• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.2
• /
• pp.111-118
• /
• 2006

In this thesis, we analyze the efficiency of the algorithm to distribute the load in the clustered system, by comparing with the existed algorithm. PWLC algorithm detects each server's load in the system at weighted period, and following the detection of the loads, a set of weights is given to each server. The system allocates new loads to each server according to its weight. PWLC algorithm is compared with DWRR algorithm in terms of variance, waiting time by varying weighted Period. When the weighted period is too short, the system bears a heavy load for detecting load over time. On the other hand, when the weighted period is too long, the load balancing control of the system becomes ineffective. The analysis shows PWLC algorithm is more efficient than DWRR algorithm for the variance and waiting time.

• The KIPS Transactions:PartA
• /
• v.15A no.4
• /
• pp.199-210
• /
• 2008

A Clustering based wireless internet proxy server needs a layer-7 load balancer with URL hashing methods to reduce the total storage space for servers. Layer-4 load balancer located in front of server cluster is to distribute client requests to the servers with the same contents at transport layer, such as TCP or UDP, without looking at the content of the request. Layer-7 load balancer located in front of server cluster is to parse client requests in application layer and distribute them to servers based on different types of request contents. Layer 7 load balancer allows servers to have different contents in an exclusive way so that it can minimize the total storage space for servers and improve overall cluster performance. However, its scalability is limited due to the high overhead of parsing requests in application layer as different from layer-4 load balancer. In order to overcome its scalability limitation, in this paper, we propose a distributed layer-7 load balancer by replacing a single layer-7 load balancer in the conventional scheme by a single layer-4 load balancer located in front of server cluster and a set of layer-7 load balancers located at server cluster. In a clustering based wireless internet proxy server, we implemented the conventional scheme by using KTCPVS(Kernel TCP Virtual Server), a linux based layer-7 load balancer. Also, we implemented the proposed scheme by using IPVS(IP Virtual Server), a linux-based layer-4 load balancer, installing KTCPVS in each server, and making them work together. We performed experiments using 16 PCs. Experimental results show scalability and high performance of the proposed scheme, as the number of servers grows, compared to the conventional scheme.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.92-94
• /
• 2000

비디오 저장 서버를 설계하는데 가장 주안을 두어야 할 점은 서버의 이용률을 증가시키고 그에 따른 비용을 최소화 해야 한다는 점이다. 이를 위한 서버로 분산 비디오 저장 서버가 주로 이용되고 있고, 그 목적으로는 균등한 비디오 할당과 부하조정(load balancing)이 제안되어 왔다. 이에 대한 방안의 하나로 디스크 기반의 비디오 저장 서버 클러스터에서 부하 시프팅(load shifting)이 그 목적을 이루기 위한 한가지 방법으로 연구되었다. 이것은 동일한 용량의 서버로 구성된 비디오 서버 클러스터에서 비디오를 다른 서버에 복사해 놓고 사용되고 있는 비디오 요구시 그 비디오에 대한 요구를 다른 서버의 복사본으로 이동시킴으로써 서버들에 대해 균등한 비디오 할당을 하고 서버나 비디오의 추가와 같은 동적인 변화에 대해 데이터 활당 및 부하 조정을 감안하여 제안된 것이다. 이 논문에서는 기존의 동일한 서버만을 사용한 것과는 달리 용량이 서로 다른 서버나 비디오를 추가할 경우에 요구되는 최적의 비디오 데이터 할당과 부하 조정에 관한 전략에 관하여 설명한다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.12
• /
• pp.568-575
• /
• 2008

Server consolidation by sever virtualization can make one physical machine(PM) to run several virtual machines simultaneously. Although It is attractive in cost, it has complex workload behaviors. For that reason, efficient resource management method is required. Dynamic relocation of virtual machine(VM)[3,4] by live migration[1,2] is one of resource management methods. We proposed SCOA(Server Consolidation Optimizing Algorithm) : a fine-grained load balancing mechanism worked on this dynamic relocation mechanism. We could obtain accurate resource distribution information through pointed physical machines on multi dimensional resource usage coordination, so we could maintain more balanced resource state. In this paper, we show the effectiveness of our algorithm by comparison of experimental results between SCOA and sandpiper[3] by software simulation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.53-55
• /
• 2000

인터넷의 급성장은 웹서버의 요청율을 급격하게 증가시키고 심각한 정체를 일으키고 있다. 이를 해결하기 위하여 클라이언트의 요청을 분산된 여러 서버들에게로 전달시키는 방법이 많이 사용되고 있다. 이 방법은 웹서버의 처리량을 향상시키고 확장성과 가용성을 제공하지만 서버들의 부하를 균등하게 하는 방법이 필요하게 된다. 이러한 부하 균등을 위해 크게 DNS(Domain Name Server)를 활용한 정책과 IP 단계에서 분배기(Dispatcher)를 사용한 정책이 제안되었다. 본 논문에서는 전자와 후자의 단점을 보완하고 성능을 향상시킨 다중 분배기를 제안하고 실험하였다.

