• Journal of information and communication convergence engineering
• /
• v.18 no.4
• /
• pp.222-229
• /
• 2020

Recent multi-core processors for smart devices use per-core dynamic voltage and frequency scaling (DVFS) that enables independent voltage and frequency control of cores. However, because the conventional task scheduler was originally designed for per-core DVFS disabled processors, it cannot effectively utilize the per-core DVFS and simply allocates tasks evenly across all cores to core utilization with the same CPU frequency. Hence, we propose a novel task scheduler to effectively utilize percore DVFS, which enables each core to have the appropriate frequency, thereby improving performance and decreasing energy consumption. The proposed scheduler classifies applications into two types, based on performance-sensitivity and allows a performance-sensitive application to have a dedicated core, which maximizes core utilization. The experimental evaluations with a real off-the-shelf smart device showed that the proposed task scheduler reduced 13.6% of CPU energy (up to 28.3%) and 3.4% of execution time (up to 24.5%) on average, as compared to the conventional task scheduler.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.497-500
• /
• 1988

The multi-task operating system called HRMTOS (HUNDAI Robot Multi-task Operating System) was developed for concurrent execution. HRMTOS consists of condition interpreter, queue constructor, task scheduler. Condition interpreter checks the status and condition of request, queue constructor makes queue according to the checked result by condition interpreter, and task scheduler finds the task that will be urgently executed by priority of queue after pending the current excuting task. HRMTOS could execute teaching, playback, monitoring function of multi-robot and could be used more effectively than other robot controllers.

• Journal of Internet Computing and Services
• /
• v.8 no.1
• /
• pp.71-78
• /
• 2007

In this paper, an effective task scheduling scheme was proposed for the flexible real time LINUX systems with the selection between EDF(earliest deadline first) and RMS(rate monotonic scheduling). It was known that many task scheduling schemes were analyzed according to the characteristics of scheduling schemes and the guarantee of an earliest deadline scheduler for process utilities.

• The KIPS Transactions:PartA
• /
• v.8A no.1
• /
• pp.16-26
• /
• 2001

This paper proposes an extended scheduler model that is an extension of the existing model proposed already in [4, 5], which consists of upper layer task scheduler and lower layer scheduling framework. However, in order to support aperiodic task scheduling, the task scheduler has been divided into two parts, such as periodic task control component and aperiodic task control component. Thus, the proposed model can support various bandwidth-preserving servers that can service aperiodic tasks. The model distinctly separates a classic monolithic kernel scheduler into several kernel components according to their functionality. This enables system developers to implement a new scheduling algorithm or aperiodic task server independent of complex low kernel mechanism, and reconfigure the system at need. In Real-Time Linux [6], we implemented the proposed scheduling framework representative scheduling algorithms, and server bandwidth-preserving servers on purpose to test. Throughout these implementations, we confirmed that a new algorithm or server could be developed independently without updates of complex low kernel modules. In order to verify efficiency of the proposed model, we measured the performance of several aperiodic task servers. The results showed this the performance of model, which even consisted of two hierarchical components and several modules, didnt have such high run-time overhead, and could efficiently support reconfiguration and scheduler development.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.12-18
• /
• 2021

A proportional share scheduler allocates CPU time to tasks and determines which task will be dispatched according to their priorities. In this paper, we investigate the correlation between the characteristics of applications and task priorities in the Linux Completely Fair Scheduler(CFS), which is one of the representative proportional share schedulers. We also propose a method of controlling the granularity of priority assignments according to the characteristics of applications. We implemented the proposed technique in a Linux system and confirmed the meaningful experimental results.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.4
• /
• pp.193-199
• /
• 2012

Virtualization allows multiple commodity operating systems to share on a single physical machine. Resource allocation among virtual machines is a key to determine virtual machine performance. To satisfy time-sensitive task on a domain, hypervisor needs to observe the resource requirements and allocates proper amount of CPU resources in a timely manner. In this paper, we propose a realtime credit scheduler for latency sensitive application on virtual machines. The key idea is to register a time event in the Xen hypervisor. Experiment result shows that the proposed scheme is superior to Credit scheduler.

• Journal of Korea Multimedia Society
• /
• v.14 no.7
• /
• pp.940-948
• /
• 2011

In this paper, we design and implement a task scheduler that considers real-time and fault tolerance in embedded system with a single processor. We propose a method how it can meet the deadlines of periodic tasks using RMS and complete the execution of aperiodic tasks by calculating surplus times from a periodic task set. And we describe a method how to recover of a transient fault task by managing backup time. We propose an important level of periodic tasks that can control the response time of periodic and aperiodic tasks. Finally, we analyse and evaluate the proposed methods by simulation.

• The KIPS Transactions:PartA
• /
• v.18A no.6
• /
• pp.255-264
• /
• 2011

A sensor network is a special network that makes physical data sensed by sensor nodes and manages the data. The sensor network is a technology that can apply to many parts of field. It is very important to transmit the data to a user at real-time. The core of the sensor network is a sensor node and small operating system that works in the node. TinyOS developed by UC Berkeley is a sensor network operating system that used many parts of field. It is event-driven and component-based operating system. Basically, it uses non-preemptive scheduler. If an urgent task needs to be executed right away while another task is running, the urgent one must wait until another one is finished. Because of that property, it is hard to guarantee real-time requirement in TinyOS. According to recent study, Priority Level Scheduler, which can let one task preempt another task, was proposed in order to have fast response in TinyOS. It has restrictively 5 priorities, so a higher priority task can preempt a lower priority task. Therefore, this paper suggests Preemptive EDF(Earliest Deadline First) Scheduler that guarantees a real-time requirement and reduces average respond time of user tasks in TinyOS.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.4
• /
• pp.201-212
• /
• 2002

This paper proposes a reconfigurable scheduler model that can support various real-time scheduling algorithms. The proposed model consists of two hierarchical upper and lower components, task scheduler and scheduling framework, respectively. The scheduling framework provides a job dispatcher and software timers. The task scheduler implements an appropriate scheduling algorithm, which supports a specific real-time application, based on the scheduling framework. If system developers observe internal kernel interfaces to communicate between two hierarchical components, they can implement a new scheduling algorithm independent of complex low kernel mechanism. Once a task scheduler is developed, it can be reused in a new real-time system in future. In Real-Time Linux (5), we implemented the proposed scheduling framework and several representative real-time scheduling algorithms. Throughout these implementations, we confirmed that a new scheduling algorithm could be developed independently without updates of complex low kernel modules. In order to confirm efficiency of the proposed model, we measured the performance of representative task schedulers. The results showed that the scheduling overhead of proposed model, which has two separated components, is similar to that of a classic monolithic kernel scheduler.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.452-457
• /
• 2017

Linux is a general-purpose operating system that supports several schedulers, allowing different schedulers to coexist. In addition, Linux uses the Control Group (cgroup) to reserve CPU resources for task groups that follow the real-time (SCHED_FIFO, SCHED_RR) and non-real-time (SCHED_NORMAL) scheduler policies, except for the deadline scheduler (SCHED_DEADLINE). The cgroup performs the schedulability analysis to guarantee the reserved CPU resource as much as possible. However, current implementation of the schedulability analysis does not distinguish between deadline tasks and real-time tasks. Therefore, if these deadline tasks and real-time task groups coexist, there is a case where the resource reservation for the real-time task group is rejected. In this paper, we analyze the problems in the schedulability analysis for real-time task groups of Linux cgroups and propose patches to solve these problems.