• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.435-447
• /
• 2004

For VOD systems, it is important to provide QoS to more users under the limited resources. To analyze QoS issues in real environment, we implement clustered VOD server and embedded client system based on the Linux open source platform. The parallel processing of MPEG data, load balancing for nodes and VCR like functions are implemented in the server side. To provide more user friendly interface, the general TV is used for a VOD client's terminal and the embedded board is used supporting for VCR functions. In this paper, we measure the performance of the implemented VOD system under the various user requirement features and evaluate the sources of performance limitations. From these analyses, we propose the dynamic admission control method based on the availability memory and network bandwidth. The proposed method enhances the utilization of the system resource for the more QoS media streams.

• Journal of Information Processing Systems
• /
• v.9 no.2
• /
• pp.205-216
• /
• 2013

In this paper, we analyze a technique for building a high-availability (HA) cluster system. We propose what we have termed the 'Selective Replication Manager (SRM),' which improves the throughput performance and reduces the latency of disk devices by means of a Distributed Replicated Block Device (DRBD), which is integrated in the recent Linux Kernel (version 2.6.33 or higher) and that still provides HA and failover capabilities. The proposed technique can be applied to any disk replication and database system with little customization and with a reasonably low performance overhead. We demonstrate that this approach using SRM increases the disk replication speed and reduces latency by 17% and 7%, respectively, as compared to the existing DRBD solution. This approach represents a good effort to increase HA with a minimum amount of risk and cost in terms of commodity hardware.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.99-102
• /
• 2001

We propose a PC cluster using general-purpose microprocessors and a high-speed network for simulating ANN (Artificial Neural Network) processes on Linux OS. We apply this cluster to intelligent information processing such as ANN simulation. The elapsed time for simulating ANNs can be reduced from 7,295 seconds by a PE (Processing Element) to 1,226 seconds by six PEs. The reliability of a pattern-classification using ANNs can be improved by the proposed ANN, Randomized-ANN. In order to generate a Randomized-ANN, we choose three ANNs and combine the output results from three huts by means of logical AND. Results are as follows: The mean correct answer rate is 94.4%, the mean wrong answer rate is only 0.1 %, and the mean unknown answer rate is 5.5 %. We make sure that Randomized-ANN approach reduces the mean wrong answer rate within a tenth part and improves the reliability of Japanese coin classification.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.106-109
• /
• 2004

This study designs a load balancer via direct routing that share a virtual service on a single IP address in the Linux system and suggests an efficient load balancing method to improve transmission speed in the web server cluster environment. It will increase performance and scalability with fast packet transfer and removing bottleneck problem by using TCP Splicing and Content-Aware Distributor method. This method is expected to be the noticeable technology that provides an important interface, which make application services for e-commerce effectively be applied to high-speed network infrastructure. At this time, it is required to study further on the optimum balancing method in the web server cluster environment so as to apply the hybrid (optimum load balancing method by software and hardware) method and improve the reuse of security cession based on high-speed TCP connections.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.313-316
• /
• 2001

At the end of 1999, the TeraCluster project in the KISTI Supercomputing Center was initiated to explore the possibility of PC clusters as a scientific computing platform to replace the Cray T3E system in KISTI by the year 2002. In order to understand whether an application is scalable to tera-flops sized cluster system, running test is inevitable. Extensive performance tests using well-known benchmarking codes with real applications' characteristics in them were carried out with different combinations of CPUs, system boards, network devices. The lessen learned shows the relationships between system performances and varied applications' different needs resulting in promises of How-Tos in building large scale cluster system. The 64/16 node clusters with Alpha EV6(466MHz), Pentium III(667 MHz) i inter-node network of Fast Ethernet. SCI[1] and Myrinet[2] were evaluated. More detailed specifications of the Linux clusters are described in Table 1.

• The KIPS Transactions:PartC
• /
• v.8C no.6
• /
• pp.765-774
• /
• 2001

In this paper, we proposed the striping policy for the storage nodes in the Linux-based parallel media stream server. We newly developed a storage clustering architecture, and named it as a system RAID architecture. In this system, many storage cluster nodes are grouped to operate as a single server. This system uses unique striping policy to distribute multimedia files into the parallel storage nodes. If a service request occurs, each storage cluster node transmits striped files concurrently to the clients. This scheme can provide the fair distribution of the preprocessing load in all storage cluster nodes. The feature of this system is a relative striping policy based on the file types, service types, and the number of storage nodes to provide the best service.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.183-186
• /
• 2002

클러스터는 부하 분산 스케줄링의 방법에 따라서 그 시스템의 성능이 달라진다. 본 논문에서는 클러스터의 한 종류인 LVS에서 제시되었던 RR, WRR, LC, WLC의 부하 분산 스케줄링을 이용하여 시스템의 각종 부하를 처리하는 방법과 클러스터의 각 서버의 성능을 측정하여 부하 분산을 결정하는 ALBM(Adaptive Load Balancing Mechanism) 방식을 비교하였다. 이 성능 평가를 하기 위하여 여러 실험 환경 설정을 하여 다양한 실험을 통하여 비교 분석 하였다. 실험을 통하여 ALMB 이 기존의 여러 스케줄링 방식에 비하여 전체적으로 좋은 성능 결과를 낳았으며 클러스터 서버간의 안정적인 부하 분산이 되는 결과를 얻었다.

• Journal of KIISE:Information Networking
• /
• v.33 no.3
• /
• pp.231-246
• /
• 2006

A server load balancer is used to accept and distribute client requests to one of servers in a wireless internet proxy server cluster. LVS(Linux Virtual Server), a software based server load balancer, can support several load balancing algorithms where client requests are distributed to servers in a round robin way, in a hashing-based way or in a way to assign first to the server with the least number of its concurrent connections to LVS. An improved load balancing algorithm to consider server performance was proposed where they check upper and lower limits of concurrent connection numbers to be allowed within each maximum server performance in advance and apply the static limits to load balancing. However, they do not apply run-time server load information dynamically to load balancing. In this paper, we propose a dynamic load balancing scheme where the load balancer keeps each server CPU load information at run time and assigns a new client request first to the server with the lowest load. Using a cluster consisting of 16 PCs, we performed experiments with static content(image and HTML). Compared to the existing schemes, experimental results show performance improvement in the cases of client requests requiring CPU-intensive processing and a cluster consisting of servers with difference performance.

• 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
• /
• 2002.04a
• /
• pp.649-651
• /
• 2002

클러스터 파일 시스템은 기존의 클러스터링 기술을 파일 시스템에 적용하여, 각 노드 단위로 파일 시스템을 구성할 때 발생되는 저장 공간과 대역폭의 제약문제를 극복하기 위한 방법이다. 클러스터 파일 시스템은 하나의 원본 파일을 여러 노드에 나누어 저장하므로, 효율적인 노드간 데이터 통신을 필요로 하며, 노드 내부에서도 클러스터 파일 시스템과 어플리케이션과의 전용 데이터 교환 메커니즘을 지원해야 한다. 본 논문에서는 클러스터 파일 시스템이 안정적이고 효율적인 방법으로 멀티미디어 데이터를 분산 저장하기 위하여 필요한 통신 모듈을 설계 및 구현한다.