• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.887-890
• /
• 2004

컴퓨터 네트워크 및 WWW의 발전으로 인터넷 사용자 및 웹 서버의 수는 기하급수적으로 증가하고 있다. 그러나 네트워크의 발달에도 불구하고 웹 서버에 접속하는 사용자의 수가 많아짐에 따라 웹 서버에 병목현상이 발생하고 있다. 이러한 문제를 해결하기 위해 클러스터 시스템이 사용된다. DNS기반 클러스터는 분산 웹 서버 환경에 적합하지만 웹 서버의 상태를 고려하지 않는다. 따라서 본 논문에서는 DNS의 단점을 보완한 부하분산 시스템을 제안한다. 이 시스템은 부하분산 시스템을 따로 설치하지 않고 기존 DNS 프로토콜의 수정 없이 부하분산 모듈을 추가하여 웹 서버의 부하를 분산한다. 본 논문에서 구현한 시스템을 이용하여 분산 웹 환경에서 서버 부하를 고려하여 클라이언트의 요청을 적절히 분배할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1097-1106
• /
• 2004

The typical web cluster architecture consists of replicated real servers and a virtual server that routes client requests among the real servers. In this paper, we proposed an efficient dynamic load distribution method with load prediction for the web cluster systems. The virtual server transmit status request message to real servers in other to get load states. However the load states dose not accurate during load distribution, thus the virtual server predict the load status of real servers and assign a request of the client to the minimum loaded real server. The proposed distribution methods works not related to partial breakdown of real servers, thus the system works with high availability. We also show that the proposed distribution method preserve scalable property and improve the throughput through a set of simulations.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04d
• /
• pp.554-556
• /
• 2003

최근 웹 서비스가 다양한 컨텐츠와 전자상거래 둥 비즈니스와 관련된 서비스로 변화함에 따라 대용량 서비스뿐만 아니라 고품질 서비스(QoS)를 제공하기 위한 연구가 진행되고 있다. 웹 서버 클러스터에서도 서버 성능 향상과 함께 005를 제공하기 위한 차별화된 서비스가 필요하다. 본 논문에서는 사용자 계층별로 차별화된 서비스를 제공하기 위해서 서버 노드를 동적으로 분할하는 기법을 제안한다.

• The KIPS Transactions:PartA
• /
• v.10A no.6
• /
• pp.729-736
• /
• 2003

With the rapid growth of the Internet, popular Web sites are visited so frequently that these cannot be constructed with a single server or mirror site of high performance. The rapid increase of Internet uses and uses raised the problems of overweighted transmission traffic and difficult load balancing. To solve these, various schemes of server clustering have been surveyed. Especially, in order to fully utilize the performance of computer systems in a cluster, a good scheduling method that distributes user requests evenly to servers in required. In this paper, we propose a new method for reducing the service latency. In our method, each Web server in the cluster has different content. This helps to reduce the complexity of load balancing algorithm and the service latency The Web server that received a request from the load balancer responds to the client directly without passing through the load balancer. Simulation studies show that our method performs better than other traditional methods. In terms of response time, our method shows shorter latency than RR (Round Robin) and LC (Least Connection) by about 16%, 14% respectively.

• The KIPS Transactions:PartC
• /
• v.9C no.1
• /
• pp.115-122
• /
• 2002

This paper presents a new web cluster scheme based on dispatcher which does not depend on operating system for server and can examine server's status interactively. Two principal functions are proposed for new web cluster technique. The one is self-controlled load distribution and the other is transaction fail-safe. Self-controlled load distribution function checks response time and status of servers periodically, then it decides where the traffic goes to guarantee rapid response for every query. Transaction fail-safe function can recover lost queries including broken transaction immediately from server errors. Proposed new web cluster scheme is implemented by C language on Unix operating system and compared with legacy web cluster products. On the comparison with broadcast based web cluster, proposed new web cluster results higher performance as more traffic comes. And on the comparison with a round-robin DNS based web cluster, it results similar performance at the case of traffic processing. But when the situation of one server crashed, proposed web cluster processed traffics more reliably without lost queries. So, new web cluster scheme Proposed on this dissertation can give alternative plan about highly increasing traffics and server load due to heavy traffics to build more reliable and utilized services.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.5
• /
• pp.265-273
• /
• 2002

