Temporal consistency analysis is an important problem in Real-Time Database Systems (RTDBSs). Most of existing works on hybrid transaction co-scheduling focus on exploring effective deadline and period assignment methods which can guarantee the temporal consistency of data objects and the schedulability of transactions. To the best of our knowledge, all existing researches have not yet invested sufficient efforts on guaranteeing the Quality of Service (QoS) of control transactions and allow control transactions finish their execution after the data obtained by these control transactions expire. In this paper, we define a new problem of how to schedule a hybrid transaction set under the guarantee on QoS of control transactions. Two deadline and period assignment methods for addressing the defined problem are proposed in this work. Both the proposed methods support the Earliest Deadline First (EDF) scheduling. Extensive experiments are conducted to evaluate the performances of the proposed methods in terms of acceptance ratio, processor workload and efficiency. INDEX TERMS Real-time database systems, QoS of control transactions, hybrid transaction set, the EDF scheduling, deadline and period assignment.
Deriving deadlines and periods for update transactions and scheduling hybrid transactions have been recognized as an important issue in real-time database systems. Despite years of research, all existing techniques focus on assigning deadlines and periods for update transactions in uniprocessor systems and, thus, cannot be applied in multiprocessor systems. Two partitioned scheduling methods for hybrid transactions in multiprocessor systems are proposed in this paper, by developing existing scheduling methods for uniprocessor systems to multiprocessor environments. An effective strategy is proposed to improve the efficiencies of the proposed methods, under which the improvement of efficiency is at the price of the acceptance ratio of transaction sets. For addressing the low acceptance ratio of the improvement strategy, we propose a novel scheduling method. A set of experiments is conducted to test the performances of the proposed methods. To the best of our knowledge, this is the first paper for co-scheduling of hybrid transactions on multiprocessor platforms.
INDEX TERMSReal-time database systems, multiprocessor, hybrid transactions, deadlines and periods, co-scheduling.
As an effective method for detecting the schedulability of real-time tasks on multiprocessor platforms, Response time analysis (RTA) has been deeply researched in recent decades. Most of the existing RTA methods are designed for tasks that can be preempted at any time. However, in some real-time systems, a task may have some fixed preemption points (FPPs) that divide its execution into a series of non-preemptive regions (NPRs). In such environments, the task can only be preempted at its FPPs, which makes existing RTA methods for arbitrary preemption tasks not applicable. In this article, we study the schedulability analysis on tasks with FPPs under both global fixed-priority (G-FP) scheduling and global earliest deadline first (G-EDF) scheduling. First, based on the idea of limiting the time interval between two consecutive executions of an NPR, a novel RTA method for tasks with FPPs under G-FP scheduling is proposed. Second, we propose an effective RTA method for tasks with FPPs under G-EDF scheduling. Finally, extensive simulations are conducted and the results validate the effectiveness of the proposed methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.