Η παρούσα διπλωματική έχει σαν σκοπό τη διερεύνηση της τεχνολογίας του Cloud Computing και της τεχνολογίας της Virtualization που την στηρίζει. Παρουσίαση της ιστορίας και μια τεχνική παρουσίαση των δυνατοτήτων και των καταβολών των τεχνολογιών. Αναφέρονται πρακτικές εφαρμογές που μπορούν οι συγκεκριμένες τεχνολογίες να εφαρμοστούν και τους σκοπούς που θα εξυπηρετήσουν. Επίσης γίνεται μια πιο αναλυτική παρουσίαση δυο προγραμμάτων (Xen Hypervisor – για το επίπεδο της Virtualization, Eucalyptus – σαν πλατφόρμα για τη δημιουργία IaaS Clouds). Παρουσιάζονται επίσης σύντομοι οδηγοί για την εγκατάσταση ενός Cloud, καθώς και το configuration μαζί με τους λόγους που χρησιμοποιήθηκε. / The scope of this thesis is to study the technology of Cloud Computing and the Virtualization technology that is supporting it. A presentation of the history, a technical overview and the origins of these technologies. There are mentioned some fields that the specified technologies could apply and the purposes that they would serve. On the third chapter, a more detailed presentation of two pieces of software is given (Xen Hypervisor – for the Virtualization Layer, Eucalyptus – as the platform to create IaaS Clouds). In the end quick how-to guides are described on the procedure to install a Cloud, the configuration and the reasons of the specific set up as well.

<p>This thesis presents an evaluation of the Solaris version of the Xen virtual machine monitor and a comparison of its performance to the performance of Solaris Containers under similar conditions. Xen is a virtual machine monitor, based on the paravirtualization approach, which provides an instruction set different to the native machine environment and therefore requires modifications to the guest operating systems. Solaris Zones is an operating system-level virtualization technology that is part of the Solaris OS. Furthermore, we provide a basic performance evaluation of the security modules for Xen and Zones, known as sHype and Solaris Trusted Extensions, respectively.</p><p>We evaluate the control domain (know as Domain-0) and the user domain performance as the number of user domains increases. Testing Domain-0 with an increasing number of user domains allows us to evaluate how much overhead virtual operating systems impose in the idle state and how their number influences the overall system performance. Testing one user domain and increasing the number of idle domains allows us to evaluate how the number of domains influences operating system performance. Testing concurrently loaded increasing numbers of user domains we investigate total system efficiency and load balancing dependent on the number of running systems.</p><p>System performance was limited by CPU, memory, and hard drive characteristics. In the case of CPU-bound tests Xen exhibited performance close to the performance of Zones and to the native Solaris performance, loosing 2-3% due to the virtualization overhead. In case of memory-bound and hard drive-bound tests Xen showed 5 to 10 times worse performance.</p>

