P2P and Cloud: A Marriage of Convenience for Replica Management

Abstract

Abstract. P2P and cloud computing are two of the latest trend in the Internet arena. They could both be labeled as "large-scale distributed systems", yet their approach is completely different: based on completely decentralized protocols exploiting edge resources the former, focusing on huge data centers the latter. Several Internet startups have quickly reached stardom by exploiting cloud resources, unlike P2P applications which often lack a business model. Recently, companies like Spotify and Wuala have started to explore how the two worlds could be merged, exploiting (free) user resources whenever possible, aiming at reducing the bill to be payed to cloud providers. This mixed model could be applied to several different applications, including backup, storage, streaming, content distribution, online gaming, etc. A generic problem in all these areas is how to guarantee the autonomic regulation of the usage of P2P vs. cloud resources: how to guarantee a minimum level of service when peer resources are not sufficient, and how to exploit as much P2P resources as possible when they are abundant.

Symbiotic coupling of P2P and cloud systems: The Wikipedia case

“…In [19] the use case of Dilbert's comic strips and the hourly News Update podcast from CNN is used for a combined p2p-supported cloud solution. In [20] the authors build an unstructured overlay with a focus on replica minimization with the help of a cloud. Another hybrid approach is the online data backup architecture proposed in [21].…”

QoS - Liquidstream : Scalable Monitoring and Bandwidth Control in Peer to Peer (P2P) Live Streaming

“…Referring to system's implementation, there are effective P2P overlay algorithms [8], [21], [22], [26] that lead to upload bandwidth utilization more than 90%, while setup time in a live streaming system has been brought down to 5-10 sec or even less [11]. Another issue in P2P live streaming is to create architectures that are able to adapt the block transmissions dynamically, according to the set of the blocks that peers miss in each time instant.…”

AVOCLOUDY: a simulator of volunteer clouds

“…Opportunities for volunteer cloud computing. The benefits of combining the cloud and volunteer paradigms are the reduction of economic costs and consumed power at data centers . The reduction of economic costs comes from better exploitation of available and unused computational resources, for the use of those made available free of charge from the volunteer community.…”

“…Instead, service-oriented applications (such as multi-tier Web applications) are not suitable for being executed in a volunteer cloud environment, because of the volatile presence of the nodes participating in the network.Opportunities for volunteer cloud computing. The benefits of combining the cloud and volunteer paradigms are the reduction of economic costs and consumed power at data centers [3][4][5][6]. The reduction of economic costs comes from better exploitation of available and unused computational resources, for the use of those made available free of charge from the volunteer community.…”