o resultado das observações de caráter etnográfico sobre um recorte proposto para um quadro específico de circulação migratória transnacional. A partir da abordagem de um caso específico, a emigração é tomada de diversas escalas de análise, mas com ênfase sobre os modos pelos quais ela é produzida e significada na esfera lo-cal. O quadro enfocado remete aos movimentos sazonais de afastamento e retorno dos emigrantes da aldeia de Vilas Boas, no interior nordeste de Portugal. Procurei seguir os agentes pelos seus deslocamentos entre o contexto de partida e os contextos de destino para os quais rumaram, sem por isso perder de vista a aldeia como foco de seu interesse e da participação social. A maior parte do trabalho de campo, no entanto, se deu no con-texto de retorno massivo dos emigrantes para a aldeia para a ocasião de celebração da festa religiosa local. Nesse contexto são observadas as diferentes maneiras pelas quais as o contingente emigrante se relaciona com o grupo que reside na aldeia, bem como os modos pelos quais constroem sua participação na festa e na vida social local. Trata-se, portanto, de uma reflexão sobre práticas que sustentam transnacionalmente relações sociais e as atualizam no reencontro ocasionado pelo retorno. / This research is the result of ethnographic observations about a proposed cut to a partic-ular frame of transnational migratory movement. From the approach of a specific case, emigration is taken from different scales of analysis, but with emphasis on the ways in which it is produced and meant at the local level. The frame refers to the seasonal movements focused on departure and return of emigrants from the village of Vilas Bo-as, northeast of Portugal. I seek to follow the agents for their displacements between the context of departure and destination contexts for which they headed, without losing the perspective of the village as the focus of interest in social participation of agents. Most of the field work, however, occurred in the context of massive return of migrants to the village for the celebration of a religious festival site. In this context are observed the different ways in which the emigrant group relates to the people residing in the village as well as the ways in which their participation in making the party and the local social life. It is, therefore, a reflection on practices that sustain social relations transnationally and update the reunion caused by return.

A presente pesquisa dissertativa foi desenvolvida para investigar como professores de Geografia de escolas da rede pública estadual de Ibitinga-SP têm trabalhado o tema hidrografia em suas práticas pedagógicas. Procuramos descrever criticamente como se dão as práticas escolares de professores de Geografia em relação à hidrografia local, refletir sobre a importância de se desenvolver práticas que tratem da localidade na qual os alunos estão inseridos e analisar as práticas dos professores, tendo em vista o desenvolvimento de uma consciência socioambiental e cidadã dos alunos. A abordagem metodológica escolhida foi a qualitativa, o que possibilitou uma avaliação dos processos e das características intrínsecas do ensino. Os procedimentos para a coleta de dados envolveram entrevistas semi-estruturadas com três professores participantes, observações das aulas em que foram desenvolvidos os temas hidrografia e localidade, e análise dos documentos produzidos e utilizados pelos professores e alunos no desenvolvimento do tema em questão. Realizamos a caracterização das escolas e dos professores participantes da pesquisa. Os dados coletados e as análises realizadas evidenciaram que as práticas escolares estão atreladas ao currículo oficial implementado pelo programa São Paulo Faz Escola, que limita o estabelecimento de relações com a localidade, abordando a Hidrografia Geral e não a da localidade. As práticas escolares decorrem de pressões sofridas pelos professores para cumprirem o currículo prescrito pela Secretaria de Educação, à carga horária muito extensa e à dificuldade que eles têm em encontrar informações sistematizadas sobre o tema para a localidade em estudo. / This research was carried out to investigate how Geography teachers from public schools of Ibitinga, São Paulo, have been teaching Hydrographs with their students. We have been looking for describing how the school practices of selected teachers have been worked in relation to Local Hydrographs, thinking about relationship between locality and the students life and discussing the teachers practices with eyes on construction of social and environmental conscience for students. The applied methodology for data collection included an interview, teachers lessons and document review. The methodological approach was qualitative to avoid better evaluations of processes and intrinsic characteristics of the teaching. A description of participating schools and teachers was performed. Data analysis demonstrated that school practices have been overruled by official program named São Paulo Faz Escola what restrains the Locality teaching. School practices have been originated from hard pressure in teachers carrying out the official lessons prescribed from government, their heavy workload and due to their difficulties to find organized information of Locality.

