Decentralized ranking in large-scale overlay networks

Alberto Montresor, M. Jelasity, Ozalp Babaoglu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Modern distributed systems are often characterized by very large scale, poor reliability, and extreme dynamism of the participating nodes, with a continuous flow of nodes joining and leaving the system. In order to develop robust applications in such environments, middleware services aimed at dealing with the inherent unpredictability of the underlying networks are required. One such service is aggregation. In the aggregation problem, each node is assumed to have attributes. The task is to extract global information about these attributes and make it available to the nodes. Examples include the total free storage, the average load, or the size of the network. Efficient protocols for computing several aggregates such as average, count, and variance have already been proposed. In this paper, we consider calculating the rank ofnodes, where the set ofnodes has to be sorted according to a numeric attribute and each node must be informed about its own rank in the global sorting. This information has a number ofapplica-tions, such as slicing. It can also be applied to calculate the median or any other percentile. We propose T-RANK, a robust and completely decentralized algorithm for solving the ranking problem with minimal assumptions. Due to the characteristics ofthe targeted environment, we aim for a probabilistic approach and accept minor errors in the output. We present extensive empirical results that suggest near logarithmic time complexity, scalability and robustness in different failure scenarios.

Original languageEnglish
Title of host publicationProceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008
Pages208-213
Number of pages6
DOIs
Publication statusPublished - 2008
Event2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008 - Venice, Veneto, Italy
Duration: Oct 20 2008Oct 24 2008

Other

Other2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008
CountryItaly
CityVenice, Veneto
Period10/20/0810/24/08

Fingerprint

Overlay networks
Agglomeration
Middleware
Sorting
Joining
Scalability
Network protocols

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Software

Cite this

Montresor, A., Jelasity, M., & Babaoglu, O. (2008). Decentralized ranking in large-scale overlay networks. In Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008 (pp. 208-213). [4800679] https://doi.org/10.1109/SASOW.2008.17

Decentralized ranking in large-scale overlay networks. / Montresor, Alberto; Jelasity, M.; Babaoglu, Ozalp.

Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008. 2008. p. 208-213 4800679.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Montresor, A, Jelasity, M & Babaoglu, O 2008, Decentralized ranking in large-scale overlay networks. in Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008., 4800679, pp. 208-213, 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008, Venice, Veneto, Italy, 10/20/08. https://doi.org/10.1109/SASOW.2008.17
Montresor A, Jelasity M, Babaoglu O. Decentralized ranking in large-scale overlay networks. In Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008. 2008. p. 208-213. 4800679 https://doi.org/10.1109/SASOW.2008.17
Montresor, Alberto ; Jelasity, M. ; Babaoglu, Ozalp. / Decentralized ranking in large-scale overlay networks. Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008. 2008. pp. 208-213
@inproceedings{1819912ed0a246f89d659faa82f39f3a,
title = "Decentralized ranking in large-scale overlay networks",
abstract = "Modern distributed systems are often characterized by very large scale, poor reliability, and extreme dynamism of the participating nodes, with a continuous flow of nodes joining and leaving the system. In order to develop robust applications in such environments, middleware services aimed at dealing with the inherent unpredictability of the underlying networks are required. One such service is aggregation. In the aggregation problem, each node is assumed to have attributes. The task is to extract global information about these attributes and make it available to the nodes. Examples include the total free storage, the average load, or the size of the network. Efficient protocols for computing several aggregates such as average, count, and variance have already been proposed. In this paper, we consider calculating the rank ofnodes, where the set ofnodes has to be sorted according to a numeric attribute and each node must be informed about its own rank in the global sorting. This information has a number ofapplica-tions, such as slicing. It can also be applied to calculate the median or any other percentile. We propose T-RANK, a robust and completely decentralized algorithm for solving the ranking problem with minimal assumptions. Due to the characteristics ofthe targeted environment, we aim for a probabilistic approach and accept minor errors in the output. We present extensive empirical results that suggest near logarithmic time complexity, scalability and robustness in different failure scenarios.",
author = "Alberto Montresor and M. Jelasity and Ozalp Babaoglu",
year = "2008",
doi = "10.1109/SASOW.2008.17",
language = "English",
isbn = "9780769535531",
pages = "208--213",
booktitle = "Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008",

}

TY - GEN

T1 - Decentralized ranking in large-scale overlay networks

AU - Montresor, Alberto

AU - Jelasity, M.

AU - Babaoglu, Ozalp

PY - 2008

Y1 - 2008

N2 - Modern distributed systems are often characterized by very large scale, poor reliability, and extreme dynamism of the participating nodes, with a continuous flow of nodes joining and leaving the system. In order to develop robust applications in such environments, middleware services aimed at dealing with the inherent unpredictability of the underlying networks are required. One such service is aggregation. In the aggregation problem, each node is assumed to have attributes. The task is to extract global information about these attributes and make it available to the nodes. Examples include the total free storage, the average load, or the size of the network. Efficient protocols for computing several aggregates such as average, count, and variance have already been proposed. In this paper, we consider calculating the rank ofnodes, where the set ofnodes has to be sorted according to a numeric attribute and each node must be informed about its own rank in the global sorting. This information has a number ofapplica-tions, such as slicing. It can also be applied to calculate the median or any other percentile. We propose T-RANK, a robust and completely decentralized algorithm for solving the ranking problem with minimal assumptions. Due to the characteristics ofthe targeted environment, we aim for a probabilistic approach and accept minor errors in the output. We present extensive empirical results that suggest near logarithmic time complexity, scalability and robustness in different failure scenarios.

AB - Modern distributed systems are often characterized by very large scale, poor reliability, and extreme dynamism of the participating nodes, with a continuous flow of nodes joining and leaving the system. In order to develop robust applications in such environments, middleware services aimed at dealing with the inherent unpredictability of the underlying networks are required. One such service is aggregation. In the aggregation problem, each node is assumed to have attributes. The task is to extract global information about these attributes and make it available to the nodes. Examples include the total free storage, the average load, or the size of the network. Efficient protocols for computing several aggregates such as average, count, and variance have already been proposed. In this paper, we consider calculating the rank ofnodes, where the set ofnodes has to be sorted according to a numeric attribute and each node must be informed about its own rank in the global sorting. This information has a number ofapplica-tions, such as slicing. It can also be applied to calculate the median or any other percentile. We propose T-RANK, a robust and completely decentralized algorithm for solving the ranking problem with minimal assumptions. Due to the characteristics ofthe targeted environment, we aim for a probabilistic approach and accept minor errors in the output. We present extensive empirical results that suggest near logarithmic time complexity, scalability and robustness in different failure scenarios.

UR - http://www.scopus.com/inward/record.url?scp=64849096147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=64849096147&partnerID=8YFLogxK

U2 - 10.1109/SASOW.2008.17

DO - 10.1109/SASOW.2008.17

M3 - Conference contribution

AN - SCOPUS:64849096147

SN - 9780769535531

SP - 208

EP - 213

BT - Proceedings - 2nd IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, SASOW 2008

ER -