Modeling Priority-Based Incentive Policies for Peer-Assisted Content Delivery Systems
Content delivery providers can improve their service scalability and offload their servers by making use of content transfers among their clients. To provide peers with incentive to transfer data to other peers, protocols such as BitTorrent typically empl
- PDF / 383,014 Bytes
- 12 Pages / 430 x 660 pts Page_size
- 64 Downloads / 173 Views
Abstract. Content delivery providers can improve their service scalability and offload their servers by making use of content transfers among their clients. To provide peers with incentive to transfer data to other peers, protocols such as BitTorrent typically employ a tit-for-tat policy in which peers give upload preference to peers that provide the highest upload rate to them. However, the tit-for-tat policy does not provide any incentive for a peer to stay in the system beyond completion of its download. This paper presents a simple fixed-point analytic model of a priority-based incentive mechanism which provides peers with strong incentive to contribute upload bandwidth beyond their own download completion. Priority is obtained based on a peer’s prior contribution to the system. Using a two-class model, we show that priority-based policies can significantly improve average download times, and that there exists a significant region of the parameter space in which both high-priority and low-priority peers experience improved performance compared to with the pure tit-for-tat approach. Our results are supported using event-based simulations. Keywords: Modeling, peer-assisted content delivery, priority-based incentive.
1 Introduction A highly scalable approach to content delivery is to utilize the upload bandwidth of the clients to offload the original content source [1, 2, 3, 4, 5, 6]. Existing peer-topeer download protocols, such as BitTorrent [1], allow each peer to download content from any peer that has content that it does not have, and do not require any organized delivery structure. With these protocols each file is split into many small pieces, each of which may be downloaded from different peers. To provide peers with an incentive to upload pieces to other peers, these protocols typically employ a tit-for-tat policy in which peers give upload preference to peers that provide the highest upload rate to them. Whereas such policies provide peers with strong incentives to upload at their full upload capacity while downloading a file, ∗
This work was supported by the Natural Sciences and Engineering Research Council of Canada.
A. Das et al. (Eds.): NETWORKING 2008, LNCS 4982, pp. 421–432, 2008. © IFIP International Federation for Information Processing 2008
422
N. Carlsson and D.L. Eager
they do not provide peers with any incentive to serve additional data after having completed their download. Therefore, unless altruistic peers graciously continue to serve data beyond their download completion, peer-assisted systems with limited server resources are not able to provide download rates much higher than the peer upload rate. When the peer download capacity significantly exceeds the upload capacity, as is commonly the case with home Internet connections (e.g., [7]), much of the download capacity in such systems is therefore underutilized. To increase the available upload resources some BitTorrent sharing communities enforce a minimum required sharing ratio (defined as the ratio between the total amount of dat
Data Loading...
