• Smart Media Journal
• /
• v.5 no.4
• /
• pp.18-25
• /
• 2016

Virtualized hardware resources provides efficiency in use and easy of management. Based on the benefits, virtualization techniques are used to build large server clusters and cloud systems. The performance of a virtualized system is significantly affected by the virtual machine scheduler. However, the existing virtual machine scheduler have a problem in that the I/O response is reduced in accordance with the scheduling delay becomes longer. In this paper, we introduce the Loan/Redemption mechanism of a virtual machine scheduler in order to improve the responsiveness to I/O events. The proposed scheme gives additional credits for to virtual machines and classifies the task characteristics of each virtual machine by analyzing the credit consumption pattern. When an I/O event arrives, the scheduling priority of a virtual machine is temporally increased based on the analysis. The evaluation based on the implementation shows that the proposed scheme improves the I/O response 60% and bandwidth of virtual machines 62% compared to those of the existing virtual machine scheduler.

• Journal of Korea Game Society
• /
• v.16 no.4
• /
• pp.57-68
• /
• 2016

As the size of the data used in the game application increase gradually, the physical resources of game server grow. Accordingly, it is necessary to/it is required to introduce I/O virtualization in game server to improve I/O performance of the server. But it is difficult to ensure high responsiveness in game server where I/O delay change from time to time. To maximize the benefit of I/O virtualization, guaranteeing I/O response time is very important and it is necessary to have I/O scheduling techniques to manage the I/O latency in the order of priority of virtual machines. In this paper, we propose an efficient delay-constrained scheduling algorithm in a virtualization environment to ensure maximum I/O latency. In addition, a reduced amount of loss of the packet was found to increase the fairness of scheduling in the experiments with the proposed scheme.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.11
• /
• pp.379-384
• /
• 2016

NAND flash storage is widely used for computer systems, because of it has faster response time, lower power consumption, and larger capacity per unit area than hard disk. However, currently used I/O scheduler in the operating system is optimized for characteristics of the hard disk. Therefore, the conventional I/O scheduler includes the unnecessary overhead in the case of the NAND flash storage to be applied. Particularly, when the write requests performed intensively, garbage collection is performed intensively. So, it occurs the problem that the processing of the I/O request delay. In this paper, we propose the new I/O scheduler to solve the problem of garbage collection performs intensively, and to optimize for NAND flash storage. In the result of performance evaluation, proposed scheme shows an improvement the user responsiveness by reducing 1% of the average read response time and 78% of the maximum response time.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.2
• /
• pp.97-102
• /
• 2019

Multi-queue I/O block layer has been recently employed in Linux kernel to support fast storage devices such as NVMe SSDs, but it lacks differentiated I/O services yet. In this paper, we propose an I/O scheduling scheme that can improve the user responsiveness of foreground processes, which are closely related to user satisfaction. To this end, we redesign the existing multi-queue block layer to classify the I/O requests from foreground processes and schedule them by exploiting the feature of NVMe interface. Experimental results show that latency and launch time of the foreground processes have been significantly improved compared to original Linux kernel.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.21 no.6
• /
• pp.7-16
• /
• 1984

This paper describes the overall procedure of the development of a digital audio response system. It has been developed specifically as an answering system to the inquiries of telephone numbers from subscribers. The system has been realized based on the residual excited linear prediction (RELP) algorithm that incorporates a pitch predictive loop. Its major advantage over other similar systems is that it produces high quality of synthetic speech, although its memory size is relatively small. The hardware which consists of a speech synthesizer, a controller and an I/O part has been constructed using 2900 series bit-slice microprocessors and an INTEL 8085 microprocessor. The system is capable of real time processing, reliable, and adaptable to other applications.