Submitted by GUSTAVO CESAR BRUSCHI null (gustavo@bruschi.net) on 2016-06-30T22:02:25Z No. of bitstreams: 1 Dissertacao_GustavoBruschi_FINAL(CORRIGIDO)_v2.pdf: 2377456 bytes, checksum: 41a5c87825aeb7131a629aee63fc450d (MD5) / Rejected by Ana Paula Grisoto (grisotoana@reitoria.unesp.br), reason: Solicitamos que realize uma nova submissão seguindo a orientação abaixo: O arquivo submetido está sem a ficha catalográfica. A versão submetida por você é considerada a versão final da dissertação/tese, portanto não poderá ocorrer qualquer alteração em seu conteúdo após a aprovação. Corrija esta informação e realize uma nova submissão contendo o arquivo correto. Agradecemos a compreensão. on 2016-07-04T18:38:19Z (GMT) / Submitted by GUSTAVO CESAR BRUSCHI null (gustavo@bruschi.net) on 2016-07-05T13:38:34Z No. of bitstreams: 2 Dissertacao_GustavoBruschi_FINAL(CORRIGIDO)_v2.pdf: 2377456 bytes, checksum: 41a5c87825aeb7131a629aee63fc450d (MD5) Dissertacao_GustavoBruschi_FINAL(CORRIGIDO)_v2.pdf: 2402200 bytes, checksum: 7d077bcd92c83a83ef1a9502d794312d (MD5) / Approved for entry into archive by Ana Paula Grisoto (grisotoana@reitoria.unesp.br) on 2016-07-07T16:26:49Z (GMT) No. of bitstreams: 1 bruschi_gc_me_sjrp.pdf: 2402200 bytes, checksum: 7d077bcd92c83a83ef1a9502d794312d (MD5) / Made available in DSpace on 2016-07-07T16:26:49Z (GMT). No. of bitstreams: 1 bruschi_gc_me_sjrp.pdf: 2402200 bytes, checksum: 7d077bcd92c83a83ef1a9502d794312d (MD5) Previous issue date: 2016-06-01 / A Computação em Nuvem tornou-se sinônimo de qualidade e eficiência em investimento na área de Tecnologia de Informação, criando novos desafios para o processamento e integração de dados. O desempenho da solução adotada é um ponto chave para o sucesso de uma solução em Nuvem, assim como a maneira como as máquinas virtuais realizam a leitura e gravação no armazenamento, podem ser determinantes para uma melhor utilização desta solução. Este trabalho apresenta o StackAct, um mecanismo que permite realizar o monitoramento e obter dados, em uma Nuvem IaaS, relativos ao consumo de recursos computacionais de uma solução em três camadas utilizando orquestrador Apache CloudStack com hypervisor XenServer e armazenamento dos dados no sistema Openfiler. Foram realizados testes de desempenho utilizando três diferentes tipos de perfil de instâncias em uma nuvem computacional privada, possibilitando mensurar os consumos de CPU, E/S e Memória nas três camadas envolvidas, com diferentes tipos de ofertas de serviços. Os testes resultaram em um comparativo entre cada item analisado para cada camada individual, onde foi possível detectar uma pequena variação entre as diferentes configurações de testes devido a forma como a camada do hypervisor enfileira as requisições realizadas pela camada do orquestrador. Já no comparativo realizado entre as camadas, foi possível constatar o alto consumo de disco na camada de armazenamento de dados, em especial E/S de gravação de dados, que levaram a realização de outros testes utilizando disco de estado sólido na camada de armazenamento, tendo um grande impacto no desempenho da solução como um todo. Foi detectado também um alto consumo de memória na camada hypervisor, que é justificada pela alocação do próprio hypervisor além das VMs que estão sendo criadas e utilizadas no processo. / Cloud Computing has become synonymous of quality, efficiency, and return of investment in Information Technology, creating new challenges for processing and data integrations. The performance of the adopted solution is a key to the success of a solution on Cloud, as well as the way that virtual machines use reading and writing to storage, which can be decisive for a better use of this solution. This work presents the StackAct, a mechanism that allows for monitoring and obtaining data on the consumption of computing resources of a solution in three layers using orchestrator IaaS Apache CloudStack with XenServer hypervisor and storage of data on the NAS OpenFiler system. Based on this mechanism, performance tests were conducted using three different instances of a private cloud. CPU, I/O, and memory usages in the three layers involved were measured with different types of loads. The tests resulted in a comparison between each item analyzed for each individual layer, and it was possible to detect a slight variation between the different configurations of tests because of the way that the hypervisor layer queues the requests made by the orchestrator layer. In the comparison made between the layers, it was possible to high consumption of disk in the data storage layer, in particular I/O data recording, which led to other tests using solid state disk in the storage layer, having an high impact on the performance of the solution as a whole. It was also detected high memory in the hypervisor layer, which is justified by the allocation of the hypervisor itself beyond the VMs being created and used in the process.

This thesis presents an evaluation of the Solaris version of the Xen virtual machine monitor and a comparison of its performance to the performance of Solaris Containers under similar conditions. Xen is a virtual machine monitor, based on the paravirtualization approach, which provides an instruction set different to the native machine environment and therefore requires modifications to the guest operating systems. Solaris Zones is an operating system-level virtualization technology that is part of the Solaris OS. Furthermore, we provide a basic performance evaluation of the security modules for Xen and Zones, known as sHype and Solaris Trusted Extensions, respectively. We evaluate the control domain (know as Domain-0) and the user domain performance as the number of user domains increases. Testing Domain-0 with an increasing number of user domains allows us to evaluate how much overhead virtual operating systems impose in the idle state and how their number influences the overall system performance. Testing one user domain and increasing the number of idle domains allows us to evaluate how the number of domains influences operating system performance. Testing concurrently loaded increasing numbers of user domains we investigate total system efficiency and load balancing dependent on the number of running systems. System performance was limited by CPU, memory, and hard drive characteristics. In the case of CPU-bound tests Xen exhibited performance close to the performance of Zones and to the native Solaris performance, loosing 2-3% due to the virtualization overhead. In case of memory-bound and hard drive-bound tests Xen showed 5 to 10 times worse performance.