The Cost of Serializability on Platforms That Use Snapshot Isolation

Authors:
Mohammad Alomari;Michael Cahill;Alan Fekete;Uwe Rohm
Affiliations:
School of Information Technologies, University of Sydney, Sydney NSW 2006, Australia. miomari@it.usyd.edu.au;School of Information Technologies, University of Sydney, Sydney NSW 2006, Australia. mjc@it.usyd.edu.au;School of Information Technologies, University of Sydney, Sydney NSW 2006, Australia. fekete@it.usyd.edu.au;School of Information Technologies, University of Sydney, Sydney NSW 2006, Australia. roehm@it.usyd.edu.au
Venue:
ICDE '08 Proceedings of the 2008 IEEE 24th International Conference on Data Engineering
Year:
2008

Citing 0
Cited 6

Serializable isolation for snapshot databases

Proceedings of the 2008 ACM SIGMOD international conference on Management of data
Snapshot isolation and integrity constraints in replicated databases

ACM Transactions on Database Systems (TODS)
Serializable isolation for snapshot databases

ACM Transactions on Database Systems (TODS)
Serializable executions with snapshot isolation: modifying application code or mixing isolation levels?

DASFAA'08 Proceedings of the 13th international conference on Database systems for advanced applications
Strict serializability is harmless: a new architecture for enterprise applications

Proceedings of the ACM international conference companion on Object oriented programming systems languages and applications companion
Performance of program modification techniques that ensure serializable executions with snapshot isolation DBMS

Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Several common DBMS engines use the multiversion concurrency control mechanism called Snapshot Isolation, even though application programs can experience non-serializable executions when run concurrently on such a platform. Several proposals exist for modifying the application programs, without changing their semantics, so that they are certain to execute serializably even on an engine that uses SI. We evaluate the performance impact of these proposals, and find that some have limited impact (only a few percent drop in throughput at a given multi-programming level) while others lead to much greater reduction in throughput of up-to 60% in high contention scenarios. We present experimental results for both an open-source and a commercial engine. We relate these to the theory, giving guidelines on which conflicts to introduce so as to ensure correctness with little impact on performance.