Constant Bandwidth Server Research Articles

ReTSN: Resilient and Efficient Time-Sensitive Network for Automotive In-Vehicle Communication

Time-sensitive networking (TSN) is being widely investigated to provide Ethernet capabilities for in-vehicle backbone communication. However, the gate control list (GCL), as a simple mechanism for achieving timing determinism for safety-critical traffic (ST) frames with hard deadlines, is too rigid to handle the intrinsic timing uncertainty of automated driving systems (ADSs). Due to the complexity and the unpredictable operating environment, there can be delayed ST frames that can disrupt the solidly fixed timing behavior. In this work, we present one novel approach to effectively use bandwidth resources to deal with delayed ST frames, which cannot be handled by a traditional fixed GCL, and the discarding of them should be reduced to improve the system’s integrity. An acceptance test is implemented to report to the application layer when an ST frame will miss its deadline and hence be rejected, i.e., prevented from entering the switch. To further improve the efficiency of bandwidth usage, we investigate how to improve the performance of the more important Class A frames in an audio-video-bridging (AVB) switch, which adopts a credit-based shaper mechanism, and we propose a constant bandwidth server to replace the credit-based shaper while taking fairness into consideration. Evaluation with extensive experiments shows that both resilience and efficiency of the TSN are significantly enhanced compared with a credit-based shaper, especially when the traffic load is relatively high. For the delayed ST frames and event-triggered traffic, our approach is able to schedule more than the solution using the AVB switch even with a high network load.

Controlador difuso para compensar cargas de comunicación en sistemas en tiempo real

Se presenta un administrador de recursos (RM) difuso para compensar las cargas de comunicación en sistemas en tiempo real. El diseño del RM se basa en un nuevo modelo de Servidor de Ancho de Banda Constante (CBS) que se encarga, a través de una plataforma virtual, de asignar tiempo de proceso a las tareas de mayor prioridad cuando existe capacidad disponible. Si se asume que cada aplicación puede ser ejecutada con diferentes niveles de servicio sin que este esté por debajo de un límite mínimo, se propone una aproximación difusa que permite actualizar de manera gradual los tiempos de proceso asignados a cada tarea. Esta aproximación permite compensar el comportamiento no lineal en las solicitudes de tiempo de proceso. El RM aumenta o disminuye la plataforma virtual para cada aplicación y le asigna un presupuesto máximo de tiempo de proceso, mismo que la aplicación usa gradualmente y que se reasigna al agotarse, sin por ello afectar el desempeño del resto de las aplicaciones. El esquema se auto-ajusta cuando ocurren a cambios repentinos en los requerimientos de tiempo de proceso de las aplicaciones.

Dynamic partitioned scheduling of real-time tasks on ARM big.LITTLE architectures

This paper presents Big-LITTLE Constant Bandwidth Server (BL-CBS), a dynamic partitioning approach to schedule real-time task sets in an energy-efficient way on multi-core platforms based on the ARM big.LITTLE architecture. BL-CBS is designed as an on-line and adaptive scheduler, based on a push/pull architecture that is suitable to be incorporated in the current SCHED_DEADLINE code base in the Linux kernel. It employs a greedy heuristic to dynamically partition the real-time tasks among the big and LITTLE cores aiming to minimize the energy consumption and the migrations imposed on the running tasks. The new approach is validated through the open-source RT-Sim simulator, which has been extended integrating an energy model of the ODROID-XU3 board, fitting tightly the power consumption profiles for the big and LITTLE cores of the board. An extensive set of simulations have been run with randomly generated real-time task sets, leading to promising results.

An adaptive, utilization-based approach to schedule real-time tasks for ARM big.LITTLE architectures

ARM big.LITTLE architectures are spreading more and more in the mobile world thanks to their power-saving capabilities due to the use of two ISA-compatible islands, one focusing on energy efficiency and the other one on computational power. This architecture makes the problem of energy-aware task scheduling particularly challenging, due to the number of variables to take into account and the need for having lightweight mechanisms that can be readily computed in an operating system kernel scheduler. This paper presents a novel task scheduler for big.LITTLE platforms, combining the well-known Constant Bandwidth Server algorithm with a power-aware per-job migration policy. This achieves real-time adaptation of the CPU islands' frequencies based on the individual cores' overall utilization, as available in the scheduler thanks to the use of the resource reservation paradigm. Preliminary results obtained by simulations based on modifications to the open-source RTSim tool show that the proposed technique is able to achieve interesting performance/energy trade-offs.

