ACM Home Page
Please provide us with feedback. Feedback
Some findings on the network performance of broadband hosts
Full text PdfPdf (154 KB)
Source Internet Measurement Conference archive
Proceedings of the 3rd ACM SIGCOMM conference on Internet measurement table of contents
Miami Beach, FL, USA
SESSION: Bandwidth table of contents
Pages: 45 - 50  
Year of Publication: 2003
ISBN:1-58113-773-7
Authors
Karthik Lakshminarayanan  Microsoft Research
Venkata N. Padmanabhan  University of California at Berkeley & Microsoft Research
Sponsors
SIGCOMM: ACM Special Interest Group on Data Communication
ACM: Association for Computing Machinery
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 10,   Downloads (12 Months): 50,   Citation Count: 9
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues   peer to peer  

Tools and Actions: Review this Article  
Save this Article to a Binder    Display Formats: BibTex  EndNote ACM Ref   
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/948205.948212
What is a DOI?

ABSTRACT

With the rapid growth in the popularity of and the research interest in peer-to-peer (P2P) systems, an interesting question is what the quality of network connectivity between peers in the "real world" is and what implications this has for applications. In this paper, we describe an effort called PeerMetric to directly measure P2P network performance from the vantage point of broadband-connected residential hosts. Our measurements indicate significant asymmetry in bandwidth, with median downstream and upstream available bandwidths of 900 Kbps and 212 Kbps, respectively. We argue that the availability of last-hop bandwidth is more important than the traditional consideration of locality for overlay multicast over broadband hosts. We also consider the peer selection problem and find that a simple delay-vector based approach is effective for finding proximate peers in terms of latency. However, P2P latency turns out to be a poor predictor of P2P TCP throughput, which may be the metric of interest for applications such as file sharing.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

1
 
2
C. Dovrolis, P. Ramanathan, and D. Moore, "What do Packet Dispersion Techniques Measure?", IEEE INFOCOM, 2001.
 
3
K. Lai and M. Baker, "Nettimer: A Tool for Measuring Bottleneck Link Bandwidth", USITS, March 2001.
 
4
T. S. E. Ng, Y. Chu, S. G. Rao, K. Sripanidkulchai, and H. Zhang. "Measurement-Based Optimization Techniques for Bandwidth-Demanding Peer-to-Peer Systems", IEEE INFOCOM, March 2003.
 
5
T. S. E. Ng and H. Zhang, "Predicting Internet Network Distance with Coordinates-Based Approaches", IEEE INFOCOM, June 2002.
6
7
 
8
 
9
 
10
S. Ratnasamy, M. Handley, R. Karp, and S. Shenker. "Topologically-Aware Overlay Construction and Server Selection", IEEE INFOCOM, June 2002.
 
11
J. Rosenberg, J. Weinberger, C. Huitema and R. Mahy. "STUN - Simple Traversal of UDP Through Network Address Translators", IETF Draft, December 2002.
 
12
S. Saroiu, P. K. Gummadi, and S. D. Gribble. "A Measurement Study of Peer-to-Peer File Sharing Systems", MMCN, January 2002.
 
13
Cisco uBR7200 Series Universal Broadband Router, http://www.cisco.com/warp/public/cc/pd/rt/ub7200/index.shtml
 
14
National Internet Measurement Infrastructure (NIMI), http://www.ncne.nlanr.net/nimi/

CITED BY  10
 
 
 
 

Collaborative Colleagues:
Karthik Lakshminarayanan: colleagues
Venkata N. Padmanabhan: colleagues

Peer to Peer - Readers of this Article have also read: