• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.7
• /
• pp.349-358
• /
• 2005

False sharing is a result of co-location of unrelated data in the same unit of memory coherency, and is one source of unnecessary overhead being of no help to keep the memory coherency in multiprocessor systems. Moreover. the damage caused by false sharing becomes large in proportion to the granularity of memory coherency. To reduce false sharing in a page-based DSM system, it is necessary to allocate unrelated data objects that have different access patterns into the separate shared pages. In this paper we propose call-site tracing-based shared memory allocator. shortly CSTallocator. CSTallocator expects that the data objects requested from the different call-sites may have different access patterns in the future. So CSTailocator places each data object requested from the different call-sites into the separate shared pages, and consequently data objects that have the same call-site are likely to get together into the same shared pages. We use execution-driven simulation of real parallel applications to evaluate the effectiveness of our CSTallocator. Our observations show that by using CSTallocator a considerable amount of false sharing misses can be additionally reduced in comparison with the existing techniques.

• Journal of Digital Contents Society
• /
• v.9 no.1
• /
• pp.77-86
• /
• 2008

False sharing is a result of co-location of unrelated data in the same unit of memory coherency, and is one source of unnecessary overhead being of no help to keep the memory coherency in multiprocessor systems. Moreover, the damage caused by false sharing becomes large in proportion to the granularity of memory coherency. To reduce false sharing in page-based DSM systems, it is necessary to allocate unrelated data objects that have different access patterns into the separate shared pages. In this paper we propose sized and call-site tracing-based shared memory allocator, shortly SCSTallocator. SCSTallocator places each data object requested from the different call-sites into the separate shared pages, and at the same time places each data object that has different size into different shared pages. Consequently data objects that have the different call-site and different object size prohibited from being allocated to the same shared page. Our observations show that our SCSTallocator outperforms the existing dynamic shared memory allocators. By combining the two existing allocation technique, we can reduce a considerable amount of false sharing misses.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.3
• /
• pp.313-325
• /
• 1999

분산 프로그램의 디버깅이 순차 프로그램의 디버깅보다 어려운 이유중의 하나는 수행중인 프로세스들 간의 통신 때문이다. 비록 분산 시스템을 위해 구축된 디버거들이 많이 있음에도 불구하고 , 프로세스들간의 통신 이벤트를 효과적으로 디버깅할수 있는 실용적인 수준의 디버거는 없는 실정이다. 본 논문에서는 분산 시스템의 개발에 널리 사용되고있는 RPC 매커니즘을 이용한 프로그램간의 통신을 효과적으로 디버깅하는 방법을 제시한다. 이를 위하여 RPC 통신 이벤트를 디버깅 객체로 정의한 RPC 이벤트 모델을 제안하고 이에 기초하여 RPC 이벤트 추적 기능을 설계 및 구현하였다. RPC 프로토콜을 분석한 결과를 이용하여 메시지의 송.수신 이벤트를 추적 기능을 설계 구현하였다. RPC 프로토콜을 분석한 결과를 이용하여 메시지의 송.수신 이벤트를 라이브러리 함수의 호출과 자료의 값으로 기술하고 해당라이브러리 함수의 호출이 발생한 위치를 인지함으로써 모든 통신 이벤트의 발생을 탐지할수 있었다. 제안된 RPC 이벤트 추적기능은 현재 분산 디버거인 유니뷰 시스템에 구현되었다. 이벤트 추적 기능의 추가적 구현으로 인하여 유니뷰 시스템은 추적된 통신의 내용을 보면서 관련된 소스 코드를 보거나 프로그램을 제어하고 원격 함수 호출에 사용된 매개변수의 값을 보는 등의 행위가 가능하다. 또한 이러한 이벤트 추적기능을 수행하기 위하여 별도의 라이브러리나 수행환경이 요구되지 않으므로 실제분산시스템의 개발 환경에 적응하기가 용이한 장점을 가진다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.117-128
• /
• 2013

u-safety service system inter-works with the diverse operation agencies, through CCTV network, such as the emergency call terminal with built-in GPS, the mobile communication network, u-safety service provider, relay system and CCTV control center. In the case of the emergency call, this service searches the location of caller in real time, and then continues to search the location of caller through the control of CCTV in the searched place, and can provide the several agencies like guardian, police office, fire station, hospitals, relief organizations and municipalities, with the diverse information necessary for the secure rescue through SMS and wired network. In this paper, a new protocol and specification for u-safety service relay system is designed and implemented. The effectiveness of presented protocol is verified by computer simulation. The designed protocol of u-safety service is applied to real 3GPP and 3GPP2 mobile communication networks to verify its performance.

