DiPIT: a Distributed Bloom-Filter based PIT Table for CCN Nodes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès ICCCN 2012: 21th International Conference on Computer Communication Networks Année : 2012

DiPIT: a Distributed Bloom-Filter based PIT Table for CCN Nodes

Wei You
  • Fonction : Auteur
  • PersonId : 936777
Gwendal Simon

Résumé

Content-Centric Network is a novel Internet design, which is motivated by the shifting of the Internet usage from browsing to content dissemination. This new Internet architecture proposal has attracted many research works, but one of the most critical components of a CCN node, the Pending Interest Table (PIT), did not get much attention. The PIT is involved in the forwarding processes in both upstream (reception of Interest messages) and downstream (reception of Data messages) ways. On the one hand, the PIT should be large enough to store a high volume of information. On the other hand, the PIT should be quick enough to not become a bottleneck in message processing. In this paper, we propose a novel implementation of PIT, named DiPIT. The idea is to deploy a small-size fast memory on every interface. Our approach relies on Bloom Filters in order to reduce the necessary memory space for implementing the PIT, completed with a central Bloom Filter for limiting the false positives generated by the individual Bloom Filters. Our evaluations highlight that our DiPIT approach can significantly reduce the memory space (up to 63%) in the CCN node and support a higher incoming packet throughput, than the hash table technology, which is largely implemented in current routers.
Fichier non déposé

Dates et versions

hal-00787048 , version 1 (11-02-2013)

Identifiants

Citer

Wei You, Bertrand Mathieu, Patrick Truong, Jean-François Peltier, Gwendal Simon. DiPIT: a Distributed Bloom-Filter based PIT Table for CCN Nodes. ICCCN 2012: 21th International Conference on Computer Communication Networks, Jul 2012, Munchen, Germany. pp.1-7, ⟨10.1109/ICCCN.2012.6289282⟩. ⟨hal-00787048⟩
60 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More