We have introduced an adaptive hierarchical scheduling framework as a solution for composing dynamic real-time systems, i.e., systems where the CPU demand of its tasks are subjected to unknown and potentially drastic changes during run-time. The framework consists of a controller which periodically adapts the system to the current load situation. In this paper, we unveil and explore the detailed behavior and performance of such an adaptive framework. Specifically, we investigate the controller configurations enabling efficient control parameters which maximizes performance, and we evaluate the adaptive framework against a traditional static one. Furthermore, we demonstrate the results of our investigation using a practical multimedia case study in which we simulate the timing behavior of video decoding tasks running on our proposed framework. In addition, we compare the results of using our framework with the results of using static resource allocation approach.

We have presented a multi-level adaptive hierarchical scheduling framework in our previous work. The framework targets compositional real-time systems which are composed of both hard and soft real-time systems. While static CPU portions are reserved for hard real-time components, the CPU portions of soft real-time components are adjusted during run-time. In this paper, we present the implementation details of our framework which is implemented as a Linux kernel loadable module. In addition, we present a case-study to evaluate the performance and the overhead of our framework.

Processor partitioning and hierarchical scheduling have been widely used for composing hard real-time systems on a shared hardware platform while preserving the timing requirements of the systems. Due to the safety critical nature of the hard real-time systems for deriving the sufficient partition size often conservative analysis is used. Applying the exact same analysis for deriving the partition sizes for soft real-time systems result in unnecessary processors overallocation and consequently waste of the CPU resource. In this paper, to address the problem of composing soft and hard real-time systems on a resource constrained shared hardware, we present a multi-level adaptive hierarchical scheduling framework. In our framework, we adapt the processor partition sizes of soft real-time systems according to their need at each time point by on-line monitoring their processor demand. Furthermore, we implement our adaptive framework in the Linux kernel and show the performance of our framework using a case-study.

Multiprocessor platforms are becoming increasingly more popular. Providing more computation capacity on a single hardware platform, multiprocessors make it possible to integrate previously federated real-time systems onto a single platform. Multiprocessor hierarchical scheduling techniques provide the ground for composing real-time components, while guaranteeing the timing correctness of the composed system. A considerable deal of compositional real-time systems are embedded systems that operate on battery power. In such systems, reducing the power consumption is of paramount importance to increase the system lifetime. In this paper, we present our idea on reducing the energy consumption when performing hierarchical scheduling on multiprocessors. We formulate the problem, present the model and sketch the outline of the solution. Finally, we present a number of challenges which will be addressed in our work.

In our previous work, we have introduced an adaptive hierarchical scheduling framework as a solution for composing dynamic real-time systems, i.e., systems where the CPU demand of their tasks are subjected to unknown and potentially drastic changes during run-time. The framework uses the PI controller which periodically adapts the system to the current load situation. The conventional PI controller despite simplicity and low CPU overhead, provides acceptable performance. However, increasing the pressure on the controller e.g, with an application consisting of multiple tasks with drastically oscillating execution times, degrades the performance of the PI controller. Therefore, in this paper we modify the structure of our adaptive framework by replacing the PI controller with a fuzzy controller to achieve better performance. Furthermore, we conduct a simulation based case study in which we compose dynamic tasks such as video decoder tasks with a set of static tasks into a single system, and we show that the new fuzzy controller outperforms our previous PI controller.

The Multi Processor Periodic Resource (MPR) model has been proposed for modeling compositional real-time systems which run on a shared multi processor hardware. In this paper we extend the MPR model such that the execution of virtual processors (servers) is not assumed to be synchronized i.e., the servers can have different phases. We believe that relaxing the server synchronization requirement provides greater deal of compatibility for implementing such a compositional method on various hardware platforms. We derive the resource supply bound function of the extended MPR model using an algorithm. Furthermore, we suggest an approach to calculate an approximate supply bound function with lower computational complexity for systems where calculating their supply bound function is computationally expensive.

Hierarchical scheduling provides predictable timing and temporal isolation; two properties desirable in real-time embedded systems. In hierarchically scheduled systems, subsystems should receive a sufficient amount of CPU resources in order to be able to guarantee timing constraints of its internal parts (tasks). In static systems, an exact amount of CPU resource can be allocated to a subsystem. However, in dynamic systems, where execution times of tasks vary considerably during runtime, it is desirable to give a dynamic portion of the CPU given the current load situation. In this paper we present a feedback control approach for adapting the amount of CPU resource that is allocated to subsystems during run-time such that each subsystem receives sufficient resources while keeping the number of deadline violations to a minimum. We also show an example simulation where the controller adapts the budget of a subsystem.

Hierarchical scheduling provides a modular framework for integrating, scheduling and guaranteeing timing constraints of compositional real-time systems. In such a scheduling framework, all modules should receive a sufficient portion of the shared CPU to be able to guarantee timing constraints of their internal parts. In dynamic systems i.e., systems where the execution time of tasks are subjected to sudden and drastic changes during run-time, assigning fixed CPU portions to the modules is conducive to either low CPU utilization or numerous task deadline misses. In this paper, in order to address this problem, we propose an adaptive CPU allocation method which dynamically assigns CPU portions to the modules during run-time based on their current CPU demand. Besides, the presented approach is evaluated using a series of different simulations. In addition, we present a method for scheduling modules in situations when the CPU resource is not sufficient for scheduling all modules. We introduce the notion of module (subsystem) criticality, and in an overload situation we distribute the CPU resource based on the criticality of modules.