Grids provide an infrastructure for seamless, secure access to a globally distributed set of shared computing resources. Grid computing has reached the stage where deployments are run in production mode. In the most active Grid community, the scientific community, jobs are data and compute intensive. Scientific Grid deployments offer the opportunity for revisiting and perhaps updating traditional beliefs related to workload models and hence reevaluate traditional resource management techniques. In this thesis, we study usage patterns from a large-scale scientificGrid collaboration in high-energy physics. We focus mainly on data usage, since data is the major resource for this class of applications. We perform a detailed workload characterization which led us to propose a new data abstraction, filecule, that groups correlated files. We characterize filecules and show that they are an appropriate data granularity for resource management. In scientific applications, job scheduling and data staging are tightly coupled. The only algorithm previously proposed for this class of applications, Greedy Request Value (GRV), uses a function that assigns a relative value to a job. We wrote a cache simulator that uses the same technique of combining cache replacement with job reordering to evaluate and compare quantitatively a set of alternative solutions. These solutions are combinations of Least Recently Used (LRU) and GRV from the cache replacement space with First-Come First-Served (FCFS) and the GRV-specific job reordering from the scheduling space. Using real workload from the DZero Experiment at Fermi National Accelerator Laboratory, we measure and compare performance based on byte hit rate, cache change, job waiting time, job waiting queue length, and scheduling overhead. Based on our experimental investigations, we propose a new technique that combines LRU for cache replacement and job scheduling based onthe relative request value. This technique incurs less data transfer costs than the GRV algorithm and shorter job processing delays than FCFS. We also propose using filecules for data management to further improve the results obtained from the above LRU and GRV combination. We show that filecules can be identified in practical situations and demonstrate how the accuracy of filecule identification influences caching performance.

Thesis (M.S.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Electrical Engineering, 2006. / Includes bibliographical references.

.

Cette thèse s'intéresse à améliorer la qualité de service (QdS) offerte par des mécanismes de gestion de file d'attente tels que RED (Random Early Detection). Nous étudions une approche adaptative de RED appelée ARED. Notre but est de trouver un extension simple de ARED afin d'améliorer la prédictibilité des mesures de performance comme le délai, le temps de gigue sans pour autant sacrifier le taux de perte. Pour cela, nous proposons un nouveau mécanisme nommé PSAND qui configure les paramètres de RED et l'évaluons à l'aide de simulations. Nos résultats de la comparaison de PSAND avec ARED et d'autres schémas bien connus ou récemment proposés ont montré que avec une complexité moindre, PSAND donne un compromis désiré et de bonnes performances telles qu'un faible délai d'attente dans la file, une faible gigue et une plus grande stabilité en présence d'un fort trafic. Une autre contribution de cette thèse est l'étude de l'interaction de FEC (Forward Error Correction) avec des schémas comme Drop Tail et RED. Les résultats ont montré que selon la valeur des paramètres comme le nombre de flux TCP actifs, le taux de redondance et de la taille des blocs FEC parfois RED ou parfois Drop Tail donne de meilleures performances. Un modèle analytique ayant confirmé les résultats obtenus par simulations a également été présenté.

<p>This thesis contributes to the knowledge of how computer-mediated communication and information sharing works in large groups and networks. In more detail, the research question put forward is: in large sharing networks, what concerns do end-users have regarding to whom to provide material? A theoretical framework of gift-giving was applied to identify, label and classify qualitative end-user concerns with provision. The data collection was performed through online ethnographical research methods in two large sharing networks, one music-oriented and one photo-oriented. The methods included forum message elicitation, online interviews, application use and observation. The result of the data collection was a total of 1360 relevant forum messages. A part from this there are also 27 informal interview logs, field notes and samples of user profiles and sharing policies. The qualitative analysis led up to a model of relationships based on the observation that many users experienced conflicts of interest between various groups of receivers and that these conflicts, or social dilemmas, evoked concerns regarding public and non-public provision of material. The groups of potential recipients were often at different relationship levels. The levels ranged from the individual (ego), to the small group of close peers (micro), to a larger network of acquaintances (meso) to the anonymous larger network (macro). It is argued that an important focal point for analysis of cooperation and conflict is situated in the relations between these levels. Deepened studies and analysis also revealed needs to address dynamic recipient groupings, the need to control the level of publicness of both digital material and its metadata (tags, contacts, comments and links to other networks) and that users often refrained from providing material unless they felt able to control its direction. A central conclusion is that public and non-public gifting need to co-emerge in large sharing networks and that non-public gifting might be an important factor for the support of continued provision of goods in sustainable networks and communities.</p>

<p>Nuvarande implementationer av distribuerade hashtabeller (DHT) har en begränsad storlek för data som kan lagras, som t.ex. OpenDHTs datastorleks gräns på 1kByte. Är det möjligt att lagra filer större än 1kByte med DHT-tekniken? Finns det någon lösning för att skydda de data som lagrats utan att försämra prestandan? Vår lösning var att utveckla en klient- och servermjukvara. Mjukvaran använder sig av DHT tekniken för att dela upp filer och distribuera delarna över ett serverkluster. För att se om mjukvaran fungerade som tänkt, gjorde vi ett test utifrån de inledande frågorna. Testet visade att det är möjligt att lagra filer större än 1kByte, säkert med DHT tekniken utan att förlora för mycket prestanda.</p> / <p>Currently existing distributed hash table (DHT) implementations use a small storage size for data, such as OpenDHT’s storage size limitation of 1kByte. Is it possible to store larger files than 1kByte using the DHT technique? Is there a way to protect the data without losing to much performance? Our solution was to develop a client and server software. This software uses the DHT technique to split files and distribute their parts across a cluster of servers. To see if the software worked as intended we created a test based on our opening questions. This test shows that it indeed is possible to store large files securely using the DHT technique without losing any significant performance.</p>

