Early measurements of a cluster-based architecture for P2P systems

Krishnamurthy, Balachander; Wang, Jia; Xie, Yinglian

doi:10.1145/505202.505216

Cited by 79 publications

(29 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Proximity clustering develops further this closeness idea, mainly for improving the routing latency [19]. A node associates with a cluster based on a proximity metric τ and selects most neighbors from the cluster.…”

Section: Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

Survey on hierarchical routing schemes in “flat” distributed hash tables

Korzun

Gurtov

2010

Peer-to-Peer Netw. Appl.

View full text Add to dashboard Cite

The first generation of DHT designs offered a completely flat structure of the key space that is randomly partitioned among participating DHT nodes. That has certain advantages, for example, even distribution of workload among nodes. On the other hand, grouping keys under a single authority or achieving latency guarantees for queries is difficult. To address these shortcomings, various kinds of hierarchy have been proposed over recent years. The last generation is hierarchical DHTs (HDHTs) where nodes are organized onto layers; each next layer consists of supernodes for the previous layer. In this survey paper, we thoroughly go over the evolution of DHTs from pure flat to pre-hierarchical. Our focus is on hierarchical schemes in DHT routing. We argue that their application is not restricted within HDHT designs. We sequentially built a set of design principles; each pro-

show abstract

Section: Clusteringmentioning

confidence: 99%

“…Initially, this hierarchy appeared in unstructured P2P systems to deal with node heterogeneity in capacity, bandwidth, CPU power, and lifetime [19,20]. Popular hierarchy-based implementations include Gnutella, 2 KaZaA, 3 EMule, 4 and BitTorrent.…”

Section: Introductionmentioning

confidence: 99%

Survey on hierarchical routing schemes in “flat” distributed hash tables

Korzun

Gurtov

2010

Peer-to-Peer Netw. Appl.

View full text Add to dashboard Cite

show abstract

“…However, their work does not take into account the query load on individual nodes. Krishmanurthy et al [12] propose a cluster-based architecture for P2P systems, which uses a network-aware clustering technique based on a central clustering server to group hosts into clusters. Each cluster has one or more delegate nodes that act as directory servers for the objects stored at nodes within the same cluster.…”

Section: Related Workmentioning

confidence: 99%

Scalable ultrapeer-based DHT protocol for file sharing

Kim

Ahn

2009

2009 International Symposium on Collaborative Technologies and Systems

View full text Add to dashboard Cite

In this paper, we present a novel file searching protocol to structure a DHT ring consisting of only ultrapeers, not all the nodes. The DHT ring in this protocol is much less sensitive to the churn rate because ultrapeers have much longer uptime compared with leaf nodes. Thus, this feature makes the protocol more scalable and efficient than the previous DHT ones in terms of costs of file search, node join and leave operations and the number of routing table entries each node should maintain. Moreover, it is more effective for locating rare files than Gnutella-like searching protocols.

show abstract

“…Early P2P identification methods utilized a P2P crawler to gather P2P signal information [27], but was quite expensive and less expandable. Subhabrata Sen [28] analyzed P2P traffic by measuring flow-level information collected at multiple border routers across a large ISP network.…”

Section: Application Identificationmentioning

confidence: 99%

P2P worm detection based on application identification

YunPing

Xia

et al. 2007

Front. Comput. Sc. China

View full text Add to dashboard Cite

P2P worm exploits common vulnerabilities and spreads through peer-to-peer networks. Despite being recognized as a potential and deadly threat to the Internet recently, few relevant countermeasures are found in extant literature. Once it breaks out, a P2P worm could result in unpredictable losses. Based on propagation characteristics of the worm, this paper presents a detection method called PWD (P2P Worm Detection), which is designed based on application identification and unknown worm detection. Simulation result and LAN-environment experiment result both indicate that PWD is an effective method to detect and block P2P worms.

show abstract

Early measurements of a cluster-based architecture for P2P systems

Cited by 79 publications

References 5 publications

Survey on hierarchical routing schemes in “flat” distributed hash tables

Survey on hierarchical routing schemes in “flat” distributed hash tables

Scalable ultrapeer-based DHT protocol for file sharing

P2P worm detection based on application identification

Contact Info

Product

Resources

About