Response Time Distribution in a Multi-Processor Database with Single-Queue StaticLocking

摘要

A transaction scheduling mechanism is designed for a shared-memory, multi-processor database system. The scheduler used is a variant of static locking, adapted for real-time and more than one processor. It is assumed that transactions arrive according to a Poisson process, execution times of transactions are independent and exponentially distributed, and all transactions use the same number of data items. The system is then represented as a Markov model. A steady state is derived from this model. By examining the path through the system a single transaction, a recursive relation that describes all moments of a transaction's response time is derived. The moments are obtained from this relation with dynamic programming. The response time distribution is approximated by fitting a distribution to the first two moments.