• Journal of Internet Computing and Services
• /
• v.3 no.5
• /
• pp.95-106
• /
• 2002

In current storage system environment, we use disk mirroring or Chained-declustering scheme to improve data availability and reliability. If disk error is occurred when these schemes are used. we need efficient recovery schemes for these situations. In this paper, it is proposed that a recovery method of disk mirroring that guarantees I/O performance similar to normal state during disk failure, Also, we execute performance evaluation for our recovery scheme and existing schemes in various environments. We show through the simulation that our algorithm outperforms the classic schemes in terms of I/O response time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.889-892
• /
• 2008

반도체 저장장치의 발달로 인하여 기존의 HDD를 대체할 SSD의 출시와 이를 위한 기술개발 및 성능 향상이 가속화 되고 있다. 이 논문에서는 현재의 운영체제들이 HDD 를 기반으로 최적화하여 제작이 되어 있는데 이러한 최적화 기법이 SSD에서도 유효한지에 대해서 알아보았다. 특히 I/O스케줄러를 변경하여 SSD에서 실험한 결과 SSD의 빠른 응답속도와 대역폭으로 인해 4개의 I/O스케줄러에서 비슷한 성능을 보이는 것으로 측정되었다. 또한 미리읽기기능과 WB에 대해서는 HDD와 마찬가지로 SSD의 성능을 향상 시킬 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.23-31
• /
• 2011

Recently, Solid state disk is mainly used because this device has lower power consumption as well as higher response time. But it features higher price and lower performance at delete and write operations compared with HDD. To compensate this defect, Hybrid hard disk with internal non-volatile flash memory was issued. This NVCache is used as a kind of cache for disk blocks. In this paper, an I/O scheme for H-HDD is proposed for improving low power consumption as well as response time. Our method is to use this NVCache as read cache mainly and write cache when write requests are concentrated. In read cache operation, disk blocks with higher priority determined on basis of time as well as spatial localities are prefetched, which can improve response time. The write operation is conducted only at write peak time as disk spindle up costs higher battery power as well as response time. Experiments results show that the suggested method can improve response time of H-HDD and lower the power consumption.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.12-15
• /
• 2016

데이터베이스 시스템의 트랜잭션 로깅이나 파일 시스템의 저널링에서 데이터 저장시 입출력 동기화(Synchronous I/O)는 올바른 프로르램 동작에 필수적이다. 하지만 입출력 동기화로 인한 프로그램의 지연 혹은 기다림은 응용 프로그램 성능의 저하를 가져온다. 본 논문에서는 차세대 저장장치인 비휘발성 메모리를 사용하여 지속성을 보장하며 쓰기 연산의 응답성을 개선하는 사용자 수준의 스토리지 모듈을 제안하고 기존의 동기화된 쓰기 연산과 성능을 비교하였다. 특히 멀티코어 환경에서 동시에 들어오는 여러 입출력 쓰기 연산 요청에 대하여 효율적으로 처리하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.408-410
• /
• 2000

인터넷 사용자의 급격한 증가로 인한 네트웍 응답 시간의 지연이 가속화되고 있으며 이에 대한 대책으로 캐쉬 서버(프락시 서버)의 사용이 대두되고 있다. 그러나 캐쉬 서버의 사용은 처리 요청이 집중에 따른 또 하나의 병목 현상을 일으킬 수 있다. 이에 따라 다중 프락시 서버를 이용하는 연구들이 활발히 진행되어 왔으나 기존의 연구들은 분산 알고리즘을 수행하는 다중 프락시 서버를 이용하는 연구들이 활발히 진행되어 왔으나 기존의 연구들은 분산 알고리즘을 수행하는 다중 프락시 서버에 편중되어 있으며 캐쉬 서버가 일반 웹 서버와 다른 점(웹 오브젝트를 디스크에 저장하는 일)을 간과하여 캐쉬 서버 자체의 성능을 효과적으로 개선하지 못하고 있다. 따라서, 요청 폭주 시에 캐쉬 미스 등의 처리에 있어서 비효율성을 나타내고 있다. 본 연구에서는 병목 현상을 일으키는 요인을 분석하고 이를 바탕으로 프락시 서버를 재구성하여 실험을 통해 이 시스템의 효율성을 분석한다.