Correctness and parallelism in composite systems
PODS '97 Proceedings of the sixteenth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
OLAP Query Routing and Physical Design in a Database Cluster
EDBT '00 Proceedings of the 7th International Conference on Extending Database Technology: Advances in Database Technology
Distributed Processing over Stand-alone Systems and Applications
VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
Scalable Distributed Query and Update Service Implementations for XML Document Elements
RIDE '01 Proceedings of the 11th International Workshop on research Issues in Data Engineering
Optimistic intra-transaction parallelism on chip multiprocessors
VLDB '05 Proceedings of the 31st international conference on Very large data bases
Incrementally parallelizing database transactions with thread-level speculation
ACM Transactions on Computer Systems (TOCS)
| Hi-index | 0.00 |
Inter-transaction parallelism, the concurrent execution of independent client transactions, is currently well supported by database systems. Intra-transaction parallelism, the parallel execution of operations within the same transaction, is generally not supported, even though often necessary especially in non-standard applications. In this paper we show how database operations within the same transaction can be executed concurrently by executing them as independent subtransactions. This is possible because we employ a two-level transaction approach where the lower level is provided by virtually any of today's databases. The higher level is realised by a transaction processing monitor that is extended with an additional transaction manager for the scheduling of application service calls. We present results of a prototype implementation using Tuxedo and a relational database system using a document management application as an example.