Replication control for fault-tolerance in distributed real-time database systems

Sang H. Son; Fengjie Zhang; Ji Hoon Kang

doi:10.1109/AERO.1998.682157

Replication control for fault-tolerance in distributed real-time database systems

Sang H. Son, Fengjie Zhang, Ji Hoon Kang

Department of Electrical Engineering and Computer Science

University of Virginia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In many distributed real-time systems, certain critical data need to be replicated to achieve fault-tolerance and improved performance. Schedulers for such distributed real-time systems must satisfy timing constraints of transactions and preserve data consistency. In this paper we presents a replication control algorithm, which integrates real-time scheduling and replication control to achieve the desired level of fault-tolerance. The algorithm adopts a majority consensus scheme for replication control and employs epsilon-serializability, a correctness criterion which is less stringent than conventional one-copy serializability. The performance of the algorithm is compared with that of a real-time token-based algorithm.

Original language	English
Title of host publication	1998 IEEE Aerospace Conference, AERO 1998 - Proceedings
Publisher	IEEE Computer Society
Pages	73-81
Number of pages	9
ISBN (Print)	0780343115
DOIs	https://doi.org/10.1109/AERO.1998.682157
State	Published - 1998
Event	1998 IEEE Aerospace Conference, AERO 1998 - Snowmass, United States Duration: 28 Mar 1998 → 28 Mar 1998

Publication series

Name	IEEE Aerospace Conference Proceedings
Volume	4
ISSN (Print)	1095-323X

Conference

Conference	1998 IEEE Aerospace Conference, AERO 1998
Country/Territory	United States
City	Snowmass
Period	28/03/98 → 28/03/98

Bibliographical note

Publisher Copyright:
© 1998 IEEE.

Access to Document

10.1109/AERO.1998.682157

Cite this

@inproceedings{15e3d91374b84bda9709ffb933126c1a,

title = "Replication control for fault-tolerance in distributed real-time database systems",

abstract = "In many distributed real-time systems, certain critical data need to be replicated to achieve fault-tolerance and improved performance. Schedulers for such distributed real-time systems must satisfy timing constraints of transactions and preserve data consistency. In this paper we presents a replication control algorithm, which integrates real-time scheduling and replication control to achieve the desired level of fault-tolerance. The algorithm adopts a majority consensus scheme for replication control and employs epsilon-serializability, a correctness criterion which is less stringent than conventional one-copy serializability. The performance of the algorithm is compared with that of a real-time token-based algorithm.",

author = "Son, \{Sang H.\} and Fengjie Zhang and Kang, \{Ji Hoon\}",

note = "Publisher Copyright: {\textcopyright} 1998 IEEE.; 1998 IEEE Aerospace Conference, AERO 1998 ; Conference date: 28-03-1998 Through 28-03-1998",

year = "1998",

doi = "10.1109/AERO.1998.682157",

language = "English",

isbn = "0780343115",

series = "IEEE Aerospace Conference Proceedings",

publisher = "IEEE Computer Society",

pages = "73--81",

booktitle = "1998 IEEE Aerospace Conference, AERO 1998 - Proceedings",

}

Son, SH, Zhang, F & Kang, JH 1998, Replication control for fault-tolerance in distributed real-time database systems. in 1998 IEEE Aerospace Conference, AERO 1998 - Proceedings., 682157, IEEE Aerospace Conference Proceedings, vol. 4, IEEE Computer Society, pp. 73-81, 1998 IEEE Aerospace Conference, AERO 1998, Snowmass, United States, 28/03/98. https://doi.org/10.1109/AERO.1998.682157

Replication control for fault-tolerance in distributed real-time database systems. / Son, Sang H.; Zhang, Fengjie; Kang, Ji Hoon.
1998 IEEE Aerospace Conference, AERO 1998 - Proceedings. IEEE Computer Society, 1998. p. 73-81 682157 (IEEE Aerospace Conference Proceedings; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Replication control for fault-tolerance in distributed real-time database systems

AU - Son, Sang H.

AU - Zhang, Fengjie

AU - Kang, Ji Hoon

PY - 1998

Y1 - 1998

N2 - In many distributed real-time systems, certain critical data need to be replicated to achieve fault-tolerance and improved performance. Schedulers for such distributed real-time systems must satisfy timing constraints of transactions and preserve data consistency. In this paper we presents a replication control algorithm, which integrates real-time scheduling and replication control to achieve the desired level of fault-tolerance. The algorithm adopts a majority consensus scheme for replication control and employs epsilon-serializability, a correctness criterion which is less stringent than conventional one-copy serializability. The performance of the algorithm is compared with that of a real-time token-based algorithm.

AB - In many distributed real-time systems, certain critical data need to be replicated to achieve fault-tolerance and improved performance. Schedulers for such distributed real-time systems must satisfy timing constraints of transactions and preserve data consistency. In this paper we presents a replication control algorithm, which integrates real-time scheduling and replication control to achieve the desired level of fault-tolerance. The algorithm adopts a majority consensus scheme for replication control and employs epsilon-serializability, a correctness criterion which is less stringent than conventional one-copy serializability. The performance of the algorithm is compared with that of a real-time token-based algorithm.

UR - https://www.scopus.com/pages/publications/0031621830

U2 - 10.1109/AERO.1998.682157

DO - 10.1109/AERO.1998.682157

M3 - Conference contribution

AN - SCOPUS:0031621830

SN - 0780343115

T3 - IEEE Aerospace Conference Proceedings

SP - 73

EP - 81

BT - 1998 IEEE Aerospace Conference, AERO 1998 - Proceedings

PB - IEEE Computer Society

T2 - 1998 IEEE Aerospace Conference, AERO 1998

Y2 - 28 March 1998 through 28 March 1998

ER -

Replication control for fault-tolerance in distributed real-time database systems

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this