Miscellaneous

[Anonymous].  2015.  Editorship of Proceedings of the First Workshop on Principles and Practice of Consistency for Distributed Data. Editorship of Proceedings of the First Workshop on Principles and Practice of Consistency for Distributed Data. Abstract

Consistency is one of the fundamental issues of distributed computing. There are many competing consistency models, with subtly different power in principle. In practice, the well-known Consistency-Availability-Partition Tolerance trade-off translates to difficult choices between fault tolerance, performance, and programmability. The issues and trade-offs are particularly vexing at scale, with a large number of processes or a large shared database, and in the presence of high latency and failure-prone networks. It is clear that there is no one universally best solution. Possible approaches cover the whole spectrum between strong and eventual consistency. Strong consistency (total ordering via, for example, linearizability or serializability) provides familiar and intuitive semantics but requires slower and, in some contexts, fragile coordination. The unlimited parallelism allowed by weaker models such as eventual consistency promises high performance, but divergence and conflicts make it difficult to ensure useful application invariants, and meta-data is hard to keep in check. The research and development communities are actively exploring intermediate models (replicated data types, monotonic programming, CRDTs, LVars, causal consistency, red-blue consistency, invariant- and proof-based systems, etc.), designed to improve efficiency, programmability, and overall operation without negatively impacting scalability.

This workshop aims to investigate the principles and practice of weak consistency models for large-scale, distributed shared data systems. It brings together theoreticians and practitioners from different horizons: system development, distributed algorithms, concurrency, fault tolerance, databases, language and verification, including both academia and industry.

Gonçalves R, Almeida PS, Moreno CB, Fonte V, Preguiça N.  2012.  Dotted Version Vectors: Efficient Causality Tracking for Distributed Key-Value Stores. DAIS - IFIP International Conference on Distributed Applications and Interoperable Systems.. poster_dais.pdf
Jesus P, Moreno CB, Almeida PS.  2007.  A Study on Aggregation by Averaging Algorithms. Abstractjesus-eurosys2007b.pdf

With the advent of multihop ad-hoc networks, sensor networks and large scale overlay networks, there is a demand for tools that can abstract meaningful system properties from given assemblies of nodes. Distributed aggregation algorithms allow the evaluation of properties such as: network size; total storage capacity; average load; and majorities. A useful class of aggregation algorithms is based on averaging techniques. Such algorithms start from a set of input values spread across the nodes, and iteratively average the values in neighbour nodes that are able to communicate. Eventually all nodes will converge to the same value and can estimate some useful metric. For instance, if one node starts with input 1 and all other nodes with input 0, eventually all nodes will end up with the same value and the aggregate property network size can be estimated by the fraction 1.

Moreno CB.  1996.  Indirect Calls: Remote invocations on loosely coupled systems. Abstract10.1.1.40.9706.pdf

Integration of Mobile computers into Worldwide networks is traditionally managed by hosting them into the fixed network. We argue that this approach excludes some important forms of interaction. We present a communication mechanism, suitable for developing applications that take advantage of transient connections. These communications can be supported by several transport mechanisms, including Email and plain file copying between non networked computers. 1 Introduction Future applications can be expected to follow two major trends, Mobility and Worldwideness. These two issues are strongly interrelated as Worldwide systems often experience disconnected operation under network partitions and Mobile computers are partially integrated (possibly hosted) into worldwide networks. A common scenario for the integration of mobile hosts (MHs) is based on a fixed worldwide network to which MHs connect from time to time, either by fixed or wireless links.

Moreno CB.  1995.  Synergetic state evolution under mobile computing. Abstract10.1.1.40.6574.pdf

The recent trend towards mobility and ubiquitous computing issued a new perspective over the traditional models of distributed computation. Observation of Human behavior, in particular the study of Human information interchange techniques and protocols presents a simple, yet fruitful, mean of gathering insight on the possible protocols for interaction among mobile hosts.This work will try to go one step further on the study of mobile interactions by leaving the usual semi-centralized approach to mobile computing. Instead of focusing on the reconciliation of mobile hosts with the networked support stations, we will study the possibility of progressive adjustments, both by a mobile host and a support station and between mobile hosts. 1 Introduction The recent trend towards mobility and ubiquitous computing issued a new perspective over the traditional models of distributed computation.