Database high availability using shadow systems

Jaemyung Kim, Kenneth Salem, Khuzaima Daudjee, Ashraf Aboulnaga, Xin Pan

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

2 Citations (Scopus)

Abstract

Hot standby techniques are widely used to implement highly available database systems. These techniques make use of two separate copies of the database, an active copy and a backup that is managed by the standby. The two database copies are stored independently and synchronized by the database systems that manage them. However, database systems deployed in computing clouds often have access to reliable persistent storage that can be shared by multiple servers. In this paper we consider how hot standby techniques can be improved in such settings. We present SHADOW systems, a novel approach to hot standby high availability. Like other database systems that use shared storage, SHADOWsystems push the task of managing database replication out of the database system and into the underlying storage service, simplifying the database system. Unlike other systems, SHADOW systems also provide write offloading, which frees the active database system from the need to update the persistent database. Instead, that responsibility is placed on the standby system. We present the results of a performance evaluation using a SHADOW prototype on Amazon's cloud, showing that write offloading enables SHADOWto outperform traditional hot standby replication and even a standalone DBMS that does not provide high availability.

Original languageEnglish
Title of host publicationACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing
PublisherAssociation for Computing Machinery, Inc
Pages209-221
Number of pages13
ISBN (Print)9781450336512
DOIs
Publication statusPublished - 27 Aug 2015
Event6th ACM Symposium on Cloud Computing, ACM SoCC 2015 - Kohala Coast, United States
Duration: 27 Aug 201529 Aug 2015

Other

Other6th ACM Symposium on Cloud Computing, ACM SoCC 2015
CountryUnited States
CityKohala Coast
Period27/8/1529/8/15

Fingerprint

High Availability
Database Systems
Availability
Replication
Cloud Computing
Performance Evaluation
Server
Update
Prototype
Cloud computing
Servers

Keywords

  • Availability
  • Design
  • Performance

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Kim, J., Salem, K., Daudjee, K., Aboulnaga, A., & Pan, X. (2015). Database high availability using shadow systems. In ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing (pp. 209-221). Association for Computing Machinery, Inc. https://doi.org/10.1145/2806777.2806841

Database high availability using shadow systems. / Kim, Jaemyung; Salem, Kenneth; Daudjee, Khuzaima; Aboulnaga, Ashraf; Pan, Xin.

ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing. Association for Computing Machinery, Inc, 2015. p. 209-221.

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

Kim, J, Salem, K, Daudjee, K, Aboulnaga, A & Pan, X 2015, Database high availability using shadow systems. in ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing. Association for Computing Machinery, Inc, pp. 209-221, 6th ACM Symposium on Cloud Computing, ACM SoCC 2015, Kohala Coast, United States, 27/8/15. https://doi.org/10.1145/2806777.2806841
Kim J, Salem K, Daudjee K, Aboulnaga A, Pan X. Database high availability using shadow systems. In ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing. Association for Computing Machinery, Inc. 2015. p. 209-221 https://doi.org/10.1145/2806777.2806841
Kim, Jaemyung ; Salem, Kenneth ; Daudjee, Khuzaima ; Aboulnaga, Ashraf ; Pan, Xin. / Database high availability using shadow systems. ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing. Association for Computing Machinery, Inc, 2015. pp. 209-221
@inproceedings{d4664b59916646ff84708344539a1417,
title = "Database high availability using shadow systems",
abstract = "Hot standby techniques are widely used to implement highly available database systems. These techniques make use of two separate copies of the database, an active copy and a backup that is managed by the standby. The two database copies are stored independently and synchronized by the database systems that manage them. However, database systems deployed in computing clouds often have access to reliable persistent storage that can be shared by multiple servers. In this paper we consider how hot standby techniques can be improved in such settings. We present SHADOW systems, a novel approach to hot standby high availability. Like other database systems that use shared storage, SHADOWsystems push the task of managing database replication out of the database system and into the underlying storage service, simplifying the database system. Unlike other systems, SHADOW systems also provide write offloading, which frees the active database system from the need to update the persistent database. Instead, that responsibility is placed on the standby system. We present the results of a performance evaluation using a SHADOW prototype on Amazon's cloud, showing that write offloading enables SHADOWto outperform traditional hot standby replication and even a standalone DBMS that does not provide high availability.",
keywords = "Availability, Design, Performance",
author = "Jaemyung Kim and Kenneth Salem and Khuzaima Daudjee and Ashraf Aboulnaga and Xin Pan",
year = "2015",
month = "8",
day = "27",
doi = "10.1145/2806777.2806841",
language = "English",
isbn = "9781450336512",
pages = "209--221",
booktitle = "ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Database high availability using shadow systems

AU - Kim, Jaemyung

AU - Salem, Kenneth

AU - Daudjee, Khuzaima

AU - Aboulnaga, Ashraf

AU - Pan, Xin

PY - 2015/8/27

Y1 - 2015/8/27

N2 - Hot standby techniques are widely used to implement highly available database systems. These techniques make use of two separate copies of the database, an active copy and a backup that is managed by the standby. The two database copies are stored independently and synchronized by the database systems that manage them. However, database systems deployed in computing clouds often have access to reliable persistent storage that can be shared by multiple servers. In this paper we consider how hot standby techniques can be improved in such settings. We present SHADOW systems, a novel approach to hot standby high availability. Like other database systems that use shared storage, SHADOWsystems push the task of managing database replication out of the database system and into the underlying storage service, simplifying the database system. Unlike other systems, SHADOW systems also provide write offloading, which frees the active database system from the need to update the persistent database. Instead, that responsibility is placed on the standby system. We present the results of a performance evaluation using a SHADOW prototype on Amazon's cloud, showing that write offloading enables SHADOWto outperform traditional hot standby replication and even a standalone DBMS that does not provide high availability.

AB - Hot standby techniques are widely used to implement highly available database systems. These techniques make use of two separate copies of the database, an active copy and a backup that is managed by the standby. The two database copies are stored independently and synchronized by the database systems that manage them. However, database systems deployed in computing clouds often have access to reliable persistent storage that can be shared by multiple servers. In this paper we consider how hot standby techniques can be improved in such settings. We present SHADOW systems, a novel approach to hot standby high availability. Like other database systems that use shared storage, SHADOWsystems push the task of managing database replication out of the database system and into the underlying storage service, simplifying the database system. Unlike other systems, SHADOW systems also provide write offloading, which frees the active database system from the need to update the persistent database. Instead, that responsibility is placed on the standby system. We present the results of a performance evaluation using a SHADOW prototype on Amazon's cloud, showing that write offloading enables SHADOWto outperform traditional hot standby replication and even a standalone DBMS that does not provide high availability.

KW - Availability

KW - Design

KW - Performance

UR - http://www.scopus.com/inward/record.url?scp=84958987038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958987038&partnerID=8YFLogxK

U2 - 10.1145/2806777.2806841

DO - 10.1145/2806777.2806841

M3 - Conference contribution

AN - SCOPUS:84958987038

SN - 9781450336512

SP - 209

EP - 221

BT - ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing

PB - Association for Computing Machinery, Inc

ER -