Energy aware mixed tasks scheduling in real-time systems

We address the problem of scheduling mixed tasks which consist of n hard real time periodic tasks with shared resources and soft aperiodic tasks and consider two conflicting goals: reducing energy consumption and decreasing response time of aperiodic tasks. Firstly, we compute the optimal speed of periodic tasks and present a novel static mixed task scheduling (SMTS) algorithm. It schedules periodic tasks with the optimal speed and aperiodic tasks with maximum processor speed. Secondly, a dynamic mixed task scheduling (DMTS) algorithm which can reclaim dynamic slack time generated from periodic tasks and the constant bandwidth server to reduce energy consumption is proposed. In addition, it combines dynamic voltage scaling and dynamic power management techniques. Finally, we prove that the DMTS algorithm is feasible. The experimental results show that the DMTS algorithm reduces average 7.18% and 53.66% energy consumption × response time compared with SMTS algorithm and baseline algorithm, respectively.

Function Allocation and Bandwidth Reservation for Mixed-critical Adaptive Software Systems

The new AutoSAR adaptive platform makes mixed-critical automotive systems able to adapt themselves in response to hardware and software failures at runtime. However, mapping functions of these automotive systems and reserving bandwidth for them are still major challenges. In this paper, we propose a model-based approach for mapping functions of an automotive system to its hardware nodes and reserving their bandwidth. To do so, an architecture description language for automotive systems (i.e. EAST-ADL) is used to design an embedded system, and to specify its timing requirements. The design model is then used for identifying functions allocation and their bandwidth in different system configurations. To schedule the critical functions of the system, the Earliest Deadline First (EDF) is used, while the Constant Bandwidth Server (CBS) is used for scheduling the non-critical functions. The quality of service for the non-critical functions is determined by their reserved bandwidth. In addition, a Tabu search-based approach is used for mapping the system functions to hardware nodes. Furthermore, there is a temporal isolation between the critical and non-critical functions. Thus, overruns of the non-critical functions do not affect the timing guarantees of the critical functions, and the quality of service for the non-critical functions is maximized.

Low Power Scheduling Algorithm for Mix Tasks Based on Constant Bandwidth Server

Low Power Scheduling Algorithm for Mix Tasks Based on Constant Bandwidth Server

Constant bandwidth server revisited

The Constant Bandwidth Server (CBS) is an algorithm for providing temporal protection and real-time guarantees to real-time sporadic tasks. Recently, an implementation of this algorithim called SCHED_DEADLINE has been included in the Linux kernel. Therefore, the CBS algorithm is now used to serve more generic tasks than do not obey to the classical sporadic task model. One important type of tasks which was not considered by the original CBS algorithm is the so called "self-suspending task model", where a task instance can suspend itself waiting for an external event. Even if the original algorithm is adapted so that the temporal protection property continues to hold, it is difficult for developers to provide guarantees and to select the most appropriate server parameters for such tasks. This paper investigates the problem of using the CBS algorithm for serving self-suspending tasks, by analysing it from a theoretical point of view and showing how to select the server parameters (budget and periods) for self-suspending tasks. Finally, the effectiveness of these proposals is shown through both simulations and real experiments on Linux / SCHED_DEADLINE.

Task Scheduling of Cloud Computing in Weapon Network System

In recent years, the rapid development of cloud computing brings significant innovation in the whole IT industry. For the local tasks scheduling on each computational node of the top model of weapon network, an open task scheduling framework was introduced a task accept control scheme based on the tasks based on load balancing, quality of service (QoS) and an improved constant bandwidth server algorithm was presented. The result of simulation shows that the scheduling policies can improve the schedule speed when the number of tasks increases and can meet the demand better for the real time requirementsof the tactical training evaluation system for complexity and Large-scale.

