• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.1-7
• /
• 2002

Since multimedia data such as video and audio data are displayed within a certain time constraint, their computation and manipulation should be handled under limited condition. Traditional real-time scheduling algorithms could not be directly applicable, because they are not suitable for multimedia scheduling applications which support many clients at the same time. Rate Regulating Proportional Share Scheduling Algorithm is a scheduling algorithm considered the time constraint of the multimedia data. This scheduling algorithm uses a rate regulator which prevents tasks from receiving more resource than its share in a given period. But this algorithm loses fairness, and does not show graceful degradation of performance under overloaded situation. This paper proposes a new modified algorithm, namely Modified Proportional Share Scheduling Algorithm considering the characteristics of multimedia data such as its continuity and time dependency. Proposed scheduling algorithm shows graceful degradation of performance in overloaded situation and the reduction in the number of context switching. Furthermore, a new evaluation method is proposed which can evaluate the flexibility of scheduling algorithm.

• Journal of Internet Computing and Services
• /
• v.9 no.3
• /
• pp.59-67
• /
• 2008

New system solves scheduling problem in medical services. The existing scheduling system by FCFS is for a hospital but new system expresses the condition of a hospital and the profit of separate system's parties by the automated negotiation. This system expresses user preference time as a priority number and is designed that the schedule is changed according to the priority number with a negotiation strategy for a patient. And a hospital makes a schedule according to the policy. The system supports customer satisfaction in medical services by considering not only equipment efficiency but also the patent waiting time unlike the existing system considering the idle time for a equipment.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.116-126
• /
• 2015

In a distributed heterogeneous computing system, the performance of a parallel application greatly depends on its task scheduling algorithm. Therefore, in order to improve the performance, it is essential to consider some factors that can have effect on the performance of the parallel application in a given environment. One of the most important factors that affects the total execution time is a critical path. In this paper, we propose the CLTS algorithm for a task scheduling. The CLTS sets the priorities of all nodes to improve overall performance by applying leveling method to improve parallelism of task execution and by reducing the delay caused by waiting for execution of critical nodes in priority phase. After that, it conditionally uses insertion based policy or duplication based policy in processor allocation phase to reduce total schedule time. To evaluate the performance of the CLTS, we compared the CLTS with the DCPD and the HCPFD in our simulation. The results of the simulations show that the CLTS is better than the HCPFD by 7.29% and the DCPD by 8.93%. with respect to the average SLR, and also better than the HCPFD by 9.21% and the DCPD by 7.66% with respect to the average speedup.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.86-88
• /
• 2000

멀티미디어 태스크는 기존 범용 운영 체제의 시분할 스케줄러에서 만족시킬 수 없는 시간적 요구사항을 가진다. 이런 태스크를 기존의 시분할 태스크와 함께 서비스하기 위해서는 새로운 스케줄링 프레임워크가 필요하다. FQ(Fair Queueing)은 태스크의 공유비율에 비례하여 자원을 할당하는 방법으로 이질적인 태스크(멀티미디어 태스크, 일반 시분할 태스크)가 공존하는 개방적인 환경에서의 스케줄링 정책으로 적합하다는 특징이 있다. 본 논문에서는 FQ의 종류인 WFQ(Weighted Fair Queueing)를 개선하여 하나의 스케줄러에서 다른 두 부류의 태스크를 모두 처리하는 요구비율 기반의 프로세서 예약 기법을 제안한다. 실시간 태스크와 시분할 태스크를 처리하기 위해서 실시간 부류의 태스크를 우선적으로 배치하고, 실시간 부류 태스크의 실행 사이에 시분할 태스크를 스케줄하여 실시간 태스크에 대해서 보장된 서비스를, 시분할 태스크에 대해서는 이 태스크에 할당된 예약만큼의 프로세서 시간을 제공한다. 모의 실험에서는 제안한 프로세서 예약 방식이 실시간 태스크와 시분할 태스크를 효율적으로 처리하며 기존의 WFQ보다 더 안정적임을 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.76-78
• /
• 2002