With the explosive growth of WWW traffic, there is an increasing demand for the high performance Web servers to provide a stable Web service to users. The cluster-based Web server is a solution to core with the heavy access from users, easily scaling the server according to the loads. In the cluster-based Web sewer, a back-end node may not be able to serve some HTTP requests directly because it does not have the requested contents in its main memory. In this case, the back-end node has to retrieve the requested contents from its local disk or other back-end nodes in the cluster. To reduce service latency, we introduce a new prefetch scheme. The back-end nodes predict the next HTTP requests and prefetch the contents of predicted requests before the next requests arrive. We develop three prefetch algorithms bated on some useful information gathered from many clients'HTTP requests. Through trace-driven simulation, the service latency of the prefetch scheme is reduced by 10 ~ 25% as compared with no prefetch scheme. Among the proposed prefetch algorithms, Time and Access Probability-based Prefetch (TAP2) algorithm, which uses the access probability and the inter-reference time of Web object, shows the best performance.

• Journal of Advanced Navigation Technology
• /
• v.13 no.5
• /
• pp.669-676
• /
• 2009

HTTP or audio/video streaming services are good candidates for future centralized navigation system and in order to provide stability for such services, service providers use a cluster of web servers. In this paper, we provide the criteria for web server cluster design of vehicular users with consideration of differentiated access per different user classes. Several feasible scenarios are examined and their performance analysis using queueing theory is presented to provide the foundation for web server cluster design using traffic load balancer. Through the thorough analysis, efficient criteria for traffic load balancer design is derived. In order to satisfy users' service requirements, priority services controlled by traffic load balancer are considered and analyzed. We also provide the evaluation of the accuracy of the analytical model through simulation.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.10a
• /
• pp.354-360
• /
• 2005

웹 클러스터 시스템은 동일 서버 군에서 하나 이상의 서비스를 제공하여 비용대비 효과 면에서 높은 가용성 및 보다 빠른 서비스를 제공할 수 있는 시스템이다. 본 연구는 폭주하는 부하를 웹 클러스터 시스템 내의 각 서버에 균등하게 분산 시키는 방법에 대하여 연구하며, 부하 분산의 방법론 및 부하 분산 알고리즘을 제시한다. 기존의 WLC 알고리즘의 변형인 PWLC 알고리즘은 주기적인 웹 클러스터의 부하 측정을 통해 가중치를 적용하고 주어진 기간 동안 부하를 가중치에 따라 점진적으로 분산 시키는 방법이다. 이 알고리즘을 동일 기종 및 이기종 웹 클러스터 시스템에 적용하였고, 또한 기존에 제안된 DWRR 알고리즘과의 시뮬레이션을 통한 비교에서 제안된 PWLC 알고리즘이 보다 효과적임을 알 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04a
• /
• pp.538-540
• /
• 2001

클러스터 시스템의 각 노드에 존재하는 메모리들을 효율적으로 관리하기 위하여 네트워크 메모리의 개념이 등장하였으며 빈번하게 디스크를 접근하는 응용분야에서 속도 향상을 위해 사용될 수 있다. 이는 전통적인 메모리 계층(hierarchy) 구조인 메모리와 디스크 사이에 네트워크 메모리를 추가함으로써 얻어진다. 본 논문에서는 웹 서버 클러스터를 대상으로 문서의 접근 유형에 대한 사전의 정보를 요구하지 않고 실제적으로 구현 가능하며 다양한 웹 문서 접근 확률 분포 값에 대하여 항상 우수한 사용자 응답시간을 가지는 메모리 관리 기법을 제안하고 시뮬레이션을 통해 제안된 방식의 우수성을 검증하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.11-18
• /
• 2011

The increasing of web users load to the excessive transmission traffic and system overload problems. To solve these problems, cluster systems are studied. In conventional cluster systems, when the request size is large owing to such types as multimedia and CGI, the particular server load and response time tend to increase even if the overall loads are distributed evenly. In this paper, we consider the methodology of efficient resource usage, specially distributed web cluster system. We develope an algorithm that distributes the load on the web cluster system to use the system resources, such as system memory equally. The response time is chosen as a performance measure on the various clustering models. And based on the concurrent user to the web cluster system, the response time is also examined as the number of users increases. Simulation experience with this algorithm shows that the response time and average throughput seems to have a good results compare to those with the other algorithm.