• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.989-992
• /
• 2000

ATM 스위치로 많이 이용되는 다단계 상호연결 네트워크(MIN)는 self-routing 및 one-to-one 연결 특성을 가진 블록킹 네트워크로써 셀 전송시 충돌이 일어날 수 있다. 따라서 버퍼를 갖는 스위치를 고려하게 된다. 본 논문에서는 스위치의 내부에 다중경로를 제공하는 입력버퍼를 이용하여 각 스위치의 입력포트에서 출력포트로의 경로를 확장시킨 스위치 구조 및 네트워크의 성능 향상에 대하여 언급한다. 이를 위해 네트워크의 stage간 상호연결 패턴이 buddy 및 constrained reachability 특성에 따른 경로설정 구조를 기본으로 이용한다. 그리고 입력버퍼 스위치 구조의 문제점인 HOL 블록킹의 방지 및 오류허용 기능을 향상시킬 수 있는 다중경로 버퍼를 갖는 ATM 스위치 구조를 제안하고, 시뮬레이션을 통해 그 성능을 분석한다.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1216-1222
• /
• 2016

The advent of large-scale web services has resulted in gradual increase in the amount of data used in those services. These big data are managed efficiently by DBMS such as MySQL and MariaDB, which use InnoDB engine as their storage engine, since InnoDB guarantees ACID and is suitable for handling large-scale data. To improve I/O performance, InnoDB caches data and index of its database through a buffer pool. It also supports multiple buffer pools to mitigate lock contentions. However, the multiple buffer pool scheme leads to the additional data consistency overhead. In this paper, we analyze the overhead of the multiple buffer pool scheme. In our experimental results, although multiple buffer pool scheme mitigates the lock contention by up to 46.3%, throughput of DMBS is significantly degraded by up to 50.6% due to increased disk I/O and fsync calls.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.9
• /
• pp.36-48
• /
• 1999

Controlled transfer (CT) service has been recently proposed as a new ATM transfer capability for high-speed data applications, which used a credit-based flow control. This paper investigates buffer allocation schemes for CT service and proposes an improved dynamic bugger allocation scheme. In order to improve the responsiveness to a congestion, the proposed method is considered the load factor of a link when determining the amounts of virtual connection (VC)s buffer allocation. Also, in this paper we compare the performance of the proposed method with those of the existing buffer allocation methods such as flow controlled virtual channels (FCVC) and zero queueing flow control (ZQFC) through simulation. Simulation results show tat the proposed scheme exhibits a better performance than the existing schemes in terms of throughput, fairness, queue length and link utilization.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.1
• /
• pp.33-39
• /
• 1998

A queueing model for performance evaluation of finite buffered inter-node communication system is proposed in this paper. Each components are modeled as M/M/I/B queues to obtain the steady state probabilities and ar-rival rate and to analyze finite buffer behavior, The overall sysrem is integrated as series queues with blocking. Average delay and throughput are the performance measures studied in this analysis. The analytical results are first validated through simulation. Next, the effect of buffer length is discussed using the proposed model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.139-141
• /
• 2005

본 논문에서는 JPEG 파일의 구조를 먼저 살펴하고, MS Windows 운영체제 상에서 비정상적인 JPEG 파일을 접근(open)할 때 발생할 수 있는 버퍼 오버런 취약성(MS04-028)을 재연하여 분석한다. JPEG 파일의 헤더에 코멘트(comment) 부분이 있을 경우 길이 필드가 잘못되어 있고 JPEG 파일의 몸체에 쉘코드(cmd.exe) 생성부분을 가지고 있을 경우, 버퍼(heap) 오버런 공격이 발생되어 예기치 못한 결과들이 발생 할 수 있다. 본 논문에서는 디버거(WinDBG) 및 역공학 도구(IDAPro)를 이용하여, 이러한 JPEG 파일 관련 취약성을 분석하면서 바이너리 코드만 주어진 경우의 취약성 분석 절차를 이해하고 보안 결함 부분을 추적하는 연구를 수행한다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.9
• /
• pp.442-460
• /
• 2001

