Availability and Locality Measurements of Peer-To-Peer File Systems

Availability and Locality Measurements of Peer-To-Peer File Systems (2002)

Cached

Download Links

[signl.cs.umass.edu]

by Jacky Chu , Kevin Labonte , Brian Neil Levine

Venue:	In Proceedings of ITCom: Scalability and Traffic Control in IP Networks
Citations:	121 - 2 self

Versions

Version History

Metadata Version 2

Datum	Value	Source
TITLE	Availability and locality measurements of peer-to-peer file systems	INFERENCE
AUTHOR NAME	Jacky Chu	SVM HeaderParse 0.1
AUTHOR AFFIL	Department of Computer Science; University of Massachusetts, Amherst	SVM HeaderParse 0.2
AUTHOR ADDR	MA 01003	SVM HeaderParse 0.1
AUTHOR NAME	Kevin Labonte	SVM HeaderParse 0.1
AUTHOR AFFIL	Department of Computer Science; University of Massachusetts, Amherst	SVM HeaderParse 0.2
AUTHOR ADDR	MA 01003	SVM HeaderParse 0.1
AUTHOR NAME	Brian Neil Levine	SVM HeaderParse 0.1
AUTHOR AFFIL	Department of Computer Science; University of Massachusetts, Amherst	SVM HeaderParse 0.2
AUTHOR ADDR	MA 01003	SVM HeaderParse 0.1
ABSTRACT	Although peer-to-peer networking applications continue to increase in popularity, there have been few measurement studies of their performance. We present the rst study of the locality of les stored and transferred among peers in Napster and Gnutella over month-long periods. Our analysis indicates that the locality of les is skewed in all four cases and ts well to a logquadratic distribution. This predicts that caches of the most popular songs would increase performance of the system. We also took baseline measurements of le types and sizes for comparison over time with future studies. Not surprisingly, audio les are most popular, however a signicant fraction of stored data is occupied by videos. Finally, we measured the distribution of time peers in Gnutella were available for downloading. We found that node availability is strongly in uenced by time-of-day eects, and that most user's tend to be available for only very short contiguous lengths of time.	SVM HeaderParse 0.1
YEAR	2002	INFERENCE
VENUE	In Proc. of ITCom: Scalability and Traffic Control in IP Networks	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
VOLUME	4868	INFERENCE
CITATIONS	6 found	ParsCit 1.0