BRISA: Combining Efficiency and Reliability in Epidemic Data Dissemination

Abstract

Abstract-There is an increasing demand for efficient and robust systems able to cope with today's global needs for intensive data dissemination, e.g., media content or news feeds. Unfortunately, traditional approaches tend to focus on one end of the efficiency/robustness design spectrum, by either leveraging rigid structures such as trees to achieve efficient distribution, or using loosely-coupled epidemic protocols to obtain robustness.In this paper we present BRISA, a hybrid approach combining the robustness of epidemic-based dissemination with the efficiency of tree-based structured approaches. This is achieved by having dissemination structures such as trees implicitly emerge from an underlying epidemic substrate by a judicious selection of links. These links are chosen with local knowledge only and in such a way that the completeness of data dissemination is not compromised, i.e., the resulting structure covers all nodes. Failures are treated as an integral part of the system as the dissemination structures can be promptly compensated and repaired thanks to the underlying epidemic substrate.Besides presenting the protocol design, we conduct an extensive evaluation in a real environment, analyzing the effectiveness of the structure creation mechanism and its robustness under faults and churn. Results confirm BRISA as an efficient and robust approach to data dissemination in the large scale.

Tight Analysis of Randomized Rumor Spreading in Complete Graphs

“…This scalability today is mostly exploited in data-intensive applications, e.g., for media content or news feeds [11]. The second main application area of rumor spreading (here often called gossip-based algorithms) are wireless sensor networks and mobile ad-hoc networks.…”

Randomized Rumor Spreading Revisited (Long Version)

“…This gives highly robust dissemination algorithms belonging to the broader class of gossip-based algorithms that, due to their epidemic nature, are surprisingly efficient and scalable. Randomized rumor spreading has found numerous applications, among others, maintaining the consistency of replicated databases [11], disseminating large amounts of data in a scalable manner [32], and organizing any kind of communication in highly dynamic and unreliable networks like wireless sensor networks and mobile ad-hoc networks [28]. Randomized rumor spreading processes are also used to model epidemic processes like viruses spreading over the internet [2], news spreading in social networks [12], or opinions forming in social networks [31].…”

Προσαρμοστική Επιδημική Διάδοση Σε Ασύρματα Αδόμητα Δίκτυα

“…Αυτές είναι και οι πιο ενεργοβόρες [59]- [64]. Μπορούν να απαιτούν μηχανισμούς ερωταποκρίσεων (polling) [61], [63] ή μηνύματα χαιρετισμού (hello messages) [60], [62].…”