A presente pesquisa dissertativa foi desenvolvida para investigar como professores de Geografia de escolas da rede pública estadual de Ibitinga-SP têm trabalhado o tema hidrografia em suas práticas pedagógicas. Procuramos descrever criticamente como se dão as práticas escolares de professores de Geografia em relação à hidrografia local, refletir sobre a importância de se desenvolver práticas que tratem da localidade na qual os alunos estão inseridos e analisar as práticas dos professores, tendo em vista o desenvolvimento de uma consciência socioambiental e cidadã dos alunos. A abordagem metodológica escolhida foi a qualitativa, o que possibilitou uma avaliação dos processos e das características intrínsecas do ensino. Os procedimentos para a coleta de dados envolveram entrevistas semi-estruturadas com três professores participantes, observações das aulas em que foram desenvolvidos os temas hidrografia e localidade, e análise dos documentos produzidos e utilizados pelos professores e alunos no desenvolvimento do tema em questão. Realizamos a caracterização das escolas e dos professores participantes da pesquisa. Os dados coletados e as análises realizadas evidenciaram que as práticas escolares estão atreladas ao currículo oficial implementado pelo programa São Paulo Faz Escola, que limita o estabelecimento de relações com a localidade, abordando a Hidrografia Geral e não a da localidade. As práticas escolares decorrem de pressões sofridas pelos professores para cumprirem o currículo prescrito pela Secretaria de Educação, à carga horária muito extensa e à dificuldade que eles têm em encontrar informações sistematizadas sobre o tema para a localidade em estudo. / This research was carried out to investigate how Geography teachers from public schools of Ibitinga, São Paulo, have been teaching Hydrographs with their students. We have been looking for describing how the school practices of selected teachers have been worked in relation to Local Hydrographs, thinking about relationship between locality and the students life and discussing the teachers practices with eyes on construction of social and environmental conscience for students. The applied methodology for data collection included an interview, teachers lessons and document review. The methodological approach was qualitative to avoid better evaluations of processes and intrinsic characteristics of the teaching. A description of participating schools and teachers was performed. Data analysis demonstrated that school practices have been overruled by official program named São Paulo Faz Escola what restrains the Locality teaching. School practices have been originated from hard pressure in teachers carrying out the official lessons prescribed from government, their heavy workload and due to their difficulties to find organized information of Locality.

Muitos sistemas recentes de processamento paralelo e distribuído trabalham com acesso intensivo a dados, combinando facilidades de computação e armazenamento de dados para a construção de sistemas de grande escala, com custos reduzidos. Nesses sistemas, a interligação de um grande número de nós resulta na divisão sucessiva da capacidade de transferência, tornando a movimentação de dados um importante fator de limitação de desempenho. Ao se escalonar as tarefas computacionais em nós próximos dos dados, melhorias significativas no desempenho podem ser obtidas. Entretanto, a informação sobre a localidade dos dados não está facilmente acessível para o programador. Seu uso requer a interação com rotinas internas dos sistemas de arquivos, ou exige a adoção de um modelo de programação específico, normalmente associado a uma plataforma de execução já preparada para escalonar tarefas com aproveitamento da localidade dos dados. Este trabalho desenvolve a proposta de um mecanismo e interface para prover acesso a informações de localidade, além de permitir o controle da distribuição de novos dados. As operações de consulta e controle são realizadas por meio de arquivos e diretórios especiais, adicionados de forma transparente a um sistema de arquivos com blocos de dados distribuídos, apropriado para a execução em ambientes de processamento paralelo. O sistema é denominado parfs e permite obter as informações de localidade com operações de leitura e escrita em arquivos comuns, sem a necessidade do uso de bibliotecas ou modelos de programação específicos. Testes foram realizados para avaliar a proposta. Utilizando o escalonamento seletivo de operações de acesso a dados, baseado na informação de localidade, foram obtidos ganhos significativos de desempenho nessas operações. / Many recent data intensive parallel processing systems are built with cost effective hardware and combine compute and storage facilities. In such systems, interconnecting large numbers of nodes results in bandwidth-bisecting networks, making data movement an important performance limiting factor. By distributing jobs near data, significant performance improvements can be achieved. However, data locality information is not easily available to the programmer. It requires interaction with file system internals, or the adoption of custom programming and run-time frameworks providing embedded locality-aware job scheduling. This document develops a proposal of a mechanism and an interface to provide locality information and new data placement control. The query and control tasks are performed through special file and directories transparently added to a distributed file system, suitable for parallel processing environments. The file system is called parfs and allows the use of locality by read and write operations over regular files, with no need of libraries or specific programming models. Tests were conducted to assess the feasibility of the proposal. Through selective scheduling of data operations, based on locality information, significant performance gains were obtained in such operations.

