LHView: Location Aware Hybrid Partial View

• Main Author: Fernandes, Flávio Duarte Pacheco
• Publication Date: 2017
• Format: Master thesis
• Language: eng
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/10362/66268
• topic: Geo-Distributed Systems; Gossip Protocol; Membership Protocol; Network Partitions; Location Inference; Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática

The rise of the Cloud creates enormous business opportunities for companies to provide global services, which requires applications supporting the operation of those services to scale while minimizing maintenance costs, either due to unnecessary allocation of resources or due to excessive human supervision and administration. Solutions designed to support such systems have tackled fundamental challenges from individual component failure to transient network partitions. A fundamental aspect that all scalable large systems have to deal with is the membership of the system, i.e, tracking the active components that compose the system. Most systems rely on membership management protocols that operate at the application level, many times exposing the interface of a logical overlay network, that should guarantee high scalability, efficiency, and robustness. Although these protocols are capable of repairing the overlay in face of large numbers of individual components faults, when scaling to global settings (i.e, geo-distributed scenarios), this robustness is a double edged-sword because it is extremely complex for a node in a system to distinguish between a set of simultaneously node failures and a (transient) network partition. Thus the occurrence of a network partition creates isolated sub-sets of nodes incapable of reconnecting even after the recovery from the partition. This work address this challenges by proposing a novel datacenter-aware membership protocol to tolerate network partitions by applying existing overlay management techniques and classification techniques that may allow the system to efficiently cope with such events without compromising the remaining properties of the overlay network. Furthermore, we strive to achieve these goals with a solution that requires minimal human intervention.