• Digital Contents
• /
• no.3 s.118
• /
• pp.129-133
• /
• 2003

트래픽 관리를 위한 요소기술로 '캐시서버'에 대한 내용을 지난 호에 살펴보았다. 이번에는 트래픽을 효과적으로 분산시켜 줄 수 있는 글로벌 로드밸런싱(Global Server Load Balancing)에 대해 살펴보겠다.'글로벌 로드밸런싱'은 미들마일 구간의 병목지역을 회피하기 위해 서버를 여러 지역에 설치해 운영할 때, 사용자들이 분산 운영되고 있는 서버들 가운데 부하가 적고, 사용자로부터 근접한 서버로 유도하는 기술이다.

• Journal of the military operations research society of Korea
• /
• v.23 no.2
• /
• pp.25-44
• /
• 1997

Internet users been rapidly increased due to the convenient GUI environment. Current Web-based HTTP/CGI client/server architecture has several problems such as the CGI bottleneck, no maintaince of state, and no load balancing. However, with Java and CORBA technologies called“Object Web technology”, we can solve them because Java is not only a mobile code but also a platform-independent code, and CORBA has ability to build distributed object and language-independent object model. The goal of “Object Web technology”is to create multivendor, multiOS, multilanguage“legoware”using objects. This paper implement“Book Search System”which is Web-based client/server architecture using distributed objects. Environments of this implementation are Hangul Windows NT(included IIS) server, Hangul Windows 95 client, Visigenic's VisiBroker for Java 1.2 which is a product of CORBA 2.0, HTTP protocol on TCP-IP-based, Sybase SQL Anywhere 5.0 database server, and the interface between application server and database is JDBC-ODBC bridge middleware.

• Journal of Korea Game Society
• /
• v.12 no.3
• /
• pp.49-58
• /
• 2012

When a company provides new games or games with a small number of users, it is convenient to provide the game service in which those games are placed in a server cluster instead of a separate server for an individual game. This paper proposes a method for placing games in a cluster of servers with the same capacities. The method reduces the load imbalance among servers and minimizes the rejection ratio of user requests. We expect that the proposed method is useful for determining the server operation factors such as the number of servers, the number of games for a server, etc. To our survey, little research has been published on game placement on a cluster of game servers.

• The KIPS Transactions:PartA
• /
• v.13A no.1 s.98
• /
• pp.45-52
• /
• 2006

To perform on-line maintenance for Distributed Information System, it is indispensable to disseminate files to participant nodes in the network. When users' requests for file deployment occur simultaneously in a short period a deployment server falls into overload phase, which is often called Flash Crowds. h common solution to avoid Flash Crowds is to increase hardware capacity. In this paper, we propose a software solution based on P2P, which does not cost any additional expense. In the proposed solution, nodes in the network are grouped into subnetworks one of which is composed of only neighboring nodes. In each subnetwork, copies of deployment files can be transferred to each other. Consequently, it brings about the effect of load balancing in deployment server. To raise the effectiveness, target files for deployment are packed into one package. Before being transferred, each package is divided into multiple equal-sized segments. A deployment server in a normal phase transmits a package requested from nodes in segment units. However a deployment server is overloaded, if segments already exist in the subnetwork participant nodes in the subnetwork receive necessary segments from neighboring nodes. In this paper, we propose data structures and algorithm for this approach and show performance improvement through simulation.

• The KIPS Transactions:PartA
• /
• v.14A no.7
• /
• pp.443-450
• /
• 2007

Performance scalability and storage scalability become important in a large scale cluster of wireless internet proxy cache servers. Performance scalability means that the whole performance of the cluster increases linearly according as servers are added. Storage scalability means that the total size of cache storage in the cluster is constant, regardless of the number of cache servers used, if the whole cache data are partitioned and each partition is stored in each server, respectively. The Round-Robin based load balancing method generally used in a large scale server cluster shows the performance scalability but no storage scalability because all the requested URL data need to be stored in each server. The hashing based load balancing method shows storage scalability because all the requested URL data are partitioned and each partition is stored in each server, respectively. but, it shows no performance scalability in case of uneven pattern of client requests or Hot-Spot. In this paper, we propose a novel dynamic hashing method with performance and storage scalability. In a time interval, the proposed scheme keeps to find some of requested URLs allocated to overloaded servers and dynamically reallocate them to other less-loaded servers. We performed experiments using 16 PCs and experimental results show that the proposed method has the performance and storage scalability as different from the existing hashing method.