• Proceedings of the KSME Conference
• /
• 2001.11a
• /
• pp.252-257
• /
• 2001

With the help of newly arrived technology such as PC clustering, molecular dynamics (MD) seems to be promising for large-scale materials simulations. A cost-effective cluster is set up using commodity PCs connected over Ethernet with fast switching devices and free software Linux. Executing MD simulations in the parallel sessions makes it possible to carry out large-scale materials simulations at acceptable computation time and costs. In this study, the MD computer code for fracture simulation is modified to comply with MPI (Message Passing Interface) specification, and runs on the PC cluster in parallel mode flawlessly. It is noted that PC clusters can provide a rather inexpensive high-performance computing environment comparing to supercomputers, if properly arranged.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10c
• /
• pp.835-837
• /
• 2001

컴퓨터의 급속한 보급과 인터넷의 사용이 급증하면서 사용자에게 좀 더 나은 서비스를 제공하기 위해 고성능 웹서버가 필요하게 되었다. 따라서 최근에는 리눅스 가상서버를 이용한 클러스터 웹 서버의 구축사례가 늘고 있다. 이는 기존의 단일 서버 시스템에 비해 가격이 저렴하면서도 지속적인 서비스를 할 수 있는 가용성과 서버의 수를 쉽게 늘릴 수 있는 확장성을 갖고 있다. 오픈소스인 리눅스와 여러 대의 저렴한 PC들을 이용하여 서버로 들어오는 부하를 분배서버가 여러 실제 서버에게 분산시킴으로써 웹 서버의 성능을 향상시키고, 서버의 가용성을 높이는 것이 클러스터 웹 서버의 목적이라 할 것이다. 본 논문에서는 서버에 들어오는 요청을 실제 서버들에게 분산시켜주는 스케줄링 알고리즘들을 알아보고 각각의 성능을 비교, 분석하였다. 그 결과 정적 스케줄링 알고리즘보다는 각 실제 서버의 부하를 고려한 알고리즘이 더 좋은 성능을 보인다는 것과 캐쉬 친화적 알고리즘이 캐쉬를 고려하지 않은 알고리즘 보다 더 좋은 성능을 보인다는 것을 알 수 있었다. 가장 중요한 결론으로는 알고리즘의 성능보다는 노드 개수 증가율이 클러스터 웹 서버 성능에 더 큰 영향을 미친다는 것을 알 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.229-231
• /
• 2003

최근 몇 년 동안 컴퓨터 사용자들의 멀티미디어 데이터에 대한 요구가 빠르게 증가하고 있다. 멀티미디어 데이터를 서비스하기 위해서는 대용량의 저장장치가 필요하며 연속재생이 가능하여야 한다. 이와 관련하여 데이터 압축기술과 스트리밍 기슬과 고성능 PC를 고속의 네트웍으로 연결하는 클러스터 기술에 대한 연구가 진행되고 있다. 클러스터 시스템은 비교적 저렴한 가격의 고성능 시스템으로 고가의 단일서버에 비해 확장성과 가격대 성능면에서 유리하다. 이에 본 연구에서는 리눅스 클러스터 기반의 오디오/비디오 실시간 및 VOD 스트리밍 서버와 일반적인 사용자에게 친숙한 윈도우 환경의 플레이어를 구현하였다. 또한 본 연구에서 구현한 시스템에서는 기존에 윈도우 NT계열에서만 스트리밍이 가능했던 ASF포맷의 멀티미디어 데이터를 리눅스 서버에서도 스트리밍 서비스가 가능하도록 하였다.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.517-524
• /
• 2006

In cluster computers, it is essential to Implement the single I/O space(SIOS) supporting integrated I/O substructure to efficiently process I/O intensive applications. SIOS service provides with global I/O address space to directly access peripherals and hard disks in its own or remote nodes from any node in the cluster computer In this thesis, we propose the implementation method of SIOS in Linux clusters by using only freewares. This method is implemented at device driver level that uses Enhanced Network Block Device(ENBD) and file system level that uses S/W RAID and NFS. The major strengths of this method are easiness of implementation and almost no cost due to using freewares. In addition, since freewares used are open sources, it is possible to apply this method to other platforms with only slight modification. Moreover, experiments show that I/O throughputs are up to 5.5 times higher in write operations and approximately 2.3 times higher in read operations than those of CDD method that uses the device driver developed at kernel level.

