In-depth analysis of the IDA-Gossip protocol - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

In-depth analysis of the IDA-Gossip protocol

Résumé

Gossip-based dissemination protocols are important building blocks of large-scale distributed systems as they may impact both the systems' efficiency and fault tolerance. There exist many flavors of gossip dissemination protocols. IDA-Gossip is one of the gossip dissemination protocols proposed in the context of blockchains to efficiently disseminate large messages. It relies on multi-chunk gossip dissemination, erasure coding, and Merkle hash trees. However, despite its claimed efficiency, there is no in-depth analysis of this protocol to understand its behavior under different conditions (e.g., with injected faults). In this work, we evaluate the behavior of IDA-Gossip by relying on extensive experiments and simulations. Specifically, we evaluate IDA-Gossip both in terms of performance and resilience to faults by varying its configuration parameters and the number of faulty nodes, respectively. This study results in several takeaways. First, IDA-Gossip provides excellent dissemination latency compared to classic gossip. Second, it provides excellent coverage even with 40 percent of faulty nodes in the system. Finally, the use of erasure coding provides an important advantage to IDA-Gossip compared to classic multi-chunk gossip dissemination protocols.
Fichier principal
Vignette du fichier
ida_gossip_nca.pdf (317.33 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03966190 , version 1 (01-02-2023)

Identifiants

Citer

Kadir Korkmaz, Joachim Bruneau-Queyreix, Stéphane Delbruel, Sonia Ben Mokhtar, Laurent Réveillère. In-depth analysis of the IDA-Gossip protocol. 21st IEEE International Symposium on Network Computing and Applications (NCA 2022), IEEE, Dec 2022, Boston, MA, United States. pp.139-147, ⟨10.1109/NCA57778.2022.10013564⟩. ⟨hal-03966190⟩
25 Consultations
124 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More