Diffusion épidémique de chunks en quasi-direct : la taille compte

Nidhi Hegde 1 Fabien Mathieu 1 Diego Perino 1, 2
2 GANG - Networks, Graphs and Algorithms
LIAFA - Laboratoire d'informatique Algorithmique : Fondements et Applications, Inria Paris-Rocquencourt
Abstract : Peer-to-peer (P2P) applications, including P2P live streaming, have become very popular in the past few years. A key issue for live streaming concerns whether the delay and quality requirements can be met by a P2P protocol. In most cases, a live streaming algorithm splits the stream into atomic units of data called chunks. We investigate the impact of parameters like the chunk size, receiver buffer size, number of peers to probe, etc. We show that there exists a suitable range of chunk sizes, where the specific choice of the chunk size ultimately depends on the desired delay/loss trade-off. A fine tuning of the number of peers to probe and the number of simultaneous chunks can also increase the performance.
Document type :
Conference papers
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

Contributor : Fabien Mathieu <>
Submitted on : Friday, May 15, 2009 - 10:40:09 PM
Last modification on : Friday, January 4, 2019 - 5:33:21 PM
Long-term archiving on : Thursday, June 10, 2010 - 11:17:01 PM


Files produced by the author(s)


  • HAL Id : inria-00384842, version 1


Nidhi Hegde, Fabien Mathieu, Diego Perino. Diffusion épidémique de chunks en quasi-direct : la taille compte. Algotel, 2009, Carry-Le-Rouet, France. ⟨inria-00384842⟩



Record views


Files downloads