Dependability in aggregation by averaging

Aggregation is an important building block of modern distributed applications, allowing the determination of meaningful properties (e.g. network size, total storage capacity, average load, majorities, etc.) that are used to direct the execution of the system. In the recent years, several approaches have been proposed to compute aggregation functions on distributed settings, exhibiting different characteristics, in terms of accuracy, time and communication complexity. However, the majority of the existing aggregation algorithms exhibit relevant dependability issues, when prospecting their use in real application environments. In this paper, we reveal some dependability issues of aggregation algorithms based on iterative averaging techniques, giving some directions to solve them. This class of algorithms is considered robust (when compared to common tree-based approaches), being independent from the used routing topology and providing an aggregation result at all nodes. However, their robustness is strongly challenged and their correctness often compromised, when changing the assumptions of their working environment to more realistic ones. The correctness of this class of algorithms relies on the maintenance of a fundamental invariant, commonly designated as mass conservation. We will argue that this main invariant is often broken in practical settings, and that additional mechanisms and modifications are required to maintain it, incurring in some degradation of the algorithms performance. In particular, we discuss the behavior of three representative algorithms (Push-Sum Protocol [1], Push- Pull Gossip protocol [2] and Distributed Random Grouping [3]) under asynchronous and faulty (with message loss and node crashes) environments. More specifically, we propose and evaluate two new versions of the Push-Pull Gossip protocol, which solve its message interleaving problem (evidenced even in a synchronous operation mode)