Optimal Scheduling Algorithm in Vehicular Real Time System

In this paper, we mainly discuss the optimal scheduling algorithms in Low-end ECU and In-vehicle information system. For Low-end ECU, we propose an optimal scheduling algorithm. This algorithm can guarantee schedulability of mandatory parts in periodic tasks, guarantee aperiodic tasks and minimize the average scheduling error of optional parts in periodic tasks. In-vehicle information system is a multi-constraint real-time and non-real-time application coexisted application system. To meet the system scheduling requirements, a feedback algorithm based on the Constant Bandwidth Server is designed to control the fraction of CPU bandwidth allocation and a precise mathematical model is provided. Finally, the experimental results prove the effectiveness of our framework and algorithm.

Scheduling and thread management with RTEMS

The goal of a real-time operating system (RTOS) is to support real-time and embedded system (RT/ES) application development, which differ from general-purpose applications because of the size, weight, and power (SWaP) and timing constraints imposed by embedded applications. Useful RTOS features include real-time thread scheduling, thread communication, synchronization, interrupt handling, memory management, file systems, device drivers, networking, and debugging support. The Real-Time Executive for Multi-processor Systems (RTEMS) is a free and open-source RTOS that supports over a dozen processor architecture families and over 150 embedded system boards. RTEMS is designed to support embedded applications with stringent real-time requirements while being compatible with open standards such as POSIX. RTEMS includes optional services such as TCP/IP networking and file systems while still offering minimum executable sizes under 20 KB in useful configurations. One of the primary functions of an RTOS is to select threads that can obtain access to resources such as shared memory and processor time. RTEMS uses multiple algorithms to manage both waiting threads and those ready to execute. The thread execution schedulers include the traditional RTOS round robin and deterministic priority schedulers, rate monotonic, earliest deadline first (EDF), constant bandwidth server (CBS), and simple SMP scheduling algorithms. The RTEMS scheduling framework allows the application developer to select the thread scheduling algorithm that best meets the application's space and time requirements. ÂăWe will present how this framework can be used by researchers to integrate their own scheduling algorithm into RTEMS and test it using a scheduling simulator before deploying it on target hardware.

Task migration for fault-tolerance in mixed-criticality embedded systems

In this paper we are interested in mixed-criticality embedded applications implemented on distributed architectures. Depending on their time-criticality, tasks can be hard or soft real-time and regarding safety-criticality, tasks can be fault-tolerant to transient faults, permanent faults, or have no dependability requirements. We use Earliest Deadline First (EDF) scheduling for the hard tasks and the Constant Bandwidth Server (CBS) for the soft tasks. The CBS parameters determine the quality of service (QoS) of soft tasks. Transient faults are tolerated using checkpointing with rollback recovery. For tolerating permanent faults in processors, we use task migration, i.e., restarting the safety-critical tasks on other processors. We propose a Greedy-based online heuristic for the migration of safety-critical tasks, in response to permanent faults, and the adjustment of CBS parameters on the target processors, such that the faults are tolerated, the deadlines for the hard real-time tasks are satisfied and the QoS for soft tasks is maximized. The proposed online adaptive approach has been evaluated using several synthetic benchmarks and a real-life case study.

A New Slack Reclaiming Algorithm for Real-time Systems

Real-time applications are ubiquitous in generalpurpose computing environments, while the real-time systems are growing in complexity. Thus in these hybrid real-time systems, schedulers must guarantee that all hard real-time jobs be completed before their deadlines and improve QoS of soft real-time tasks as much as possible. Towards this goal we have proposed a new slack reclaiming algorithm for server-based real-time systems, and have also implemented it in a real time emulator (RTSIM). This algorithm, named HBASH, which enhances the Constant Bandwidth Server (CBS) by slack reclaiming, allocates slack generated from the running process to the task that needs the slack most, and then this selected task will be scheduled immediately. Hence the algorithm is able to make full use of slack and reduce the response time of soft realtime tasks as much as possible. In this paper, we proved that our algorithm does not violate the schedulability of tasks, and we also evaluated the performance of this algorithm. The experimental results demonstrate that HBASH outperforms other slack reclaiming algorithms and improves soft real-time performance significantly.