A ancestralidade do edifício sinagogal atribuiu a este um papel central na formação da arquitetura religiosa ocidental. Entretanto sua adaptação à localidade, no decorrer dos séculos, concedeu-lhe os mais variados repertórios. Aspectos ligados ao uso, porém, demandaram soluções espaciais para problemáticas que permaneceram ao longo do tempo. Essas soluções que envolvem o programa de necessidades dos edifícios, sua dimensão e capacidade de uso, suas relações com a arquitetura das diferentes localidades e as consequentes ações de preservação da identidade e a organização dos elementos da liturgia, dentro do espaço interno do edifício, geraram as transformações que, reunidas, constituem uma radiografia da arquitetura da sinagoga no tempo. / The ancestry of the synagogue building attributed to this a central paper in the formation of the religious architecture occidental person. However, its adaptation to the locality in elapsing of the centuries granted to it the most varied repertoires. On aspects to the use, however, had demanded space solutions for problematic that they had remained throughout the time. These solutions that involve the program of necessities of the buildings, its dimension and capacity of use, its relations with the architecture of the different localities and the subsequent actions of preservation of the identity and the organization of the elements of the liturgy inside of the internal space of the building, had generated the transformations that, congregated, constitute a picture of the architecture of the synagogue in the time.

X.509 certificate revocation defends against man-in-the-middle attacks involving a compromised certificate. Certificate revocation strategies face scalability, effectiveness, and deployment challenges as HTTPS adoption rates have soared. We propose Certificate Revocation Table (CRT), a new revocation strategy that is competitive with or exceeds alternative state-of-the-art solutions in effectiveness, efficiency, certificate growth scalability, mass revocation event scalability, revocation timeliness, privacy, and deployment requirements. The CRT periodically checks the revocation status of X.509 certificates recently used by an organization, such as clients on a university's private network. By prechecking the revocation status of each certificate the client is likely to use, the client can avoid the security problems of on-demand certificate revocation checking. To validate both the effectiveness and efficiency of using a CRT, we used 60 days of TLS traffic logs from Brigham Young University to measure the effects of actively refreshing certificates for various certificate working set window lengths. Using a certificate working set window size of 45 days, an average of 99.86% of the TLS handshakes from BYU would have revocation information cached in advance using our approach. Revocation status information can be initially downloaded by clients with a 6.7 MB file and then subsequently updated using only 205.1 KB of bandwidth daily. Updates to this CRT that only include revoked certificates require just 215 bytes of bandwidth per day.

Outlier detection remains a heated area due to its essential role in a wide range of applications, including intrusion detection, fraud detection in finance, medical diagnosis, etc. Local Outlier Factor (LOF) has been one of the most influential outlier detection techniques over the past decades. LOF has distinctive advantages on skewed datasets with regions of various densities. However, the traditional centralized LOF faces new challenges in the era of big data and no longer satisfies the rigid time constraints required by many modern applications, due to its expensive computation overhead. A few researchers have explored the distributed solution of LOF, but existant methods are limited by their grid-based data partitioning strategy, which falls short when applied to high-dimensional data. In this thesis, we study efficient distributed solutions for LOF. A baseline MapReduce solution for LOF implemented with Apache Spark, named MR-LOF, is introduced. We demonstrate its disadvantages in communication cost and execution time through complexity analysis and experimental evaluation. Then an approximate LOF method is proposed, which relies on locality-sensitive hashing (LSH) for partitioning data and enables fully distributed local computation. We name it MR-LOF-LSH. To further improve the approximate LOF, we introduce a process called cross-partition updating. With cross-partition updating, the actual global k-nearest neighbors (k-NN) of the outlier candidates are found, and the related information of the neighbors is used to update the outlier scores of the candidates. The experimental results show that MR-LOF achieves a speedup of up to 29 times over the centralized LOF. MR-LOF-LSH further reduces the execution time by a factor of up to 9.9 compared to MR-LOF. The results also highlight that MR-LOF-LSH scales well as the cluster size increases. Moreover, with a sufficient candidate size, MR-LOF-LSH is able to detect in most scenarios over 90% of the top outliers with the highest LOF scores computed by the centralized LOF algorithm.

