Università della Svizzera italiana

On the many faces of atomic multicast

Coelho, Paulo ; Pedone, Fernando (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2019 ; 2019INFO004.

Many current online services need to serve clients distributed across geographic areas. Coordinating highly available and scalable geographically distributed replicas, however, is challenging. While State Machine Replication is the most direct way of achieving availability, no scalability comes from the traditional approach. Typically, scalability is obtained by partitioning the original...

Università della Svizzera italiana

Building global and scalable systems with atomic multicast

Benz, Samuel ; Pedone, Fernando (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2018 ; 2018INFO003.

The rise of worldwide Internet-scale services demands large distributed systems. Indeed, when handling several millions of users, it is common to operate thousands of servers spread across the globe. Here, replication plays a central role, as it contributes to improve the user experience by hiding failures and by providing acceptable latency. In this thesis, we claim that atomic multicast,...

Università della Svizzera italiana

High performance deferred update replication

Sciascia, Daniele ; Pedone, Fernando (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2015 ; 2015INFO004.

Replication is a well-known approach to implementing storage systems that can tolerate failures. Replicated storage systems are designed such that the state of the system is kept at several replicas. A replication protocol ensures that the failure of a replica is masked by the rest of the system, in a way that is transparent to its users. Replicated storage systems are among the most...

Università della Svizzera italiana

High-performance state-machine replication

Jalili Marandi, Parisa ; Pedone, Fernando (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2014 ; 2014INFO006.

Replication, a common approach to protecting applications against failures, refers to maintaining several copies of a service on independent machines (replicas). Unlike a stand-alone service, a replicated service remains available to its clients despite the failure of some of its copies. Consistency among replicas is an immediate concern raised by replication. In effect, an important factor...

Università della Svizzera italiana

On multicast primitives in large networks and partial replication protocols

Schiper, Nicolas ; Pedone, Fernando (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2009 ; 2009INFO005.

Recent years have seen the rapid growth of web-based applications such as search engines, social networks, and e-commerce platforms. As a consequence, our daily life activities rely on computers more and more each day. Designing reliable computer systems has thus become of a prime importance. Reliability alone is not sufficient however. These systems must support high loads of client...

Università della Svizzera italiana

On non-intrusive workload-aware database replication

Narváez, Vaide ; Pedone, Fernando (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2009 ; 2009INFO002.

Performance and high-availability are the crucial factors in the development of nowadays distributed database systems. Both of these challenges are commonly addressed by means of the same technique, database replication. The overall throughput of the system is increased by leveraging parallel computation on different sites, and in case of replica failures, availability is improved by...


Deferred-update database replication : theory and algorithms

Malta Schmidt, Rodrigo ; Zwaenepoel, Willy (Dir.) ; Pedone, Fernando (Dir.)

Thèse sciences Ecole polytechnique fédérale de Lausanne EPFL : 2008 ; no 4022.

Università della Svizzera italiana

Multicoordinated agreement protocols and the log service

Camargos, Lasaro Jonas ; Pedone, Fernando (Dir.) ; Madeira, Edmundo R.M. (Codir.)

Thèse de doctorat : Università della Svizzera italiana, 2008 ; 2008INFO001.

Agreement problems are a common abstraction in distributed systems. They appear when the components of the system must concur on reconfigurations, changes of state, or in lines of action in general. Examples of agreement problems are Consensus, Atomic Commitment, and Atomic Broadcast. In this thesis we investigate these abstractions in the context of the environment in which they will run and the...