최근 멀티미디어 데이터 서버로 리눅스 시스템을 쓰는 경우가 많아 졌다. 이 경우, 멀티미디어 데이터에 관한 서비스를 효율적으로 제공할 수 있어야 한다. 이를 위하여, 본 논문에서는 기존의 리눅스 scheduling 방식이 갖는 단일레벨 run-queue 구조를 변형한 다중레벨 run-queue를 제안하였다. 기존의 단일레벨 run-queue에서는 queue 내에 프로세스의 수가 많아질수록 검색시간이 길어지는 단점이 있다. 본 논문에서는 기존의 run-queue를 여러 단계로 나누고, scheduling 과정에서 상위 queue부터 프로세스가 존재하는지를 조사하도록 스케줄러를 변형하였다. 따라서, 상위 queue에 프로세스가 있는 경우에는 하위의 queue는 더 이상 조사한 필요가 없게 되므로. 결과적으로 검색시간을 줄일 수 있게 된다. 한편, 다중 레벨의 run-queue를 사용할 경우, 이를 관리하기 위한 오버헤드가 별도로 발생한다. 본 논문에서는, 제안한 다중레벨의 run-queue 시스템의 성능을 최적화하기 위하여, queue의 적절한 개수 선정 및 각 프로세스를 어떤 queue에 넣을 것인지를 결정하는 것이 성능에 미치는 영향에 대하여 실험적으로 연구하여 새로운 스케줄러의 성능을 기존 스케줄러와 비로 분석하였다. 본 논문에서 제안한 멀티레벨 run-queue를 사용함으로써, 각 queue의 스케줄링 정책(policy)과 관련 파라메터 간을 독자적으로 변화시킬 수 있다. 따라서, 여러 가지 상황에 적합한 스케줄링을 각각의 경우에 맞게 최적화하는 것이 손쉬워 지므로 여러 분야에서 매우 유용하게 쓰일 것이다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.9
• /
• pp.113-119
• /
• 2005

The methods that are used for receiving data from attached devices under real-time preemptive multi-task operating system (OS) by general processors can be categorized as polling and interrupt driven. The technical approach to these methods may be different due to the application specific scheduling policy of the OS and the programming architecture of the flight software. It is one of the most important requirements on the development of the flight software to process the data received from satellite subsystems or components with the exact timeliness and accuracy. This paper presents the analysis of the I/O method of device related scheduling mechanism and the reliable data I/O methods between processor and devices.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.205-216
• /
• 2022

One of the many tools used for distributed deep learning training is Kubeflow, which runs on Kubernetes, a container orchestration tool. TensorFlow jobs can be managed using the existing operator provided by Kubeflow. However, when considering the distributed deep learning training jobs based on the parameter server architecture, the scheduling policy used by the existing operator does not consider the task affinity of the distributed training job and does not provide the ability to dynamically allocate or release resources. This can lead to long job completion time and low resource utilization rate. Therefore, in this paper we proposes a new operator that efficiently schedules distributed deep learning training jobs to minimize the job completion time and increase resource utilization rate. We implemented the new operator by modifying the existing operator and conducted experiments to evaluate its performance. The experiment results showed that our scheduling policy improved the average job completion time reduction rate of up to 84% and average CPU utilization increase rate of up to 92%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.202-204
• /
• 2003

경성 실시간 시스템(Hard Real-Time System)어서는 주기 태스크들의 엄격한 마감시간(Deadline) 보장이 시스템의 성능을 좌우한다. 본 논문에서는 CPU의 이용률(Utilization)이 높아 비율단조 정책으로는 마감시간을 보장 할 수 없는 주기 태스크들을 위해 확장된 스케줄 가능성 검사를 통해 수행할 태스크들의 공통 주기(L.C.M : Least Common Multiple)내에서 EDF(Earliest-Deadline First) 정책을 기반으로 마감시간 보장 수행패턴(Feasible Pattern)을 찾고, 이를 참조하여 우선순위를 고려하지 않고 태스크들을 강제 수행할 수 있게 하는 비율단조 기반의 스케쥴링 기법을 제안한다. EDF를 기반으로 생성된 패턴은 EDF 정책의 특성에 따라 CPU의 이용률을 100% 까지 가능하게 하며 패턴을 참조하여 강제 수행함으로써 EDF 정책이 갖는 실행시간 스케쥴링 오버헤드를 없앨 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.377-378
• /
• 2008

• Journal of Digital Convergence
• /
• v.12 no.3
• /
• pp.227-235
• /
• 2014

Mobile virtualization is an approach to mobile device management in which two virtual platforms are installed on a single wireless device. A smartphone, a single wireless device, might have one virtual environment for business use and one for personal use. Mobile virtualization might also allow one device to run two different operating systems, allowing the same phone to run both RTOS and Android apps. In this paper, we propose the techniques to virtualize the cores of a multicore, allowing the reassign any number of vCPUs that are exposed to a OS to any subset of the pCPUs. And then we also propose the real-time scheduling method to assigning the vCPUs to the pCPU. Suggested technology in this paper solves problem that increases time of real-time process when interrupt are handled, and is able more to fast processing than previous algorithm.