<p>Titel: Into tomorrow – Constructing scenarios for the record industry in the 21-century.Number of Pages: 54 (55 including enclosures)Author: Erik G AgebergTutor: Else NygrenCourse: Media and Communication Studies DPeriod: Spring semester 2009University: Division of Media and Communication studies, Department ofinformation science, Uppsala University.Purpose/Aim: The aim of this paper is to, through scenario planning methodology,present recommendations in order for record companies to be competitive in the nearfuture. In order to achieve this goal three question where asked. (1) What are the mostcentral problems of the record industry? (2) How can these problems affect the futurein the industry? (3) In what way can record companies’ work to avoid theseproblems? The paper focuses on the Swedish market partly because of the giventimeframe but also because of Sweden’s position in that of file sharing as well astechnological advances. It is also assumed in this paper that the future of music saleswill be concentrated to the Internet.Material/Method: The chosen method for this paper was scenario planning. Anextensive literature study was complemented with interviews of key players involvedin content consumption over the Internet.Main results: A fundamental issue for the future of the music industry is that oflegislation. The outcome of the record industry’s future is almost exclusivelydependent on the way, which the legislation takes. A stricter legislation, whichincludes violations of citizens’ personal integrity, may backfire and result in politicalpirate parties’ becoming members of parliaments. This may in turn result in that theintellectual property laws of the nineteenth century are removed. Suing privatepersons and trackers can result in record companies alienating an entire generation ofmusic consumers. Record companies attempts to retain music as a product may proveto be futile within time, but they can absolutely prolong the period in which it is aproduct. It is nevertheless, not entirely negative for music to become a service. Bybeing a service music can more easily be attached to another service, like an Internetsubscription, or an experience.</p>

<p>Abstract</p><p>Purpose/Aim: To study how Piratbyrån argues for a free distribution of information and culture products and to find a possible ideological explanation for their argumentation.</p><p>Method/Material: I have used a rhetorical analysis to study and describe Piratbyrån´s website, a website that promotes free distribution of information and culture products. I have done so to find out how Piratbyrån argues for a free distribution and to find out what ideological foundation their argumentation is based on.</p><p>Main results: The main results of the study show that Piratbyrån uses a variety of rhetorical techniques depending on the subject and purpose of the analyzed text. Their main arguments both promote their own thesis and argue against the copyright industry. The main part of the argumentation is based on logical and factual arguments, but parts of it also rely on an emotional appeal to the reader’s heart in order to persuade. The analysis also showed great similarities between Piratbyrån´s argumentation and the ideology that Siva Vaidhyanathan describes as information anarchy. An ideology that promotes free distribution of information and culture products, that relies on decentralized systems and nonhierarchical structures and is a result of the technological development such as digitalization and peer-to-peer networks.</p><p>Keywords: Rhetoric, technology, file sharing, digitalization, network, ideology, anarchy, oligarchy, copyright, website</p>

Abstract Purpose/Aim: To study how Piratbyrån argues for a free distribution of information and culture products and to find a possible ideological explanation for their argumentation. Method/Material: I have used a rhetorical analysis to study and describe Piratbyrån´s website, a website that promotes free distribution of information and culture products. I have done so to find out how Piratbyrån argues for a free distribution and to find out what ideological foundation their argumentation is based on. Main results: The main results of the study show that Piratbyrån uses a variety of rhetorical techniques depending on the subject and purpose of the analyzed text. Their main arguments both promote their own thesis and argue against the copyright industry. The main part of the argumentation is based on logical and factual arguments, but parts of it also rely on an emotional appeal to the reader’s heart in order to persuade. The analysis also showed great similarities between Piratbyrån´s argumentation and the ideology that Siva Vaidhyanathan describes as information anarchy. An ideology that promotes free distribution of information and culture products, that relies on decentralized systems and nonhierarchical structures and is a result of the technological development such as digitalization and peer-to-peer networks. Keywords: Rhetoric, technology, file sharing, digitalization, network, ideology, anarchy, oligarchy, copyright, website

Problem: Record companies are facing a downturn in sales of music. This is seen as consequence of the growth of distribution of music through Internet by file sharing networks such as BitTorrent networks. On one side there are record companies who feel threatened of the illegal file sharing, and on the other side file sharing BitTorrent networks has increased dramatically in number of users since they first approached. Some record companies have responded by taking hostile actions towards the BitTorrent networks and their users with lawsuits and penalties for illegal file sharing. Other record companies and artists have joined forces with BitTorrent networks and see them as an advantage. Purpose: The purpose of this paper is to explore and analyze if, and how record companies can collaborate with the BitTorrent networks. Method: A hermeneutic inductive approach is used, in combination with qualitative interviews with both record companies and BitTorrent networks. Conclusions: It is argued that record companies can find a way in communicating and cooperating with BitTorrent networks. Instead of adopting hostile approaches and trying to restrict the technologies adopted by end users, companies should open themselves up and accept the current changes initiated and developed by BitTorrent networks. Thus, it was concluded that companies have to concentrate around collaborating with BitTorrent networks rather than fiercely protecting old business models. By opening up to the users, record companies will adopt open innovations approach that is characterized by combining external and internal ideas, as well internal and external paths to market, thus obtaining future technological developments. As for the BitTorrent networks, by going from outlaw to crowdsourcing mode, the networks’ creative solutions can be further harnessed by record companies. Finally, strengthening relationships between customers and music artists can be considered as beneficial for both record companies and BitTorrent networks. Thus, giving opportunities for customers to win special items, tickets for concerts, watch sound check, eat dinner backstage with the group, take pictures, get autographs, watch the show from the side of the stage, etc. can lead to valuable relationship in a long run.