• Journal of the Korea Society for Simulation
• /
• v.12 no.3
• /
• pp.69-81
• /
• 2003

To manage a cluster of distributed server systems, a number of management aspects should be considered in terms of configuration management, fault management, performance management, and user management. System performance monitoring and reporting take an important role for performance and fault management. In this paper, we present distributed system architecture modeling of a performance monitoring and reporting tool. Modeling architecture of four subsystems are introduced: node agent, data collection, performance management & report, and DB schema. The performance-related information collected from distributed servers are categorized into performance counters, event data for system status changes, service quality, and system configuration data. In order to analyze those performance information, we use a number of ways to evaluate data corelation. By using some results from a real site of a company and from simulation of artificial workload, we show the example of performance collection and analysis. Since our report tool detects system fault or node component failure and analyzes performances through resource usage and service quality, we are able to provide information for server load balancing, in short term view, and the cause of system faults and decision for system scale-out and scale-up, in long term view.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.310-312
• /
• 2005

무선 인터넷 프록시 서버 클러스터에서 부하 분산기는 사용자의 요청을 각 서버(호스트)로 분산시키는 역할을 한다. 리눅스 가상 서버(LVS: Linux Virtual Server)는 소프트웨어적으로 사용되는 부하 분산기로서 여러 가지 스케줄링 방식들을 가지고 있다. 그러나 부하 분산시에 서버(호스트)의 유동적인 부하 정보를 반영하지 못하는 단점이 있다. 이에 개선된 방식으로 서버의 동시 연결 개수에 따라 상한계(Upper Bound)와 하한계(Lower Bound)를 설정하고, 요청을 분산하는 동적 스케줄링(Dynamic Scheduling)이 존재한다. 그러나 사용자의 요청 컨텐츠에 따라 상한계와 하한계가 바뀔 수 있음에도 불구하고 이 값들이 고정되어 있다는 단점을 가진다. 본 논문에서는 호스트 부하 정보에 기반한 스케줄링 방식을 제안한다. 제안된 방식은 호스트의 부하 정보를 바탕으로 사용자의 요청을 분산하였으며, 사용자의 요청에 따라 상한계와 하한계가 바뀔 수 있음을 고려하여 상한계와 하한계를 설정하지 않고 사용자 요청 컨텐츠에 따라 적절하게 요청이 분배되도록 하였다. 16대의 컴퓨터를 사용하여 실험을 수행하였으며, 실험 결과 사용자가 요청하는 컨텐츠가 동일한 경우에는 기존 스케줄링 방식과 $13\%$ 성능 감소를 다른 경우에는 기존 스케줄링 방식보다 $102\%$의 성능 향상을 보임을 확인하였다.

• Journal of Power Electronics
• /
• v.10 no.6
• /
• pp.611-620
• /
• 2010

This paper presents a new architecture, called "Power Electronics Remote Wiring and Measurement Laboratory (PermLAB)", that translates a common gateway interface (CGI) string from a remote web user to a web server connected to a 3-dimension switching matrix board, can be used to switch on and off, and to control a cluster of instruments and components. PermLAB addresses real-time connection, switching, and data acquisition over the Internet instead of using simulated data. A software procedure uses a signature system to identify each instrument and component in a complex system. The Web-server application is developed in HTML, JavaScript and Java, and in C language for the CGI interface, which resides in a controller portion of LabVIEW. The LabVIEW software fully integrates the Web sever, LabVIEW data acquisition boards and controllers, and the 3-dimensional switching matrix board. The paper will analyze a half-wave rectifier (AC - DC converter) circuit connected over the Internet using the PermLAB. PermLAB allows students to obtain real data by real-time wiring of real circuits in the laboratory using a "virtual breadboard" on the Web. The software for the Web-based 3-dimensional system is flexible, portable, can be integrated into many laboratory applications or expanded, and easily accessible worldwide.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.79-82
• /
• 2012

기존의 서버 전원 모드 제어에는 서버를 Off할 때 정적 종료 방식을 사용하는 관계로 서버가 사용자 요청을 모두 처리하는 최적의 종료 시간을 찾는데 시간이 많이 걸리는 단점을 가진다. 이 시간이 짧게 되면 사용자 QoS를 보장할 수 없고, 반대로 이 시간이 길게 되면 전력 절감을 기대할 수 없다. 본 논문에서는 정적 종료 방식의 단점을 극복하는 동적 종료 방식을 제안한다. 제안된 방식은 최적의 종료 시간을 찾을 필요 없이 각 서버가 사용자의 요청을 모두 처리하였을 때 자동적으로 서버를 Off한다. 제안된 방법은 최적의 시간을 자동적으로 찾아내기 때문에 사용자 QoS를 보장하고, 전력을 절감한다. 실험은 30대의 PC 클러스터를 이용하여 수행되었고, 실험을 통하여 제안하는 동적 종료 방법이 기존의 정적 종료 방법에 비해 운영자의 수고 없이 자동적으로 전력 절감 및 사용자 QoS에 기여함을 확인하였다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.4
• /
• pp.153-161
• /
• 2021