With the extremely rapid development of the Internet in recent years, emerging peer-to-peer network overlays are meeting the requirements of a more sophisticated communications environment, providing a useful substrate for applications such as scalable file sharing, data storage, large-scale multicast, web-cache, and publish-subscribe services. Due to its design flexibility, peer-to-peer networks can offer features including self-organization, fault-tolerance, scalability, load-balancing, locality and anonymity. As the Internet grows, there is an urgent requirement to understand real-time network performance degradation. Measurement tools currently used are ping, traceroute and variations of these. SNMP (Simple Network Management Protocol) is also used by network administrators to monitor local networks. However, ping and traceroute can only be used temporarily, SNMP can only be deployed at certain points in networks and these tools are incapable of sharing network measurements among end-users. Due to the distributed nature of networking performance data, peer-to-peer overlay networks present an attractive platform to distribute this information among Internet users. This thesis aims at investigating the desirable locality property of peer-to-peer overlays to create an application to share Internet measurement performance. When measurement data are distributed amongst users, it needs to be localized in the network allowing users to retrieve it when external Internet links fail. Thus, network locality and robustness are the most desirable properties. Although some unstructured overlays also integrate locality in design, they fail to reach rarely located data items. Consequently, structured overlays are chosen because they can locate a rare data item deterministically and they can perform well during network failures. In structured peer-to-peer overlays, Tapestry, Pastry and Chord with proximity neighbour selection, were studied due to their explicit notion of locality. To differentiate the level of locality and resiliency in these protocols, P2Psim simulations were performed. The results show that Tapestry is the more suitable peer-to-peer substrate to build such an application due to its superior localizing data performance. Furthermore, due to the routing similarity between Tapestry and Pastry, an implementation that shares network measurement information was developed on freepastry, verifying the application feasibility. This project also contributes to the extension of P2Psim to integrate with GT-ITM and link failures.

MapReduce 是目前最熱門的雲端技術之一，用來處理大量資料，不論資料探勘、非結構化的紀錄檔、網頁索引處理及其他需要大量資料處理的科學研究，都可透過 MapReduce 得到極佳的執行效率。MapReduce 為一分散式批次資料處理程式框架，將一個工作分解為許多較小的 map 任務以及 reduce 任務，由map 處理每個小問題，再由reduce將問題彙整，得到最終的結果。 Hadoop 是一個開放原始碼的 MapReduce 架構，並且被廣泛地應用在以大規模資料運算為主的雲端計算。Hadoop有一個非常重要的元件稱為scheduler ，是 hadoop的中樞，負責調度、指派任務和資源分配的優先順序。Scheduler的任務選擇與分配方式，將會影響 MapReduce 工作的執行效率與整個叢集的使用率，目前Hadoop預設的scheduler是將任務以先進先出(FIFO)的方式進行排程。提升MapReduce運算效能的挑戰之一為如何適當的分配Mapper 和 Reducer給雲端裡的每個節點來執行。儘管過去已經有許多改善MapReduce運算效能的研究，但是大部分的方法在實際的運作中，仍存在很多的問題，如工作節點的動態負載、data locality的問題，計算節點的異質性等等。我們發現目前Hadoop對於這些問題並沒有妥善處理，並且在相關的情況下，整體效能仍有改進空間。 我們提出Data Locality Driven Scheduler(DLDS)的方法，並實踐在 Hadoop上，試圖提高scheduler的效能。我們設計不同的實驗，比較DLDS在不同狀況下和其他的排程演算法的差異。實驗結果顯示，透過提高資料的地域性，平均可提昇10% 至 15% 的效能。 / MapReduce is programming model for processing large data set. It is typically used to do distributed computing on clusters of computers such as Cloud computing platform. Examples of bit data set include unstructured logs, web indexing, scientific data, surveillance data, etc. MapReduce is a distributed processing program framework, a computing job is broken down into many smaller Map tasks and a Reduce task.Each Map task processes a partition of the given data set and Reduce aggregates the results of Maps to produce final result. Hadoop is an open-source MapReduce architecture, and is widely used in many cloud-based services.To best utilize computing resource in a cloud server, a task scheduler is essential to assign tasks to appropriate processors as well as to prioritize resource allocation. The default scheduler of Hadoop is first-in-first-out (FIFO) scheduler which is simple but has a performance inefficiency yet to be improved. Although there have been many researches aiming to improve the performance of MapReduce platform in the past year, there still have many issues hindering the performance improvement, such as dynamic load balance, data locality, and heterogeneity of computing nodes. To improve data locality, we propose a new scheduler called Data Locality Driven Scheduler (DLDS) based on Hadoop platform. DLDS improve Hadoop's performamce by allocating Map tasks as close as possible to the data block they are to process. We evaluated the proposed DLDS against several other schedulers by simulation on an 8 nodes real Hadoop system. Experimental results show that DLDS can improve data locality by 10-15%, which results in a significant performamce improvement.