A comparative study of spanning tree and gossip protocols for aggregation

Abstract

Distributed aggregation queries like average and sum can be implemented in different paradigms like gossip and hierarchical approaches. In the literature, these two paradigms are routinely associated with stereotypes such as "trees are fragile and complicated" and "gossip is slow and expensive". However, a closer look reveals that these statements are not backed up by systematic studies. A fair and informative comparison is clearly needed. However, this is a hard task because the performance of protocols from the two paradigms depends on different subtleties of the environment and the implementation of the protocols. We tackle this problem by carefully designing the comparison study. We use state-of-the-art algorithms and propose the problem of monitoring the network size in the presence of churn as the ideal problem for comparing very different paradigms for global aggregation. Our simulation study helps us identify the most important factors that differentiate between gossip and spanning tree aggregation: the time needed to compute a truly global output, the properties of the underlying topology, and sensitivity to dynamism. We demonstrate the effect of these factors in different practical topologies and scenarios. Our results help us to choose the right protocol in the light of the topology and dynamism patterns. IntroductionFully distributed aggregation is an important problem where we wish to execute queries such as sum, average, minimum, or maximum over unreliable networks (sensor networks, physical networks of routers, overlay networks, etc.), in which no central servers are directly accessible.At least two paradigms are known that solve this problem. The first one is the gossip approach where algorithms were proposed to achieve large degrees of robustness. Gossip protocols do not rely on fixed topologies: nodes exchange information with random neighbors to implement a diffusion-like computation pattern, and as a result the system converges to a state where all the nodes know the query result. From the literature, here we just focus on the adaptive approaches. In [1], the authors propose the restarting technique to convert any one-shot algorithm into an adaptive one. Apart from restarting, other approaches have been proposed that focus on error correction through some form of bookkeeping at the nodes [2][3][4][5].The second paradigm is hierarchical aggregation, which is a popular method in sensor networks [6]. It was also proposed for general process groups [7]. Tree-based aggregation remained unpopular in some areas like peer-to-peer networks due to the widely held assumptions about its lack of robustness. There are a few notable exceptions however: the Astrolabe framework [8], which is in fact only a virtual tree with completely unstructured gossip communication patterns behind it; the GAP protocol and its variants [5, 9-11] that actually build a spanning tree over a distributed network; and PRISM [12], a hierarchical approach that is built on top of a distributed hashtable, with a focus on dete...

Self-Corrective Dynamic Networks via Decentralized Reverse Computations

“…The pervasiveness and increasing computational capacity of smart Internet of Things devices equipped with networking capabilities allow complex distributed computations to be performed over networks, for instance, sensor networks computing the spread of oil spills [1], smart grids measuring power peaks in energy demand [2] or monitoring of automotive traffic [3]. Decentralized computations over dynamic networks are highly challenging to perform accurately and fast under changing input data, nodes temporarily leaving, failing or rejoining the network [4], [5], [6], [7], [8]. However, algorithms for computations in decentralized networks are by design more privacy-preserving, scalable, respect users' autonomy and do not require significant investments in expensive big data computational resources [9], [10], [11], [12].…”

DiVote: A Distributed Voting Protocol for Mobile Device-to-Device Communication

“…There are two main paradigms to address this problem, namely gossip-based and tree-based aggregation. Tree-based aggregation protocols have been shown to perform poorly in dynamic environments with high levels of churn [4], therefore for the rest of this section we focus on discussing the applicability of state-of-the-art gossip-based protocols to our scenario.…”

“…Contrary, decentralized (or distributed) processing requires nodes to compute local estimates of the result based on partial system knowledge. As opposed to conventional distributed processing scenarios where nodes are considered to be static or semi-static [4], in this work we examine scenarios, in which nodes exhibit high mobility. We consider a node to be a pedestrian carrying some device equipped with a wireless communication interface such as a mobile phone.…”

Special Issue: Euro‐Par 2014

“…Their coarse-grain hybrid simulation/emulation of StarPU ‡ on SimGrid, a versatile simulator for distributed systems, yields performance predictions of dense linear algebra applications in a matter of seconds and with an accuracy of within a few percent. The reviewers appreciated particularly the volume of experimental results and analysis on a wide range of heterogeneous platforms.Topic 8 on Distributed Systems and Algorithms is represented by the paper A comparative study of spanning tree and gossip protocols for aggregation authored by Lehel Nyers and Márk Jelasity [2]. The authors provide a carefully designed comparative study of two paradigms for distributed aggregation queries, like average and sum: gossiping and tree algorithms.…”

“…Topic 8 on Distributed Systems and Algorithms is represented by the paper A comparative study of spanning tree and gossip protocols for aggregation authored by Lehel Nyers and Márk Jelasity [2]. The authors provide a carefully designed comparative study of two paradigms for distributed aggregation queries, like average and sum: gossiping and tree algorithms.…”