This paper analyzes the adoption of unstructured P2P overlay networks to build publish-subscribe systems. We consider a very simple distributed communication protocol, based on gossip and on the local knowledge each node has about subscriptions made by its neighbours. A mathematical analysis is provided to estimate the number of nodes receiving the event. These outcomes are compared to those obtained via simulation. Results show even when the amount of subscribers represents a very small (yet non-negligible) portion of network nodes, by tuning the gossip probability the event can percolate through the overlay.
Publish-subscribe systems via gossip: a study based on complex networks
S. Ferretti
2012
Abstract
This paper analyzes the adoption of unstructured P2P overlay networks to build publish-subscribe systems. We consider a very simple distributed communication protocol, based on gossip and on the local knowledge each node has about subscriptions made by its neighbours. A mathematical analysis is provided to estimate the number of nodes receiving the event. These outcomes are compared to those obtained via simulation. Results show even when the amount of subscribers represents a very small (yet non-negligible) portion of network nodes, by tuning the gossip probability the event can percolate through the overlay.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