• 한국전산유체공학회:학술대회논문집
• /
• 2001.10a
• /
• pp.58-62
• /
• 2001

Aparallel computing environment was constructed based on Windows 2000 operating system. This cluster was configured using Fast-Ethernet system to hold up together the clients within a network domain. For the parallel computation, MPI implements for Windows such as MPICH.NT.1.2.2 and MP-MPICHNT.1.2 were used with Compaq Visual Fortran compiler which produce a well optimized executives for x86 systems. The evaluation of this cluster performance was carried out using a preconditioned Navier-Stokes code for the 2D analysis of a compressible and viscous flow around a compressor blade. The parallel performance was examined in comparison with those of Linux clusters studied previously by changing a number of processors, problem size and MPI libraries. The result from the test problems presents that parallel performance of the low cost Fast-Ethernet Windows cluster is superior to that of a Linux cluster of similar configuration and is comparable to that of a Myrinet cluster.

• The KIPS Transactions:PartA
• /
• v.10A no.4
• /
• pp.285-294
• /
• 2003

The request scheduling algorithms being used for the cluster web servers are mostly in two categories : load-balancing and contents-based cache affinity The goal of the load-balancing algorithms is to balance the loads between real servers. On the other hand, contents-based scheduling algorithm exploits the cache affinity in a way that the same type of requests are to be directed to a dedicated real server allowing load imbalance. So the performance comparison of the two algorithms is necessary, nevertheless the related experiment results are not much suggested. In this paper, performance evaluations have been done to compare the performance of the two scheduling algorithms. To accomplish this, we first implement a linux cluster web server, and then present the performance measurement results. The main contribution of this paper is to help the cluster web server administrators to select an algorithm fitting in with their circumstances from the two algorithms.

• 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 KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.635-645
• /
• 2003

One of very important features that are necessarily supported by clustered parallel computer systems is a single I/O system image in which users can access both the local and remote I/O resources transparently. In this paper, we propose an efficient disk sharing technique supporting a single disk I/O system image architecture. The design separates the I/O subsystem of a cluster into the file system and a set of virtual hard disk drivers. The virtual hard disk driver deals with a hard disk in the remote node as a local hard disk. All services provided by it are performed in the device driver level without any modification of file systems. Users can, therefore, access all the disks in the cluster regardless of their locations. Our virtual hard disk driver is implemented under the linux, and also tested in a linux cluster system. We find by experiments that it can successfully support a single disk I/O space, and at the same time it shows better performance than NFS. We are sure that this paper can be a guideline for single I/O space of other devices to be easily constructed.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.8
• /
• pp.33-40
• /
• 2006

A parallel computing strategy for finite element(FE) processing is described and implemented in nonlinear explicit FE code and its parallel performances are evaluated. A self-made linux-cluster supercomputer with 520 CPUs is used as a bench mark test bed. It is observed that speed-up is increased almost idealy even up to 256 CPUs for a large scale model. A communication over head and its effect on the parallel performance is also examined. Parallel performance is compare with the commercial code and developed code shows superior performance as the number of CPUs used are increased.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.52-54
• /
• 2005

Beowulf 타입의 리눅스 클러스터 시스템의 핵심노드인 계산노드는 일반적으로 범용 엔트리급 서버 및 PC 등을 이용하여 구성되며, 이 계산노드의 성능은 전체 클러스터의 계산 성능을 결정하는 가장 중요한 요소 중의 하나이다. 이에 본 논문에서는 현재 시중에서 유통 중인 대표적인 로엔드 플랫폼-Xeon, P-IV, Opteron, Athlon64-들을 대상으로 HPL, NPB, stream등 고성능 컴퓨팅 분야에서 널리 쓰이는 벤치마킹 테스트 도구를 사용하여 개별 노드의 성능을 측정하여 비교 분석하였다.