Transactions and consistency in distributed database systems
ACM Transactions on Database Systems (TODS)
Towards robust distributed systems (abstract)
Proceedings of the nineteenth annual ACM symposium on Principles of distributed computing
Database Systems Concepts
Analysis of distributed commit protocols
SIGMOD '82 Proceedings of the 1982 ACM SIGMOD international conference on Management of data
Composable memory transactions
Communications of the ACM - Designing games with a purpose
PNUTS: Yahoo!'s hosted data serving platform
Proceedings of the VLDB Endowment
Scalable Transactions for Web Applications in the Cloud
Euro-Par '09 Proceedings of the 15th International Euro-Par Conference on Parallel Processing
Schism: a workload-driven approach to database replication and partitioning
Proceedings of the VLDB Endowment
Data-oriented transaction execution
Proceedings of the VLDB Endowment
High-throughput transaction executions on graphics processors
Proceedings of the VLDB Endowment
Principles of Distributed Database Systems
Principles of Distributed Database Systems
Enforcing Policy and Data Consistency of Cloud Transactions
ICDCSW '11 Proceedings of the 2011 31st International Conference on Distributed Computing Systems Workshops
Distributed database systems in high-speed wide-area networks
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
In the distributed transactional database systems, there are a large number of concurrent transactions. Each transaction independently executes on a separate thread this is known as thread-to-transaction. The lock manager is hence responsible for maintaining isolation between concurrently-executing transactions, which takes more time from the total time of the execution. In this paper we present a system that improves the response time by using thread-to-metadata policy instead of using thread-to-transaction policy. The system consists of two modules: (a) Transaction Module, and (b) Data Module. The system minimizes the interaction with the lock manager and maintains all the ACID properties of the transactions. We also present experimental results that show how thread-to-metadata policy improves the response time.