Experimental evaluation of behavior-based failure-detection schemes in real-time communication networks

Seungjae Han; Kang G. Shin

doi:10.1109/71.774910

Experimental evaluation of behavior-based failure-detection schemes in real-time communication networks

Seungjae Han, Kang G. Shin

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

Effective detection of failures is essential for reliable communication services. Traditionally, non-real-time computer networks have relied on behavior-based techniques for detecting communication failures. That is, each node uses heartbeats to detect the failure of its neighbors and the end-to-end transport protocol (e.g., TCP) achieves reliable communication by acknowledgment/retransmission. Recently, there has been a growing demand for reliable `real-time' communication, but little research has been done on the failure detection problem. In this paper, we present two behavior-based failure-detection schemes - neighbor detection and end-to-end detection - for reliable real-time communication services and experimentally evaluate their effectiveness. Specifically, we measure and analyze the coverage and latency of these detection schemes through fault-injection experiments. The experimental results have shown that nearly all failures can be detected very quickly by the neighbor detection scheme, while the end-to-end detection scheme uncovers the remaining failures with larger detection latencies.

Original language	English
Pages (from-to)	613-626
Number of pages	14
Journal	IEEE Transactions on Parallel and Distributed Systems
Volume	10
Issue number	6
DOIs	https://doi.org/10.1109/71.774910
Publication status	Published - 1999

Bibliographical note

Funding Information:
We would like to thank Harold Rosenberg and Jaehyun Park for their contribution in the implementation of DOCTOR. Atri Indiresan provided the skeleton of the real-time channel protocol used in our experiment. The work reported in this paper was supported in part by the U.S. National Science Foundation under Grant MIP-9203895, the U.S. Office of Naval Research under Grant N00014-94-1-0229, and Mitsubishi Electric Research Laboratory, Cambridge, Massachusetts. A subset of the materials of this paper was presented at the IEEE International Symposium on Fault-Tolerant Computing (FTCS-27), June 1997, in Seattle, Washington.

All Science Journal Classification (ASJC) codes

Signal Processing
Hardware and Architecture
Computational Theory and Mathematics

Access to Document

10.1109/71.774910

Fingerprint Dive into the research topics of 'Experimental evaluation of behavior-based failure-detection schemes in real-time communication networks'. Together they form a unique fingerprint.

Cite this

@article{fe5ea518c2b14625aaaa44750e7d0ca7,

title = "Experimental evaluation of behavior-based failure-detection schemes in real-time communication networks",

abstract = "Effective detection of failures is essential for reliable communication services. Traditionally, non-real-time computer networks have relied on behavior-based techniques for detecting communication failures. That is, each node uses heartbeats to detect the failure of its neighbors and the end-to-end transport protocol (e.g., TCP) achieves reliable communication by acknowledgment/retransmission. Recently, there has been a growing demand for reliable `real-time' communication, but little research has been done on the failure detection problem. In this paper, we present two behavior-based failure-detection schemes - neighbor detection and end-to-end detection - for reliable real-time communication services and experimentally evaluate their effectiveness. Specifically, we measure and analyze the coverage and latency of these detection schemes through fault-injection experiments. The experimental results have shown that nearly all failures can be detected very quickly by the neighbor detection scheme, while the end-to-end detection scheme uncovers the remaining failures with larger detection latencies.",

author = "Seungjae Han and Shin, {Kang G.}",

note = "Funding Information: We would like to thank Harold Rosenberg and Jaehyun Park for their contribution in the implementation of DOCTOR. Atri Indiresan provided the skeleton of the real-time channel protocol used in our experiment. The work reported in this paper was supported in part by the U.S. National Science Foundation under Grant MIP-9203895, the U.S. Office of Naval Research under Grant N00014-94-1-0229, and Mitsubishi Electric Research Laboratory, Cambridge, Massachusetts. A subset of the materials of this paper was presented at the IEEE International Symposium on Fault-Tolerant Computing (FTCS-27), June 1997, in Seattle, Washington.",

year = "1999",

doi = "10.1109/71.774910",

language = "English",

volume = "10",

pages = "613--626",

journal = "IEEE Transactions on Parallel and Distributed Systems",

issn = "1045-9219",

publisher = "IEEE Computer Society",

number = "6",

}

TY - JOUR

T1 - Experimental evaluation of behavior-based failure-detection schemes in real-time communication networks

AU - Han, Seungjae

AU - Shin, Kang G.

N1 - Funding Information: We would like to thank Harold Rosenberg and Jaehyun Park for their contribution in the implementation of DOCTOR. Atri Indiresan provided the skeleton of the real-time channel protocol used in our experiment. The work reported in this paper was supported in part by the U.S. National Science Foundation under Grant MIP-9203895, the U.S. Office of Naval Research under Grant N00014-94-1-0229, and Mitsubishi Electric Research Laboratory, Cambridge, Massachusetts. A subset of the materials of this paper was presented at the IEEE International Symposium on Fault-Tolerant Computing (FTCS-27), June 1997, in Seattle, Washington.

PY - 1999

Y1 - 1999

N2 - Effective detection of failures is essential for reliable communication services. Traditionally, non-real-time computer networks have relied on behavior-based techniques for detecting communication failures. That is, each node uses heartbeats to detect the failure of its neighbors and the end-to-end transport protocol (e.g., TCP) achieves reliable communication by acknowledgment/retransmission. Recently, there has been a growing demand for reliable `real-time' communication, but little research has been done on the failure detection problem. In this paper, we present two behavior-based failure-detection schemes - neighbor detection and end-to-end detection - for reliable real-time communication services and experimentally evaluate their effectiveness. Specifically, we measure and analyze the coverage and latency of these detection schemes through fault-injection experiments. The experimental results have shown that nearly all failures can be detected very quickly by the neighbor detection scheme, while the end-to-end detection scheme uncovers the remaining failures with larger detection latencies.

AB - Effective detection of failures is essential for reliable communication services. Traditionally, non-real-time computer networks have relied on behavior-based techniques for detecting communication failures. That is, each node uses heartbeats to detect the failure of its neighbors and the end-to-end transport protocol (e.g., TCP) achieves reliable communication by acknowledgment/retransmission. Recently, there has been a growing demand for reliable `real-time' communication, but little research has been done on the failure detection problem. In this paper, we present two behavior-based failure-detection schemes - neighbor detection and end-to-end detection - for reliable real-time communication services and experimentally evaluate their effectiveness. Specifically, we measure and analyze the coverage and latency of these detection schemes through fault-injection experiments. The experimental results have shown that nearly all failures can be detected very quickly by the neighbor detection scheme, while the end-to-end detection scheme uncovers the remaining failures with larger detection latencies.

UR - http://www.scopus.com/inward/record.url?scp=0032624089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032624089&partnerID=8YFLogxK

U2 - 10.1109/71.774910

DO - 10.1109/71.774910

M3 - Article

AN - SCOPUS:0032624089

VL - 10

SP - 613

EP - 626

JO - IEEE Transactions on Parallel and Distributed Systems

JF - IEEE Transactions on Parallel and Distributed Systems

SN - 1045-9219

IS - 6

ER -