Tolerância a falha em um ambiente de computação em nuvem open source

• Autor(a) principal: Martins, Henrique Pachioni [UNESP]
• Data de Publicação: 2014
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://hdl.handle.net/11449/127619; http://www.athena.biblioteca.unesp.br/exlibris/bd/cathedra/31-08-2015/000843909.pdf
• topic: Computação; Computação em nuvem; Software gratuito; Tolerância a falha (Computação); Arquitetura de computador

Cloud computing is a set of features and services offered over the internet, delivered from data centers located around the world. With the rapid growth in cloud computing, increases the concern about the need for services offered and a major challenge is to implement a faulttolerant environment. The main issues of fault tolerance in cloud computing are the fault detection and recovery. To combat these problems, many fault tolerance techniques are designed to reduce them. Paid managers offer this kind of support, but the open source managers do not provide evidence to tolerate failures and leave users vulnerable failures of a technology environment. The aim of this work is to develop a tolerant mechanism to failures in OpenStack. It was created a redundancy mechanism in virtual machines instantiated in cloud nodes, if a node present a transient or intermittent failure, the virtual machine will be stored in a safe place, waiting for the return of a node failure. The mechanism developed is feasible and efficient because after a node to recover from a failure, the virtual machine is not lost, getting back to the active user