Improving the schedulability of soft real-time open dynamic systems: The inheritor is actually a debtor

This paper presents the Clearing Fund Protocol, a three layered protocol designed to schedule soft real-time sets of precedence related tasks with shared resources. These sets are processed in an open dynamic environment. Open because new applications may enter the system at any time and dynamic because the schedulability is tested on-line as tasks request admission. Top-down, the three layers are the Clearing Fund, the Bandwidth Inheritance and two versions of the Constant Bandwidth Server algorithms. Bandwidth Inheritance applies a priority inheritance mechanism to the Constant Bandwidth Server. However, a serious drawback is its unfairness. In fact, a task executing in a server can potentially steal the bandwidth of another server without paying any penalty. The main idea of the Clearing Fund Algorithm is to keep track of processor-time debts contracted by lower priority tasks that block higher priority ones and are executed in the higher priority servers by having inherited the higher priority. The proposed algorithm reduces the undesirable effects of those priority inversions because the blocked task can finish its execution in its own server or in the server of the blocking task, whichever has the nearest deadline. If demanded, debts are paid back in that way. Inheritors are therefore debtors. Moreover, at certain instants in time, all existing debts may be waived and the servers are reset making a clear restart of the system. The Clearing Fund Protocol showed definite better performances when evaluated by simulations against Bandwidth Inheritance, the protocol it tries to improve.

Reservation-based feedback scheduling of MPC tasks

Abstract A reservation-based feedback scheduling (FS-CBS) of a set of model predictive control (MPC) tasks is presented to optimize the global control performance subject to limited computational resource. Implemented as anytime algorithm, MPC task allows computation time to be traded for control performance. Each MPC task is assigned with a constant bandwidth server (CBS), whose reserved processor time is adjusted dynamically. The FS-CBS is shown robust against the varying of execution time of MPC tasks at runtime. Simulation results illustrate its effectiveness.

Optimal feedback scheduling of model predictive controllers

Model predictive control (MPC) could not be reliably applied to real-time control systems because its computation time is not well defined. Implemented as anytime algorithm, MPC task allows computation time to be traded for control performance, thus obtaining the predictability in time. Optimal feedback scheduling (FS-CBS) of a set of MPC tasks is presented to maximize the global control performance subject to limited processor time. Each MPC task is assigned with a constant bandwidth server (CBS), whose reserved processor time is adjusted dynamically. The constraints in the FS-CBS guarantee scheduler of the total task set and stability of each component. The FS-CBS is shown robust against the variation of execution time of MPC tasks at runtime. Simulation results illustrate its effectiveness.

Efficient reclaiming in reservation-based real-time systems with variable execution times

We present a general CPU scheduling methodology for managing overruns in a real-time environment, where tasks may have different criticality, flexible timing constraints, shared resources, and variable execution times. The proposed method enhances, the constant bandwidth server (CBS) by providing two important extensions. First, it includes an efficient bandwidth sharing mechanism that reclaims the unused bandwidth to enhance task responsiveness. It is proven that the reclaiming mechanism does not violate the isolation property of the CBS and can be safely adopted to achieve temporal protection even when resource reservations are not precisely assigned. Second, the proposed method allows the CBS to work in the presence of shared resources. The enhancements achieved by the proposed approach turned out to be very effective with respect to classical CPU reservation schemes. The algorithm complexity is O(ln N), where N is the number of real-time tasks in the system, and its performance has been experimentally evaluated by extensive simulations.

Resource Reservation in Dynamic Real-Time Systems

This paper focuses on the problem of providing efficient run-time support to multimedia applications in a real-time system, where different types of tasks (characterized by different criticality) can coexist. Whereas critical real-time tasks (hard tasks) are guaranteed based on worst-case execution times and minimum interarrival times, multimedia tasks are served based on mean parameters. A novel bandwidth reservation mechanism (the constant bandwidth server) allows real-time tasks to execute in a dynamic environment under a temporal protection mechanism, so that each task will never exceed a predefined bandwidth, independently of its actual requests. The paper also discusses how the proposed server can be used for handling aperiodic tasks efficiently and how a statistical analysis can be applied to perform a probabilistic guarantee of soft tasks. The performance of the proposed method is compared with that of similar service mechanisms (dynamic real-time servers and proportional share schedulers) through extensive simulation experiments.