• Journal of Korea Multimedia Society
• /
• v.11 no.7
• /
• pp.1016-1024
• /
• 2008

In this paper, we designed and implemented the ACE(ACtive Emergency call service system) system for emergency call service actively. ACE system has two physical components; E-Device(Emergency Mobile Device) and E-Server(Emergency Server). The role of E-Device is the mobile device in order to call emergency by using mild handi-capped, the elderly and children who are able to communicate theirs intention to another. E-Server is the server for management E-devices with realtime monitering. E-Device will be developed to the portable size for easily mild handi-capped, the elderly and children. When they need the service of emergency call, the button of E-device can be used and the call signal is transmitted to the emergency office and the guardian through Internet and CDMA. E-server should be developed the integrated control system for management of E-Devices basically. And it also supported to realtime monitoring of E-devices with respect to high quality of emergency call service for rise the efficiency.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.10 no.1
• /
• pp.39-52
• /
• 2000

컴퓨터망의 확대 및 컴퓨터 이용의 급격한 증가에 따른 부작용으로 컴퓨터 보안 문제가 중요하게 대두되고 있다. 이에 따라 침입자들로부터 침입을 줄이기 위한 침입탐지시스템에 관한 연구가 활발하다. 본 논문에서는 컴퓨터 면역 시스템을 바탕으로 한 새로운 IDS 모델을 제안하고, 이를 설계하고 프로토타입을 구현하는 그 타당성을 보인다. 제안한 모델에서 IDS들은 여러 컴퓨터에 분산되고, 분산된 IDS들 중 어느 하나가 특권 프로세스(Privilege process)에 의해 발생된 시스템 호출 순서 중 비정상적인 시스템 호출을 탐지한 경우 이를 다른 IDS들과 서로 동적으로 공유하여 새로운 침입에 대한 면역력을 향상시킨다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.1
• /
• pp.225-233
• /
• 1999

One of the reasons that debugging distributed programs is much more difficult than sequential programs is the communication among processes. Even though there are many debuggers constructed on distributed system environment, no available debugger provides an efficient way to debug communication events.. In this paper, we show the way to debug RPC communication, which is regarded as one of the most popular communication protocol in distributed system development. This paper presents the implementation of the RPC event trace function based on the RPC event model, which is proposed to accommodate communication events into debugging objects. Analyzing conventional RPC protocols, we formalized library function calls as corresponding actions to sending and receiving of messages. B recognizing the locations of library calls the debugger can detect all occurrences of communication events, This RPC event trace function is implemented on the on-line distributed debugger UniVIEW system.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.1
• /
• pp.79-86
• /
• 2004

In general, operating system is offering the security function of OS level to support several web services. However, it is true that security side of OS level is weak from many parts. Specially, it is needed to audit/trace function in security kernel level to satisfy security more than B2 level that define in TCSEC(Trusted Computer System Evaluation Criteria). So we need to create audit data at system call invocation for this, and do to create audit data of equal format about almost event and supply information to do traceback late. This Paper Proposes audit/trace system module that use LKM(Loadable Kernel Module) technique. It is applicable without alteration about existing linux kernel to ensure safe evidence. It offers interface that can utilize external audit data such as intrusion detection system, and also offers safe role based system that is divided system administrator and security administrator These data will going to utilize to computer forensics' data that legal confrontation is Possible.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.33-39
• /
• 2009

As the usage of computers and mobile handsets is popularized, the processing and storing of private and business data are increased. Hence we note that these sensitive data should never be transferred out of these personal devices without user's permission. In this paper, we propose a simple method to prevent transferring the sensitive data out of personal computing devices through their networking interfaces. The proposed method determines which processes invoke open system call related to the sensitive data, and then traces them within a specific duration. The proposed scheme has advantage over the existing ones using authentication or encryption because it could be still working well independent upon the new attack technologies or the latest vulnerabilities of hardware and software. In order to verify the proposed algorithm, we test it by implementing the necessary codes at the user and kernel spaces of Linux.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.223-227
• /
• 2010

Since the most of existing virtual model house used non-immersive type virtual reality technology, it was made to control using direct input type device such as keyboard and mouse. But in this paper realized not only direct data entry method but also indirect data entry method using eyetracking technology through universal webcam for virtual model house based upon modeling. In this paper showed the position of pointer controlled according to the relative movement of pupils or the part of function related to the equipment entry called by comparing the value of gray after extracting the area of pupil in the user' video data received from webcam. Such a method provided the convenience of navigation and interface to the user.