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 language | English |
---|---|
Title of host publication | ACM SoCC 2015 - Proceedings of the 6th ACM Symposium on Cloud Computing |
Publisher | Association for Computing Machinery, Inc |
Pages | 209-221 |
Number of pages | 13 |
ISBN (Print) | 9781450336512 |
DOIs | |
Publication status | Published - 27 Aug 2015 |
Event | 6th ACM Symposium on Cloud Computing, ACM SoCC 2015 - Kohala Coast, United States Duration: 27 Aug 2015 → 29 Aug 2015 |
Other
Other | 6th ACM Symposium on Cloud Computing, ACM SoCC 2015 |
---|---|
Country | United States |
City | Kohala Coast |
Period | 27/8/15 → 29/8/15 |
Fingerprint
Keywords
- Availability
- Design
- Performance
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Theoretical Computer Science
Cite this
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 proceeding › Conference contribution
}
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 -