Network as an On-Demand Service for Multi-Cloud Workloads

Pagliari, Alessio (2017) Network as an On-Demand Service for Multi-Cloud Workloads. [Laurea magistrale], Università di Bologna, Corso di Studio in Informatica [LM-DM270], Documento full-text non disponibile
Il full-text non è disponibile per scelta dell'autore. (Contatta l'autore)


The PrEstoCloud project aims to enable on-demand resource scaling of Big Data applications to the cloud. In this context, we have to deal with the huge amount of data processed and more, in particular, its transportation between one cloud and another. The scope of this thesis is to develop a network-level architecture that could easily deal with Big Data application challenges and could be integrated into the PrEstoCloud consortium staying transparent to the application level. However, the connection between multiple cloud providers in this context presents a series of challenges: the architecture should adapt to the variable number of clouds to connect, it have to bypass the limitations of the cloud infrastructure and most importantly, it must have a general design able to work in every cloud provider. In this report, we present a general VPN-based Inter-Cloud architecture able to work in every kind of environment. We implemented a prototype with IPSec and OpenVPN, connecting the i3s laboratory with Amazon AWS and Azure, we evaluate our architecture and the used tools in two ways: (i) we test the stability over time of the architecture via latency tests; (ii) we perform non-intrusive Pathload tests in the Amazon, showing the usability of the available bandwidth estimator in the cloud, the AWS network characteristics discovered through the tests and a final comparison of the VPN tools overhead.

Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Pagliari, Alessio
Relatore della tesi
Corso di studio
Curriculum C: Sistemi e reti
Ordinamento Cds
Parole chiave
inter-cloud,vpn,architecture,datacenter,big data,multi-cloud
Data di discussione della Tesi
20 Dicembre 2017

Altri metadati

Gestione del documento: Visualizza il documento