Deferrable Scheduling for Maintaining Real-Time Data Freshness: Algorithms, Analysis, and Results

Abstract

Abstract-The periodic update transaction model has been used to maintain the freshness (or temporal validity) of real-time data. Period and deadline assignment has been the main focus of past studies, such as the More-Less scheme [25], in which update transactions are guaranteed by the Deadline Monotonic scheduling algorithm [16] to complete by their deadlines. In this paper, we propose a deferrable scheduling algorithm for fixed-priority transactions, a novel approach for minimizing update workload while maintaining the temporal validity of real-time data. In contrast to prior work on maintaining data freshness periodically, update transactions follow an aperiodic task model in the deferrable scheduling algorithm. The deferrable scheduling algorithm exploits the semantics of temporal validity constraint of real-time data by judiciously deferring the sampling times of update transaction jobs as late as possible. We present a theoretical estimation of its processor utilization and a sufficient condition for its schedulability. Our experimental results verify the theoretical estimation of the processor utilization. We demonstrate through the experiments that the deferrable scheduling algorithm is an effective approach and it significantly outperforms the More-Less scheme in terms of reducing processor workload.

An effective fixed priority co-scheduling algorithm for periodic update and application transactions

“…Extensive research works have been done on maintaining temporal validity and freshness of real-time data objects [1,7,9,19,32,33,35]. The basic method is to use periodic update transactions.…”

“…The details of ML will be reviewed in Section 3.2. To further reduce the total update workload for maintaining temporal validity, in contrast to HH and ML, the deferrable scheduling approach was proposed (DS-FP ) [33,35] by following an aperiodic update model to generate update jobs. To reduce the online scheduling overhead of DS-FP , [34,36] proposed two extensions to produce a hyperperiod for DS-FP so that the schedule generated by repeating the hyperperiod infinitely will satisfy the temporal validity constraints of the real-time data objects, and reduce the online schduling overhead to constant.…”

On Co-scheduling of Periodic Update and Application Transactions with Fixed Priority Assignment for Real-Time Monitoring

“…There has been extensive research work on maintaining validity and freshness of real-time data objects [6,[12][13][14][15][16][17]. The basic method is to use periodic update transactions to maintain data validity, i.e., update jobs are generated from an update transaction periodically to maintain the validity of a data object [6,7].…”

“…In [6], the More-Less (ML) method is proposed in which the sum of the period and relative deadline of an update transaction is set to be not larger than the validity interval of the corresponding data object to reduce the update workload. In [15], by the use of aperiodic update transactions, it proposes the deferrable scheduling algorithm for fixed-priority update transactions (DS-FP). In [8], based on a sufficient feasibility condition of the earliest deadline first (EDF) scheduling, it proposes an extension of ML called ML which is a linear-time algorithm to solve the period and deadline assignment problem.…”

Online Scheduling Switch for Maintaining Data Freshness in Flexible Real-Time Systems

“…In recent years, many efforts have been devoted to design and analyze algorithms to maintain the temporal validity of real-time data [1], [5]- [13]. In general, the simpler algorithms maintain higher data freshness and incur lower online scheduling overhead but impose much heavier update workload, while sophisticated ones improve the schedulability by sacrificing data freshness.…”