Real-time access is required to handle continuous and unstructured data and should be flexible in management under dynamic state. Platform can be built to allow data collection, storage, and processing from local-server or multi-server. Although the former centralize method is easy to control, it creates an overload problem because it proceeds all the processing in one unit, and the latter distributed method performs parallel processing, so it is fast to respond and can easily scale system capacity, but the design is complex. This paper provides data collection and processing on one platform to derive significant insights from various data held by an enterprise or agency in the latter manner, which is intuitively available on dashboards and utilizes Spark to improve distributed processing performance. All service utilize dockers to distribute and management. The data used in this study was 100% collected from Kafka, showing that when the file size is 4.4 gigabytes, the data processing speed in spark cluster mode is 2 minute 15 seconds, about 3 minutes 19 seconds faster than the local mode.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.175-178
• /
• 2011

서버 클러스터는 성능을 보장하기 위하여, 요청 수에 상관없이 미리 측정된 최대 부하 시점에서 처리 가능한 서버 수를 항상 운영하고 있다. 이것은 서비스의 품질은 보장할 수 있으나, 소비 전력 효율이 낮아 상당한 전력을 낭비하는 단점이 있다. 본 논문에서는 사용자 요청 수에 기반하여 동작시킬 서버의 수를 결정하는 알고리즘을 제안한다. 제안된 방식은 기존에 학습된 정보(과거 정보)와 현재의 정보에 근거하여 Off/Sleep 상태의 서버를 On 시키거나, On 상태의 서버를 Off/Sleep시켜, 현 시점에서 필요한 최적의 서버대수를 유지하도록 했다. 15대의 서버로 클러스터를 구성하고, SPECweb을 통해 실험을 수행하였다. 실험결과, 서버 모드를 제어할 경우에 제어하지 않는 경우에 비해 약 35%의 전력이 절감되고, 본 논문에서 제안하는 학습 방법을 추가로 적용할 경우 약 5%의 전력이 추가로 절감되었다.

• Progress in Medical Physics
• /
• v.17 no.3
• /
• pp.144-152
• /
• 2006

The telemedicine using independent client-server system via networks can provide high quality normalized services to many hospitals, specifically to local/rural area hospitals. This will eventually lead to a decreased medical cost because the centralized institute can handle big computer hardware systems and complicated software systems efficiently and economically, Customized cancer radiation treatment planning for each patient Is very useful for both a patient and a doctor because it makes possible for the most effective treatment with the least possible dose to patient. Radiation planners know that too small a dose to the tumor can result in recurrence of the cancer, while too large a dose to healthy tissue can cause complications or even death. The best solution is to build an accurate planning simulation system to provide better treatment strategies based on each patient's computerized tomography (CT) image. We are developing a web-based and a network-based customized cancer radiation therapy simulation system consisting of four Important computer codes; a CT managing code for preparing the patients target data from their CT image files, a parallel Monte Carlo high-energy beam code (PMCEPT code) for calculating doses against the target generated from the patient CT image, a parallel linear programming code for optimizing the treatment plan, and scientific data visualization code for efficient pre/post evaluation of the results. The whole softwares will run on a high performance Beowulf PC cluster of about 100-200 CPUs. Efficient management of the hardware and software systems is not an easy task for a hospital. Therefore, we integrated our system into the client-sewer system via network or web and provide high quality normalized services to many hospitals. Seamless communication with doctors is maintained via messenger function of the server-client system.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.2025-2035
• /
• 2014

The read range of UHF mobile readers can be extended by a booster for mobile RFID readers (BoMR). But in an environment where multiple BoMRs are installed, the read success rate may be decreased due to signal interference. This paper proposes three arbitration methods based on interference estimation with the purpose of enhancing the read success rate. A central arbitration server manages global information in centralized arbitration method (CAM) without broadcast/multicast communication facility. In fully distributed arbitration method (FDAM), all the arbitration messages are broadcasted from a BoMR to every BoMR, and each BoMR decides with broadcasted global information. Events in FDAM are serialized naturally with broadcasted messages. Cluster Distributed Arbitration Method (CDAM) forms clusters with multicasted BoMRs and a selected BoMR acts as an arbiter in the cluster. Such effects as lengthened read range, improved the read success rates of readers can be obtained by the proposed methods without any hardware modification. In order to evaluate the arbitration methods, the RFID system is modeled by using the DEVS formalism and simulated by using the DEVSim++.

• The KIPS Transactions:PartA
• /
• v.12A no.7 s.97
• /
• pp.613-620
• /
• 2005

To provide reliable differentiated service for internet clients, many studies on differentiated service are widely done. According to the types of the request of the clients in cluster-based web systems, SLA (Service Level Agreement) between service provider and the clients is considered. In this Paper, we study primary-backup web switch in the web systems that distribute the request of clients to each of web servers and also study performance isolation and admission control schemes of heterogeneous web systems which distinguish the servers into each different function domains. We analyze the availability, the response time and the performance of admission control through various simulated experiments on the proposed web systems.

• Journal of Korea Multimedia Society
• /
• v.4 no.6
• /
• pp.534-542
• /
• 2001

Recent content-based image retrieval systems make use of a local single server contained a limited number of images. So these systems are not satisfactory for the Web user's needs that make request for various images on the Web. A content-based image retrieval system that has regard for a great number of Web images has to stand on the basis of real-time first of all. Therefore, to implement the above system we have to resolve a problem of large waste time to take for an image collection and feature extractions. In recent, PC clusters with a load distribution are implemented for the purpose of high-performance data processing. In this paper, we decreased the whole retrieval time by distributing the tasks of image collection and feature extraction to take much time among the slave computers of the PC cluster, and so we found the possibility of the real-time processing in the retrieval of Web images.