Abstract
We study the scheduling problem in shared-nothing parallel transaction processing (TP) systems with two-phase locking concurrency control. A transaction scheduling algorithm called SCST (Synchronizing Completion of Sub-Transactions) is proposed to reduce the data contention and thus to improve the system performance in the shared-nothing parallel TP systems. Furthermore, a comprehensive simulator for shared-nothing parallel TP systems is developed for studying the performance behavior of the SCST algorithm. Using this simulator, we compare the SCST algorithm with the conventional FCFS (First-Come-First-Served) scheduling algorithm. We show that the SCST algorithm outperforms the FCFS algorithm significantly in terms of the transaction throughput, the 95th percentile of the response time, and the restart ratio.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.