CoralCDN is a peer-to-peer content distribution network that allows a user to run a web site that offers high performance and meets huge demand, all for the price of a cheap broadband Internet connection. Volunteer sites that run CoralCDN automatically replicate content as a side effect of users accessing it. Publishing through CoralCDN is as simple as making a small change to the hostname in an object's URL; a peer-to-peer DNS layer transparently redirects browsers to nearby participating cache nodes, which in turn cooperate to minimize load on the origin web server. One of the system's key goals is to avoid creating hot spots that might dissuade volunteers and hurt performance. It achieves this through Coral, a latency-optimized hierarchical indexing infrastructure based on a novel abstraction called a distributed sloppy hash table, or DSHT.

Unstructured overlays form an important class of peer-to-peer networks, notably when content-based searching is at stake. The construction of these overlays, which is essentially a membership management issue, is crucial. Ideally, the resulting overlays should have low diameter and be resilient to massive node failures, which are both characteristic properties of random graphs. In addition, they should be able to deal with a high node churn (i.e., expect high-frequency membership changes). Inexpensive membership management while retaining random-graph properties is therefore important. In this paper, we describe a novel gossip-based membership management protocol that meets these requirements. Our protocol is shown to construct graphs that have low diameter, low clustering, highly symmetric node degrees, and that are highly resilient to massive node failures. Moreover, we show that the protocol is highly reactive to restoring randomness when a large number of nodes fail. KEY WORDS: Membership management; peer-to-peer; epidemic/gossiping protocols; unstructured overlays; random graphs.

We are building Coral, a peer-to-peer content distribution system. Coral creates self-organizing clusters of nodes that fetch information from each other to avoid communicating with more distant or heavily-loaded servers. Coral indexes data, but does not store it. The actual content resides where it is used, such as in nodes' local web caches. Thus, replication happens exactly in proportion to demand.

Online content distribution has increasingly gained popularity among the entertainment industry and the consumers alike. A key challenge in online content distribution is a cost-efficient solution to handle demand peaks. To address this challenge, we propose Dandelion, a system for robust cooperative (peer-to-peer) content distribution. Dandelion explicitly addresses two crucial issues in cooperative content distribution. First, it provides robust incentives for clients who possess content to serve others. A client that honestly serves other clients is rewarded with credit that can be redeemed for future downloads at the content server. Second, Dandelion discourages unauthorized content distribution. A client that uploads to another client is rewarded for its service only after the server has verified the other client’s legitimacy. Our preliminary evaluation of a prototype system running on commodity hardware with 1 Mbps uplink and 1 Mbps downlink indicates that Dandelion can achieve aggregate client download throughput three orders of magnitude higher than the one achieved by an HTTP/FTP-like server. 1

Personal webservers have proven to be a popular means of sharing files and peer collaboration. Unfortunately, the transient availability and rapidly evolving content on such hosts render centralized, crawl-based search indices stale and incomplete. To address this problem, we propose YouSearch, a distributed search application for personal webservers operating within a shared context (e.g., a corporate intranet). With YouSearch, search results are always fast, fresh and complete --- properties we show arise from an architecture that exploits both the extensive distributed resources available at the peer webservers in addition to a centralized repository of summarized network state. YouSearch extends the concept of a shared context within web communities by enabling peers to aggregate into groups and users to search over specific groups. In this paper, we describe the challenges, design, implementation and experiences with a successful intranet deployment of YouSearch.

Peer-to-peer systems can be used to form a low-latency decentralized data delivery system. Structured peer-to-peer systems provide both low latency and excellent load balance with uniform query and data distributions. Under the more common skewed access distributions, however, individual nodes are easily overloaded, resulting in poor global performance and lost messages. This paper describes a lightweight, adaptive, and system-neutral replication protocol, calledLAR, that maintains low access latencies and good load balance even under highly skewed demand. We apply LAR to Chord and show that it has lower overhead and better performance than existing replication strategies. 1.

Even with reasonable overprovisioning, today’s Internet application clusters are unable to handle major traffic spikes and flash crowds. As an alternative to fixed-size, dedicated clusters, we propose a dynamically-shared application cluster model based on virtual machines. The system is dubbed “OnCall” for the extra computing capacity that is always on call in case of traffic spikes. OnCall’s approach to spike management relies on the use of an economicallyefficient marketplace of cluster resources. OnCall works autonomically by allowing applications to trade computing capacity on a free market through the use of automated market policies; the appropriate applications are then automatically activated on the traded nodes. As demonstrated in our prototype implementation, OnCall allows applications to handle spikes while still maintaining inter-application performance isolation and providing useful resource guarantees to all applications on the cluster. 1.

Despite the increasing degree of multi-homing, path and data redundancy, and capacity available in the Internet, today’s clients experience outage rates of a few percent when accessing Web sites. MONET (“Multi-homed Overlay NETwork), is a new system that improves client availability to Web sites using a combination of link multi-homing and a cooperative overlay network of peer proxies to obtain a diverse collection of paths between clients and Web sites. This approach creates many potential paths between clients and Web sites, requiring a scalable way to selecting a good path. MONET solves this problem using a waypoint selection algorithm, which picks a good small subset of all available paths to actively probe. MONET runs on FreeBSD, Linux, and Mac OS X, and is deployed at six different sites. These installations have been running MONET for over one year, serving about fifty users on a daily basis. Our analysis of proxy traces shows that the proxy network avoids between 60 % and 94 % of observed failures, including access link failures, Internet routing problems, persistent path congestion, and DNS failures. The proxy avoids nearly 100 % of failures due to client and wide-area network failures, with negligible overhead. 1

To distribute video and audio data in real-time streaming mode, both CDN (Content Distributed Network) based and peer-to-peer based architectures have been proposed. However, each architecture has its limitations. CDN servers are expensive to deploy and maintain. The storage space and out-bound bandwidth allocated to each media file are limited and incur a cost. Current solutions to lowering such cost usually compromise the media quality delivered. On the other hand, a peer-to-peer architecture needs a sufficient number of `seed' supplying peers to `jumpstart' the system. Compared with a CDN server, a peer offers very low out-bound bandwidth. Furthermore, it is not clear how to fairly determine the contribution of each supplying peer.

Gossip, or epidemic, protocols have emerged as a powerful strategy to implement highly scalable and resilient reliable broadcast primitives. Due to scalability reasons, each participant in a gossip protocol maintains a partial view of the system. The reliability of the gossip protocol depends upon some critical properties of these views, such as degree distribution and clustering coefficient. Several algorithms have been proposed to maintain partial views for gossip protocols. In this paper, we show that under a high number of faults, these algorithms take a long time to restore the desirable view properties. To address this problem, we present HyParView, a new membership protocol to support gossip-based broadcast that ensures high levels of reliability even in the presence of high rates of node failure. The HyParView protocol is based on a novel approach that relies in the use of two distinct partial views, which are maintained with different goals by different strategies. 1