Overrun and Skipping in Hierarchically Scheduled Real-Time Systems
ABSTRACT Recently, two SRP-based synchronization protocols for hierarchically scheduled real-time systems based on fixed priority preemptive scheduling (FPPS) have been presented, i.e., HSRP and SIRAP. Preventing depletion of budget during global resource access, the former implements an overrun mechanism, while the later exploits a skipping mechanism. A theoretical comparison of the performance of these mechanisms revealed that none of them was superior to the other, as their performance is heavily dependent on the system's parameters. To better understand the relative strengths and weaknesses of these mechanisms, this paper presents a comparative evaluation of the depletion prevention mechanisms overrun (with or without payback) and skipping. These mechanisms are investigated in detail and the corresponding system load imposed by these mechanisms is explored in a simulation study. The mechanisms are evaluated assuming FPPS and a periodic resource model. The periodic resource model is selected as it supports locality of schedulability analysis, allowing for a truthful comparison of the mechanisms. Given system characteristics, guiding the design of hierarchically scheduled real-time systems, the results of this paper indicate when one mechanism is better than the other and how a system should be configured in order to operate efficiently.
- SourceAvailable from: Johan J Lukkien[Show abstract] [Hide abstract]
ABSTRACT: Hierarchical scheduling frameworks (HSFs) provide means for composing complex real-time systems from well-defined independently developed and analyzed subsystems. To support shared logical resources requiring mutual exclusive access in two-level HSFs, overrun without payback has been proposed as a mechanism to prevent budget depletion during resource access arbitrated by the stack resource policy (SRP). In this paper, we revisit the global schedulability analysis of synchronization protocols based on SRP and overrun without payback for fixed-priority scheduled HSFs. We derive a new global schedulability analysis based on the observation that the overrun budget is merely meant to prevent budget depletion during global resource access. The deadline of a subsystem therefore only needs to hold for its normal budget rather than the sum of the normal and overrun budget. Our novel analysis is considerably simpler than an earlier, initially improved analysis, which improved both the original local and global schedulability analyses. We evaluate the new analysis based on an extensive simulation study and compare the results with the existing analysis. Our simplified analysis does not significantly affect schedulability compared to the initially improved analysis. It is therefore proposed as a preferable engineering approach to synchronization protocols for compositional real-time systems. We accordingly present the implementation of our improvement in an OSEK-compliant real-time operating system to sketch its applicability in today's industrial automotive standards. Both implementation and run-time overheads are discussed providing measured results.Industrial Embedded Systems (SIES), 2011 6th IEEE International Symposium on; 07/2011
Conference Paper: Refining SIRAP with a dedicated resource ceiling for self-blocking.[Show abstract] [Hide abstract]
ABSTRACT: In recent years, several synchronization protocols for resource sharing have been presented for use in a Hierarchical Scheduling Framework (HSF). An initial comparative assessment of existing protocols revealed that none of the protocols is superior to the others and that the performance of a protocol heavily depends on system parameters. In this paper, we aim at efficiency improvements of the synchronization protocol SIRAP  and its associated schedulability analysis, where efficiency refers to calculated CPU resource needs. The contribution of the paper is threefold. Firstly, we present an improvement of the schedulability analysis for SIRAP, which makes SIRAP more efficient. Secondly, we generalize SIRAP by distinguishing separate resource ceilings for self-blocking and resource access. Using a separate resource ceiling for self-blocking enables a reduction of the interference from lower priority tasks, which can result in efficiency improvements. The efficiency improvement depends on both subsystem characteristics and the value selected for the resource ceiling for self-blocking, however. The third contribution of this paper is therefore an algorithm that given a subsystem selects for each globally shared resource an optimal value in terms of efficiency for its resource ceiling for self-blocking. The efficiency improvement gained by the algorithm compared to the original SIRAP approach is evaluated by means of simulation.Proceedings of the 9th ACM & IEEE International conference on Embedded software, EMSOFT 2009, Grenoble, France, October 12-16, 2009; 01/2009