In video-on-demand(VOD) systems it is important to minimize initial latency and memory requirements. The minimization of initial latency enables the system to provide services with short response time, and the minimization of memory requirements enables the system to service more concurrent user requests with the same amount of memory. In VOD systems, since initial latency and memory requirement increase according to the increment of buffer size allocated to user requests, the buffer size allocated to user requests must be minimized. The existing static buffer allocation scheme, however, determines the buffer size based on the assumption that thy system is in fully loaded state. Thus, when the system is in partially loaded state, the scheme allocates user requests unnecessarily large buffers. This paper proposes a dynamics buffer allocation scheme that allocates user requests the minimum buffer size in fully loaded state as well as a partially loaded state. This scheme dynamically determines the buffer size based on the number of user requests in service and the number of user requests arriving while servicing current requests. In addition, through analyses and simulations, this paper validates that the dynamics buffer allocation outperforms the statics buffer allocation in initial latency and the number of concurrent user requests that can be supported. Our simulation results show that, in proportion to the static buffer allocation scheme, the dynamic buffer allocation scheme reduces the average initial latency by 29%~65%, and in a systems having several disks. increases the average number of concurrent user requests by 48%~68%. Our results show that the dynamic buffer allocation scheme significantly improves the performance and reduce the capacity requirements of VOD systems.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.10
• /
• pp.30-39
• /
• 1999

In this paper, the size of IWU frame cell buffer is analyzed that receives FR frame cells from other FR networks through ATM backbone network. The frame cell buffer receives multiplexed ATM cells from other IWUs that provide interworking with ATM network for other FR networks A receiving IWU reassembles frames from multiplexed ATM cells by identifying the VPI/VCIs. The reassembled frames are transmitted on FR network links according to their destination. Therefore, IWU needs sufficient amount of buffers for the assembly of the frames and for providing the assembled frames with the queue to wait until the frame is transmitted by FR network link. In this paper, the probability of frame loss at the frame cell buffer is derived in terms of traffic parameters, the number of multiplexed FR connections, the number of FR links and the transmission capacity. By applying the derived results, we analyzed the required buffer size for a given probability of frame loss. Also, it is presented that how the probability and the required size are effected by the number of multiplexed FR connections and FR transmission links.

• The Journal of the Korea Contents Association
• /
• v.18 no.3
• /
• pp.34-40
• /
• 2018

In this study, the optimal buffer size is calculated for seamless video playback on a mobile device. Buffer means the memory space for multimedia packet which arrives in mobile device for video play such as VOD service. If the buffer size is too large, latency time before video playback can be longer. However, if it is too short, playback service can be paused because of shortage of packets arrived. Hence, the optimal buffer size insures QoS of video playback on mobile devices. We model the process of buffering into a discret-time queueing model. Mean busy period length and mean waiting time of Geo/G/1 queue with N-policy is analyzed. After then, we uses the main performance measures to present numerical examples to decide the optimal buffer size on mobile devices. Our results enhance the user satisfaction by insuring the seamless playback and minimizing the initial delay time in VOD streaming process.

• Journal of Digital Contents Society
• /
• v.16 no.3
• /
• pp.365-371
• /
• 2015

In wireless network, the amount of video streaming packet information in receiver replay buffer can be varied according tothe wireless network condition. By the effect, unforeseeable delay and jitter are generated and then busty video traffics can be made. If the amount of buffer information coming in receiver replay buffer is larger than the amount of a specific buffer information, buffer overflow is generated. Such a problem makes the image skip effect and packet loss, and then causes the quality degradation and replay discontinuity of the video streaming service in destination receiver. To solve the buffer overflow problem, this paper applies the token bucket for the busty traffic to the receiver terminal and analyzes the effect of the token bucket. The simulation result using NS-2 and JSVM shows that the proposed scheme with the token bucket has significantly better performance than the conventional scheme without the token bucket in terms of overflow generation number, packet loss rate and PSNR.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.248-254
• /
• 2005

본 논문에서는 대화형 GEO 위성 네트워크에서 패킷 손실량 기대값의 총합을 최소화하는 최적 버퍼 및 타임슬롯 할당 체계를 제시한다. 이를 위해 각 단말에서의 패킷 손실량 기대값을 분석하고, 최적 버퍼 및 타임슬롯 할당 방법을 구하기 위한 최적화 모형을 정형화하고, 정형화된 모형을 빠른 시간 내에 해결할 수 있는 방법을 제시한다. 실험을 통해 제시한 방법이 기존 방법에 비해 패킷 손실량 기대값의 총합을 의미 있게 감소시킴을 보인다.